diff options
25 files changed, 26111 insertions, 63 deletions
diff --git a/resources/tools/testbed-setup/ansible/roles/consul/tasks/main.yaml b/resources/tools/testbed-setup/ansible/roles/consul/tasks/main.yaml index 9d1ca1980d..f87590edb7 100644 --- a/resources/tools/testbed-setup/ansible/roles/consul/tasks/main.yaml +++ b/resources/tools/testbed-setup/ansible/roles/consul/tasks/main.yaml @@ -125,6 +125,16 @@ tags: - consul-conf +- name: Conf - Telemetry Configuration + template: + src: telemetry.hcl.j2 + dest: "{{ consul_config_dir }}/telemetry.hcl" + owner: "{{ consul_user }}" + group: "{{ consul_group }}" + mode: 0644 + tags: + - consul-conf + - name: Conf - Services Configuration template: src: services.json.j2 @@ -156,8 +166,8 @@ owner: "root" group: "root" mode: 0644 - notify: - - "Restart Consul" +# notify: +# - "Restart Consul" # - "Stop Systemd-resolved" # - "Restart Nomad" tags: diff --git a/resources/tools/testbed-setup/ansible/roles/consul/templates/telemetry.hcl.j2 b/resources/tools/testbed-setup/ansible/roles/consul/templates/telemetry.hcl.j2 new file mode 100644 index 0000000000..ec7fabc9da --- /dev/null +++ b/resources/tools/testbed-setup/ansible/roles/consul/templates/telemetry.hcl.j2 @@ -0,0 +1,3 @@ +telemetry { + prometheus_retention_time = "24h" +}
\ No newline at end of file diff --git a/terraform-ci-infra/1n_nmd/.terraform.lock.hcl b/terraform-ci-infra/1n_nmd/.terraform.lock.hcl index 3a2e4ef85f..3a2e4ef85f 100755..100644 --- a/terraform-ci-infra/1n_nmd/.terraform.lock.hcl +++ b/terraform-ci-infra/1n_nmd/.terraform.lock.hcl diff --git a/terraform-ci-infra/1n_nmd/alertmanager/conf/nomad/alertmanager.hcl b/terraform-ci-infra/1n_nmd/alertmanager/conf/nomad/alertmanager.hcl new file mode 100644 index 0000000000..4560cf07ab --- /dev/null +++ b/terraform-ci-infra/1n_nmd/alertmanager/conf/nomad/alertmanager.hcl @@ -0,0 +1,333 @@ +job "${job_name}" { + # The "region" parameter specifies the region in which to execute the job. + # If omitted, this inherits the default region name of "global". + # region = "global" + # + # The "datacenters" parameter specifies the list of datacenters which should + # be considered when placing this task. This must be provided. + datacenters = "${datacenters}" + + # The "type" parameter controls the type of job, which impacts the scheduler's + # decision on placement. This configuration is optional and defaults to + # "service". For a full list of job types and their differences, please see + # the online documentation. + # + # For more information, please see the online documentation at: + # + # https://www.nomadproject.io/docs/jobspec/schedulers + # + type = "service" + + update { + # The "max_parallel" parameter specifies the maximum number of updates to + # perform in parallel. In this case, this specifies to update a single task + # at a time. + max_parallel = 1 + + health_check = "checks" + + # The "min_healthy_time" parameter specifies the minimum time the allocation + # must be in the healthy state before it is marked as healthy and unblocks + # further allocations from being updated. + min_healthy_time = "10s" + + # The "healthy_deadline" parameter specifies the deadline in which the + # allocation must be marked as healthy after which the allocation is + # automatically transitioned to unhealthy. Transitioning to unhealthy will + # fail the deployment and potentially roll back the job if "auto_revert" is + # set to true. + healthy_deadline = "3m" + + # The "progress_deadline" parameter specifies the deadline in which an + # allocation must be marked as healthy. The deadline begins when the first + # allocation for the deployment is created and is reset whenever an allocation + # as part of the deployment transitions to a healthy state. If no allocation + # transitions to the healthy state before the progress deadline, the + # deployment is marked as failed. + progress_deadline = "10m" + +%{ if use_canary } + # The "canary" parameter specifies that changes to the job that would result + # in destructive updates should create the specified number of canaries + # without stopping any previous allocations. Once the operator determines the + # canaries are healthy, they can be promoted which unblocks a rolling update + # of the remaining allocations at a rate of "max_parallel". + # + # Further, setting "canary" equal to the count of the task group allows + # blue/green deployments. When the job is updated, a full set of the new + # version is deployed and upon promotion the old version is stopped. + canary = 1 + + # Specifies if the job should auto-promote to the canary version when all + # canaries become healthy during a deployment. Defaults to false which means + # canaries must be manually updated with the nomad deployment promote + # command. + auto_promote = true + + # The "auto_revert" parameter specifies if the job should auto-revert to the + # last stable job on deployment failure. A job is marked as stable if all the + # allocations as part of its deployment were marked healthy. + auto_revert = true +%{ endif } + } + + # The "group" stanza defines a series of tasks that should be co-located on + # the same Nomad client. Any task within a group will be placed on the same + # client. + # + # For more information and examples on the "group" stanza, please see + # the online documentation at: + # + # https://www.nomadproject.io/docs/job-specification/group + # + group "prod-group1-${service_name}" { + # The "count" parameter specifies the number of the task groups that should + # be running under this group. This value must be non-negative and defaults + # to 1. + count = ${group_count} + + # The constraint allows restricting the set of eligible nodes. Constraints + # may filter on attributes or client metadata. + # + # For more information and examples on the "volume" stanza, please see + # the online documentation at: + # + # https://www.nomadproject.io/docs/job-specification/constraint + # + constraint { + attribute = "$${attr.cpu.arch}" + operator = "!=" + value = "arm64" + } + + # The "task" stanza creates an individual unit of work, such as a Docker + # container, web application, or batch processing. + # + # For more information and examples on the "task" stanza, please see + # the online documentation at: + # + # https://www.nomadproject.io/docs/job-specification/task + # + task "prod-task1-${service_name}" { + # The "driver" parameter specifies the task driver that should be used to + # run the task. + driver = "exec" + + %{ if use_vault_provider } + vault { + policies = "${vault_kv_policy_name}" + } + %{ endif } + + # The "config" stanza specifies the driver configuration, which is passed + # directly to the driver to start the task. The details of configurations + # are specific to each driver, so please see specific driver + # documentation for more information. + config { + command = "local/alertmanager-${version}.linux-amd64/alertmanager" + args = [ + "--config.file=secrets/alertmanager.yml" + ] + } + + # The artifact stanza instructs Nomad to fetch and unpack a remote resource, + # such as a file, tarball, or binary. Nomad downloads artifacts using the + # popular go-getter library, which permits downloading artifacts from a + # variety of locations using a URL as the input source. + # + # For more information and examples on the "artifact" stanza, please see + # the online documentation at: + # + # https://www.nomadproject.io/docs/job-specification/artifact + # + artifact { + source = "${url}" + } + + # The "template" stanza instructs Nomad to manage a template, such as + # a configuration file or script. This template can optionally pull data + # from Consul or Vault to populate runtime configuration data. + # + # For more information and examples on the "template" stanza, please see + # the online documentation at: + # + # https://www.nomadproject.io/docs/job-specification/template + # + template { + change_mode = "noop" + change_signal = "SIGINT" + destination = "secrets/alertmanager.yml" + left_delimiter = "{{{" + right_delimiter = "}}}" + data = <<EOH +global: + # The API URL to use for Slack notifications. + slack_api_url: '${slack_api_url}' + +# The directory from which notification templates are read. +templates: +- '/etc/alertmanager/template/*.tmpl' + +#tls_config: +# # CA certificate to validate the server certificate with. +# ca_file: <filepath> ] +# +# # Certificate and key files for client cert authentication to the server. +# cert_file: <filepath> +# key_file: <filepath> +# +# # ServerName extension to indicate the name of the server. +# # http://tools.ietf.org/html/rfc4366#section-3.1 +# server_name: <string> +# +# # Disable validation of the server certificate. +# insecure_skip_verify: true + +# The root route on which each incoming alert enters. +route: + receiver: '${default_receiver}' + + # The labels by which incoming alerts are grouped together. For example, + # multiple alerts coming in for cluster=A and alertname=LatencyHigh would + # be batched into a single group. + # + # To aggregate by all possible labels use '...' as the sole label name. + # This effectively disables aggregation entirely, passing through all + # alerts as-is. This is unlikely to be what you want, unless you have + # a very low alert volume or your upstream notification system performs + # its own grouping. Example: group_by: [...] + group_by: ['alertname', 'cluster', 'service'] + + # When a new group of alerts is created by an incoming alert, wait at + # least 'group_wait' to send the initial notification. + # This way ensures that you get multiple alerts for the same group that start + # firing shortly after another are batched together on the first + # notification. + group_wait: 30s + + # When the first notification was sent, wait 'group_interval' to send a batch + # of new alerts that started firing for that group. + group_interval: 5m + + # If an alert has successfully been sent, wait 'repeat_interval' to + # resend them. + repeat_interval: 3h + + # All the above attributes are inherited by all child routes and can + # overwritten on each. + # The child route trees. + routes: + # This routes performs a regular expression match on alert labels to + # catch alerts that are related to a list of services. + - match_re: + service: .* + receiver: ${default_receiver} + # The service has a sub-route for critical alerts, any alerts + # that do not match, i.e. severity != critical, fall-back to the + # parent node and are sent to 'team-X-mails' + routes: + - match: + severity: critical + receiver: '${default_receiver}' + +# Inhibition rules allow to mute a set of alerts given that another alert is +# firing. +# We use this to mute any warning-level notifications if the same alert is +# already critical. +inhibit_rules: +- source_match: + severity: 'critical' + target_match: + severity: 'warning' + # Apply inhibition if the alertname is the same. + # CAUTION: + # If all label names listed in `equal` are missing + # from both the source and target alerts, + # the inhibition rule will apply! + equal: ['alertname', 'cluster', 'service'] + +receivers: +- name: '${default_receiver}' + slack_configs: + - channel: '#${slack_channel}' + send_resolved: true + icon_url: https://avatars3.githubusercontent.com/u/3380462 + title: |- + [{{ .Status | toUpper }}{{ if eq .Status "firing" }}:{{ .Alerts.Firing | len }}{{ end }}] {{ .CommonLabels.alertname }} for {{ .CommonLabels.job }} + {{- if gt (len .CommonLabels) (len .GroupLabels) -}} + {{" "}}( + {{- with .CommonLabels.Remove .GroupLabels.Names }} + {{- range $index, $label := .SortedPairs -}} + {{ if $index }}, {{ end }} + {{- $label.Name }}="{{ $label.Value -}}" + {{- end }} + {{- end -}} + ) + {{- end }} + text: >- + {{ range .Alerts -}} + *Alert:* {{ .Annotations.summary }}{{ if .Labels.severity }} - `{{ .Labels.severity }}`{{ end }} + + *Description:* {{ .Annotations.description }} + + *Details:* + {{ range .Labels.SortedPairs }} • *{{ .Name }}:* `{{ .Value }}` + {{ end }} + {{ end }} +EOH + } + + # The service stanza instructs Nomad to register a service with Consul. + # + # For more information and examples on the "task" stanza, please see + # the online documentation at: + # + # https://www.nomadproject.io/docs/job-specification/service + # + service { + name = "${service_name}" + port = "${service_name}" + tags = [ "${service_name}$${NOMAD_ALLOC_INDEX}" ] + check { + name = "Alertmanager Check Live" + type = "http" + path = "/-/healthy" + interval = "10s" + timeout = "2s" + } + } + + # The "resources" stanza describes the requirements a task needs to + # execute. Resource requirements include memory, network, cpu, and more. + # This ensures the task will execute on a machine that contains enough + # resource capacity. + # + # For more information and examples on the "resources" stanza, please see + # the online documentation at: + # + # https://www.nomadproject.io/docs/job-specification/resources + # + resources { + cpu = ${cpu} + memory = ${mem} + # The network stanza specifies the networking requirements for the task + # group, including the network mode and port allocations. When scheduling + # jobs in Nomad they are provisioned across your fleet of machines along + # with other jobs and services. Because you don't know in advance what host + # your job will be provisioned on, Nomad will provide your tasks with + # network configuration when they start up. + # + # For more information and examples on the "template" stanza, please see + # the online documentation at: + # + # https://www.nomadproject.io/docs/job-specification/network + # + network { + port "${service_name}" { + static = ${port} + } + } + } + } + } +}
\ No newline at end of file diff --git a/terraform-ci-infra/1n_nmd/alertmanager/main.tf b/terraform-ci-infra/1n_nmd/alertmanager/main.tf new file mode 100644 index 0000000000..411c78a558 --- /dev/null +++ b/terraform-ci-infra/1n_nmd/alertmanager/main.tf @@ -0,0 +1,37 @@ +locals { + datacenters = join(",", var.nomad_datacenters) + + alertmanager_url = join("", + [ + "https://github.com", + "/prometheus/alertmanager/releases/download/", + "v${var.alertmanager_version}/", + "alertmanager-${var.alertmanager_version}.linux-amd64.tar.gz" + ] + ) +} + +data "template_file" "nomad_job_alertmanager" { + template = file("${path.module}/conf/nomad/alertmanager.hcl") + vars = { + datacenters = local.datacenters + url = local.alertmanager_url + job_name = var.alertmanager_job_name + use_canary = var.alertmanager_use_canary + group_count = var.alertmanager_group_count + service_name = var.alertmanager_service_name + use_vault_provider = var.alertmanager_vault_secret.use_vault_provider + version = var.alertmanager_version + cpu = var.alertmanager_cpu + mem = var.alertmanager_mem + port = var.alertmanager_port + slack_api_url = var.alertmanager_slack_api_url + slack_channel = var.alertmanager_slack_channel + default_receiver = var.alertmanager_default_receiver + } +} + +resource "nomad_job" "nomad_job_alertmanager" { + jobspec = data.template_file.nomad_job_alertmanager.rendered + detach = false +}
\ No newline at end of file diff --git a/terraform-ci-infra/1n_nmd/alertmanager/variables.tf b/terraform-ci-infra/1n_nmd/alertmanager/variables.tf new file mode 100644 index 0000000000..ebd862123d --- /dev/null +++ b/terraform-ci-infra/1n_nmd/alertmanager/variables.tf @@ -0,0 +1,84 @@ +# Nomad +variable "nomad_datacenters" { + description = "Nomad data centers" + type = list(string) + default = [ "dc1" ] +} + +# Alermanager +variable "alertmanager_job_name" { + description = "Job name" + type = string + default = "alertmanager" +} + +variable "alertmanager_group_count" { + description = "Number of group instances" + type = number + default = 1 +} + +variable "alertmanager_service_name" { + description = "Service name" + type = string + default = "alertmanager" +} + +variable "alertmanager_version" { + description = "Version" + type = string + default = "0.21.0" +} + +variable "alertmanager_use_canary" { + description = "Uses canary deployment" + type = bool + default = false +} + +variable "alertmanager_vault_secret" { + description = "Set of properties to be able to fetch secret from vault" + type = object({ + use_vault_provider = bool, + vault_kv_policy_name = string, + vault_kv_path = string, + vault_kv_field_access_key = string, + vault_kv_field_secret_key = string + }) +} + +variable "alertmanager_cpu" { + description = "CPU allocation" + type = number + default = 1000 +} + +variable "alertmanager_mem" { + description = "RAM allocation" + type = number + default = 1024 +} + +variable "alertmanager_port" { + description = "TCP allocation" + type = number + default = 9093 +} + +variable "alertmanager_default_receiver" { + description = "Alertmanager default receiver" + type = string + default = "default-receiver" +} + +variable "alertmanager_slack_api_url" { + description = "Alertmanager slack API URL" + type = string + default = "https://hooks.slack.com/services/XXXXXXXXX/XXXXXXXXXXX/XXXXXXXXXXXXXXXXXXXXXXXX" +} + +variable "alertmanager_slack_channel" { + description = "Alertmanager slack channel" + type = string + default = "slack-channel" +}
\ No newline at end of file diff --git a/terraform-ci-infra/1n_nmd/exporter/conf/nomad/exporter.hcl b/terraform-ci-infra/1n_nmd/exporter/conf/nomad/exporter.hcl new file mode 100644 index 0000000000..4fd0768ae7 --- /dev/null +++ b/terraform-ci-infra/1n_nmd/exporter/conf/nomad/exporter.hcl @@ -0,0 +1,587 @@ +job "${job_name}" { + # The "region" parameter specifies the region in which to execute the job. + # If omitted, this inherits the default region name of "global". + # region = "global" + # + # The "datacenters" parameter specifies the list of datacenters which should + # be considered when placing this task. This must be provided. + datacenters = "${datacenters}" + + # The "type" parameter controls the type of job, which impacts the scheduler's + # decision on placement. This configuration is optional and defaults to + # "service". For a full list of job types and their differences, please see + # the online documentation. + # + # https://www.nomadproject.io/docs/jobspec/schedulers + # + type = "system" + + update { + # The "max_parallel" parameter specifies the maximum number of updates to + # perform in parallel. In this case, this specifies to update a single task + # at a time. + max_parallel = 1 + + health_check = "checks" + + # The "min_healthy_time" parameter specifies the minimum time the allocation + # must be in the healthy state before it is marked as healthy and unblocks + # further allocations from being updated. + min_healthy_time = "10s" + + # The "healthy_deadline" parameter specifies the deadline in which the + # allocation must be marked as healthy after which the allocation is + # automatically transitioned to unhealthy. Transitioning to unhealthy will + # fail the deployment and potentially roll back the job if "auto_revert" is + # set to true. + healthy_deadline = "3m" + + # The "progress_deadline" parameter specifies the deadline in which an + # allocation must be marked as healthy. The deadline begins when the first + # allocation for the deployment is created and is reset whenever an allocation + # as part of the deployment transitions to a healthy state. If no allocation + # transitions to the healthy state before the progress deadline, the + # deployment is marked as failed. + progress_deadline = "10m" + +%{ if use_canary } + # The "canary" parameter specifies that changes to the job that would result + # in destructive updates should create the specified number of canaries + # without stopping any previous allocations. Once the operator determines the + # canaries are healthy, they can be promoted which unblocks a rolling update + # of the remaining allocations at a rate of "max_parallel". + # + # Further, setting "canary" equal to the count of the task group allows + # blue/green deployments. When the job is updated, a full set of the new + # version is deployed and upon promotion the old version is stopped. + canary = 1 + + # Specifies if the job should auto-promote to the canary version when all + # canaries become healthy during a deployment. Defaults to false which means + # canaries must be manually updated with the nomad deployment promote + # command. + auto_promote = true + + # The "auto_revert" parameter specifies if the job should auto-revert to the + # last stable job on deployment failure. A job is marked as stable if all the + # allocations as part of its deployment were marked healthy. + auto_revert = true +%{ endif } + } + + # The "group" stanza defines a series of tasks that should be co-located on + # the same Nomad client. Any task within a group will be placed on the same + # client. + # + # https://www.nomadproject.io/docs/job-specification/group + # + group "prod-group1-exporter-amd64" { + # The constraint allows restricting the set of eligible nodes. Constraints + # may filter on attributes or client metadata. + # + # https://www.nomadproject.io/docs/job-specification/constraint + # + constraint { + attribute = "$${attr.cpu.arch}" + operator = "!=" + value = "arm64" + } + + # The "task" stanza creates an individual unit of work, such as a Docker + # container, web application, or batch processing. + # + # https://www.nomadproject.io/docs/job-specification/task + # + task "prod-task1-${node_service_name}-amd64" { + # The "driver" parameter specifies the task driver that should be used to + # run the task. + driver = "raw_exec" + + # The "config" stanza specifies the driver configuration, which is passed + # directly to the driver to start the task. The details of configurations + # are specific to each driver, so please see specific driver + # documentation for more information. + config { + command = "local/node_exporter-${node_version}.linux-amd64/node_exporter" + } + + # The artifact stanza instructs Nomad to fetch and unpack a remote resource, + # such as a file, tarball, or binary. Nomad downloads artifacts using the + # popular go-getter library, which permits downloading artifacts from a + # variety of locations using a URL as the input source. + # + # https://www.nomadproject.io/docs/job-specification/artifact + # + artifact { + source = "${node_url_amd64}" + } + + # The service stanza instructs Nomad to register a service with Consul. + # + # https://www.nomadproject.io/docs/job-specification/service + # + service { + name = "${node_service_name}" + port = "${node_service_name}" + check { + name = "Node Exporter Check Live" + type = "http" + path = "/metrics" + interval = "10s" + timeout = "2s" + } + } + + # The "resources" stanza describes the requirements a task needs to + # execute. Resource requirements include memory, network, cpu, and more. + # This ensures the task will execute on a machine that contains enough + # resource capacity. + # + # https://www.nomadproject.io/docs/job-specification/resources + # + resources { + cpu = 500 + # The network stanza specifies the networking requirements for the task + # group, including the network mode and port allocations. When scheduling + # jobs in Nomad they are provisioned across your fleet of machines along + # with other jobs and services. Because you don't know in advance what host + # your job will be provisioned on, Nomad will provide your tasks with + # network configuration when they start up. + # + # https://www.nomadproject.io/docs/job-specification/network + # + network { + port "${node_service_name}" { + static = ${node_port} + } + } + } + } + task "prod-task2-${blackbox_service_name}-amd64" { + # The "driver" parameter specifies the task driver that should be used to + # run the task. + driver = "exec" + + # The "config" stanza specifies the driver configuration, which is passed + # directly to the driver to start the task. The details of configurations + # are specific to each driver, so please see specific driver + # documentation for more information. + config { + command = "local/blackbox_exporter-${blackbox_version}.linux-amd64/blackbox_exporter" + args = [ + "--config.file=secrets/blackbox.yml" + ] + } + + # The "template" stanza instructs Nomad to manage a template, such as + # a configuration file or script. This template can optionally pull data + # from Consul or Vault to populate runtime configuration data. + # + # https://www.nomadproject.io/docs/job-specification/template + # + template { + change_mode = "noop" + change_signal = "SIGINT" + destination = "secrets/blackbox.yml" + data = <<EOH +modules: + http_2xx: + prober: http + timeout: 5s + http: + valid_http_versions: ["HTTP/1.1", "HTTP/2.0"] + no_follow_redirects: false + fail_if_ssl: false + fail_if_not_ssl: true + tls_config: + insecure_skip_verify: false + preferred_ip_protocol: "ip4" + icmp_v4: + prober: icmp + timeout: 5s + icmp: + preferred_ip_protocol: "ip4" + dns_udp: + prober: dns + timeout: 5s + dns: + query_name: "jenkins.fd.io" + query_type: "A" + valid_rcodes: + - NOERROR +EOH + } + + # The artifact stanza instructs Nomad to fetch and unpack a remote resource, + # such as a file, tarball, or binary. Nomad downloads artifacts using the + # popular go-getter library, which permits downloading artifacts from a + # variety of locations using a URL as the input source. + # + # https://www.nomadproject.io/docs/job-specification/artifact + # + artifact { + source = "${blackbox_url_amd64}" + } + + # The service stanza instructs Nomad to register a service with Consul. + # + # https://www.nomadproject.io/docs/job-specification/service + # + service { + name = "${blackbox_service_name}" + port = "${blackbox_service_name}" + tags = [ "${blackbox_service_name}$${NOMAD_ALLOC_INDEX}" ] + check { + name = "Blackbox Exporter Check Live" + type = "http" + path = "/metrics" + interval = "10s" + timeout = "2s" + } + } + + # The "resources" stanza describes the requirements a task needs to + # execute. Resource requirements include memory, network, cpu, and more. + # This ensures the task will execute on a machine that contains enough + # resource capacity. + # + # https://www.nomadproject.io/docs/job-specification/resources + # + resources { + cpu = 500 + # The network stanza specifies the networking requirements for the task + # group, including the network mode and port allocations. When scheduling + # jobs in Nomad they are provisioned across your fleet of machines along + # with other jobs and services. Because you don't know in advance what host + # your job will be provisioned on, Nomad will provide your tasks with + # network configuration when they start up. + # + # https://www.nomadproject.io/docs/job-specification/network + # + network { + port "${blackbox_service_name}" { + static = ${blackbox_port} + } + } + } + } + + task "prod-task3-${cadvisor_service_name}-amd64" { + # The "driver" parameter specifies the task driver that should be used to + # run the task. + driver = "docker" + + # The "config" stanza specifies the driver configuration, which is passed + # directly to the driver to start the task. The details of configurations + # are specific to each driver, so please see specific driver + # documentation for more information. + config { + image = "${cadvisor_image}" + volumes = [ + "/:/rootfs:ro", + "/var/run:/var/run:rw", + "/sys:/sys:ro", + "/var/lib/docker/:/var/lib/docker:ro", + "/cgroup:/cgroup:ro" + ] + } + + # The service stanza instructs Nomad to register a service with Consul. + # + # https://www.nomadproject.io/docs/job-specification/service + # + service { + name = "${cadvisor_service_name}" + port = "${cadvisor_service_name}" + check { + name = "cAdvisor Check Live" + type = "http" + path = "/metrics" + interval = "10s" + timeout = "2s" + } + } + + # The "resources" stanza describes the requirements a task needs to + # execute. Resource requirements include memory, network, cpu, and more. + # This ensures the task will execute on a machine that contains enough + # resource capacity. + # + # https://www.nomadproject.io/docs/job-specification/resources + # + resources { + cpu = 500 + # The network stanza specifies the networking requirements for the task + # group, including the network mode and port allocations. When scheduling + # jobs in Nomad they are provisioned across your fleet of machines along + # with other jobs and services. Because you don't know in advance what host + # your job will be provisioned on, Nomad will provide your tasks with + # network configuration when they start up. + # + # https://www.nomadproject.io/docs/job-specification/network + # + network { + port "${cadvisor_service_name}" { + static = ${cadvisor_port} + } + } + } + } + } + + group "prod-group1-exporter-arm64" { + # The constraint allows restricting the set of eligible nodes. Constraints + # may filter on attributes or client metadata. + # + # https://www.nomadproject.io/docs/job-specification/constraint + # + constraint { + attribute = "$${attr.cpu.arch}" + operator = "==" + value = "arm64" + } + + # The "task" stanza creates an individual unit of work, such as a Docker + # container, web application, or batch processing. + # + # https://www.nomadproject.io/docs/job-specification/task + # + task "prod-task1-${node_service_name}-arm64" { + # The "driver" parameter specifies the task driver that should be used to + # run the task. + driver = "raw_exec" + + # The "config" stanza specifies the driver configuration, which is passed + # directly to the driver to start the task. The details of configurations + # are specific to each driver, so please see specific driver + # documentation for more information. + config { + command = "local/node_exporter-${node_version}.linux-arm64/node_exporter" + } + + # The artifact stanza instructs Nomad to fetch and unpack a remote resource, + # such as a file, tarball, or binary. Nomad downloads artifacts using the + # popular go-getter library, which permits downloading artifacts from a + # variety of locations using a URL as the input source. + # + # https://www.nomadproject.io/docs/job-specification/artifact + # + artifact { + source = "${node_url_arm64}" + } + + # The service stanza instructs Nomad to register a service with Consul. + # + # https://www.nomadproject.io/docs/job-specification/service + # + service { + name = "${node_service_name}" + port = "${node_service_name}" + check { + name = "Node Exporter Check Live" + type = "http" + path = "/metrics" + interval = "10s" + timeout = "2s" + } + } + + # The "resources" stanza describes the requirements a task needs to + # execute. Resource requirements include memory, network, cpu, and more. + # This ensures the task will execute on a machine that contains enough + # resource capacity. + # + # https://www.nomadproject.io/docs/job-specification/resources + # + resources { + cpu = 500 + # The network stanza specifies the networking requirements for the task + # group, including the network mode and port allocations. When scheduling + # jobs in Nomad they are provisioned across your fleet of machines along + # with other jobs and services. Because you don't know in advance what host + # your job will be provisioned on, Nomad will provide your tasks with + # network configuration when they start up. + # + # https://www.nomadproject.io/docs/job-specification/network + # + network { + port "${node_service_name}" { + static = ${node_port} + } + } + } + } + + task "prod-task2-${blackbox_service_name}-arm64" { + # The "driver" parameter specifies the task driver that should be used to + # run the task. + driver = "exec" + + # The "config" stanza specifies the driver configuration, which is passed + # directly to the driver to start the task. The details of configurations + # are specific to each driver, so please see specific driver + # documentation for more information. + config { + command = "local/blackbox_exporter-${blackbox_version}.linux-arm64/blackbox_exporter" + args = [ + "--config.file=secrets/blackbox.yml" + ] + } + + # The "template" stanza instructs Nomad to manage a template, such as + # a configuration file or script. This template can optionally pull data + # from Consul or Vault to populate runtime configuration data. + # + # https://www.nomadproject.io/docs/job-specification/template + # + template { + change_mode = "noop" + change_signal = "SIGINT" + destination = "secrets/blackbox.yml" + data = <<EOH +modules: + http_2xx: + prober: http + timeout: 5s + http: + valid_http_versions: ["HTTP/1.1", "HTTP/2.0"] + no_follow_redirects: false + fail_if_ssl: false + fail_if_not_ssl: true + tls_config: + insecure_skip_verify: false + preferred_ip_protocol: "ip4" + icmp_v4: + prober: icmp + timeout: 5s + icmp: + preferred_ip_protocol: "ip4" + dns_udp: + prober: dns + timeout: 5s + dns: + query_name: "jenkins.fd.io" + query_type: "A" + valid_rcodes: + - NOERROR +EOH + } + + # The artifact stanza instructs Nomad to fetch and unpack a remote resource, + # such as a file, tarball, or binary. Nomad downloads artifacts using the + # popular go-getter library, which permits downloading artifacts from a + # variety of locations using a URL as the input source. + # + # https://www.nomadproject.io/docs/job-specification/artifact + # + artifact { + source = "${blackbox_url_arm64}" + } + + # The service stanza instructs Nomad to register a service with Consul. + # + # https://www.nomadproject.io/docs/job-specification/service + # + service { + name = "${blackbox_service_name}" + port = "${blackbox_service_name}" + tags = [ "${blackbox_service_name}$${NOMAD_ALLOC_INDEX}" ] + check { + name = "Blackbox Exporter Check Live" + type = "http" + path = "/metrics" + interval = "10s" + timeout = "2s" + } + } + + # The "resources" stanza describes the requirements a task needs to + # execute. Resource requirements include memory, network, cpu, and more. + # This ensures the task will execute on a machine that contains enough + # resource capacity. + # + # https://www.nomadproject.io/docs/job-specification/resources + # + resources { + cpu = 500 + # The network stanza specifies the networking requirements for the task + # group, including the network mode and port allocations. When scheduling + # jobs in Nomad they are provisioned across your fleet of machines along + # with other jobs and services. Because you don't know in advance what host + # your job will be provisioned on, Nomad will provide your tasks with + # network configuration when they start up. + # + # https://www.nomadproject.io/docs/job-specification/network + # + network { + port "${blackbox_service_name}" { + static = ${blackbox_port} + } + } + } + } + + task "prod-task3-${cadvisor_service_name}-arm64" { + # The "driver" parameter specifies the task driver that should be used to + # run the task. + driver = "docker" + + # The "config" stanza specifies the driver configuration, which is passed + # directly to the driver to start the task. The details of configurations + # are specific to each driver, so please see specific driver + # documentation for more information. + config { + # There is currently no official release for arm yet...using community. + image = "zcube/cadvisor:latest" + volumes = [ + "/:/rootfs:ro", + "/var/run:/var/run:rw", + "/sys:/sys:ro", + "/var/lib/docker/:/var/lib/docker:ro", + "/cgroup:/cgroup:ro" + ] + } + + # The service stanza instructs Nomad to register a service with Consul. + # + # https://www.nomadproject.io/docs/job-specification/service + # + service { + name = "${cadvisor_service_name}" + port = "${cadvisor_service_name}" + check { + name = "cAdvisor Check Live" + type = "http" + path = "/metrics" + interval = "10s" + timeout = "2s" + } + } + + # The "resources" stanza describes the requirements a task needs to + # execute. Resource requirements include memory, network, cpu, and more. + # This ensures the task will execute on a machine that contains enough + # resource capacity. + # + # https://www.nomadproject.io/docs/job-specification/resources + # + resources { + cpu = 500 + # The network stanza specifies the networking requirements for the task + # group, including the network mode and port allocations. When scheduling + # jobs in Nomad they are provisioned across your fleet of machines along + # with other jobs and services. Because you don't know in advance what host + # your job will be provisioned on, Nomad will provide your tasks with + # network configuration when they start up. + # + # https://www.nomadproject.io/docs/job-specification/network + # + network { + port "${cadvisor_service_name}" { + static = ${cadvisor_port} + } + } + } + } + } +}
\ No newline at end of file diff --git a/terraform-ci-infra/1n_nmd/exporter/main.tf b/terraform-ci-infra/1n_nmd/exporter/main.tf new file mode 100644 index 0000000000..35eb95b071 --- /dev/null +++ b/terraform-ci-infra/1n_nmd/exporter/main.tf @@ -0,0 +1,64 @@ +locals { + datacenters = join(",", var.nomad_datacenters) + + node_url_amd64 = join("", + [ + "https://github.com", + "/prometheus/node_exporter/releases/download/", + "v${var.node_version}/", + "node_exporter-${var.node_version}.linux-amd64.tar.gz" + ] + ) + node_url_arm64 = join("", + [ + "https://github.com", + "/prometheus/node_exporter/releases/download/", + "v${var.node_version}/", + "node_exporter-${var.node_version}.linux-arm64.tar.gz" + ] + ) + + blackbox_url_amd64 = join("", + [ + "https://github.com", + "/prometheus/blackbox_exporter/releases/download/", + "v${var.blackbox_version}/", + "blackbox_exporter-${var.blackbox_version}.linux-amd64.tar.gz" + ] + ) + blackbox_url_arm64 = join("", + [ + "https://github.com", + "/prometheus/blackbox_exporter/releases/download/", + "v${var.blackbox_version}/", + "blackbox_exporter-${var.blackbox_version}.linux-arm64.tar.gz" + ] + ) +} + +data "template_file" "nomad_job_exporter" { + template = file("${path.module}/conf/nomad/exporter.hcl") + vars = { + datacenters = local.datacenters + job_name = var.exporter_job_name + use_canary = var.exporter_use_canary + node_url_amd64 = local.node_url_amd64 + node_url_arm64 = local.node_url_arm64 + node_version = var.node_version + node_service_name = var.node_service_name + node_port = var.node_port + blackbox_url_amd64 = local.blackbox_url_amd64 + blackbox_url_arm64 = local.blackbox_url_arm64 + blackbox_version = var.blackbox_version + blackbox_service_name = var.blackbox_service_name + blackbox_port = var.blackbox_port + cadvisor_image = var.cadvisor_image + cadvisor_service_name = var.cadvisor_service_name + cadvisor_port = var.cadvisor_port + } +} + +resource "nomad_job" "nomad_job_exporter" { + jobspec = data.template_file.nomad_job_exporter.rendered + detach = false +}
\ No newline at end of file diff --git a/terraform-ci-infra/1n_nmd/exporter/variables.tf b/terraform-ci-infra/1n_nmd/exporter/variables.tf new file mode 100644 index 0000000000..bfa8bd37ac --- /dev/null +++ b/terraform-ci-infra/1n_nmd/exporter/variables.tf @@ -0,0 +1,76 @@ +# Nomad +variable "nomad_datacenters" { + description = "Nomad data centers" + type = list(string) + default = [ "dc1" ] +} + +# Exporter +variable "exporter_job_name" { + description = "Exporter job name" + type = string + default = "exporter" +} + +variable "exporter_use_canary" { + description = "Uses canary deployment" + type = bool + default = false +} + +# Node Exporter +variable "node_service_name" { + description = "Node exporter service name" + type = string + default = "nodeexporter" +} + +variable "node_version" { + description = "Node exporter version" + type = string + default = "1.0.1" +} + +variable "node_port" { + description = "Node exporter TCP allocation" + type = number + default = 9100 +} + +# Blackbox Exporter +variable "blackbox_service_name" { + description = "Blackbox exporter service name" + type = string + default = "blackboxexporter" +} + +variable "blackbox_version" { + description = "Blackbox exporter version" + type = string + default = "0.18.0" +} + +variable "blackbox_port" { + description = "Blackbox exporter TCP allocation" + type = number + default = 9115 +} + +# cAdvisor Exporter +variable "cadvisor_service_name" { + description = "cAdvisor exporter service name" + type = string + default = "cadvisorexporter" +} + +variable "cadvisor_image" { + description = "cAdvisor exporter docker image" + type = string + default = "gcr.io/cadvisor/cadvisor:v0.38.7" +} + +variable "cadvisor_port" { + description = "cAdvisor exporter TCP allocation" + type = number + default = 8080 +}
\ No newline at end of file diff --git a/terraform-ci-infra/1n_nmd/grafana/conf/blackbox_exporter_http.json b/terraform-ci-infra/1n_nmd/grafana/conf/blackbox_exporter_http.json new file mode 100644 index 0000000000..f9df1b239e --- /dev/null +++ b/terraform-ci-infra/1n_nmd/grafana/conf/blackbox_exporter_http.json @@ -0,0 +1,1030 @@ +{ + "__inputs": [ + { + "name": "DS_PROMETHEUS", + "label": "signcl-prometheus", + "description": "", + "type": "datasource", + "pluginId": "prometheus", + "pluginName": "Prometheus" + } + ], + "__requires": [ + { + "type": "grafana", + "id": "grafana", + "name": "Grafana", + "version": "5.2.2" + }, + { + "type": "panel", + "id": "graph", + "name": "Graph", + "version": "5.0.0" + }, + { + "type": "datasource", + "id": "prometheus", + "name": "Prometheus", + "version": "5.0.0" + }, + { + "type": "panel", + "id": "singlestat", + "name": "Singlestat", + "version": "5.0.0" + } + ], + "annotations": { + "list": [ + { + "builtIn": 1, + "datasource": "-- Grafana --", + "enable": true, + "hide": true, + "iconColor": "rgba(0, 211, 255, 1)", + "name": "Annotations & Alerts", + "type": "dashboard" + } + ] + }, + "description": "Prometheus Blackbox Exporter Overview", + "editable": true, + "gnetId": 7587, + "graphTooltip": 0, + "id": null, + "iteration": 1534695504413, + "links": [], + "panels": [ + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "fill": 1, + "gridPos": { + "h": 8, + "w": 24, + "x": 0, + "y": 0 + }, + "id": 138, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "probe_duration_seconds{instance=~\"$target\"}", + "format": "time_series", + "interval": "$interval", + "intervalFactor": 1, + "legendFormat": "{{ instance }}", + "refId": "A" + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "Global Probe Duration", + "tooltip": { + "shared": true, + "sort": 1, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "collapsed": false, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 8 + }, + "id": 15, + "panels": [], + "repeat": "target", + "title": "$target status", + "type": "row" + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "fill": 1, + "gridPos": { + "h": 6, + "w": 10, + "x": 4, + "y": 9 + }, + "id": 25, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "probe_http_duration_seconds{instance=~\"$target\"}", + "format": "time_series", + "interval": "$interval", + "intervalFactor": 1, + "legendFormat": "{{ phase }}", + "refId": "B" + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "HTTP Duration", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "fill": 1, + "gridPos": { + "h": 6, + "w": 10, + "x": 14, + "y": 9 + }, + "id": 17, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "probe_duration_seconds{instance=~\"$target\"}", + "format": "time_series", + "interval": "$interval", + "intervalFactor": 1, + "legendFormat": "seconds", + "refId": "A" + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "Probe Duration", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "#299c46", + "rgba(237, 129, 40, 0.89)", + "#d44a3a" + ], + "datasource": "${DS_PROMETHEUS}", + "decimals": 0, + "format": "none", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + "h": 2, + "w": 4, + "x": 0, + "y": 11 + }, + "id": 20, + "interval": null, + "links": [], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "minSpan": 3, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "repeat": null, + "repeatDirection": "h", + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "probe_http_status_code{instance=~\"$target\"}", + "format": "time_series", + "interval": "$interval", + "intervalFactor": 1, + "refId": "A" + } + ], + "thresholds": "201, 399", + "title": "HTTP Status Code", + "transparent": false, + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + }, + { + "op": "=", + "text": "YES", + "value": "1" + }, + { + "op": "=", + "text": "N/A", + "value": "0" + } + ], + "valueName": "current" + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "#299c46", + "rgba(237, 129, 40, 0.89)", + "#d44a3a" + ], + "datasource": "${DS_PROMETHEUS}", + "format": "none", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + "h": 2, + "w": 4, + "x": 0, + "y": 13 + }, + "id": 27, + "interval": null, + "links": [], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "probe_http_version{instance=~\"$target\"}", + "format": "time_series", + "intervalFactor": 1, + "refId": "A" + } + ], + "thresholds": "", + "title": "HTTP Version", + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "current" + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": true, + "colors": [ + "#d44a3a", + "rgba(237, 129, 40, 0.89)", + "#299c46" + ], + "datasource": "${DS_PROMETHEUS}", + "format": "none", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + "h": 2, + "w": 4, + "x": 0, + "y": 15 + }, + "id": 18, + "interval": null, + "links": [], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "minSpan": 3, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "repeat": null, + "repeatDirection": "v", + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "probe_http_ssl{instance=~\"$target\"}", + "format": "time_series", + "interval": "$interval", + "intervalFactor": 1, + "refId": "A" + } + ], + "thresholds": "0, 1", + "title": "SSL", + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + }, + { + "op": "=", + "text": "YES", + "value": "1" + }, + { + "op": "=", + "text": "NO", + "value": "0" + } + ], + "valueName": "current" + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": true, + "colors": [ + "#d44a3a", + "rgba(237, 129, 40, 0.89)", + "#299c46" + ], + "datasource": "${DS_PROMETHEUS}", + "decimals": 2, + "format": "dtdurations", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + "h": 2, + "w": 10, + "x": 4, + "y": 15 + }, + "id": 19, + "interval": null, + "links": [], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "minSpan": 3, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "repeat": null, + "repeatDirection": "h", + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "probe_ssl_earliest_cert_expiry{instance=~\"$target\"} - time()", + "format": "time_series", + "interval": "$interval", + "intervalFactor": 1, + "refId": "A" + } + ], + "thresholds": "0,1209600", + "timeFrom": null, + "title": "SSL Expiry", + "transparent": false, + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + }, + { + "op": "=", + "text": "YES", + "value": "1" + }, + { + "op": "=", + "text": "NO", + "value": "0" + } + ], + "valueName": "current" + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "#299c46", + "rgba(237, 129, 40, 0.89)", + "#d44a3a" + ], + "datasource": "${DS_PROMETHEUS}", + "format": "s", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + "h": 2, + "w": 5, + "x": 14, + "y": 15 + }, + "id": 23, + "interval": null, + "links": [], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "repeat": null, + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "avg(probe_duration_seconds{instance=~\"$target\"})", + "format": "time_series", + "interval": "$interval", + "intervalFactor": 1, + "refId": "A" + } + ], + "thresholds": "", + "title": "Average Probe Duration", + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "current" + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "#299c46", + "rgba(237, 129, 40, 0.89)", + "#d44a3a" + ], + "datasource": "${DS_PROMETHEUS}", + "format": "s", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + "h": 2, + "w": 5, + "x": 19, + "y": 15 + }, + "id": 24, + "interval": null, + "links": [], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "repeat": null, + "repeatDirection": "h", + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "avg(probe_dns_lookup_time_seconds{instance=~\"$target\"})", + "format": "time_series", + "interval": "$interval", + "intervalFactor": 1, + "refId": "A" + } + ], + "thresholds": "", + "title": "Average DNS Lookup", + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "current" + } + ], + "refresh": "10s", + "schemaVersion": 16, + "style": "dark", + "tags": [ + "blackbox", + "prometheus" + ], + "templating": { + "list": [ + { + "current": { + "selected": false, + "text": "default", + "value": "default" + }, + "hide": 0, + "includeAll": false, + "label": "datasource", + "multi": false, + "name": "DS_PROMETHEUS", + "options": [], + "query": "prometheus", + "refresh": 1, + "regex": "", + "skipUrlSync": false, + "type": "datasource" + }, + { + "auto": true, + "auto_count": 10, + "auto_min": "10s", + "current": { + "text": "10s", + "value": "10s" + }, + "hide": 0, + "label": "Interval", + "name": "interval", + "options": [ + { + "selected": false, + "text": "auto", + "value": "$__auto_interval_interval" + }, + { + "selected": false, + "text": "5s", + "value": "5s" + }, + { + "selected": true, + "text": "10s", + "value": "10s" + }, + { + "selected": false, + "text": "30s", + "value": "30s" + }, + { + "selected": false, + "text": "1m", + "value": "1m" + }, + { + "selected": false, + "text": "10m", + "value": "10m" + }, + { + "selected": false, + "text": "30m", + "value": "30m" + }, + { + "selected": false, + "text": "1h", + "value": "1h" + }, + { + "selected": false, + "text": "6h", + "value": "6h" + }, + { + "selected": false, + "text": "12h", + "value": "12h" + }, + { + "selected": false, + "text": "1d", + "value": "1d" + }, + { + "selected": false, + "text": "7d", + "value": "7d" + }, + { + "selected": false, + "text": "14d", + "value": "14d" + }, + { + "selected": false, + "text": "30d", + "value": "30d" + } + ], + "query": "5s,10s,30s,1m,10m,30m,1h,6h,12h,1d,7d,14d,30d", + "refresh": 2, + "type": "interval" + }, + { + "allValue": null, + "current": {}, + "datasource": "${DS_PROMETHEUS}", + "hide": 0, + "includeAll": true, + "label": null, + "multi": true, + "name": "target", + "options": [], + "query": "label_values(probe_success, instance)", + "refresh": 1, + "regex": "", + "sort": 0, + "tagValuesQuery": "", + "tags": [], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-4h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "browser", + "title": "HTTP Exporter", + "version": 1 +}
\ No newline at end of file diff --git a/terraform-ci-infra/1n_nmd/grafana/conf/blackbox_exporter_icmp.json b/terraform-ci-infra/1n_nmd/grafana/conf/blackbox_exporter_icmp.json new file mode 100644 index 0000000000..df30506348 --- /dev/null +++ b/terraform-ci-infra/1n_nmd/grafana/conf/blackbox_exporter_icmp.json @@ -0,0 +1,368 @@ +{ + "__inputs": [ + { + "name": "DS_PROMETHEUS", + "label": "localhost", + "description": "", + "type": "datasource", + "pluginId": "prometheus", + "pluginName": "Prometheus" + } + ], + "__requires": [ + { + "type": "grafana", + "id": "grafana", + "name": "Grafana", + "version": "6.5.2" + }, + { + "type": "panel", + "id": "graph", + "name": "Graph", + "version": "" + }, + { + "type": "panel", + "id": "heatmap", + "name": "Heatmap", + "version": "" + }, + { + "type": "datasource", + "id": "prometheus", + "name": "Prometheus", + "version": "1.0.0" + } + ], + "annotations": { + "list": [ + { + "builtIn": 1, + "datasource": "-- Grafana --", + "enable": true, + "hide": true, + "iconColor": "rgba(0, 211, 255, 1)", + "name": "Annotations & Alerts", + "type": "dashboard" + } + ] + }, + "editable": true, + "gnetId": 12412, + "graphTooltip": 0, + "id": null, + "iteration": 1591284149575, + "links": [], + "panels": [ + { + "cards": { + "cardPadding": null, + "cardRound": null + }, + "color": { + "cardColor": "#b4ff00", + "colorScale": "sqrt", + "colorScheme": "interpolateRdYlGn", + "exponent": 0.5, + "mode": "spectrum" + }, + "dataFormat": "tsbuckets", + "datasource": "${DS_PROMETHEUS}", + "gridPos": { + "h": 8, + "w": 24, + "x": 0, + "y": 0 + }, + "heatmap": {}, + "hideZeroBuckets": false, + "highlightCards": true, + "id": 7, + "legend": { + "show": true + }, + "options": {}, + "reverseYBuckets": true, + "targets": [ + { + "expr": "sum(probe_icmp_duration_seconds{phase=\"rtt\"}) by (instance)", + "legendFormat": "{{instance}}", + "refId": "A" + } + ], + "timeFrom": null, + "timeShift": null, + "title": "ICMP RTT", + "tooltip": { + "show": true, + "showHistogram": true + }, + "type": "heatmap", + "xAxis": { + "show": true + }, + "xBucketNumber": null, + "xBucketSize": null, + "yAxis": { + "decimals": null, + "format": "s", + "logBase": 1, + "max": null, + "min": null, + "show": true, + "splitFactor": null + }, + "yBucketBound": "middle", + "yBucketNumber": null, + "yBucketSize": null + }, + { + "cards": { + "cardPadding": null, + "cardRound": null + }, + "color": { + "cardColor": "#b4ff00", + "colorScale": "sqrt", + "colorScheme": "interpolateRdYlGn", + "exponent": 0.5, + "mode": "spectrum" + }, + "dataFormat": "tsbuckets", + "datasource": "${DS_PROMETHEUS}", + "gridPos": { + "h": 8, + "w": 24, + "x": 0, + "y": 8 + }, + "heatmap": {}, + "hideZeroBuckets": false, + "highlightCards": true, + "id": 8, + "legend": { + "show": true + }, + "options": {}, + "reverseYBuckets": true, + "targets": [ + { + "expr": "1-avg_over_time(probe_success{instance=~\"$instance\"}[$__interval])", + "format": "time_series", + "hide": false, + "legendFormat": "{{instance}}", + "refId": "A" + } + ], + "timeFrom": null, + "timeShift": null, + "title": "ICMP packet loss", + "tooltip": { + "show": true, + "showHistogram": true + }, + "type": "heatmap", + "xAxis": { + "show": true + }, + "xBucketNumber": null, + "xBucketSize": null, + "yAxis": { + "decimals": null, + "format": "percentunit", + "logBase": 1, + "max": null, + "min": null, + "show": true, + "splitFactor": null + }, + "yBucketBound": "middle", + "yBucketNumber": null, + "yBucketSize": null + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "decimals": null, + "description": "This uses the blackbox exporter, which does not expose packet loss, for example. It could be improved with https://github.com/SuperQ/smokeping_prober because it also keeps track of lost samples (https://github.com/SuperQ/smokeping_prober/issues/24). Unfortunately, that still won't make graphs as nice as smokeping, because each probe only keeps one sample, instead of doing multiple like smokeping does (https://github.com/SuperQ/smokeping_prober/issues/36).", + "fill": 0, + "fillGradient": 0, + "gridPos": { + "h": 7, + "w": 24, + "x": 0, + "y": 16 + }, + "hiddenSeries": false, + "id": 2, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "hideEmpty": false, + "hideZero": false, + "max": true, + "min": true, + "rightSide": false, + "show": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "maxPerRow": 2, + "nullPointMode": "connected", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 0.5, + "points": false, + "renderer": "flot", + "repeat": "instance", + "repeatDirection": "v", + "seriesOverrides": [ + { + "alias": "packet loss", + "color": "#C4162A", + "lines": false, + "pointradius": 1, + "points": true, + "yaxis": 2 + } + ], + "spaceLength": 10, + "stack": false, + "steppedLine": true, + "targets": [ + { + "expr": "sum(probe_icmp_duration_seconds{phase=\"rtt\",instance=~\"$instance\"}) by (instance) > 0", + "instant": false, + "legendFormat": "RTT", + "refId": "A" + }, + { + "expr": "1-avg_over_time(probe_success{instance=~\"$instance\"}[$__interval])", + "format": "time_series", + "legendFormat": "packet loss", + "refId": "B" + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "ICMP round trip time ($instance)", + "tooltip": { + "shared": true, + "sort": 1, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "decimals": null, + "format": "dtdurations", + "label": "RTT", + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "format": "percentunit", + "label": "packet loss", + "logBase": 1, + "max": "1", + "min": "0.0001", + "show": true + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + } + ], + "refresh": false, + "schemaVersion": 21, + "style": "dark", + "tags": [], + "templating": { + "list": [ + { + "current": { + "selected": false, + "text": "default", + "value": "default" + }, + "hide": 0, + "includeAll": false, + "label": "datasource", + "multi": false, + "name": "DS_PROMETHEUS", + "options": [], + "query": "prometheus", + "refresh": 1, + "regex": "", + "skipUrlSync": false, + "type": "datasource" + }, + { + "allValue": null, + "current": {}, + "datasource": "${DS_PROMETHEUS}", + "definition": "label_values(probe_success, instance)", + "hide": 0, + "includeAll": true, + "label": null, + "multi": true, + "name": "instance", + "options": [], + "query": "label_values(probe_success, instance)", + "refresh": 2, + "regex": "", + "skipUrlSync": false, + "sort": 0, + "tagValuesQuery": "", + "tags": [], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-4h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ] + }, + "timezone": "", + "title": "ICMP exporter", + "version": 1, + "description": "Graph ICMP metrics from the blackbox exporter, Smokeping-style" +}
\ No newline at end of file diff --git a/terraform-ci-infra/1n_nmd/grafana/conf/consul.json b/terraform-ci-infra/1n_nmd/grafana/conf/consul.json new file mode 100644 index 0000000000..2e4a36f076 --- /dev/null +++ b/terraform-ci-infra/1n_nmd/grafana/conf/consul.json @@ -0,0 +1,1438 @@ +{ + "__inputs": [ + { + "name": "DS_PROMETHEUS", + "label": "Prometheus", + "description": "", + "type": "datasource", + "pluginId": "prometheus", + "pluginName": "Prometheus" + } + ], + "__requires": [ + { + "type": "grafana", + "id": "grafana", + "name": "Grafana", + "version": "4.3.0-beta1" + }, + { + "type": "panel", + "id": "graph", + "name": "Graph", + "version": "" + }, + { + "type": "datasource", + "id": "prometheus", + "name": "Prometheus", + "version": "1.0.0" + }, + { + "type": "panel", + "id": "singlestat", + "name": "Singlestat", + "version": "" + } + ], + "annotations": { + "list": [] + }, + "editable": true, + "gnetId": 2351, + "graphTooltip": 0, + "hideControls": false, + "id": null, + "links": [], + "rows": [ + { + "collapse": false, + "height": 153, + "panels": [ + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "rgba(245, 54, 54, 0.9)", + "rgba(237, 129, 40, 0.89)", + "rgba(50, 172, 45, 0.97)" + ], + "datasource": "${DS_PROMETHEUS}", + "format": "none", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "id": 1, + "interval": null, + "links": [], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "span": 2, + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "consul_raft_leader_lastcontact_count", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "{{host}}", + "refId": "A", + "step": 60 + } + ], + "thresholds": "", + "title": "Consul Leader", + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "name" + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "rgba(245, 54, 54, 0.9)", + "rgba(237, 129, 40, 0.89)", + "rgba(50, 172, 45, 0.97)" + ], + "datasource": "${DS_PROMETHEUS}", + "format": "none", + "gauge": { + "maxValue": 3, + "minValue": 0, + "show": true, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "id": 17, + "interval": null, + "links": [], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "span": 2, + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "COUNT (changes(consul_memberlist_gossep_sum[1m]) > 0) BY (labels)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 60 + } + ], + "thresholds": "1,2", + "title": "# servers in cluster", + "type": "singlestat", + "valueFontSize": "100%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "current" + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "rgba(245, 54, 54, 0.9)", + "rgba(237, 129, 40, 0.89)", + "rgba(50, 172, 45, 0.97)" + ], + "datasource": "${DS_PROMETHEUS}", + "decimals": null, + "format": "percent", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": true, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "id": 18, + "interval": null, + "links": [], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "span": 2, + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "sum(irate(node_cpu{mode=\"idle\", host=\"$consul\"}[1m])) * 100 / count_scalar(node_cpu{mode=\"user\", host=\"$consul\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 60 + } + ], + "thresholds": "", + "title": "CPU Idle", + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "avg" + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "rgba(50, 172, 45, 0.97)", + "rgba(237, 129, 40, 0.89)", + "rgba(245, 54, 54, 0.9)" + ], + "datasource": "${DS_PROMETHEUS}", + "format": "none", + "gauge": { + "maxValue": 4, + "minValue": 0, + "show": true, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "id": 14, + "interval": null, + "links": [], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "span": 2, + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "node_load1{host=\"$consul\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 60 + } + ], + "thresholds": "1,2", + "title": "Load 1", + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "avg" + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "rgba(50, 172, 45, 0.97)", + "rgba(237, 129, 40, 0.89)", + "rgba(245, 54, 54, 0.9)" + ], + "datasource": "${DS_PROMETHEUS}", + "format": "none", + "gauge": { + "maxValue": 4, + "minValue": 0, + "show": true, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "id": 15, + "interval": null, + "links": [], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "span": 2, + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "node_load5{host=\"$consul\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 60 + } + ], + "thresholds": "1,2", + "title": "Load 5", + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "avg" + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "rgba(50, 172, 45, 0.97)", + "rgba(237, 129, 40, 0.89)", + "rgba(245, 54, 54, 0.9)" + ], + "datasource": "${DS_PROMETHEUS}", + "format": "none", + "gauge": { + "maxValue": 4, + "minValue": 0, + "show": true, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "id": 16, + "interval": null, + "links": [], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "span": 2, + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "node_load15{host=\"$consul\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 60 + } + ], + "thresholds": "1,2", + "title": "Load 15", + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "avg" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6" + }, + { + "collapse": false, + "height": 250, + "panels": [ + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "description": "The amount of TCP messages that are sent/received from the server.", + "fill": 1, + "id": 3, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "irate(consul_memberlist_tcp{host=\"$consul\"}[1m])", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "{{type}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "Memberlist TCP Messages", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "description": "The amount of UDP messages that are sent/received from the server.", + "fill": 1, + "id": 5, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "irate(consul_memberlist_udp{host=\"$consul\"}[1m])", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "{{type}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "Memberlist UDP Messages", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "none", + "label": null, + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6" + }, + { + "collapse": false, + "height": 250, + "panels": [ + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "description": "This measures the time it takes to replicate log entries to followers. This is a general indicator of the load pressure on the Consul servers, as well as the performance of the communication between the servers.", + "fill": 1, + "id": 6, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "consul_raft_replication_appendEntries_rpc", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "{{query}} - {{quantile}}%", + "refId": "A", + "step": 10 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "Log replication from leader to servers", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "fill": 1, + "id": 7, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "consul_raft_replication_heartbeat", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "{{query}} - {{quantile}}%", + "refId": "A", + "step": 10 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "consul_raft_replication_heartbeat", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6" + }, + { + "collapse": false, + "height": 250, + "panels": [ + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "description": "This measures the time it takes for the leader to write log entries to disk.", + "fill": 1, + "id": 8, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "consul_raft_leader_dispatchLog", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "{{quantile}}%", + "refId": "A", + "step": 10 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "Write logs", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "description": "This measures the time it takes to commit a new entry to the Raft log on the leader.", + "fill": 1, + "id": 4, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "consul_raft_commitTime", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "{{quantile}}%", + "refId": "A", + "step": 10 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "Commit time Leader", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6" + }, + { + "collapse": false, + "height": 250, + "panels": [ + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "description": "This counts the number of Raft transactions occurring over the interval, which is a general indicator of the write load on the Consul servers.", + "fill": 1, + "id": 9, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "delta(consul_raft_apply[30s])", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "Transactions", + "refId": "A", + "step": 10 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "Raft Transactions", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "description": "This will only be emitted by the Raft leader and measures the time since the leader was last able to contact the follower nodes when checking its leader lease. It can be used as a measure for how stable the Raft timing is and how close the leader is to timing out its lease.\n\nThe lease timeout is 500 ms times the raft_multiplier configuration, so this telemetry value should not be getting close to that configured value, otherwise the Raft timing is marginal and might need to be tuned, or more powerful servers might be needed. See the Server Performance guide for more details.", + "fill": 1, + "id": 10, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "consul_raft_leader_lastcontact", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{quantile}}%", + "refId": "A", + "step": 10 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "Leader lastContact", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6" + }, + { + "collapse": false, + "height": 250, + "panels": [ + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "fill": 1, + "id": 12, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "delta(consul_rpc_query{host=\"$consul\"}[30s])", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Requests", + "refId": "A", + "step": 10 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "RPC Requests", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "description": "Consul uses a network tomography system to compute network coordinates for nodes in the cluster. These coordinates allow the network round trip time to be estimated between any two nodes using a very simple calculation. This allows for many useful applications, such as finding the service node nearest a requesting node, or failing over to services in the next closest datacenter.", + "fill": 1, + "id": 13, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "consul_serf_coordinate_adjustment_ms{host=\"$consul\"}", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "{{quantile}}%", + "refId": "A", + "step": 10 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "Serf Coordinates", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [], + "templating": { + "list": [ + { + "current": { + "selected": false, + "text": "default", + "value": "default" + }, + "hide": 0, + "includeAll": false, + "label": "datasource", + "multi": false, + "name": "DS_PROMETHEUS", + "options": [], + "query": "prometheus", + "refresh": 1, + "regex": "", + "skipUrlSync": false, + "type": "datasource" + }, + { + "allValue": null, + "current": {}, + "datasource": "${DS_PROMETHEUS}", + "hide": 0, + "includeAll": false, + "label": null, + "multi": false, + "name": "consul", + "options": [], + "query": "label_values(consul_memberlist_gossep_sum, host)", + "refresh": 1, + "regex": "", + "sort": 0, + "tagValuesQuery": "", + "tags": [], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-4h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "browser", + "title": "Consul", + "version": 1 +}
\ No newline at end of file diff --git a/terraform-ci-infra/1n_nmd/grafana/conf/docker_cadvisor.json b/terraform-ci-infra/1n_nmd/grafana/conf/docker_cadvisor.json new file mode 100644 index 0000000000..bbad614bb4 --- /dev/null +++ b/terraform-ci-infra/1n_nmd/grafana/conf/docker_cadvisor.json @@ -0,0 +1,2040 @@ +{ + "__inputs": [ + { + "name": "DS_PROMETHEUS", + "label": "Prometheus", + "description": "", + "type": "datasource", + "pluginId": "prometheus", + "pluginName": "Prometheus" + } + ], + "__requires": [ + { + "type": "grafana", + "id": "grafana", + "name": "Grafana", + "version": "6.2.4" + }, + { + "type": "panel", + "id": "graph", + "name": "Graph", + "version": "" + }, + { + "type": "datasource", + "id": "prometheus", + "name": "Prometheus", + "version": "1.0.0" + }, + { + "type": "panel", + "id": "singlestat", + "name": "Singlestat", + "version": "" + }, + { + "type": "panel", + "id": "table", + "name": "Table", + "version": "" + } + ], + "annotations": { + "list": [ + { + "builtIn": 1, + "datasource": "-- Grafana --", + "enable": true, + "hide": true, + "iconColor": "rgba(0, 211, 255, 1)", + "name": "Annotations & Alerts", + "type": "dashboard" + } + ] + }, + "description": "A simple overview of the most important Docker host and container metrics. (cAdvisor/Prometheus)", + "editable": true, + "gnetId": 10657, + "graphTooltip": 1, + "id": null, + "iteration": 1564715574785, + "links": [], + "panels": [ + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "rgba(245, 54, 54, 0.9)", + "rgba(237, 129, 40, 0.89)", + "rgba(50, 172, 45, 0.97)" + ], + "datasource": "${DS_PROMETHEUS}", + "decimals": 0, + "editable": true, + "error": false, + "format": "s", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + "h": 4, + "w": 4, + "x": 0, + "y": 0 + }, + "height": "", + "id": 24, + "interval": null, + "links": [], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "options": {}, + "postfix": "", + "postfixFontSize": "30%", + "prefix": "", + "prefixFontSize": "20%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "time() - node_boot_time_seconds{instance=~\"$node:.*\"}", + "format": "time_series", + "hide": false, + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 1800 + } + ], + "thresholds": "", + "title": "Uptime", + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "current" + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "rgba(245, 54, 54, 0.9)", + "rgba(237, 129, 40, 0.89)", + "rgba(50, 172, 45, 0.97)" + ], + "datasource": "${DS_PROMETHEUS}", + "editable": true, + "error": false, + "format": "none", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + "h": 4, + "w": 4, + "x": 4, + "y": 0 + }, + "id": 31, + "interval": null, + "links": [], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "options": {}, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "count(container_last_seen{instance=~\"$node:$port\",job=~\"$job\",image!=\"\"})", + "format": "time_series", + "intervalFactor": 2, + "refId": "A", + "step": 1800 + } + ], + "thresholds": "", + "title": "Containers", + "type": "singlestat", + "valueFontSize": "120%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "current" + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "rgba(50, 172, 45, 0.97)", + "rgba(237, 129, 40, 0.89)", + "rgba(245, 54, 54, 0.9)" + ], + "datasource": "${DS_PROMETHEUS}", + "decimals": 0, + "editable": true, + "error": false, + "format": "decbytes", + "gauge": { + "maxValue": 500000000, + "minValue": 0, + "show": true, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + "h": 4, + "w": 4, + "x": 8, + "y": 0 + }, + "id": 30, + "interval": null, + "links": [], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "options": {}, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "(node_memory_SwapTotal_bytes{instance=~'$node:9100'} - node_memory_SwapFree_bytes{instance=~'$node:9100'})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 1800 + } + ], + "thresholds": "400000000", + "title": "Swap", + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "current" + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "rgba(245, 54, 54, 0.9)", + "rgba(237, 129, 40, 0.89)", + "rgba(50, 172, 45, 0.97)" + ], + "datasource": "${DS_PROMETHEUS}", + "decimals": 0, + "editable": true, + "error": false, + "format": "percentunit", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + "h": 4, + "w": 4, + "x": 12, + "y": 0 + }, + "id": 27, + "interval": null, + "links": [], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "options": {}, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "sparkline": { + "fillColor": "rgba(50, 189, 31, 0.18)", + "full": false, + "lineColor": "rgb(69, 193, 31)", + "show": true + }, + "tableColumn": "", + "targets": [ + { + "expr": "node_load1{instance=~\"$node:9100\"} / count by(job, instance)(count by(job, instance, cpu)(node_cpu_seconds_total{instance=~\"$node:9100\"}))", + "format": "time_series", + "intervalFactor": 2, + "refId": "A", + "step": 1800 + } + ], + "thresholds": "0.8,0.9", + "title": "Load", + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "avg" + }, + { + "alert": { + "conditions": [ + { + "evaluator": { + "params": [ + 10000000000 + ], + "type": "gt" + }, + "query": { + "params": [ + "A", + "5m", + "now" + ] + }, + "reducer": { + "params": [], + "type": "avg" + }, + "type": "query" + } + ], + "executionErrorState": "alerting", + "frequency": "60s", + "handler": 1, + "name": "Available Memory alert", + "noDataState": "keep_state", + "notifications": [ + { + "id": 1 + } + ] + }, + "aliasColors": { + "Available Memory": "#7EB26D", + "Unavailable Memory": "#7EB26D" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "editable": true, + "error": false, + "fill": 1, + "grid": {}, + "gridPos": { + "h": 10, + "w": 4, + "x": 16, + "y": 0 + }, + "id": 20, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": false, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null as zero", + "options": {}, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "container_memory_rss{name=~\".+\"}", + "format": "time_series", + "hide": true, + "intervalFactor": 2, + "legendFormat": "{{__name__}}", + "refId": "D", + "step": 20 + }, + { + "expr": "sum(container_memory_rss{name=~\".+\"})", + "format": "time_series", + "hide": true, + "intervalFactor": 2, + "legendFormat": "{{__name__}}", + "refId": "A", + "step": 20 + }, + { + "expr": "container_memory_usage_bytes{name=~\".+\"}", + "format": "time_series", + "hide": true, + "intervalFactor": 2, + "legendFormat": "{{name}}", + "refId": "B", + "step": 20 + }, + { + "expr": "container_memory_rss{id=\"/\"}", + "format": "time_series", + "hide": true, + "intervalFactor": 2, + "legendFormat": "{{__name__}}", + "refId": "C", + "step": 20 + }, + { + "expr": "sum(container_memory_rss)", + "format": "time_series", + "hide": true, + "intervalFactor": 2, + "legendFormat": "{{__name__}}", + "refId": "E", + "step": 20 + }, + { + "expr": "node_memory_Buffers", + "format": "time_series", + "hide": true, + "intervalFactor": 2, + "legendFormat": "node_memory_Dirty", + "refId": "N", + "step": 30 + }, + { + "expr": "node_memory_MemFree", + "format": "time_series", + "hide": true, + "intervalFactor": 2, + "legendFormat": "{{__name__}}", + "refId": "F", + "step": 20 + }, + { + "expr": "node_memory_MemAvailable", + "format": "time_series", + "hide": true, + "intervalFactor": 2, + "legendFormat": "Available Memory", + "refId": "H", + "step": 20 + }, + { + "expr": "node_memory_MemTotal_bytes{instance=~\"$node:9100\"} - node_memory_MemAvailable_bytes{instance=~\"$node:9100\"}", + "format": "time_series", + "hide": false, + "intervalFactor": 2, + "legendFormat": "Unavailable Memory", + "refId": "G", + "step": 600 + }, + { + "expr": "node_memory_Inactive", + "format": "time_series", + "hide": true, + "intervalFactor": 2, + "legendFormat": "{{__name__}}", + "refId": "I", + "step": 30 + }, + { + "expr": "node_memory_KernelStack", + "format": "time_series", + "hide": true, + "intervalFactor": 2, + "legendFormat": "{{__name__}}", + "refId": "J", + "step": 30 + }, + { + "expr": "node_memory_Active", + "format": "time_series", + "hide": true, + "intervalFactor": 2, + "legendFormat": "{{__name__}}", + "refId": "K", + "step": 30 + }, + { + "expr": "node_memory_MemTotal - (node_memory_Active + node_memory_MemFree + node_memory_Inactive)", + "format": "time_series", + "hide": true, + "intervalFactor": 2, + "legendFormat": "Unknown", + "refId": "L", + "step": 40 + }, + { + "expr": "node_memory_MemFree + node_memory_Inactive ", + "format": "time_series", + "hide": true, + "intervalFactor": 2, + "legendFormat": "{{__name__}}", + "refId": "M", + "step": 30 + }, + { + "expr": "container_memory_rss{name=~\".+\"}", + "format": "time_series", + "hide": true, + "intervalFactor": 2, + "legendFormat": "{{__name__}}", + "refId": "O", + "step": 30 + }, + { + "expr": "node_memory_Inactive + node_memory_MemFree + node_memory_MemAvailable", + "format": "time_series", + "hide": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "P", + "step": 40 + } + ], + "thresholds": [ + { + "colorMode": "critical", + "fill": true, + "line": true, + "op": "gt", + "value": 10000000000, + "yaxis": "left" + } + ], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Available Memory", + "tooltip": { + "msResolution": true, + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": false, + "values": [] + }, + "yaxes": [ + { + "format": "bytes", + "label": "", + "logBase": 1, + "max": 16000000000, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "alert": { + "conditions": [ + { + "evaluator": { + "params": [ + 850000000000 + ], + "type": "gt" + }, + "query": { + "params": [ + "A", + "5m", + "now" + ] + }, + "reducer": { + "params": [], + "type": "avg" + }, + "type": "query" + } + ], + "executionErrorState": "alerting", + "frequency": "60s", + "handler": 1, + "name": "Free/Used Disk Space alert", + "noDataState": "keep_state", + "notifications": [ + { + "id": 1 + } + ] + }, + "aliasColors": { + "Belegete Festplatte": "#BF1B00", + "Free Disk Space": "#7EB26D", + "Used Disk Space": "#7EB26D", + "{}": "#BF1B00" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "editable": true, + "error": false, + "fill": 1, + "grid": {}, + "gridPos": { + "h": 10, + "w": 4, + "x": 20, + "y": 0 + }, + "id": 13, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": false, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null as zero", + "options": {}, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "Used Disk Space", + "yaxis": 1 + } + ], + "spaceLength": 10, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "node_filesystem_size_bytes{fstype=\"rootfs\"} - node_filesystem_free_bytes{fstype=\"rootfs\"}", + "format": "time_series", + "hide": false, + "intervalFactor": 2, + "legendFormat": "Used Disk Space", + "refId": "A", + "step": 600 + } + ], + "thresholds": [ + { + "colorMode": "critical", + "fill": true, + "line": true, + "op": "gt", + "value": 850000000000 + } + ], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Used Disk Space", + "tooltip": { + "msResolution": true, + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": false, + "values": [] + }, + "yaxes": [ + { + "format": "bytes", + "label": "", + "logBase": 1, + "max": 1000000000000, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": { + "SENT": "#BF1B00" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "editable": true, + "error": false, + "fill": 1, + "grid": {}, + "gridPos": { + "h": 6, + "w": 4, + "x": 0, + "y": 4 + }, + "id": 19, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": false, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null as zero", + "options": {}, + "percentage": false, + "pointradius": 1, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(container_network_receive_bytes_total{id=\"/\"}[$interval])) by (id)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "RECEIVED", + "refId": "A", + "step": 600 + }, + { + "expr": "- sum(rate(container_network_transmit_bytes_total{id=\"/\"}[$interval])) by (id)", + "format": "time_series", + "hide": false, + "intervalFactor": 2, + "legendFormat": "SENT", + "refId": "B", + "step": 600 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Network Traffic", + "tooltip": { + "msResolution": true, + "shared": true, + "sort": 0, + "value_type": "cumulative" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": false, + "values": [] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "rgba(50, 172, 45, 0.97)", + "rgba(237, 129, 40, 0.89)", + "rgba(245, 54, 54, 0.9)" + ], + "datasource": "${DS_PROMETHEUS}", + "decimals": 0, + "editable": true, + "error": false, + "format": "percent", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": true, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + "h": 6, + "w": 4, + "x": 4, + "y": 4 + }, + "id": 25, + "interval": null, + "links": [], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "options": {}, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "((node_memory_MemTotal_bytes{instance=~\"$node:9100\"} - node_memory_MemAvailable_bytes{instance=~\"$node:9100\"}) / node_memory_MemTotal_bytes{instance=~\"$node:9100\"}) * 100", + "format": "time_series", + "intervalFactor": 2, + "refId": "A", + "step": 1800 + } + ], + "thresholds": "70, 90", + "title": "Memory", + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "current" + }, + { + "aliasColors": { + "{id=\"/\",instance=\"cadvisor:8080\",job=\"prometheus\"}": "#BA43A9" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "editable": true, + "error": false, + "fill": 1, + "grid": {}, + "gridPos": { + "h": 6, + "w": 4, + "x": 8, + "y": 4 + }, + "id": 5, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": false, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null as zero", + "options": {}, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(container_cpu_system_seconds_total[1m]))", + "format": "time_series", + "hide": true, + "intervalFactor": 2, + "legendFormat": "a", + "refId": "B", + "step": 120 + }, + { + "expr": "sum(rate(container_cpu_system_seconds_total{name=~\".+\"}[1m]))", + "format": "time_series", + "hide": true, + "interval": "", + "intervalFactor": 2, + "legendFormat": "nur container", + "refId": "F", + "step": 10 + }, + { + "expr": "sum(rate(container_cpu_system_seconds_total{id=\"/\"}[1m]))", + "format": "time_series", + "hide": true, + "interval": "", + "intervalFactor": 2, + "legendFormat": "nur docker host", + "metric": "", + "refId": "A", + "step": 20 + }, + { + "expr": "sum(rate(process_cpu_seconds_total[$interval])) * 100", + "format": "time_series", + "hide": false, + "interval": "", + "intervalFactor": 2, + "legendFormat": "host", + "metric": "", + "refId": "C", + "step": 600 + }, + { + "expr": "sum(rate(container_cpu_system_seconds_total{name=~\".+\"}[1m])) + sum(rate(container_cpu_system_seconds_total{id=\"/\"}[1m])) + sum(rate(process_cpu_seconds_total[1m]))", + "format": "time_series", + "hide": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "D", + "step": 120 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "CPU Usage", + "tooltip": { + "msResolution": true, + "shared": true, + "sort": 0, + "value_type": "cumulative" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": false, + "values": [] + }, + "yaxes": [ + { + "format": "percent", + "label": "", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": { + "IN on /sda": "#7EB26D", + "OUT on /sda": "#890F02" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "editable": true, + "error": false, + "fill": 1, + "grid": {}, + "gridPos": { + "h": 6, + "w": 4, + "x": 12, + "y": 4 + }, + "id": 3, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": false, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null as zero", + "options": {}, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "-sum(rate(node_disk_read_bytes_total[$interval])) by (device)", + "format": "time_series", + "hide": false, + "intervalFactor": 2, + "legendFormat": "OUT on /{{device}}", + "metric": "node_disk_bytes_read", + "refId": "A", + "step": 600 + }, + { + "expr": "sum(rate(node_disk_written_bytes_total[$interval])) by (device)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "IN on /{{device}}", + "metric": "", + "refId": "B", + "step": 600 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Disk I/O", + "tooltip": { + "msResolution": true, + "shared": true, + "sort": 0, + "value_type": "cumulative" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": false, + "values": [] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "editable": true, + "error": false, + "fill": 1, + "grid": {}, + "gridPos": { + "h": 7, + "w": 12, + "x": 0, + "y": 10 + }, + "id": 8, + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [], + "nullPointMode": "null as zero", + "options": {}, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(container_network_receive_bytes_total{instance=~\"$node:$port\",job=~\"$job\",image!=\"\"}[$interval])) by (name)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{name}}", + "refId": "A", + "step": 240 + }, + { + "expr": "- rate(container_network_transmit_bytes_total{name=~\".+\"}[$interval])", + "format": "time_series", + "hide": true, + "intervalFactor": 2, + "legendFormat": "{{name}}", + "refId": "B", + "step": 10 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Received Network Traffic per Container", + "tooltip": { + "msResolution": true, + "shared": true, + "sort": 0, + "value_type": "cumulative" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "editable": true, + "error": false, + "fill": 1, + "grid": {}, + "gridPos": { + "h": 7, + "w": 12, + "x": 12, + "y": 10 + }, + "id": 9, + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "hideEmpty": false, + "hideZero": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [], + "nullPointMode": "null as zero", + "options": {}, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(container_network_transmit_bytes_total{instance=~\"$node:$port\",job=~\"$job\",image!=\"\"}[$interval])) by (name)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{name}}", + "refId": "A", + "step": 240 + }, + { + "expr": "rate(container_network_transmit_bytes_total{id=\"/\"}[$interval])", + "format": "time_series", + "hide": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "B", + "step": 10 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Sent Network Traffic per Container", + "tooltip": { + "msResolution": true, + "shared": true, + "sort": 0, + "value_type": "cumulative" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "Bps", + "label": "", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": "", + "logBase": 10, + "max": 8, + "min": 0, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "editable": true, + "error": false, + "fill": 5, + "grid": {}, + "gridPos": { + "h": 7, + "w": 12, + "x": 0, + "y": 17 + }, + "id": 1, + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null as zero", + "options": {}, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(container_cpu_usage_seconds_total{instance=~\"$node:$port\",job=~\"$job\",image!=\"\"}[$interval])) by (name) * 100", + "format": "time_series", + "hide": false, + "interval": "", + "intervalFactor": 2, + "legendFormat": "{{name}}", + "metric": "", + "refId": "F", + "step": 240 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "CPU Usage per Container", + "tooltip": { + "msResolution": true, + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "percent", + "label": "", + "logBase": 1, + "max": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "editable": true, + "error": false, + "fill": 3, + "grid": {}, + "gridPos": { + "h": 7, + "w": 12, + "x": 12, + "y": 17 + }, + "id": 34, + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [], + "nullPointMode": "null as zero", + "options": {}, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(container_memory_swap{instance=~\"$node:$port\",job=~\"$job\",image!=\"\"}) by (name)", + "format": "time_series", + "hide": false, + "intervalFactor": 2, + "legendFormat": "{{name}}", + "refId": "A", + "step": 240 + }, + { + "expr": "container_memory_usage_bytes{name=~\".+\"}", + "format": "time_series", + "hide": true, + "intervalFactor": 2, + "legendFormat": "{{name}}", + "refId": "B", + "step": 240 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Memory Swap per Container", + "tooltip": { + "msResolution": true, + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "bytes", + "label": "", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "editable": true, + "error": false, + "fill": 3, + "grid": {}, + "gridPos": { + "h": 7, + "w": 12, + "x": 0, + "y": 24 + }, + "id": 10, + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [], + "nullPointMode": "null as zero", + "options": {}, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(container_memory_rss{instance=~\"$node:$port\",job=~\"$job\",image!=\"\"}) by (name)", + "format": "time_series", + "hide": false, + "intervalFactor": 2, + "legendFormat": "{{name}}", + "refId": "A", + "step": 240 + }, + { + "expr": "container_memory_usage_bytes{name=~\".+\"}", + "format": "time_series", + "hide": true, + "intervalFactor": 2, + "legendFormat": "{{name}}", + "refId": "B", + "step": 240 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Memory Usage per Container", + "tooltip": { + "msResolution": true, + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "bytes", + "label": "", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "columns": [ + { + "text": "Current", + "value": "current" + } + ], + "editable": true, + "error": false, + "fontSize": "100%", + "gridPos": { + "h": 7, + "w": 12, + "x": 12, + "y": 24 + }, + "id": 36, + "links": [], + "options": {}, + "pageSize": null, + "scroll": true, + "showHeader": true, + "sort": { + "col": 0, + "desc": true + }, + "styles": [ + { + "colorMode": null, + "colors": [ + "rgba(245, 54, 54, 0.9)", + "rgba(237, 129, 40, 0.89)", + "rgba(50, 172, 45, 0.97)" + ], + "decimals": 2, + "pattern": "/.*/", + "thresholds": [ + "10000000", + " 25000000" + ], + "type": "number", + "unit": "decbytes" + } + ], + "targets": [ + { + "expr": "sum(container_spec_memory_limit_bytes{name=~\".+\"} - container_memory_usage_bytes{name=~\".+\"}) by (name) ", + "format": "table", + "hide": true, + "intervalFactor": 2, + "legendFormat": "{{name}}", + "metric": "", + "refId": "A", + "step": 240 + }, + { + "expr": "sum(container_spec_memory_limit_bytes{instance=~\"$node:$port\",job=~\"$job\",image!=\"\"}) by (name) ", + "format": "table", + "hide": false, + "intervalFactor": 2, + "legendFormat": "{{name}}", + "refId": "B", + "step": 240 + }, + { + "expr": "container_memory_usage_bytes{name=~\".+\"}", + "format": "table", + "hide": true, + "intervalFactor": 2, + "legendFormat": "{{name}}", + "refId": "C", + "step": 240 + } + ], + "title": "Limit memory", + "transform": "table", + "type": "table" + } + ], + "refresh": "5m", + "schemaVersion": 18, + "style": "dark", + "tags": [], + "templating": { + "list": [ + { + "current": { + "selected": false, + "text": "default", + "value": "default" + }, + "hide": 0, + "includeAll": false, + "label": "datasource", + "multi": false, + "name": "DS_PROMETHEUS", + "options": [], + "query": "prometheus", + "refresh": 1, + "regex": "", + "skipUrlSync": false, + "type": "datasource" + }, + { + "allValue": null, + "current": {}, + "datasource": "${DS_PROMETHEUS}", + "definition": "label_values(container_cpu_user_seconds_total, job)", + "hide": 0, + "includeAll": false, + "label": "Job", + "multi": false, + "name": "job", + "options": [], + "query": "label_values(container_cpu_user_seconds_total, job)", + "refresh": 1, + "regex": "", + "skipUrlSync": false, + "sort": 1, + "tagValuesQuery": "", + "tags": [], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": {}, + "datasource": "${DS_PROMETHEUS}", + "definition": "label_values(container_cpu_user_seconds_total{job=~\"$job\"}, instance)", + "hide": 0, + "includeAll": false, + "label": "Host:", + "multi": false, + "name": "node", + "options": [], + "query": "label_values(container_cpu_user_seconds_total{job=~\"$job\"}, instance)", + "refresh": 1, + "regex": "/([^:]+):.*/", + "skipUrlSync": false, + "sort": 1, + "tagValuesQuery": null, + "tags": [], + "tagsQuery": null, + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": {}, + "datasource": "${DS_PROMETHEUS}", + "definition": "label_values(container_cpu_user_seconds_total{instance=~\"$node:(.*)\"}, instance)", + "hide": 0, + "includeAll": false, + "label": "Port", + "multi": false, + "name": "port", + "options": [], + "query": "label_values(container_cpu_user_seconds_total{instance=~\"$node:(.*)\"}, instance)", + "refresh": 1, + "regex": "/[^:]+:(.*)/", + "skipUrlSync": false, + "sort": 3, + "tagValuesQuery": "", + "tags": [], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "auto": true, + "auto_count": 30, + "auto_min": "50s", + "current": { + "text": "1m", + "value": "1m" + }, + "hide": 0, + "label": "Interval", + "name": "interval", + "options": [ + { + "selected": false, + "text": "auto", + "value": "$__auto_interval_interval" + }, + { + "selected": true, + "text": "1m", + "value": "1m" + }, + { + "selected": false, + "text": "5m", + "value": "5m" + }, + { + "selected": false, + "text": "10m", + "value": "10m" + }, + { + "selected": false, + "text": "30m", + "value": "30m" + }, + { + "selected": false, + "text": "1h", + "value": "1h" + }, + { + "selected": false, + "text": "6h", + "value": "6h" + }, + { + "selected": false, + "text": "12h", + "value": "12h" + }, + { + "selected": false, + "text": "1d", + "value": "1d" + }, + { + "selected": false, + "text": "7d", + "value": "7d" + }, + { + "selected": false, + "text": "14d", + "value": "14d" + }, + { + "selected": false, + "text": "30d", + "value": "30d" + } + ], + "query": "1m,5m,10m,30m,1h,6h,12h,1d,7d,14d,30d", + "refresh": 2, + "skipUrlSync": false, + "type": "interval" + } + ] + }, + "time": { + "from": "now-4h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "browser", + "title": "Docker cAdvisor", + "version": 1 +} diff --git a/terraform-ci-infra/1n_nmd/grafana/conf/node_exporter.json b/terraform-ci-infra/1n_nmd/grafana/conf/node_exporter.json new file mode 100644 index 0000000000..766d5afec3 --- /dev/null +++ b/terraform-ci-infra/1n_nmd/grafana/conf/node_exporter.json @@ -0,0 +1,13696 @@ +{ + "__inputs": [ + { + "name": "DS_PROMETHEUS", + "label": "Prometheus", + "description": "", + "type": "datasource", + "pluginId": "prometheus", + "pluginName": "Prometheus" + } + ], + "__requires": [ + { + "type": "panel", + "id": "gauge", + "name": "Gauge", + "version": "" + }, + { + "type": "grafana", + "id": "grafana", + "name": "Grafana", + "version": "6.7.3" + }, + { + "type": "panel", + "id": "graph", + "name": "Graph", + "version": "" + }, + { + "type": "datasource", + "id": "prometheus", + "name": "Prometheus", + "version": "1.0.0" + }, + { + "type": "panel", + "id": "singlestat", + "name": "Singlestat", + "version": "" + } + ], + "annotations": { + "list": [ + { + "$$hashKey": "object:1058", + "builtIn": 1, + "datasource": "-- Grafana --", + "enable": true, + "hide": true, + "iconColor": "rgba(0, 211, 255, 1)", + "name": "Annotations & Alerts", + "type": "dashboard" + } + ] + }, + "editable": true, + "gnetId": 1860, + "graphTooltip": 0, + "id": null, + "iteration": 1595837627257, + "links": [], + "panels": [ + { + "collapsed": false, + "datasource": "${DS_PROMETHEUS}", + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 0 + }, + "id": 261, + "panels": [], + "repeat": null, + "title": "Quick CPU / Mem / Disk", + "type": "row" + }, + { + "cacheTimeout": null, + "datasource": "${DS_PROMETHEUS}", + "description": "Busy state of all CPU cores together", + "gridPos": { + "h": 4, + "w": 3, + "x": 0, + "y": 1 + }, + "id": 20, + "links": [], + "options": { + "fieldOptions": { + "calcs": [ + "lastNotNull" + ], + "defaults": { + "color": { + "mode": "thresholds" + }, + "mappings": [ + { + "id": 0, + "op": "=", + "text": "N/A", + "type": 1, + "value": "null" + } + ], + "max": 100, + "min": 0, + "nullValueMode": "null", + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "rgba(50, 172, 45, 0.97)", + "value": null + }, + { + "color": "rgba(237, 129, 40, 0.89)", + "value": 85 + }, + { + "color": "rgba(245, 54, 54, 0.9)", + "value": 95 + } + ] + }, + "unit": "percent" + }, + "overrides": [], + "values": false + }, + "orientation": "horizontal", + "showThresholdLabels": false, + "showThresholdMarkers": true + }, + "pluginVersion": "6.7.3", + "targets": [ + { + "expr": "(((count(count(node_cpu_seconds_total{instance=\"$node\",job=\"$job\"}) by (cpu))) - avg(sum by (mode)(irate(node_cpu_seconds_total{mode='idle',instance=\"$node\",job=\"$job\"}[5m])))) * 100) / count(count(node_cpu_seconds_total{instance=\"$node\",job=\"$job\"}) by (cpu))", + "hide": false, + "intervalFactor": 1, + "legendFormat": "", + "refId": "A", + "step": 900 + } + ], + "title": "CPU Busy", + "type": "gauge" + }, + { + "cacheTimeout": null, + "datasource": "${DS_PROMETHEUS}", + "description": "Busy state of all CPU cores together (5 min average)", + "gridPos": { + "h": 4, + "w": 3, + "x": 3, + "y": 1 + }, + "id": 155, + "links": [], + "options": { + "fieldOptions": { + "calcs": [ + "lastNotNull" + ], + "defaults": { + "color": { + "mode": "thresholds" + }, + "mappings": [ + { + "id": 0, + "op": "=", + "text": "N/A", + "type": 1, + "value": "null" + } + ], + "max": 100, + "min": 0, + "nullValueMode": "null", + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "rgba(50, 172, 45, 0.97)", + "value": null + }, + { + "color": "rgba(237, 129, 40, 0.89)", + "value": 85 + }, + { + "color": "rgba(245, 54, 54, 0.9)", + "value": 95 + } + ] + }, + "unit": "percent" + }, + "overrides": [], + "values": false + }, + "orientation": "horizontal", + "showThresholdLabels": false, + "showThresholdMarkers": true + }, + "pluginVersion": "6.7.3", + "targets": [ + { + "expr": "avg(node_load5{instance=\"$node\",job=\"$job\"}) / count(count(node_cpu_seconds_total{instance=\"$node\",job=\"$job\"}) by (cpu)) * 100", + "format": "time_series", + "hide": false, + "intervalFactor": 1, + "refId": "A", + "step": 900 + } + ], + "title": "Sys Load (5m avg)", + "type": "gauge" + }, + { + "cacheTimeout": null, + "datasource": "${DS_PROMETHEUS}", + "description": "Busy state of all CPU cores together (15 min average)", + "gridPos": { + "h": 4, + "w": 3, + "x": 6, + "y": 1 + }, + "id": 19, + "links": [], + "options": { + "fieldOptions": { + "calcs": [ + "lastNotNull" + ], + "defaults": { + "color": { + "mode": "thresholds" + }, + "mappings": [ + { + "id": 0, + "op": "=", + "text": "N/A", + "type": 1, + "value": "null" + } + ], + "max": 100, + "min": 0, + "nullValueMode": "null", + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "rgba(50, 172, 45, 0.97)", + "value": null + }, + { + "color": "rgba(237, 129, 40, 0.89)", + "value": 85 + }, + { + "color": "rgba(245, 54, 54, 0.9)", + "value": 95 + } + ] + }, + "unit": "percent" + }, + "overrides": [], + "values": false + }, + "orientation": "horizontal", + "showThresholdLabels": false, + "showThresholdMarkers": true + }, + "pluginVersion": "6.7.3", + "targets": [ + { + "expr": "avg(node_load15{instance=\"$node\",job=\"$job\"}) / count(count(node_cpu_seconds_total{instance=\"$node\",job=\"$job\"}) by (cpu)) * 100", + "hide": false, + "intervalFactor": 1, + "refId": "A", + "step": 900 + } + ], + "title": "Sys Load (15m avg)", + "type": "gauge" + }, + { + "cacheTimeout": null, + "datasource": "${DS_PROMETHEUS}", + "description": "Non available RAM memory", + "gridPos": { + "h": 4, + "w": 3, + "x": 9, + "y": 1 + }, + "hideTimeOverride": false, + "id": 16, + "links": [], + "options": { + "fieldOptions": { + "calcs": [ + "lastNotNull" + ], + "defaults": { + "color": { + "mode": "thresholds" + }, + "decimals": 0, + "mappings": [], + "max": 100, + "min": 0, + "nullValueMode": "null", + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "rgba(50, 172, 45, 0.97)", + "value": null + }, + { + "color": "rgba(237, 129, 40, 0.89)", + "value": 80 + }, + { + "color": "rgba(245, 54, 54, 0.9)", + "value": 90 + } + ] + }, + "unit": "percent" + }, + "overrides": [], + "values": false + }, + "orientation": "horizontal", + "showThresholdLabels": false, + "showThresholdMarkers": true + }, + "pluginVersion": "6.7.3", + "targets": [ + { + "expr": "((node_memory_MemTotal_bytes{instance=\"$node\",job=\"$job\"} - node_memory_MemFree_bytes{instance=\"$node\",job=\"$job\"}) / (node_memory_MemTotal_bytes{instance=\"$node\",job=\"$job\"} )) * 100", + "format": "time_series", + "hide": true, + "intervalFactor": 1, + "refId": "A", + "step": 900 + }, + { + "expr": "100 - ((node_memory_MemAvailable_bytes{instance=\"$node\",job=\"$job\"} * 100) / node_memory_MemTotal_bytes{instance=\"$node\",job=\"$job\"})", + "format": "time_series", + "hide": false, + "intervalFactor": 1, + "refId": "B", + "step": 900 + } + ], + "title": "RAM Used", + "type": "gauge" + }, + { + "cacheTimeout": null, + "datasource": "${DS_PROMETHEUS}", + "description": "Used Swap", + "gridPos": { + "h": 4, + "w": 3, + "x": 12, + "y": 1 + }, + "id": 21, + "links": [], + "options": { + "fieldOptions": { + "calcs": [ + "lastNotNull" + ], + "defaults": { + "color": { + "mode": "thresholds" + }, + "mappings": [ + { + "id": 0, + "op": "=", + "text": "N/A", + "type": 1, + "value": "null" + } + ], + "max": 100, + "min": 0, + "nullValueMode": "null", + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "rgba(50, 172, 45, 0.97)", + "value": null + }, + { + "color": "rgba(237, 129, 40, 0.89)", + "value": 10 + }, + { + "color": "rgba(245, 54, 54, 0.9)", + "value": 25 + } + ] + }, + "unit": "percent" + }, + "overrides": [], + "values": false + }, + "orientation": "horizontal", + "showThresholdLabels": false, + "showThresholdMarkers": true + }, + "pluginVersion": "6.7.3", + "targets": [ + { + "expr": "((node_memory_SwapTotal_bytes{instance=\"$node\",job=\"$job\"} - node_memory_SwapFree_bytes{instance=\"$node\",job=\"$job\"}) / (node_memory_SwapTotal_bytes{instance=\"$node\",job=\"$job\"} )) * 100", + "intervalFactor": 1, + "refId": "A", + "step": 900 + } + ], + "title": "SWAP Used", + "type": "gauge" + }, + { + "cacheTimeout": null, + "datasource": "${DS_PROMETHEUS}", + "description": "Used Root FS", + "gridPos": { + "h": 4, + "w": 3, + "x": 15, + "y": 1 + }, + "id": 154, + "links": [], + "options": { + "fieldOptions": { + "calcs": [ + "lastNotNull" + ], + "defaults": { + "color": { + "mode": "thresholds" + }, + "mappings": [ + { + "id": 0, + "op": "=", + "text": "N/A", + "type": 1, + "value": "null" + } + ], + "max": 100, + "min": 0, + "nullValueMode": "null", + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "rgba(50, 172, 45, 0.97)", + "value": null + }, + { + "color": "rgba(237, 129, 40, 0.89)", + "value": 80 + }, + { + "color": "rgba(245, 54, 54, 0.9)", + "value": 90 + } + ] + }, + "unit": "percent" + }, + "overrides": [], + "values": false + }, + "orientation": "horizontal", + "showThresholdLabels": false, + "showThresholdMarkers": true + }, + "pluginVersion": "6.7.3", + "targets": [ + { + "expr": "100 - ((node_filesystem_avail_bytes{instance=\"$node\",job=\"$job\",mountpoint=\"/\",fstype!=\"rootfs\"} * 100) / node_filesystem_size_bytes{instance=\"$node\",job=\"$job\",mountpoint=\"/\",fstype!=\"rootfs\"})", + "format": "time_series", + "intervalFactor": 1, + "refId": "A", + "step": 900 + } + ], + "title": "Root FS Used", + "type": "gauge" + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "rgba(245, 54, 54, 0.9)", + "rgba(237, 129, 40, 0.89)", + "rgba(50, 172, 45, 0.97)" + ], + "datasource": "${DS_PROMETHEUS}", + "description": "Total number of CPU cores", + "format": "short", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + "h": 2, + "w": 2, + "x": 18, + "y": 1 + }, + "id": 14, + "interval": null, + "links": [], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "maxPerRow": 6, + "nullPointMode": "null", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "count(count(node_cpu_seconds_total{instance=\"$node\",job=\"$job\"}) by (cpu))", + "interval": "", + "intervalFactor": 1, + "legendFormat": "", + "refId": "A", + "step": 900 + } + ], + "thresholds": "", + "title": "CPU Cores", + "type": "singlestat", + "valueFontSize": "50%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "current" + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "rgba(245, 54, 54, 0.9)", + "rgba(237, 129, 40, 0.89)", + "rgba(50, 172, 45, 0.97)" + ], + "datasource": "${DS_PROMETHEUS}", + "decimals": 1, + "description": "System uptime", + "format": "s", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + "h": 2, + "w": 4, + "x": 20, + "y": 1 + }, + "hideTimeOverride": true, + "id": 15, + "interval": null, + "links": [], + "mappingType": 1, + "mappingTypes": [ + { + "$$hashKey": "object:1094", + "name": "value to text", + "value": 1 + }, + { + "$$hashKey": "object:1095", + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "null", + "nullText": null, + "postfix": "s", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "node_time_seconds{instance=\"$node\",job=\"$job\"} - node_boot_time_seconds{instance=\"$node\",job=\"$job\"}", + "intervalFactor": 2, + "refId": "A", + "step": 1800 + } + ], + "thresholds": "", + "title": "Uptime", + "type": "singlestat", + "valueFontSize": "50%", + "valueMaps": [ + { + "$$hashKey": "object:1097", + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "current" + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "rgba(50, 172, 45, 0.97)", + "rgba(237, 129, 40, 0.89)", + "rgba(245, 54, 54, 0.9)" + ], + "datasource": "${DS_PROMETHEUS}", + "decimals": 0, + "description": "Total RootFS", + "format": "bytes", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + "h": 2, + "w": 2, + "x": 18, + "y": 3 + }, + "id": 23, + "interval": null, + "links": [], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "maxPerRow": 6, + "nullPointMode": "null", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "node_filesystem_size_bytes{instance=\"$node\",job=\"$job\",mountpoint=\"/\",fstype!=\"rootfs\"}", + "format": "time_series", + "hide": false, + "intervalFactor": 1, + "refId": "A", + "step": 900 + } + ], + "thresholds": "70,90", + "title": "RootFS Total", + "type": "singlestat", + "valueFontSize": "50%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "current" + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "rgba(245, 54, 54, 0.9)", + "rgba(237, 129, 40, 0.89)", + "rgba(50, 172, 45, 0.97)" + ], + "datasource": "${DS_PROMETHEUS}", + "decimals": 0, + "description": "Total RAM", + "format": "bytes", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + "h": 2, + "w": 2, + "x": 20, + "y": 3 + }, + "id": 75, + "interval": null, + "links": [], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "maxPerRow": 6, + "nullPointMode": "null", + "nullText": null, + "postfix": "", + "postfixFontSize": "70%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "node_memory_MemTotal_bytes{instance=\"$node\",job=\"$job\"}", + "intervalFactor": 1, + "refId": "A", + "step": 900 + } + ], + "thresholds": "", + "title": "RAM Total", + "type": "singlestat", + "valueFontSize": "50%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "current" + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "rgba(245, 54, 54, 0.9)", + "rgba(237, 129, 40, 0.89)", + "rgba(50, 172, 45, 0.97)" + ], + "datasource": "${DS_PROMETHEUS}", + "decimals": 0, + "description": "Total SWAP", + "format": "bytes", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + "h": 2, + "w": 2, + "x": 22, + "y": 3 + }, + "id": 18, + "interval": null, + "links": [], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "maxPerRow": 6, + "nullPointMode": "null", + "nullText": null, + "postfix": "", + "postfixFontSize": "70%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "node_memory_SwapTotal_bytes{instance=\"$node\",job=\"$job\"}", + "intervalFactor": 1, + "refId": "A", + "step": 900 + } + ], + "thresholds": "", + "title": "SWAP Total", + "type": "singlestat", + "valueFontSize": "50%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "current" + }, + { + "collapsed": false, + "datasource": "${DS_PROMETHEUS}", + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 5 + }, + "id": 263, + "panels": [], + "repeat": null, + "title": "Basic CPU / Mem / Net / Disk", + "type": "row" + }, + { + "aliasColors": { + "Busy": "#EAB839", + "Busy Iowait": "#890F02", + "Busy other": "#1F78C1", + "Idle": "#052B51", + "Idle - Waiting for something to happen": "#052B51", + "guest": "#9AC48A", + "idle": "#052B51", + "iowait": "#EAB839", + "irq": "#BF1B00", + "nice": "#C15C17", + "softirq": "#E24D42", + "steal": "#FCE2DE", + "system": "#508642", + "user": "#5195CE" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "decimals": 2, + "description": "Basic CPU info", + "fill": 4, + "fillGradient": 0, + "gridPos": { + "h": 7, + "w": 12, + "x": 0, + "y": 6 + }, + "hiddenSeries": false, + "id": 77, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": 250, + "sort": null, + "sortDesc": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "maxPerRow": 6, + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": true, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "Busy Iowait", + "color": "#890F02" + }, + { + "alias": "Idle", + "color": "#7EB26D" + }, + { + "alias": "Busy System", + "color": "#EAB839" + }, + { + "alias": "Busy User", + "color": "#0A437C" + }, + { + "alias": "Busy Other", + "color": "#6D1F62" + } + ], + "spaceLength": 10, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by (instance)(irate(node_cpu_seconds_total{mode=\"system\",instance=\"$node\",job=\"$job\"}[5m])) * 100", + "format": "time_series", + "hide": false, + "intervalFactor": 2, + "legendFormat": "Busy System", + "refId": "A", + "step": 240 + }, + { + "expr": "sum by (instance)(irate(node_cpu_seconds_total{mode='user',instance=\"$node\",job=\"$job\"}[5m])) * 100", + "format": "time_series", + "hide": false, + "intervalFactor": 2, + "legendFormat": "Busy User", + "refId": "B", + "step": 240 + }, + { + "expr": "sum by (instance)(irate(node_cpu_seconds_total{mode='iowait',instance=\"$node\",job=\"$job\"}[5m])) * 100", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Busy Iowait", + "refId": "C", + "step": 240 + }, + { + "expr": "sum by (instance)(irate(node_cpu_seconds_total{mode=~\".*irq\",instance=\"$node\",job=\"$job\"}[5m])) * 100", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Busy IRQs", + "refId": "D", + "step": 240 + }, + { + "expr": "sum (irate(node_cpu_seconds_total{mode!='idle',mode!='user',mode!='system',mode!='iowait',mode!='irq',mode!='softirq',instance=\"$node\",job=\"$job\"}[5m])) * 100", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Busy Other", + "refId": "E", + "step": 240 + }, + { + "expr": "sum by (mode)(irate(node_cpu_seconds_total{mode='idle',instance=\"$node\",job=\"$job\"}[5m])) * 100", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Idle", + "refId": "F", + "step": 240 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "CPU Basic", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "short", + "label": "", + "logBase": 1, + "max": "100", + "min": "0", + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": { + "Apps": "#629E51", + "Buffers": "#614D93", + "Cache": "#6D1F62", + "Cached": "#511749", + "Committed": "#508642", + "Free": "#0A437C", + "Hardware Corrupted - Amount of RAM that the kernel identified as corrupted / not working": "#CFFAFF", + "Inactive": "#584477", + "PageTables": "#0A50A1", + "Page_Tables": "#0A50A1", + "RAM_Free": "#E0F9D7", + "SWAP Used": "#BF1B00", + "Slab": "#806EB7", + "Slab_Cache": "#E0752D", + "Swap": "#BF1B00", + "Swap Used": "#BF1B00", + "Swap_Cache": "#C15C17", + "Swap_Free": "#2F575E", + "Unused": "#EAB839" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "decimals": 2, + "description": "Basic memory usage", + "fill": 4, + "fillGradient": 0, + "gridPos": { + "h": 7, + "w": 12, + "x": 12, + "y": 6 + }, + "hiddenSeries": false, + "id": 78, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": 350, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "maxPerRow": 6, + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "RAM Total", + "color": "#E0F9D7", + "fill": 0, + "stack": false + }, + { + "alias": "RAM Cache + Buffer", + "color": "#052B51" + }, + { + "alias": "RAM Free", + "color": "#7EB26D" + }, + { + "alias": "Avaliable", + "color": "#DEDAF7", + "fill": 0, + "stack": false + } + ], + "spaceLength": 10, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "node_memory_MemTotal_bytes{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "hide": false, + "intervalFactor": 2, + "legendFormat": "RAM Total", + "refId": "A", + "step": 240 + }, + { + "expr": "node_memory_MemTotal_bytes{instance=\"$node\",job=\"$job\"} - node_memory_MemFree_bytes{instance=\"$node\",job=\"$job\"} - (node_memory_Cached_bytes{instance=\"$node\",job=\"$job\"} + node_memory_Buffers_bytes{instance=\"$node\",job=\"$job\"})", + "format": "time_series", + "hide": false, + "intervalFactor": 2, + "legendFormat": "RAM Used", + "refId": "B", + "step": 240 + }, + { + "expr": "node_memory_Cached_bytes{instance=\"$node\",job=\"$job\"} + node_memory_Buffers_bytes{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "RAM Cache + Buffer", + "refId": "C", + "step": 240 + }, + { + "expr": "node_memory_MemFree_bytes{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "RAM Free", + "refId": "D", + "step": 240 + }, + { + "expr": "(node_memory_SwapTotal_bytes{instance=\"$node\",job=\"$job\"} - node_memory_SwapFree_bytes{instance=\"$node\",job=\"$job\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "SWAP Used", + "refId": "E", + "step": 240 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Memory Basic", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "bytes", + "label": "", + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": { + "Recv_bytes_eth2": "#7EB26D", + "Recv_bytes_lo": "#0A50A1", + "Recv_drop_eth2": "#6ED0E0", + "Recv_drop_lo": "#E0F9D7", + "Recv_errs_eth2": "#BF1B00", + "Recv_errs_lo": "#CCA300", + "Trans_bytes_eth2": "#7EB26D", + "Trans_bytes_lo": "#0A50A1", + "Trans_drop_eth2": "#6ED0E0", + "Trans_drop_lo": "#E0F9D7", + "Trans_errs_eth2": "#BF1B00", + "Trans_errs_lo": "#CCA300", + "recv_bytes_lo": "#0A50A1", + "recv_drop_eth0": "#99440A", + "recv_drop_lo": "#967302", + "recv_errs_eth0": "#BF1B00", + "recv_errs_lo": "#890F02", + "trans_bytes_eth0": "#7EB26D", + "trans_bytes_lo": "#0A50A1", + "trans_drop_eth0": "#99440A", + "trans_drop_lo": "#967302", + "trans_errs_eth0": "#BF1B00", + "trans_errs_lo": "#890F02" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "description": "Basic network info per interface", + "fill": 4, + "fillGradient": 0, + "gridPos": { + "h": 7, + "w": 12, + "x": 0, + "y": 13 + }, + "hiddenSeries": false, + "id": 74, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "hideEmpty": false, + "hideZero": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sort": "current", + "sortDesc": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "/.*trans.*/", + "transform": "negative-Y" + } + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "irate(node_network_receive_bytes_total{instance=\"$node\",job=\"$job\"}[5m])*8", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "recv {{device}}", + "refId": "A", + "step": 240 + }, + { + "expr": "irate(node_network_transmit_bytes_total{instance=\"$node\",job=\"$job\"}[5m])*8", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "trans {{device}} ", + "refId": "B", + "step": 240 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Network Traffic Basic", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "bps", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "pps", + "label": "", + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "decimals": 3, + "description": "Disk space used of all filesystems mounted", + "fill": 4, + "fillGradient": 0, + "gridPos": { + "h": 7, + "w": 12, + "x": 12, + "y": 13 + }, + "height": "", + "hiddenSeries": false, + "id": 152, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sort": "current", + "sortDesc": false, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "maxPerRow": 6, + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "100 - ((node_filesystem_avail_bytes{instance=\"$node\",job=\"$job\",device!~'rootfs'} * 100) / node_filesystem_size_bytes{instance=\"$node\",job=\"$job\",device!~'rootfs'})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{mountpoint}}", + "refId": "A", + "step": 240 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Disk Space Used Basic", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "percent", + "label": null, + "logBase": 1, + "max": "100", + "min": "0", + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "collapsed": true, + "datasource": "${DS_PROMETHEUS}", + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 20 + }, + "id": 265, + "panels": [ + { + "aliasColors": { + "Idle - Waiting for something to happen": "#052B51", + "guest": "#9AC48A", + "idle": "#052B51", + "iowait": "#EAB839", + "irq": "#BF1B00", + "nice": "#C15C17", + "softirq": "#E24D42", + "steal": "#FCE2DE", + "system": "#508642", + "user": "#5195CE" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "decimals": 2, + "description": "", + "fill": 4, + "fillGradient": 0, + "gridPos": { + "h": 12, + "w": 12, + "x": 0, + "y": 21 + }, + "hiddenSeries": false, + "id": 3, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": true, + "min": true, + "rightSide": false, + "show": true, + "sideWidth": 250, + "sort": null, + "sortDesc": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "maxPerRow": 6, + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": true, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [], + "spaceLength": 10, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by (mode)(irate(node_cpu_seconds_total{mode=\"system\",instance=\"$node\",job=\"$job\"}[5m])) * 100", + "format": "time_series", + "interval": "10s", + "intervalFactor": 2, + "legendFormat": "System - Processes executing in kernel mode", + "refId": "A", + "step": 20 + }, + { + "expr": "sum by (mode)(irate(node_cpu_seconds_total{mode='user',instance=\"$node\",job=\"$job\"}[5m])) * 100", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "User - Normal processes executing in user mode", + "refId": "B", + "step": 240 + }, + { + "expr": "sum by (mode)(irate(node_cpu_seconds_total{mode='nice',instance=\"$node\",job=\"$job\"}[5m])) * 100", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Nice - Niced processes executing in user mode", + "refId": "C", + "step": 240 + }, + { + "expr": "sum by (mode)(irate(node_cpu_seconds_total{mode='idle',instance=\"$node\",job=\"$job\"}[5m])) * 100", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Idle - Waiting for something to happen", + "refId": "D", + "step": 240 + }, + { + "expr": "sum by (mode)(irate(node_cpu_seconds_total{mode='iowait',instance=\"$node\",job=\"$job\"}[5m])) * 100", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Iowait - Waiting for I/O to complete", + "refId": "E", + "step": 240 + }, + { + "expr": "sum by (mode)(irate(node_cpu_seconds_total{mode='irq',instance=\"$node\",job=\"$job\"}[5m])) * 100", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Irq - Servicing interrupts", + "refId": "F", + "step": 240 + }, + { + "expr": "sum by (mode)(irate(node_cpu_seconds_total{mode='softirq',instance=\"$node\",job=\"$job\"}[5m])) * 100", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Softirq - Servicing softirqs", + "refId": "G", + "step": 240 + }, + { + "expr": "sum by (mode)(irate(node_cpu_seconds_total{mode='steal',instance=\"$node\",job=\"$job\"}[5m])) * 100", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Steal - Time spent in other operating systems when running in a virtualized environment", + "refId": "H", + "step": 240 + }, + { + "expr": "sum by (mode)(irate(node_cpu_seconds_total{mode='guest',instance=\"$node\",job=\"$job\"}[5m])) * 100", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Guest - Time spent running a virtual CPU for a guest operating system", + "refId": "I", + "step": 240 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "CPU", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "short", + "label": "percentage", + "logBase": 1, + "max": "100", + "min": "0", + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": { + "Apps": "#629E51", + "Buffers": "#614D93", + "Cache": "#6D1F62", + "Cached": "#511749", + "Committed": "#508642", + "Free": "#0A437C", + "Hardware Corrupted - Amount of RAM that the kernel identified as corrupted / not working": "#CFFAFF", + "Inactive": "#584477", + "PageTables": "#0A50A1", + "Page_Tables": "#0A50A1", + "RAM_Free": "#E0F9D7", + "Slab": "#806EB7", + "Slab_Cache": "#E0752D", + "Swap": "#BF1B00", + "Swap - Swap memory usage": "#BF1B00", + "Swap_Cache": "#C15C17", + "Swap_Free": "#2F575E", + "Unused": "#EAB839", + "Unused - Free memory unassigned": "#052B51" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "decimals": 2, + "description": "", + "fill": 4, + "fillGradient": 0, + "gridPos": { + "h": 12, + "w": 12, + "x": 12, + "y": 21 + }, + "hiddenSeries": false, + "id": 24, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": true, + "min": true, + "rightSide": false, + "show": true, + "sideWidth": 350, + "sort": null, + "sortDesc": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "maxPerRow": 6, + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "/.*Hardware Corrupted - *./", + "stack": false + } + ], + "spaceLength": 10, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "node_memory_MemTotal_bytes{instance=\"$node\",job=\"$job\"} - node_memory_MemFree_bytes{instance=\"$node\",job=\"$job\"} - node_memory_Buffers_bytes{instance=\"$node\",job=\"$job\"} - node_memory_Cached_bytes{instance=\"$node\",job=\"$job\"} - node_memory_Slab_bytes{instance=\"$node\",job=\"$job\"} - node_memory_PageTables_bytes{instance=\"$node\",job=\"$job\"} - node_memory_SwapCached_bytes{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "hide": false, + "intervalFactor": 2, + "legendFormat": "Apps - Memory used by user-space applications", + "refId": "A", + "step": 240 + }, + { + "expr": "node_memory_PageTables_bytes{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "hide": false, + "intervalFactor": 2, + "legendFormat": "PageTables - Memory used to map between virtual and physical memory addresses", + "refId": "B", + "step": 240 + }, + { + "expr": "node_memory_SwapCached_bytes{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "SwapCache - Memory that keeps track of pages that have been fetched from swap but not yet been modified", + "refId": "C", + "step": 240 + }, + { + "expr": "node_memory_Slab_bytes{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "hide": false, + "intervalFactor": 2, + "legendFormat": "Slab - Memory used by the kernel to cache data structures for its own use (caches like inode, dentry, etc)", + "refId": "D", + "step": 240 + }, + { + "expr": "node_memory_Cached_bytes{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "hide": false, + "intervalFactor": 2, + "legendFormat": "Cache - Parked file data (file content) cache", + "refId": "E", + "step": 240 + }, + { + "expr": "node_memory_Buffers_bytes{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "hide": false, + "intervalFactor": 2, + "legendFormat": "Buffers - Block device (e.g. harddisk) cache", + "refId": "F", + "step": 240 + }, + { + "expr": "node_memory_MemFree_bytes{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "hide": false, + "intervalFactor": 2, + "legendFormat": "Unused - Free memory unassigned", + "refId": "G", + "step": 240 + }, + { + "expr": "(node_memory_SwapTotal_bytes{instance=\"$node\",job=\"$job\"} - node_memory_SwapFree_bytes{instance=\"$node\",job=\"$job\"})", + "format": "time_series", + "hide": false, + "intervalFactor": 2, + "legendFormat": "Swap - Swap space used", + "refId": "H", + "step": 240 + }, + { + "expr": "node_memory_HardwareCorrupted_bytes{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "hide": false, + "intervalFactor": 2, + "legendFormat": "Hardware Corrupted - Amount of RAM that the kernel identified as corrupted / not working", + "refId": "I", + "step": 240 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Memory Stack", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "bytes", + "label": "bytes", + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": { + "receive_packets_eth0": "#7EB26D", + "receive_packets_lo": "#E24D42", + "transmit_packets_eth0": "#7EB26D", + "transmit_packets_lo": "#E24D42" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "fill": 4, + "fillGradient": 0, + "gridPos": { + "h": 12, + "w": 12, + "x": 0, + "y": 33 + }, + "hiddenSeries": false, + "id": 84, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": true, + "min": true, + "rightSide": false, + "show": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "$$hashKey": "object:5871", + "alias": "/.*Trans.*/", + "transform": "negative-Y" + } + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "irate(node_network_receive_bytes_total{instance=\"$node\",job=\"$job\"}[5m])*8", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{device}} - Receive", + "refId": "A", + "step": 240 + }, + { + "expr": "irate(node_network_transmit_bytes_total{instance=\"$node\",job=\"$job\"}[5m])*8", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{device}} - Transmit", + "refId": "B", + "step": 240 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Network Traffic", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "$$hashKey": "object:5884", + "format": "bps", + "label": "bits out (-) / in (+)", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "$$hashKey": "object:5885", + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "decimals": 3, + "description": "", + "fill": 4, + "fillGradient": 0, + "gridPos": { + "h": 12, + "w": 12, + "x": 12, + "y": 33 + }, + "height": "", + "hiddenSeries": false, + "id": 156, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": true, + "min": true, + "rightSide": false, + "show": true, + "sort": "current", + "sortDesc": false, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "maxPerRow": 6, + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "node_filesystem_size_bytes{instance=\"$node\",job=\"$job\",device!~'rootfs'} - node_filesystem_avail_bytes{instance=\"$node\",job=\"$job\",device!~'rootfs'}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{mountpoint}}", + "refId": "A", + "step": 240 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Disk Space Used", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "bytes", + "label": "bytes", + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "description": "", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 12, + "w": 12, + "x": 0, + "y": 45 + }, + "hiddenSeries": false, + "id": 229, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "hideZero": true, + "max": true, + "min": true, + "rightSide": false, + "show": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "maxPerRow": 6, + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "/.*Read.*/", + "transform": "negative-Y" + }, + { + "alias": "/.*sda_.*/", + "color": "#7EB26D" + }, + { + "alias": "/.*sdb_.*/", + "color": "#EAB839" + }, + { + "alias": "/.*sdc_.*/", + "color": "#6ED0E0" + }, + { + "alias": "/.*sdd_.*/", + "color": "#EF843C" + }, + { + "alias": "/.*sde_.*/", + "color": "#E24D42" + }, + { + "alias": "/.*sda1.*/", + "color": "#584477" + }, + { + "alias": "/.*sda2_.*/", + "color": "#BA43A9" + }, + { + "alias": "/.*sda3_.*/", + "color": "#F4D598" + }, + { + "alias": "/.*sdb1.*/", + "color": "#0A50A1" + }, + { + "alias": "/.*sdb2.*/", + "color": "#BF1B00" + }, + { + "alias": "/.*sdb2.*/", + "color": "#BF1B00" + }, + { + "alias": "/.*sdb3.*/", + "color": "#E0752D" + }, + { + "alias": "/.*sdc1.*/", + "color": "#962D82" + }, + { + "alias": "/.*sdc2.*/", + "color": "#614D93" + }, + { + "alias": "/.*sdc3.*/", + "color": "#9AC48A" + }, + { + "alias": "/.*sdd1.*/", + "color": "#65C5DB" + }, + { + "alias": "/.*sdd2.*/", + "color": "#F9934E" + }, + { + "alias": "/.*sdd3.*/", + "color": "#EA6460" + }, + { + "alias": "/.*sde1.*/", + "color": "#E0F9D7" + }, + { + "alias": "/.*sdd2.*/", + "color": "#FCEACA" + }, + { + "alias": "/.*sde3.*/", + "color": "#F9E2D2" + } + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "irate(node_disk_reads_completed_total{instance=\"$node\",job=\"$job\",device=~\"$diskdevices\"}[5m])", + "intervalFactor": 4, + "legendFormat": "{{device}} - Reads completed", + "refId": "A", + "step": 480 + }, + { + "expr": "irate(node_disk_writes_completed_total{instance=\"$node\",job=\"$job\",device=~\"$diskdevices\"}[5m])", + "intervalFactor": 2, + "legendFormat": "{{device}} - Writes completed", + "refId": "B", + "step": 240 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Disk IOps", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "iops", + "label": "IO read (-) / write (+)", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": { + "io time": "#890F02" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "decimals": 3, + "description": "", + "fill": 4, + "fillGradient": 0, + "gridPos": { + "h": 12, + "w": 12, + "x": 12, + "y": 45 + }, + "hiddenSeries": false, + "id": 42, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": true, + "min": true, + "rightSide": false, + "show": true, + "sort": null, + "sortDesc": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "maxPerRow": 6, + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "/.*read*./", + "transform": "negative-Y" + }, + { + "alias": "/.*sda.*/", + "color": "#7EB26D" + }, + { + "alias": "/.*sdb.*/", + "color": "#EAB839" + }, + { + "alias": "/.*sdc.*/", + "color": "#6ED0E0" + }, + { + "alias": "/.*sdd.*/", + "color": "#EF843C" + }, + { + "alias": "/.*sde.*/", + "color": "#E24D42" + } + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "irate(node_disk_read_bytes_total{instance=\"$node\",job=\"$job\",device=~\"$diskdevices\"}[5m])", + "format": "time_series", + "hide": false, + "intervalFactor": 2, + "legendFormat": "{{device}} - Successfully read bytes", + "refId": "A", + "step": 240 + }, + { + "expr": "irate(node_disk_written_bytes_total{instance=\"$node\",job=\"$job\",device=~\"$diskdevices\"}[5m])", + "format": "time_series", + "hide": false, + "intervalFactor": 2, + "legendFormat": "{{device}} - Successfully written bytes", + "refId": "B", + "step": 240 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "I/O Usage Read / Write", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": false, + "values": [] + }, + "yaxes": [ + { + "format": "bytes", + "label": "bytes read (-) / write (+)", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "ms", + "label": "", + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": { + "io time": "#890F02" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "decimals": 3, + "description": "", + "fill": 4, + "fillGradient": 0, + "gridPos": { + "h": 12, + "w": 12, + "x": 0, + "y": 57 + }, + "hiddenSeries": false, + "id": 127, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": true, + "min": true, + "rightSide": false, + "show": true, + "sort": null, + "sortDesc": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "maxPerRow": 6, + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "irate(node_disk_io_time_seconds_total{instance=\"$node\",job=\"$job\",device=~\"$diskdevices\"} [5m])", + "format": "time_series", + "hide": false, + "intervalFactor": 2, + "legendFormat": "{{device}} - Time spent doing I/Os", + "refId": "A", + "step": 240 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "I/O Usage Times", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": false, + "values": [] + }, + "yaxes": [ + { + "format": "s", + "label": "time", + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "format": "s", + "label": "", + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + } + ], + "repeat": null, + "title": "CPU / Memory / Net / Disk", + "type": "row" + }, + { + "collapsed": true, + "datasource": "${DS_PROMETHEUS}", + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 21 + }, + "id": 266, + "panels": [ + { + "aliasColors": { + "Apps": "#629E51", + "Buffers": "#614D93", + "Cache": "#6D1F62", + "Cached": "#511749", + "Committed": "#508642", + "Free": "#0A437C", + "Hardware Corrupted - Amount of RAM that the kernel identified as corrupted / not working": "#CFFAFF", + "Inactive": "#584477", + "PageTables": "#0A50A1", + "Page_Tables": "#0A50A1", + "RAM_Free": "#E0F9D7", + "Slab": "#806EB7", + "Slab_Cache": "#E0752D", + "Swap": "#BF1B00", + "Swap_Cache": "#C15C17", + "Swap_Free": "#2F575E", + "Unused": "#EAB839" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "decimals": 2, + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 0, + "y": 70 + }, + "hiddenSeries": false, + "id": 136, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": true, + "min": true, + "rightSide": false, + "show": true, + "sideWidth": 350, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "maxPerRow": 2, + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "node_memory_Inactive_bytes{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Inactive - Memory which has been less recently used. It is more eligible to be reclaimed for other purposes", + "refId": "A", + "step": 4 + }, + { + "expr": "node_memory_Active_bytes{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Active - Memory that has been used more recently and usually not reclaimed unless absolutely necessary", + "refId": "B", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Memory Active / Inactive", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "cumulative" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "bytes", + "label": "bytes", + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": { + "Apps": "#629E51", + "Buffers": "#614D93", + "Cache": "#6D1F62", + "Cached": "#511749", + "Committed": "#508642", + "Free": "#0A437C", + "Hardware Corrupted - Amount of RAM that the kernel identified as corrupted / not working": "#CFFAFF", + "Inactive": "#584477", + "PageTables": "#0A50A1", + "Page_Tables": "#0A50A1", + "RAM_Free": "#E0F9D7", + "Slab": "#806EB7", + "Slab_Cache": "#E0752D", + "Swap": "#BF1B00", + "Swap_Cache": "#C15C17", + "Swap_Free": "#2F575E", + "Unused": "#EAB839" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "decimals": 2, + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 12, + "y": 70 + }, + "hiddenSeries": false, + "id": 135, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": true, + "min": true, + "rightSide": false, + "show": true, + "sideWidth": 350, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "maxPerRow": 6, + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "/.*Committed_AS - *./" + }, + { + "alias": "/.*CommitLimit - *./", + "color": "#BF1B00", + "fill": 0 + } + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "node_memory_Committed_AS_bytes{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Committed_AS - Amount of memory presently allocated on the system", + "refId": "A", + "step": 4 + }, + { + "expr": "node_memory_CommitLimit_bytes{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "CommitLimit - Amount of memory currently available to be allocated on the system", + "refId": "B", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Memory Commited", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "cumulative" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "bytes", + "label": "bytes", + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": { + "Apps": "#629E51", + "Buffers": "#614D93", + "Cache": "#6D1F62", + "Cached": "#511749", + "Committed": "#508642", + "Free": "#0A437C", + "Hardware Corrupted - Amount of RAM that the kernel identified as corrupted / not working": "#CFFAFF", + "Inactive": "#584477", + "PageTables": "#0A50A1", + "Page_Tables": "#0A50A1", + "RAM_Free": "#E0F9D7", + "Slab": "#806EB7", + "Slab_Cache": "#E0752D", + "Swap": "#BF1B00", + "Swap_Cache": "#C15C17", + "Swap_Free": "#2F575E", + "Unused": "#EAB839" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "decimals": 2, + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 0, + "y": 80 + }, + "hiddenSeries": false, + "id": 191, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": true, + "min": true, + "rightSide": false, + "show": true, + "sideWidth": 350, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "maxPerRow": 6, + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "node_memory_Inactive_file_bytes{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "hide": false, + "intervalFactor": 2, + "legendFormat": "Inactive_file - File-backed memory on inactive LRU list", + "refId": "A", + "step": 4 + }, + { + "expr": "node_memory_Inactive_anon_bytes{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "hide": false, + "intervalFactor": 2, + "legendFormat": "Inactive_anon - Anonymous and swap cache on inactive LRU list, including tmpfs (shmem)", + "refId": "B", + "step": 4 + }, + { + "expr": "node_memory_Active_file_bytes{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "hide": false, + "intervalFactor": 2, + "legendFormat": "Active_file - File-backed memory on active LRU list", + "refId": "C", + "step": 4 + }, + { + "expr": "node_memory_Active_anon_bytes{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "hide": false, + "intervalFactor": 2, + "legendFormat": "Active_anon - Anonymous and swap cache on active least-recently-used (LRU) list, including tmpfs", + "refId": "D", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Memory Active / Inactive Detail", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "cumulative" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "bytes", + "label": "bytes", + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": { + "Active": "#99440A", + "Buffers": "#58140C", + "Cache": "#6D1F62", + "Cached": "#511749", + "Committed": "#508642", + "Dirty": "#6ED0E0", + "Free": "#B7DBAB", + "Inactive": "#EA6460", + "Mapped": "#052B51", + "PageTables": "#0A50A1", + "Page_Tables": "#0A50A1", + "Slab_Cache": "#EAB839", + "Swap": "#BF1B00", + "Swap_Cache": "#C15C17", + "Total": "#511749", + "Total RAM": "#052B51", + "Total RAM + Swap": "#052B51", + "Total Swap": "#614D93", + "VmallocUsed": "#EA6460" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "decimals": 2, + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 12, + "y": 80 + }, + "hiddenSeries": false, + "id": 130, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": true, + "min": true, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "maxPerRow": 2, + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "node_memory_Writeback_bytes{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Writeback - Memory which is actively being written back to disk", + "refId": "A", + "step": 4 + }, + { + "expr": "node_memory_WritebackTmp_bytes{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "WritebackTmp - Memory used by FUSE for temporary writeback buffers", + "refId": "B", + "step": 4 + }, + { + "expr": "node_memory_Dirty_bytes{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Dirty - Memory which is waiting to get written back to the disk", + "refId": "C", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Memory Writeback and Dirty", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "bytes", + "label": "bytes", + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": { + "Apps": "#629E51", + "Buffers": "#614D93", + "Cache": "#6D1F62", + "Cached": "#511749", + "Committed": "#508642", + "Free": "#0A437C", + "Hardware Corrupted - Amount of RAM that the kernel identified as corrupted / not working": "#CFFAFF", + "Inactive": "#584477", + "PageTables": "#0A50A1", + "Page_Tables": "#0A50A1", + "RAM_Free": "#E0F9D7", + "Slab": "#806EB7", + "Slab_Cache": "#E0752D", + "Swap": "#BF1B00", + "Swap_Cache": "#C15C17", + "Swap_Free": "#2F575E", + "Unused": "#EAB839" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "decimals": 2, + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 0, + "y": 90 + }, + "hiddenSeries": false, + "id": 138, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": true, + "min": true, + "rightSide": false, + "show": true, + "sideWidth": 350, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "maxPerRow": 6, + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "$$hashKey": "object:4131", + "alias": "ShmemHugePages - Memory used by shared memory (shmem) and tmpfs allocated with huge pages", + "fill": 0 + }, + { + "$$hashKey": "object:4138", + "alias": "ShmemHugePages - Memory used by shared memory (shmem) and tmpfs allocated with huge pages", + "fill": 0 + } + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "node_memory_Mapped_bytes{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Mapped - Used memory in mapped pages files which have been mmaped, such as libraries", + "refId": "A", + "step": 4 + }, + { + "expr": "node_memory_Shmem_bytes{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Shmem - Used shared memory (shared between several processes, thus including RAM disks)", + "refId": "B", + "step": 4 + }, + { + "expr": "node_memory_ShmemHugePages_bytes{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "ShmemHugePages - Memory used by shared memory (shmem) and tmpfs allocated with huge pages", + "refId": "C", + "step": 4 + }, + { + "expr": "node_memory_ShmemPmdMapped_bytes{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "ShmemPmdMapped - Ammount of shared (shmem/tmpfs) memory backed by huge pages", + "refId": "D", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Memory Shared and Mapped", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "cumulative" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "$$hashKey": "object:4106", + "format": "bytes", + "label": "bytes", + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "$$hashKey": "object:4107", + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": { + "Active": "#99440A", + "Buffers": "#58140C", + "Cache": "#6D1F62", + "Cached": "#511749", + "Committed": "#508642", + "Dirty": "#6ED0E0", + "Free": "#B7DBAB", + "Inactive": "#EA6460", + "Mapped": "#052B51", + "PageTables": "#0A50A1", + "Page_Tables": "#0A50A1", + "Slab_Cache": "#EAB839", + "Swap": "#BF1B00", + "Swap_Cache": "#C15C17", + "Total": "#511749", + "Total RAM": "#052B51", + "Total RAM + Swap": "#052B51", + "Total Swap": "#614D93", + "VmallocUsed": "#EA6460" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "decimals": 2, + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 12, + "y": 90 + }, + "hiddenSeries": false, + "id": 131, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": true, + "min": true, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "maxPerRow": 2, + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "node_memory_SUnreclaim_bytes{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "SUnreclaim - Part of Slab, that cannot be reclaimed on memory pressure", + "refId": "A", + "step": 4 + }, + { + "expr": "node_memory_SReclaimable_bytes{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "SReclaimable - Part of Slab, that might be reclaimed, such as caches", + "refId": "B", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Memory Slab", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "bytes", + "label": "bytes", + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": { + "Active": "#99440A", + "Buffers": "#58140C", + "Cache": "#6D1F62", + "Cached": "#511749", + "Committed": "#508642", + "Dirty": "#6ED0E0", + "Free": "#B7DBAB", + "Inactive": "#EA6460", + "Mapped": "#052B51", + "PageTables": "#0A50A1", + "Page_Tables": "#0A50A1", + "Slab_Cache": "#EAB839", + "Swap": "#BF1B00", + "Swap_Cache": "#C15C17", + "Total": "#511749", + "Total RAM": "#052B51", + "Total RAM + Swap": "#052B51", + "VmallocUsed": "#EA6460" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "decimals": 2, + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 0, + "y": 100 + }, + "hiddenSeries": false, + "id": 70, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": true, + "min": true, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "maxPerRow": 6, + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "node_memory_VmallocChunk_bytes{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "hide": false, + "intervalFactor": 2, + "legendFormat": "VmallocChunk - Largest contigious block of vmalloc area which is free", + "refId": "A", + "step": 4 + }, + { + "expr": "node_memory_VmallocTotal_bytes{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "hide": false, + "intervalFactor": 2, + "legendFormat": "VmallocTotal - Total size of vmalloc memory area", + "refId": "B", + "step": 4 + }, + { + "expr": "node_memory_VmallocUsed_bytes{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "hide": false, + "intervalFactor": 2, + "legendFormat": "VmallocUsed - Amount of vmalloc area which is used", + "refId": "C", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Memory Vmalloc", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "bytes", + "label": "bytes", + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": { + "Apps": "#629E51", + "Buffers": "#614D93", + "Cache": "#6D1F62", + "Cached": "#511749", + "Committed": "#508642", + "Free": "#0A437C", + "Hardware Corrupted - Amount of RAM that the kernel identified as corrupted / not working": "#CFFAFF", + "Inactive": "#584477", + "PageTables": "#0A50A1", + "Page_Tables": "#0A50A1", + "RAM_Free": "#E0F9D7", + "Slab": "#806EB7", + "Slab_Cache": "#E0752D", + "Swap": "#BF1B00", + "Swap_Cache": "#C15C17", + "Swap_Free": "#2F575E", + "Unused": "#EAB839" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "decimals": 2, + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 12, + "y": 100 + }, + "hiddenSeries": false, + "id": 159, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": true, + "min": true, + "rightSide": false, + "show": true, + "sideWidth": 350, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "maxPerRow": 6, + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "node_memory_Bounce_bytes{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Bounce - Memory used for block device bounce buffers", + "refId": "A", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Memory Bounce", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "cumulative" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "bytes", + "label": "bytes", + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": { + "Active": "#99440A", + "Buffers": "#58140C", + "Cache": "#6D1F62", + "Cached": "#511749", + "Committed": "#508642", + "Dirty": "#6ED0E0", + "Free": "#B7DBAB", + "Inactive": "#EA6460", + "Mapped": "#052B51", + "PageTables": "#0A50A1", + "Page_Tables": "#0A50A1", + "Slab_Cache": "#EAB839", + "Swap": "#BF1B00", + "Swap_Cache": "#C15C17", + "Total": "#511749", + "Total RAM": "#052B51", + "Total RAM + Swap": "#052B51", + "VmallocUsed": "#EA6460" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "decimals": 2, + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 0, + "y": 110 + }, + "hiddenSeries": false, + "id": 129, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": true, + "min": true, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "maxPerRow": 6, + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "/.*Inactive *./", + "transform": "negative-Y" + } + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "node_memory_AnonHugePages_bytes{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "AnonHugePages - Memory in anonymous huge pages", + "refId": "A", + "step": 4 + }, + { + "expr": "node_memory_AnonPages_bytes{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "AnonPages - Memory in user pages not backed by files", + "refId": "B", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Memory Anonymous", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "bytes", + "label": "bytes", + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": { + "Apps": "#629E51", + "Buffers": "#614D93", + "Cache": "#6D1F62", + "Cached": "#511749", + "Committed": "#508642", + "Free": "#0A437C", + "Hardware Corrupted - Amount of RAM that the kernel identified as corrupted / not working": "#CFFAFF", + "Inactive": "#584477", + "PageTables": "#0A50A1", + "Page_Tables": "#0A50A1", + "RAM_Free": "#E0F9D7", + "Slab": "#806EB7", + "Slab_Cache": "#E0752D", + "Swap": "#BF1B00", + "Swap_Cache": "#C15C17", + "Swap_Free": "#2F575E", + "Unused": "#EAB839" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "decimals": 2, + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 12, + "y": 110 + }, + "hiddenSeries": false, + "id": 160, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": true, + "min": true, + "rightSide": false, + "show": true, + "sideWidth": 350, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "maxPerRow": 2, + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "node_memory_KernelStack_bytes{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "KernelStack - Kernel memory stack. This is not reclaimable", + "refId": "A", + "step": 4 + }, + { + "expr": "node_memory_Percpu_bytes{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "PerCPU - Per CPU memory allocated dynamically by loadable modules", + "refId": "B", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Memory Kernel / CPU", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "cumulative" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "bytes", + "label": "bytes", + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": { + "Active": "#99440A", + "Buffers": "#58140C", + "Cache": "#6D1F62", + "Cached": "#511749", + "Committed": "#508642", + "Dirty": "#6ED0E0", + "Free": "#B7DBAB", + "Inactive": "#EA6460", + "Mapped": "#052B51", + "PageTables": "#0A50A1", + "Page_Tables": "#0A50A1", + "Slab_Cache": "#EAB839", + "Swap": "#BF1B00", + "Swap_Cache": "#C15C17", + "Total": "#511749", + "Total RAM": "#806EB7", + "Total RAM + Swap": "#806EB7", + "VmallocUsed": "#EA6460" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "decimals": 2, + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 0, + "y": 120 + }, + "hiddenSeries": false, + "id": 140, + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "max": true, + "min": true, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "maxPerRow": 6, + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "node_memory_HugePages_Free{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "HugePages_Free - Huge pages in the pool that are not yet allocated", + "refId": "A", + "step": 4 + }, + { + "expr": "node_memory_HugePages_Rsvd{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "HugePages_Rsvd - Huge pages for which a commitment to allocate from the pool has been made, but no allocation has yet been made", + "refId": "B", + "step": 4 + }, + { + "expr": "node_memory_HugePages_Surp{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "HugePages_Surp - Huge pages in the pool above the value in /proc/sys/vm/nr_hugepages", + "refId": "C", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Memory HugePages Counter", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "short", + "label": "pages", + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "format": "short", + "label": "", + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": { + "Active": "#99440A", + "Buffers": "#58140C", + "Cache": "#6D1F62", + "Cached": "#511749", + "Committed": "#508642", + "Dirty": "#6ED0E0", + "Free": "#B7DBAB", + "Inactive": "#EA6460", + "Mapped": "#052B51", + "PageTables": "#0A50A1", + "Page_Tables": "#0A50A1", + "Slab_Cache": "#EAB839", + "Swap": "#BF1B00", + "Swap_Cache": "#C15C17", + "Total": "#511749", + "Total RAM": "#806EB7", + "Total RAM + Swap": "#806EB7", + "VmallocUsed": "#EA6460" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "decimals": 2, + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 12, + "y": 120 + }, + "hiddenSeries": false, + "id": 71, + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "max": true, + "min": true, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "maxPerRow": 2, + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "node_memory_HugePages_Total{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "HugePages - Total size of the pool of huge pages", + "refId": "A", + "step": 4 + }, + { + "expr": "node_memory_Hugepagesize_bytes{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Hugepagesize - Huge Page size", + "refId": "B", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Memory HugePages Size", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "bytes", + "label": "bytes", + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "format": "short", + "label": "", + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": { + "Active": "#99440A", + "Buffers": "#58140C", + "Cache": "#6D1F62", + "Cached": "#511749", + "Committed": "#508642", + "Dirty": "#6ED0E0", + "Free": "#B7DBAB", + "Inactive": "#EA6460", + "Mapped": "#052B51", + "PageTables": "#0A50A1", + "Page_Tables": "#0A50A1", + "Slab_Cache": "#EAB839", + "Swap": "#BF1B00", + "Swap_Cache": "#C15C17", + "Total": "#511749", + "Total RAM": "#052B51", + "Total RAM + Swap": "#052B51", + "VmallocUsed": "#EA6460" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "decimals": 2, + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 0, + "y": 130 + }, + "hiddenSeries": false, + "id": 128, + "legend": { + "alignAsTable": true, + "avg": true, + "current": false, + "hideEmpty": false, + "hideZero": false, + "max": true, + "min": true, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "maxPerRow": 6, + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "node_memory_DirectMap1G_bytes{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "DirectMap1G - Amount of pages mapped as this size", + "refId": "A", + "step": 4 + }, + { + "expr": "node_memory_DirectMap2M_bytes{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "DirectMap2M - Amount of pages mapped as this size", + "refId": "B", + "step": 4 + }, + { + "expr": "node_memory_DirectMap4k_bytes{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "DirectMap4K - Amount of pages mapped as this size", + "refId": "C", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Memory DirectMap", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "bytes", + "label": "bytes", + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": { + "Apps": "#629E51", + "Buffers": "#614D93", + "Cache": "#6D1F62", + "Cached": "#511749", + "Committed": "#508642", + "Free": "#0A437C", + "Hardware Corrupted - Amount of RAM that the kernel identified as corrupted / not working": "#CFFAFF", + "Inactive": "#584477", + "PageTables": "#0A50A1", + "Page_Tables": "#0A50A1", + "RAM_Free": "#E0F9D7", + "Slab": "#806EB7", + "Slab_Cache": "#E0752D", + "Swap": "#BF1B00", + "Swap_Cache": "#C15C17", + "Swap_Free": "#2F575E", + "Unused": "#EAB839" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "decimals": 2, + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 12, + "y": 130 + }, + "hiddenSeries": false, + "id": 137, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": true, + "min": true, + "rightSide": false, + "show": true, + "sideWidth": 350, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "maxPerRow": 6, + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "node_memory_Unevictable_bytes{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Unevictable - Amount of unevictable memory that can't be swapped out for a variety of reasons", + "refId": "A", + "step": 4 + }, + { + "expr": "node_memory_Mlocked_bytes{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "MLocked - Size of pages locked to memory using the mlock() system call", + "refId": "B", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Memory Unevictable and MLocked", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "cumulative" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "bytes", + "label": "bytes", + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": { + "Active": "#99440A", + "Buffers": "#58140C", + "Cache": "#6D1F62", + "Cached": "#511749", + "Committed": "#508642", + "Dirty": "#6ED0E0", + "Free": "#B7DBAB", + "Inactive": "#EA6460", + "Mapped": "#052B51", + "PageTables": "#0A50A1", + "Page_Tables": "#0A50A1", + "Slab_Cache": "#EAB839", + "Swap": "#BF1B00", + "Swap_Cache": "#C15C17", + "Total": "#511749", + "Total RAM": "#052B51", + "Total RAM + Swap": "#052B51", + "Total Swap": "#614D93", + "VmallocUsed": "#EA6460" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "decimals": 2, + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 0, + "y": 140 + }, + "hiddenSeries": false, + "id": 132, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": true, + "min": true, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "maxPerRow": 6, + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "node_memory_NFS_Unstable_bytes{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "NFS Unstable - Memory in NFS pages sent to the server, but not yet commited to the storage", + "refId": "A", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Memory NFS", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "bytes", + "label": "bytes", + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + } + ], + "repeat": null, + "title": "Memory Meminfo", + "type": "row" + }, + { + "collapsed": true, + "datasource": "${DS_PROMETHEUS}", + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 22 + }, + "id": 267, + "panels": [ + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 0, + "y": 23 + }, + "hiddenSeries": false, + "id": 176, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": true, + "min": true, + "rightSide": false, + "show": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "maxPerRow": 6, + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "/.*out/", + "transform": "negative-Y" + } + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "irate(node_vmstat_pgpgin{instance=\"$node\",job=\"$job\"}[5m])", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Pagesin - Page in operations", + "refId": "A", + "step": 4 + }, + { + "expr": "irate(node_vmstat_pgpgout{instance=\"$node\",job=\"$job\"}[5m])", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Pagesout - Page out operations", + "refId": "B", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Memory Pages In / Out", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "short", + "label": "pages out (-) / in (+)", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 12, + "y": 23 + }, + "hiddenSeries": false, + "id": 22, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": true, + "min": true, + "rightSide": false, + "show": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "maxPerRow": 6, + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "/.*out/", + "transform": "negative-Y" + } + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "irate(node_vmstat_pswpin{instance=\"$node\",job=\"$job\"}[5m])", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Pswpin - Pages swapped in", + "refId": "A", + "step": 4 + }, + { + "expr": "irate(node_vmstat_pswpout{instance=\"$node\",job=\"$job\"}[5m])", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Pswpout - Pages swapped out", + "refId": "B", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Memory Pages Swap In / Out", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "short", + "label": "pages out (-) / in (+)", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": { + "Apps": "#629E51", + "Buffers": "#614D93", + "Cache": "#6D1F62", + "Cached": "#511749", + "Committed": "#508642", + "Free": "#0A437C", + "Hardware Corrupted - Amount of RAM that the kernel identified as corrupted / not working": "#CFFAFF", + "Inactive": "#584477", + "PageTables": "#0A50A1", + "Page_Tables": "#0A50A1", + "RAM_Free": "#E0F9D7", + "Slab": "#806EB7", + "Slab_Cache": "#E0752D", + "Swap": "#BF1B00", + "Swap_Cache": "#C15C17", + "Swap_Free": "#2F575E", + "Unused": "#EAB839" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "decimals": 2, + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 0, + "y": 33 + }, + "hiddenSeries": false, + "id": 175, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": true, + "min": true, + "rightSide": false, + "show": true, + "sideWidth": 350, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "maxPerRow": 6, + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "$$hashKey": "object:6118", + "alias": "Pgfault - Page major and minor fault operations", + "fill": 0, + "stack": false + } + ], + "spaceLength": 10, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "irate(node_vmstat_pgfault{instance=\"$node\",job=\"$job\"}[5m])", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Pgfault - Page major and minor fault operations", + "refId": "A", + "step": 4 + }, + { + "expr": "irate(node_vmstat_pgmajfault{instance=\"$node\",job=\"$job\"}[5m])", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Pgmajfault - Major page fault operations", + "refId": "B", + "step": 4 + }, + { + "expr": "irate(node_vmstat_pgfault{instance=\"$node\",job=\"$job\"}[5m]) - irate(node_vmstat_pgmajfault{instance=\"$node\",job=\"$job\"}[5m])", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Pgminfault - Minor page fault operations", + "refId": "C", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Memory Page Faults", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "cumulative" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "$$hashKey": "object:6133", + "format": "short", + "label": "faults", + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "$$hashKey": "object:6134", + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": { + "Active": "#99440A", + "Buffers": "#58140C", + "Cache": "#6D1F62", + "Cached": "#511749", + "Committed": "#508642", + "Dirty": "#6ED0E0", + "Free": "#B7DBAB", + "Inactive": "#EA6460", + "Mapped": "#052B51", + "PageTables": "#0A50A1", + "Page_Tables": "#0A50A1", + "Slab_Cache": "#EAB839", + "Swap": "#BF1B00", + "Swap_Cache": "#C15C17", + "Total": "#511749", + "Total RAM": "#052B51", + "Total RAM + Swap": "#052B51", + "Total Swap": "#614D93", + "VmallocUsed": "#EA6460" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "decimals": 2, + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 12, + "y": 33 + }, + "hiddenSeries": false, + "id": 307, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": true, + "min": true, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "maxPerRow": 6, + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "irate(node_vmstat_oom_kill{instance=\"$node\",job=\"$job\"}[5m])", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "oom killer invocations ", + "refId": "A", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "OOM Killer", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "$$hashKey": "object:5373", + "format": "short", + "label": "counter", + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "$$hashKey": "object:5374", + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + } + ], + "repeat": null, + "title": "Memory Vmstat", + "type": "row" + }, + { + "collapsed": true, + "datasource": "${DS_PROMETHEUS}", + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 23 + }, + "id": 293, + "panels": [ + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "description": "", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 0, + "y": 24 + }, + "hiddenSeries": false, + "id": 260, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": true, + "min": true, + "show": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "/.*Variation*./", + "color": "#890F02" + } + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "node_timex_estimated_error_seconds{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "hide": false, + "interval": "", + "intervalFactor": 2, + "legendFormat": "Estimated error in seconds", + "refId": "A", + "step": 240 + }, + { + "expr": "node_timex_offset_seconds{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "hide": false, + "interval": "", + "intervalFactor": 2, + "legendFormat": "Time offset in between local system and reference clock", + "refId": "B", + "step": 240 + }, + { + "expr": "node_timex_maxerror_seconds{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "hide": false, + "interval": "", + "intervalFactor": 2, + "legendFormat": "Maximum error in seconds", + "refId": "C", + "step": 240 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Time Syncronized Drift", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "s", + "label": "seconds", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": "counter", + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "description": "", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 12, + "y": 24 + }, + "hiddenSeries": false, + "id": 291, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": true, + "min": true, + "show": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "node_timex_loop_time_constant{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "Phase-locked loop time adjust", + "refId": "A", + "step": 240 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Time PLL Adjust", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "short", + "label": "counter", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "description": "", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 0, + "y": 34 + }, + "hiddenSeries": false, + "id": 168, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": true, + "min": true, + "show": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "/.*Variation*./", + "color": "#890F02" + } + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "node_timex_sync_status{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "Is clock synchronized to a reliable server (1 = yes, 0 = no)", + "refId": "A", + "step": 240 + }, + { + "expr": "node_timex_frequency_adjustment_ratio{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "Local clock frequency adjustment", + "refId": "B", + "step": 240 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Time Syncronized Status", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "short", + "label": "counter", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "description": "", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 12, + "y": 34 + }, + "hiddenSeries": false, + "id": 294, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": true, + "min": true, + "show": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "node_timex_tick_seconds{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "Seconds between clock ticks", + "refId": "A", + "step": 240 + }, + { + "expr": "node_timex_tai_offset_seconds{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "International Atomic Time (TAI) offset", + "refId": "B", + "step": 240 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Time Misc", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "s", + "label": "seconds", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + } + ], + "title": "System Timesync", + "type": "row" + }, + { + "collapsed": true, + "datasource": "${DS_PROMETHEUS}", + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 24 + }, + "id": 312, + "panels": [ + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 0, + "y": 7 + }, + "hiddenSeries": false, + "id": 62, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": true, + "min": true, + "show": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "maxPerRow": 6, + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "node_procs_blocked{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Processes blocked waiting for I/O to complete", + "refId": "A", + "step": 240 + }, + { + "expr": "node_procs_running{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Processes in runnable state", + "refId": "B", + "step": 240 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Processes Status", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "$$hashKey": "object:6500", + "format": "short", + "label": "counter", + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "$$hashKey": "object:6501", + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 12, + "y": 7 + }, + "hiddenSeries": false, + "id": 315, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": true, + "min": true, + "show": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "maxPerRow": 6, + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "node_processes_state{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "{{ state }}", + "refId": "A", + "step": 240 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Processes State", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "$$hashKey": "object:6500", + "format": "short", + "label": "counter", + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "$$hashKey": "object:6501", + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 0, + "y": 17 + }, + "hiddenSeries": false, + "id": 148, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": true, + "min": true, + "show": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "maxPerRow": 6, + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "irate(node_forks_total{instance=\"$node\",job=\"$job\"}[5m])", + "format": "time_series", + "hide": false, + "intervalFactor": 2, + "legendFormat": "Processes forks second", + "refId": "A", + "step": 240 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Processes Forks", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "$$hashKey": "object:6640", + "format": "short", + "label": "forks / sec", + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "$$hashKey": "object:6641", + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 12, + "y": 17 + }, + "hiddenSeries": false, + "id": 149, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": true, + "min": true, + "show": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "/.*Max.*/", + "fill": 0 + } + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "irate(process_virtual_memory_bytes{instance=\"$node\",job=\"$job\"}[5m])", + "hide": false, + "interval": "", + "intervalFactor": 2, + "legendFormat": "Processes virtual memory size in bytes", + "refId": "A", + "step": 240 + }, + { + "expr": "process_resident_memory_max_bytes{instance=\"$node\",job=\"$job\"}", + "hide": false, + "interval": "", + "intervalFactor": 2, + "legendFormat": "Maximum amount of virtual memory available in bytes", + "refId": "B", + "step": 240 + }, + { + "expr": "irate(process_virtual_memory_bytes{instance=\"$node\",job=\"$job\"}[5m])", + "hide": false, + "interval": "", + "intervalFactor": 2, + "legendFormat": "Processes virtual memory size in bytes", + "refId": "C", + "step": 240 + }, + { + "expr": "irate(process_virtual_memory_max_bytes{instance=\"$node\",job=\"$job\"}[5m])", + "hide": false, + "interval": "", + "intervalFactor": 2, + "legendFormat": "Maximum amount of virtual memory available in bytes", + "refId": "D", + "step": 240 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Processes Memory", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "decbytes", + "label": "bytes", + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 0, + "y": 27 + }, + "hiddenSeries": false, + "id": 313, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": true, + "min": true, + "show": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "maxPerRow": 6, + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "$$hashKey": "object:709", + "alias": "PIDs limit", + "color": "#F2495C", + "fill": 0 + } + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "node_processes_pids{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "Number of PIDs", + "refId": "A", + "step": 240 + }, + { + "expr": "node_processes_max_processes{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "PIDs limit", + "refId": "B", + "step": 240 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "PIDs Number and Limit", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "$$hashKey": "object:6500", + "format": "short", + "label": "counter", + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "$$hashKey": "object:6501", + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 12, + "y": 27 + }, + "hiddenSeries": false, + "id": 305, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": true, + "min": true, + "show": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "maxPerRow": 6, + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "$$hashKey": "object:4963", + "alias": "/.*waiting.*/", + "transform": "negative-Y" + } + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "irate(node_schedstat_running_seconds_total{instance=\"$node\",job=\"$job\"}[5m])", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "CPU {{ cpu }} - seconds spent running a process", + "refId": "A", + "step": 240 + }, + { + "expr": "irate(node_schedstat_waiting_seconds_total{instance=\"$node\",job=\"$job\"}[5m])", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "CPU {{ cpu }} - seconds spent by processing waiting for this CPU", + "refId": "B", + "step": 240 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Process schedule stats Running / Waiting", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "$$hashKey": "object:4860", + "format": "s", + "label": "seconds", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "$$hashKey": "object:4861", + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 12, + "y": 37 + }, + "hiddenSeries": false, + "id": 314, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": true, + "min": true, + "show": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "maxPerRow": 6, + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "$$hashKey": "object:709", + "alias": "Threads limit", + "color": "#F2495C", + "fill": 0 + } + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "node_processes_threads{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "Allocated threads", + "refId": "A", + "step": 240 + }, + { + "expr": "node_processes_max_threads{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "Threads limit", + "refId": "B", + "step": 240 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Threads Number and Limit", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "$$hashKey": "object:6500", + "format": "short", + "label": "counter", + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "$$hashKey": "object:6501", + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + } + ], + "title": "System Processes", + "type": "row" + }, + { + "collapsed": true, + "datasource": "${DS_PROMETHEUS}", + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 25 + }, + "id": 269, + "panels": [ + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 0, + "y": 8 + }, + "hiddenSeries": false, + "id": 8, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": true, + "min": true, + "show": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "maxPerRow": 6, + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "irate(node_context_switches_total{instance=\"$node\",job=\"$job\"}[5m])", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Context switches", + "refId": "A", + "step": 240 + }, + { + "expr": "irate(node_intr_total{instance=\"$node\",job=\"$job\"}[5m])", + "format": "time_series", + "hide": false, + "intervalFactor": 2, + "legendFormat": "Interrupts", + "refId": "B", + "step": 240 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Context Switches / Interrupts", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "short", + "label": "counter", + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 12, + "y": 8 + }, + "hiddenSeries": false, + "id": 7, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": true, + "min": true, + "show": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "maxPerRow": 6, + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "node_load1{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "intervalFactor": 4, + "legendFormat": "Load 1m", + "refId": "A", + "step": 480 + }, + { + "expr": "node_load5{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "intervalFactor": 4, + "legendFormat": "Load 5m", + "refId": "B", + "step": 480 + }, + { + "expr": "node_load15{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "intervalFactor": 4, + "legendFormat": "Load 15m", + "refId": "C", + "step": 480 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "System Load", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "$$hashKey": "object:6261", + "format": "short", + "label": "counter", + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "$$hashKey": "object:6262", + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 0, + "y": 18 + }, + "hiddenSeries": false, + "id": 259, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": true, + "min": true, + "show": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "/.*Critical*./", + "color": "#E24D42", + "fill": 0 + }, + { + "alias": "/.*Max*./", + "color": "#EF843C", + "fill": 0 + } + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "irate(node_interrupts_total{instance=\"$node\",job=\"$job\"}[5m])", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "{{ type }} - {{ info }}", + "refId": "A", + "step": 240 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Interrupts Detail", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "short", + "label": "counter", + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 12, + "y": 18 + }, + "hiddenSeries": false, + "id": 306, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": true, + "min": true, + "show": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "maxPerRow": 6, + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "irate(node_schedstat_timeslices_total{instance=\"$node\",job=\"$job\"}[5m])", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "CPU {{ cpu }}", + "refId": "A", + "step": 240 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Schedule timeslices executed by each cpu", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "$$hashKey": "object:4860", + "format": "short", + "label": "counter", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "$$hashKey": "object:4861", + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 0, + "y": 28 + }, + "hiddenSeries": false, + "id": 151, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": true, + "min": true, + "show": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "maxPerRow": 6, + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "node_entropy_available_bits{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Entropy available to random number generators", + "refId": "A", + "step": 240 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Entropy", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "$$hashKey": "object:6568", + "format": "short", + "label": "counter", + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "$$hashKey": "object:6569", + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 12, + "y": 28 + }, + "hiddenSeries": false, + "id": 308, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": true, + "min": true, + "show": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "maxPerRow": 6, + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "irate(process_cpu_seconds_total{instance=\"$node\",job=\"$job\"}[5m])", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "Time spent", + "refId": "A", + "step": 240 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "CPU time spent in user and system contexts", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "$$hashKey": "object:4860", + "format": "s", + "label": "seconds", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "$$hashKey": "object:4861", + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 0, + "y": 38 + }, + "hiddenSeries": false, + "id": 64, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": true, + "min": true, + "show": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "$$hashKey": "object:6323", + "alias": "/.*Max*./", + "color": "#890F02", + "fill": 0 + } + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "process_max_fds{instance=\"$node\",job=\"$job\"}", + "interval": "", + "intervalFactor": 2, + "legendFormat": "Maximum open file descriptors", + "refId": "A", + "step": 240 + }, + { + "expr": "process_open_fds{instance=\"$node\",job=\"$job\"}", + "interval": "", + "intervalFactor": 2, + "legendFormat": "Open file descriptors", + "refId": "B", + "step": 240 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "File Descriptors", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "$$hashKey": "object:6338", + "format": "short", + "label": "counter", + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "$$hashKey": "object:6339", + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + } + ], + "repeat": null, + "title": "System Misc", + "type": "row" + }, + { + "collapsed": true, + "datasource": "${DS_PROMETHEUS}", + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 26 + }, + "id": 304, + "panels": [ + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 0, + "y": 26 + }, + "hiddenSeries": false, + "id": 158, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": true, + "min": true, + "show": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "$$hashKey": "object:6726", + "alias": "/.*Critical*./", + "color": "#E24D42", + "fill": 0 + }, + { + "$$hashKey": "object:6727", + "alias": "/.*Max*./", + "color": "#EF843C", + "fill": 0 + } + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "node_hwmon_temp_celsius{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "{{ chip }} {{ sensor }} temp", + "refId": "A", + "step": 240 + }, + { + "expr": "node_hwmon_temp_crit_alarm_celsius{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "hide": true, + "interval": "", + "intervalFactor": 2, + "legendFormat": "{{ chip }} {{ sensor }} Critical Alarm", + "refId": "B", + "step": 240 + }, + { + "expr": "node_hwmon_temp_crit_celsius{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "{{ chip }} {{ sensor }} Critical", + "refId": "C", + "step": 240 + }, + { + "expr": "node_hwmon_temp_crit_hyst_celsius{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "hide": true, + "interval": "", + "intervalFactor": 2, + "legendFormat": "{{ chip }} {{ sensor }} Critical Historical", + "refId": "D", + "step": 240 + }, + { + "expr": "node_hwmon_temp_max_celsius{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "hide": true, + "interval": "", + "intervalFactor": 2, + "legendFormat": "{{ chip }} {{ sensor }} Max", + "refId": "E", + "step": 240 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Hardware temperature monitor", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "$$hashKey": "object:6750", + "format": "celsius", + "label": "temperature", + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "$$hashKey": "object:6751", + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 12, + "y": 26 + }, + "hiddenSeries": false, + "id": 300, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": true, + "min": true, + "show": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "$$hashKey": "object:1655", + "alias": "/.*Max*./", + "color": "#EF843C", + "fill": 0 + } + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "node_cooling_device_cur_state{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "hide": false, + "interval": "", + "intervalFactor": 2, + "legendFormat": "Current {{ name }} in {{ type }}", + "refId": "A", + "step": 240 + }, + { + "expr": "node_cooling_device_max_state{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "Max {{ name }} in {{ type }}", + "refId": "B", + "step": 240 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Throttle cooling device", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "$$hashKey": "object:1678", + "format": "short", + "label": "counter", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "$$hashKey": "object:1679", + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 0, + "y": 36 + }, + "hiddenSeries": false, + "id": 302, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": true, + "min": true, + "show": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "node_power_supply_online{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "hide": false, + "interval": "", + "intervalFactor": 2, + "legendFormat": "{{ power_supply }} online", + "refId": "A", + "step": 240 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Power supply", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "$$hashKey": "object:1678", + "format": "short", + "label": "counter", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "$$hashKey": "object:1679", + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + } + ], + "title": "Hardware Misc", + "type": "row" + }, + { + "collapsed": true, + "datasource": "${DS_PROMETHEUS}", + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 27 + }, + "id": 296, + "panels": [ + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 0, + "y": 10 + }, + "hiddenSeries": false, + "id": 297, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": true, + "min": true, + "show": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "irate(node_systemd_socket_accepted_connections_total{instance=\"$node\",job=\"$job\"}[5m])", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "{{ name }} Connections", + "refId": "A", + "step": 240 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Systemd Sockets", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "short", + "label": "counter", + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 12, + "y": 10 + }, + "hiddenSeries": false, + "id": 298, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": true, + "min": true, + "show": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "Failed", + "color": "#F2495C" + }, + { + "alias": "Inactive", + "color": "#FF9830" + }, + { + "alias": "Active", + "color": "#73BF69" + }, + { + "alias": "Deactivating", + "color": "#FFCB7D" + }, + { + "alias": "Activating", + "color": "#C8F2C2" + } + ], + "spaceLength": 10, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "node_systemd_units{instance=\"$node\",job=\"$job\",state=\"activating\"}", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "Activating", + "refId": "A", + "step": 240 + }, + { + "expr": "node_systemd_units{instance=\"$node\",job=\"$job\",state=\"active\"}", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "Active", + "refId": "B", + "step": 240 + }, + { + "expr": "node_systemd_units{instance=\"$node\",job=\"$job\",state=\"deactivating\"}", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "Deactivating", + "refId": "C", + "step": 240 + }, + { + "expr": "node_systemd_units{instance=\"$node\",job=\"$job\",state=\"failed\"}", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "Failed", + "refId": "D", + "step": 240 + }, + { + "expr": "node_systemd_units{instance=\"$node\",job=\"$job\",state=\"inactive\"}", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "Inactive", + "refId": "E", + "step": 240 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Systemd Units State", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "short", + "label": "counter", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + } + ], + "title": "Systemd", + "type": "row" + }, + { + "collapsed": true, + "datasource": "${DS_PROMETHEUS}", + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 28 + }, + "id": 270, + "panels": [ + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "description": "", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 0, + "y": 29 + }, + "hiddenSeries": false, + "id": 9, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "hideZero": true, + "max": true, + "min": true, + "rightSide": false, + "show": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "maxPerRow": 6, + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + { + "$$hashKey": "object:2033", + "alias": "/.*Read.*/", + "transform": "negative-Y" + }, + { + "$$hashKey": "object:2034", + "alias": "/.*sda_.*/", + "color": "#7EB26D" + }, + { + "$$hashKey": "object:2035", + "alias": "/.*sdb_.*/", + "color": "#EAB839" + }, + { + "$$hashKey": "object:2036", + "alias": "/.*sdc_.*/", + "color": "#6ED0E0" + }, + { + "$$hashKey": "object:2037", + "alias": "/.*sdd_.*/", + "color": "#EF843C" + }, + { + "$$hashKey": "object:2038", + "alias": "/.*sde_.*/", + "color": "#E24D42" + }, + { + "$$hashKey": "object:2039", + "alias": "/.*sda1.*/", + "color": "#584477" + }, + { + "$$hashKey": "object:2040", + "alias": "/.*sda2_.*/", + "color": "#BA43A9" + }, + { + "$$hashKey": "object:2041", + "alias": "/.*sda3_.*/", + "color": "#F4D598" + }, + { + "$$hashKey": "object:2042", + "alias": "/.*sdb1.*/", + "color": "#0A50A1" + }, + { + "$$hashKey": "object:2043", + "alias": "/.*sdb2.*/", + "color": "#BF1B00" + }, + { + "$$hashKey": "object:2044", + "alias": "/.*sdb3.*/", + "color": "#E0752D" + }, + { + "$$hashKey": "object:2045", + "alias": "/.*sdc1.*/", + "color": "#962D82" + }, + { + "$$hashKey": "object:2046", + "alias": "/.*sdc2.*/", + "color": "#614D93" + }, + { + "$$hashKey": "object:2047", + "alias": "/.*sdc3.*/", + "color": "#9AC48A" + }, + { + "$$hashKey": "object:2048", + "alias": "/.*sdd1.*/", + "color": "#65C5DB" + }, + { + "$$hashKey": "object:2049", + "alias": "/.*sdd2.*/", + "color": "#F9934E" + }, + { + "$$hashKey": "object:2050", + "alias": "/.*sdd3.*/", + "color": "#EA6460" + }, + { + "$$hashKey": "object:2051", + "alias": "/.*sde1.*/", + "color": "#E0F9D7" + }, + { + "$$hashKey": "object:2052", + "alias": "/.*sdd2.*/", + "color": "#FCEACA" + }, + { + "$$hashKey": "object:2053", + "alias": "/.*sde3.*/", + "color": "#F9E2D2" + } + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "irate(node_disk_reads_completed_total{instance=\"$node\",job=\"$job\"}[5m])", + "intervalFactor": 4, + "legendFormat": "{{device}} - Reads completed", + "refId": "A", + "step": 8 + }, + { + "expr": "irate(node_disk_writes_completed_total{instance=\"$node\",job=\"$job\"}[5m])", + "intervalFactor": 2, + "legendFormat": "{{device}} - Writes completed", + "refId": "B", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Disk IOps Completed", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "$$hashKey": "object:2186", + "format": "iops", + "label": "IO read (-) / write (+)", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "$$hashKey": "object:2187", + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "description": "", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 12, + "y": 29 + }, + "hiddenSeries": false, + "id": 33, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "hideZero": true, + "max": true, + "min": true, + "rightSide": false, + "show": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "maxPerRow": 6, + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "/.*Read.*/", + "transform": "negative-Y" + }, + { + "alias": "/.*sda_.*/", + "color": "#7EB26D" + }, + { + "alias": "/.*sdb_.*/", + "color": "#EAB839" + }, + { + "alias": "/.*sdc_.*/", + "color": "#6ED0E0" + }, + { + "alias": "/.*sdd_.*/", + "color": "#EF843C" + }, + { + "alias": "/.*sde_.*/", + "color": "#E24D42" + }, + { + "alias": "/.*sda1.*/", + "color": "#584477" + }, + { + "alias": "/.*sda2_.*/", + "color": "#BA43A9" + }, + { + "alias": "/.*sda3_.*/", + "color": "#F4D598" + }, + { + "alias": "/.*sdb1.*/", + "color": "#0A50A1" + }, + { + "alias": "/.*sdb2.*/", + "color": "#BF1B00" + }, + { + "alias": "/.*sdb3.*/", + "color": "#E0752D" + }, + { + "alias": "/.*sdc1.*/", + "color": "#962D82" + }, + { + "alias": "/.*sdc2.*/", + "color": "#614D93" + }, + { + "alias": "/.*sdc3.*/", + "color": "#9AC48A" + }, + { + "alias": "/.*sdd1.*/", + "color": "#65C5DB" + }, + { + "alias": "/.*sdd2.*/", + "color": "#F9934E" + }, + { + "alias": "/.*sdd3.*/", + "color": "#EA6460" + }, + { + "alias": "/.*sde1.*/", + "color": "#E0F9D7" + }, + { + "alias": "/.*sdd2.*/", + "color": "#FCEACA" + }, + { + "alias": "/.*sde3.*/", + "color": "#F9E2D2" + } + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "irate(node_disk_read_bytes_total{instance=\"$node\",job=\"$job\"}[5m])", + "format": "time_series", + "intervalFactor": 4, + "legendFormat": "{{device}} - Read bytes", + "refId": "A", + "step": 8 + }, + { + "expr": "irate(node_disk_written_bytes_total{instance=\"$node\",job=\"$job\"}[5m])", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{device}} - Written bytes", + "refId": "B", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Disk R/W Data", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "Bps", + "label": "bytes read (-) / write (+)", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "description": "", + "fill": 3, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 0, + "y": 39 + }, + "hiddenSeries": false, + "id": 37, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "hideZero": true, + "max": true, + "min": true, + "rightSide": false, + "show": true, + "sort": "current", + "sortDesc": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "maxPerRow": 6, + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "/.*Read.*/", + "transform": "negative-Y" + }, + { + "alias": "/.*sda_.*/", + "color": "#7EB26D" + }, + { + "alias": "/.*sdb_.*/", + "color": "#EAB839" + }, + { + "alias": "/.*sdc_.*/", + "color": "#6ED0E0" + }, + { + "alias": "/.*sdd_.*/", + "color": "#EF843C" + }, + { + "alias": "/.*sde_.*/", + "color": "#E24D42" + }, + { + "alias": "/.*sda1.*/", + "color": "#584477" + }, + { + "alias": "/.*sda2_.*/", + "color": "#BA43A9" + }, + { + "alias": "/.*sda3_.*/", + "color": "#F4D598" + }, + { + "alias": "/.*sdb1.*/", + "color": "#0A50A1" + }, + { + "alias": "/.*sdb2.*/", + "color": "#BF1B00" + }, + { + "alias": "/.*sdb3.*/", + "color": "#E0752D" + }, + { + "alias": "/.*sdc1.*/", + "color": "#962D82" + }, + { + "alias": "/.*sdc2.*/", + "color": "#614D93" + }, + { + "alias": "/.*sdc3.*/", + "color": "#9AC48A" + }, + { + "alias": "/.*sdd1.*/", + "color": "#65C5DB" + }, + { + "alias": "/.*sdd2.*/", + "color": "#F9934E" + }, + { + "alias": "/.*sdd3.*/", + "color": "#EA6460" + }, + { + "alias": "/.*sde1.*/", + "color": "#E0F9D7" + }, + { + "alias": "/.*sdd2.*/", + "color": "#FCEACA" + }, + { + "alias": "/.*sde3.*/", + "color": "#F9E2D2" + } + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "irate(node_disk_read_time_seconds_total{instance=\"$node\",job=\"$job\"}[5m])", + "hide": false, + "intervalFactor": 4, + "legendFormat": "{{device}} - Read time", + "refId": "A", + "step": 8 + }, + { + "expr": "irate(node_disk_write_time_seconds_total{instance=\"$node\",job=\"$job\"}[5m])", + "hide": false, + "intervalFactor": 2, + "legendFormat": "{{device}} - Write time", + "refId": "B", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Disk R/W Time", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "s", + "label": "time. read (-) / write (+)", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "description": "", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 12, + "y": 39 + }, + "hiddenSeries": false, + "id": 35, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "hideZero": true, + "max": true, + "min": true, + "rightSide": false, + "show": true, + "sort": "current", + "sortDesc": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "maxPerRow": 6, + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "/.*sda_.*/", + "color": "#7EB26D" + }, + { + "alias": "/.*sdb_.*/", + "color": "#EAB839" + }, + { + "alias": "/.*sdc_.*/", + "color": "#6ED0E0" + }, + { + "alias": "/.*sdd_.*/", + "color": "#EF843C" + }, + { + "alias": "/.*sde_.*/", + "color": "#E24D42" + }, + { + "alias": "/.*sda1.*/", + "color": "#584477" + }, + { + "alias": "/.*sda2_.*/", + "color": "#BA43A9" + }, + { + "alias": "/.*sda3_.*/", + "color": "#F4D598" + }, + { + "alias": "/.*sdb1.*/", + "color": "#0A50A1" + }, + { + "alias": "/.*sdb2.*/", + "color": "#BF1B00" + }, + { + "alias": "/.*sdb3.*/", + "color": "#E0752D" + }, + { + "alias": "/.*sdc1.*/", + "color": "#962D82" + }, + { + "alias": "/.*sdc2.*/", + "color": "#614D93" + }, + { + "alias": "/.*sdc3.*/", + "color": "#9AC48A" + }, + { + "alias": "/.*sdd1.*/", + "color": "#65C5DB" + }, + { + "alias": "/.*sdd2.*/", + "color": "#F9934E" + }, + { + "alias": "/.*sdd3.*/", + "color": "#EA6460" + }, + { + "alias": "/.*sde1.*/", + "color": "#E0F9D7" + }, + { + "alias": "/.*sdd2.*/", + "color": "#FCEACA" + }, + { + "alias": "/.*sde3.*/", + "color": "#F9E2D2" + } + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "irate(node_disk_io_time_weighted_seconds_total{instance=\"$node\",job=\"$job\"}[5m])", + "intervalFactor": 4, + "legendFormat": "{{device}} - IO time weighted", + "refId": "A", + "step": 8 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Disk IOs Weighted", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "s", + "label": "time", + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "description": "", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 0, + "y": 49 + }, + "hiddenSeries": false, + "id": 133, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "hideZero": true, + "max": true, + "min": true, + "rightSide": false, + "show": true, + "sort": "current", + "sortDesc": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "maxPerRow": 6, + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "/.*Read.*/", + "transform": "negative-Y" + }, + { + "alias": "/.*sda_.*/", + "color": "#7EB26D" + }, + { + "alias": "/.*sdb_.*/", + "color": "#EAB839" + }, + { + "alias": "/.*sdc_.*/", + "color": "#6ED0E0" + }, + { + "alias": "/.*sdd_.*/", + "color": "#EF843C" + }, + { + "alias": "/.*sde_.*/", + "color": "#E24D42" + }, + { + "alias": "/.*sda1.*/", + "color": "#584477" + }, + { + "alias": "/.*sda2_.*/", + "color": "#BA43A9" + }, + { + "alias": "/.*sda3_.*/", + "color": "#F4D598" + }, + { + "alias": "/.*sdb1.*/", + "color": "#0A50A1" + }, + { + "alias": "/.*sdb2.*/", + "color": "#BF1B00" + }, + { + "alias": "/.*sdb3.*/", + "color": "#E0752D" + }, + { + "alias": "/.*sdc1.*/", + "color": "#962D82" + }, + { + "alias": "/.*sdc2.*/", + "color": "#614D93" + }, + { + "alias": "/.*sdc3.*/", + "color": "#9AC48A" + }, + { + "alias": "/.*sdd1.*/", + "color": "#65C5DB" + }, + { + "alias": "/.*sdd2.*/", + "color": "#F9934E" + }, + { + "alias": "/.*sdd3.*/", + "color": "#EA6460" + }, + { + "alias": "/.*sde1.*/", + "color": "#E0F9D7" + }, + { + "alias": "/.*sdd2.*/", + "color": "#FCEACA" + }, + { + "alias": "/.*sde3.*/", + "color": "#F9E2D2" + } + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "irate(node_disk_reads_merged_total{instance=\"$node\",job=\"$job\"}[5m])", + "intervalFactor": 2, + "legendFormat": "{{device}} - Read merged", + "refId": "A", + "step": 4 + }, + { + "expr": "irate(node_disk_writes_merged_total{instance=\"$node\",job=\"$job\"}[5m])", + "intervalFactor": 2, + "legendFormat": "{{device}} - Write merged", + "refId": "B", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Disk R/W Merged", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "iops", + "label": "I/Os", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "description": "", + "fill": 3, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 12, + "y": 49 + }, + "hiddenSeries": false, + "id": 36, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "hideZero": true, + "max": true, + "min": true, + "rightSide": false, + "show": true, + "sort": "current", + "sortDesc": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "maxPerRow": 6, + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "/.*sda_.*/", + "color": "#7EB26D" + }, + { + "alias": "/.*sdb_.*/", + "color": "#EAB839" + }, + { + "alias": "/.*sdc_.*/", + "color": "#6ED0E0" + }, + { + "alias": "/.*sdd_.*/", + "color": "#EF843C" + }, + { + "alias": "/.*sde_.*/", + "color": "#E24D42" + }, + { + "alias": "/.*sda1.*/", + "color": "#584477" + }, + { + "alias": "/.*sda2_.*/", + "color": "#BA43A9" + }, + { + "alias": "/.*sda3_.*/", + "color": "#F4D598" + }, + { + "alias": "/.*sdb1.*/", + "color": "#0A50A1" + }, + { + "alias": "/.*sdb2.*/", + "color": "#BF1B00" + }, + { + "alias": "/.*sdb3.*/", + "color": "#E0752D" + }, + { + "alias": "/.*sdc1.*/", + "color": "#962D82" + }, + { + "alias": "/.*sdc2.*/", + "color": "#614D93" + }, + { + "alias": "/.*sdc3.*/", + "color": "#9AC48A" + }, + { + "alias": "/.*sdd1.*/", + "color": "#65C5DB" + }, + { + "alias": "/.*sdd2.*/", + "color": "#F9934E" + }, + { + "alias": "/.*sdd3.*/", + "color": "#EA6460" + }, + { + "alias": "/.*sde1.*/", + "color": "#E0F9D7" + }, + { + "alias": "/.*sdd2.*/", + "color": "#FCEACA" + }, + { + "alias": "/.*sde3.*/", + "color": "#F9E2D2" + } + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "irate(node_disk_io_time_seconds_total{instance=\"$node\",job=\"$job\"}[5m])", + "intervalFactor": 4, + "legendFormat": "{{device}} - IO time", + "refId": "A", + "step": 8 + }, + { + "expr": "irate(node_disk_discard_time_seconds_total{instance=\"$node\",job=\"$job\"}[5m])", + "interval": "", + "intervalFactor": 4, + "legendFormat": "{{device}} - discard time", + "refId": "B", + "step": 8 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Time Spent Doing I/Os", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "s", + "label": "time", + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "description": "", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 0, + "y": 59 + }, + "hiddenSeries": false, + "id": 34, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "hideZero": true, + "max": true, + "min": true, + "rightSide": false, + "show": true, + "sort": "current", + "sortDesc": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "maxPerRow": 6, + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "/.*sda_.*/", + "color": "#7EB26D" + }, + { + "alias": "/.*sdb_.*/", + "color": "#EAB839" + }, + { + "alias": "/.*sdc_.*/", + "color": "#6ED0E0" + }, + { + "alias": "/.*sdd_.*/", + "color": "#EF843C" + }, + { + "alias": "/.*sde_.*/", + "color": "#E24D42" + }, + { + "alias": "/.*sda1.*/", + "color": "#584477" + }, + { + "alias": "/.*sda2_.*/", + "color": "#BA43A9" + }, + { + "alias": "/.*sda3_.*/", + "color": "#F4D598" + }, + { + "alias": "/.*sdb1.*/", + "color": "#0A50A1" + }, + { + "alias": "/.*sdb2.*/", + "color": "#BF1B00" + }, + { + "alias": "/.*sdb3.*/", + "color": "#E0752D" + }, + { + "alias": "/.*sdc1.*/", + "color": "#962D82" + }, + { + "alias": "/.*sdc2.*/", + "color": "#614D93" + }, + { + "alias": "/.*sdc3.*/", + "color": "#9AC48A" + }, + { + "alias": "/.*sdd1.*/", + "color": "#65C5DB" + }, + { + "alias": "/.*sdd2.*/", + "color": "#F9934E" + }, + { + "alias": "/.*sdd3.*/", + "color": "#EA6460" + }, + { + "alias": "/.*sde1.*/", + "color": "#E0F9D7" + }, + { + "alias": "/.*sdd2.*/", + "color": "#FCEACA" + }, + { + "alias": "/.*sde3.*/", + "color": "#F9E2D2" + } + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "irate(node_disk_io_now{instance=\"$node\",job=\"$job\"}[5m])", + "intervalFactor": 4, + "legendFormat": "{{device}} - IO now", + "refId": "A", + "step": 8 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Disk IOs Current in Progress", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "iops", + "label": "I/Os", + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "description": "", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 12, + "y": 59 + }, + "hiddenSeries": false, + "id": 301, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "hideZero": true, + "max": true, + "min": true, + "rightSide": false, + "show": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "maxPerRow": 6, + "nullPointMode": "null as zero", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "$$hashKey": "object:2034", + "alias": "/.*sda_.*/", + "color": "#7EB26D" + }, + { + "$$hashKey": "object:2035", + "alias": "/.*sdb_.*/", + "color": "#EAB839" + }, + { + "$$hashKey": "object:2036", + "alias": "/.*sdc_.*/", + "color": "#6ED0E0" + }, + { + "$$hashKey": "object:2037", + "alias": "/.*sdd_.*/", + "color": "#EF843C" + }, + { + "$$hashKey": "object:2038", + "alias": "/.*sde_.*/", + "color": "#E24D42" + }, + { + "$$hashKey": "object:2039", + "alias": "/.*sda1.*/", + "color": "#584477" + }, + { + "$$hashKey": "object:2040", + "alias": "/.*sda2_.*/", + "color": "#BA43A9" + }, + { + "$$hashKey": "object:2041", + "alias": "/.*sda3_.*/", + "color": "#F4D598" + }, + { + "$$hashKey": "object:2042", + "alias": "/.*sdb1.*/", + "color": "#0A50A1" + }, + { + "$$hashKey": "object:2043", + "alias": "/.*sdb2.*/", + "color": "#BF1B00" + }, + { + "$$hashKey": "object:2044", + "alias": "/.*sdb3.*/", + "color": "#E0752D" + }, + { + "$$hashKey": "object:2045", + "alias": "/.*sdc1.*/", + "color": "#962D82" + }, + { + "$$hashKey": "object:2046", + "alias": "/.*sdc2.*/", + "color": "#614D93" + }, + { + "$$hashKey": "object:2047", + "alias": "/.*sdc3.*/", + "color": "#9AC48A" + }, + { + "$$hashKey": "object:2048", + "alias": "/.*sdd1.*/", + "color": "#65C5DB" + }, + { + "$$hashKey": "object:2049", + "alias": "/.*sdd2.*/", + "color": "#F9934E" + }, + { + "$$hashKey": "object:2050", + "alias": "/.*sdd3.*/", + "color": "#EA6460" + }, + { + "$$hashKey": "object:2051", + "alias": "/.*sde1.*/", + "color": "#E0F9D7" + }, + { + "$$hashKey": "object:2052", + "alias": "/.*sdd2.*/", + "color": "#FCEACA" + }, + { + "$$hashKey": "object:2053", + "alias": "/.*sde3.*/", + "color": "#F9E2D2" + } + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "irate(node_disk_discards_completed_total{instance=\"$node\",job=\"$job\"}[5m])", + "interval": "", + "intervalFactor": 4, + "legendFormat": "{{device}} - Discards completed", + "refId": "A", + "step": 8 + }, + { + "expr": "irate(node_disk_discards_merged_total{instance=\"$node\",job=\"$job\"}[5m])", + "interval": "", + "intervalFactor": 2, + "legendFormat": "{{device}} - Discards merged", + "refId": "B", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Disk IOps Discards completed / merged", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "$$hashKey": "object:2186", + "format": "iops", + "label": "IOs", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "$$hashKey": "object:2187", + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + } + ], + "repeat": null, + "title": "Storage Disk", + "type": "row" + }, + { + "collapsed": true, + "datasource": "${DS_PROMETHEUS}", + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 29 + }, + "id": 271, + "panels": [ + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "decimals": 3, + "description": "", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 0, + "y": 78 + }, + "hiddenSeries": false, + "id": 43, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": true, + "min": true, + "rightSide": false, + "show": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "maxPerRow": 6, + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "node_filesystem_avail_bytes{instance=\"$node\",job=\"$job\",device!~'rootfs'}", + "format": "time_series", + "hide": false, + "intervalFactor": 2, + "legendFormat": "{{mountpoint}} - Available", + "metric": "", + "refId": "A", + "step": 4 + }, + { + "expr": "node_filesystem_free_bytes{instance=\"$node\",job=\"$job\",device!~'rootfs'}", + "format": "time_series", + "hide": true, + "intervalFactor": 2, + "legendFormat": "{{mountpoint}} - Free", + "refId": "B", + "step": 2 + }, + { + "expr": "node_filesystem_size_bytes{instance=\"$node\",job=\"$job\",device!~'rootfs'}", + "format": "time_series", + "hide": true, + "intervalFactor": 2, + "legendFormat": "{{mountpoint}} - Size", + "refId": "C", + "step": 2 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Filesystem space available", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "$$hashKey": "object:3826", + "format": "bytes", + "label": "bytes", + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "$$hashKey": "object:3827", + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "description": "", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 12, + "y": 78 + }, + "hiddenSeries": false, + "id": 41, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "hideZero": true, + "max": true, + "min": true, + "rightSide": false, + "show": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "node_filesystem_files_free{instance=\"$node\",job=\"$job\",device!~'rootfs'}", + "format": "time_series", + "hide": false, + "intervalFactor": 2, + "legendFormat": "{{mountpoint}} - Free file nodes", + "refId": "A", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "File Nodes Free", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "$$hashKey": "object:3894", + "format": "short", + "label": "file nodes", + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "$$hashKey": "object:3895", + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "description": "", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 0, + "y": 88 + }, + "hiddenSeries": false, + "id": 28, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": true, + "min": true, + "show": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "maxPerRow": 6, + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "node_filefd_maximum{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "intervalFactor": 4, + "legendFormat": "Max open files", + "refId": "A", + "step": 8 + }, + { + "expr": "node_filefd_allocated{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Open files", + "refId": "B", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "File Descriptor", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "short", + "label": "files", + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "description": "", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 12, + "y": 88 + }, + "hiddenSeries": false, + "id": 219, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "hideZero": true, + "max": true, + "min": true, + "rightSide": false, + "show": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "node_filesystem_files{instance=\"$node\",job=\"$job\",device!~'rootfs'}", + "format": "time_series", + "hide": false, + "intervalFactor": 2, + "legendFormat": "{{mountpoint}} - File nodes total", + "refId": "A", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "File Nodes Size", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "short", + "label": "file Nodes", + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": { + "/ ReadOnly": "#890F02" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "decimals": null, + "description": "", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 0, + "y": 98 + }, + "hiddenSeries": false, + "id": 44, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "hideEmpty": true, + "hideZero": true, + "max": true, + "min": true, + "rightSide": false, + "show": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "maxPerRow": 6, + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "node_filesystem_readonly{instance=\"$node\",job=\"$job\",device!~'rootfs'}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{mountpoint}} - ReadOnly", + "refId": "A", + "step": 4 + }, + { + "expr": "node_filesystem_device_error{instance=\"$node\",job=\"$job\",device!~'rootfs',fstype!~'tmpfs'}", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "{{mountpoint}} - Device error", + "refId": "B", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Filesystem in ReadOnly / Error", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "$$hashKey": "object:3670", + "format": "short", + "label": "counter", + "logBase": 1, + "max": "1", + "min": "0", + "show": true + }, + { + "$$hashKey": "object:3671", + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + } + ], + "repeat": null, + "title": "Storage Filesystem", + "type": "row" + }, + { + "collapsed": true, + "datasource": "${DS_PROMETHEUS}", + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 30 + }, + "id": 272, + "panels": [ + { + "aliasColors": { + "receive_packets_eth0": "#7EB26D", + "receive_packets_lo": "#E24D42", + "transmit_packets_eth0": "#7EB26D", + "transmit_packets_lo": "#E24D42" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 0, + "y": 30 + }, + "hiddenSeries": false, + "id": 60, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": true, + "min": true, + "rightSide": false, + "show": true, + "sideWidth": 300, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "/.*Trans.*/", + "transform": "negative-Y" + } + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "irate(node_network_receive_packets_total{instance=\"$node\",job=\"$job\"}[5m])", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "{{device}} - Receive", + "refId": "A", + "step": 4 + }, + { + "expr": "irate(node_network_transmit_packets_total{instance=\"$node\",job=\"$job\"}[5m])", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "{{device}} - Transmit", + "refId": "B", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Network Traffic by Packets", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "pps", + "label": "packets out (-) / in (+)", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 12, + "y": 30 + }, + "hiddenSeries": false, + "id": 142, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "hideEmpty": false, + "hideZero": false, + "max": true, + "min": true, + "rightSide": false, + "show": true, + "sideWidth": 300, + "sort": "current", + "sortDesc": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "/.*Trans.*/", + "transform": "negative-Y" + } + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "irate(node_network_receive_errs_total{instance=\"$node\",job=\"$job\"}[5m])", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{device}} - Receive errors", + "refId": "A", + "step": 4 + }, + { + "expr": "irate(node_network_transmit_errs_total{instance=\"$node\",job=\"$job\"}[5m])", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{device}} - Rransmit errors", + "refId": "B", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Network Traffic Errors", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "pps", + "label": "packets out (-) / in (+)", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 0, + "y": 40 + }, + "hiddenSeries": false, + "id": 143, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "hideEmpty": false, + "hideZero": false, + "max": true, + "min": true, + "rightSide": false, + "show": true, + "sideWidth": 300, + "sort": "current", + "sortDesc": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "/.*Trans.*/", + "transform": "negative-Y" + } + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "irate(node_network_receive_drop_total{instance=\"$node\",job=\"$job\"}[5m])", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{device}} - Receive drop", + "refId": "A", + "step": 4 + }, + { + "expr": "irate(node_network_transmit_drop_total{instance=\"$node\",job=\"$job\"}[5m])", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{device}} - Transmit drop", + "refId": "B", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Network Traffic Drop", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "pps", + "label": "packets out (-) / in (+)", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 12, + "y": 40 + }, + "hiddenSeries": false, + "id": 141, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "hideEmpty": false, + "hideZero": false, + "max": true, + "min": true, + "rightSide": false, + "show": true, + "sideWidth": 300, + "sort": "current", + "sortDesc": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "/.*Trans.*/", + "transform": "negative-Y" + } + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "irate(node_network_receive_compressed_total{instance=\"$node\",job=\"$job\"}[5m])", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{device}} - Receive compressed", + "refId": "A", + "step": 4 + }, + { + "expr": "irate(node_network_transmit_compressed_total{instance=\"$node\",job=\"$job\"}[5m])", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{device}} - Transmit compressed", + "refId": "B", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Network Traffic Compressed", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "pps", + "label": "packets out (-) / in (+)", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 0, + "y": 50 + }, + "hiddenSeries": false, + "id": 146, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "hideEmpty": false, + "hideZero": false, + "max": true, + "min": true, + "rightSide": false, + "show": true, + "sideWidth": 300, + "sort": "current", + "sortDesc": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "/.*Trans.*/", + "transform": "negative-Y" + } + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "irate(node_network_receive_multicast_total{instance=\"$node\",job=\"$job\"}[5m])", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{device}} - Receive multicast", + "refId": "A", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Network Traffic Multicast", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "pps", + "label": "packets out (-) / in (+)", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 12, + "y": 50 + }, + "hiddenSeries": false, + "id": 144, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "hideEmpty": false, + "hideZero": false, + "max": true, + "min": true, + "rightSide": false, + "show": true, + "sideWidth": 300, + "sort": "current", + "sortDesc": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "/.*Trans.*/", + "transform": "negative-Y" + } + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "irate(node_network_receive_fifo_total{instance=\"$node\",job=\"$job\"}[5m])", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{device}} - Receive fifo", + "refId": "A", + "step": 4 + }, + { + "expr": "irate(node_network_transmit_fifo_total{instance=\"$node\",job=\"$job\"}[5m])", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{device}} - Transmit fifo", + "refId": "B", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Network Traffic Fifo", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "pps", + "label": "packets out (-) / in (+)", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 0, + "y": 60 + }, + "hiddenSeries": false, + "id": 145, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "hideEmpty": false, + "hideZero": false, + "max": true, + "min": true, + "rightSide": false, + "show": true, + "sideWidth": 300, + "sort": "current", + "sortDesc": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "$$hashKey": "object:576", + "alias": "/.*Trans.*/", + "transform": "negative-Y" + } + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "irate(node_network_receive_frame_total{instance=\"$node\",job=\"$job\"}[5m])", + "format": "time_series", + "hide": false, + "intervalFactor": 2, + "legendFormat": "{{device}} - Receive frame", + "refId": "A", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Network Traffic Frame", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "$$hashKey": "object:589", + "format": "pps", + "label": "packets out (-) / in (+)", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "$$hashKey": "object:590", + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 12, + "y": 60 + }, + "hiddenSeries": false, + "id": 231, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "hideEmpty": false, + "hideZero": false, + "max": true, + "min": true, + "rightSide": false, + "show": true, + "sideWidth": 300, + "sort": "current", + "sortDesc": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "irate(node_network_transmit_carrier_total{instance=\"$node\",job=\"$job\"}[5m])", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{device}} - Statistic transmit_carrier", + "refId": "A", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Network Traffic Carrier", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "short", + "label": "counter", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 0, + "y": 70 + }, + "hiddenSeries": false, + "id": 232, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "hideEmpty": false, + "hideZero": false, + "max": true, + "min": true, + "rightSide": false, + "show": true, + "sideWidth": 300, + "sort": "current", + "sortDesc": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "/.*Trans.*/", + "transform": "negative-Y" + } + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "irate(node_network_transmit_colls_total{instance=\"$node\",job=\"$job\"}[5m])", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{device}} - Transmit colls", + "refId": "A", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Network Traffic Colls", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "short", + "label": "counter", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 12, + "y": 70 + }, + "hiddenSeries": false, + "id": 61, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": true, + "min": true, + "rightSide": false, + "show": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "$$hashKey": "object:663", + "alias": "NF conntrack limit", + "color": "#890F02", + "fill": 0 + } + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "node_nf_conntrack_entries{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "NF conntrack entries", + "refId": "A", + "step": 4 + }, + { + "expr": "node_nf_conntrack_entries_limit{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "NF conntrack limit", + "refId": "B", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "NF Contrack", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "$$hashKey": "object:678", + "format": "short", + "label": "entries", + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "$$hashKey": "object:679", + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 0, + "y": 80 + }, + "hiddenSeries": false, + "id": 230, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": true, + "min": true, + "rightSide": false, + "show": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "node_arp_entries{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{ device }} - ARP entries", + "refId": "A", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "ARP Entries", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "short", + "label": "Entries", + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 12, + "y": 80 + }, + "hiddenSeries": false, + "id": 288, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": true, + "min": true, + "rightSide": false, + "show": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 1, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "node_network_mtu_bytes{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{ device }} - Bytes", + "refId": "A", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "MTU", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "decimals": 0, + "format": "bytes", + "label": "bytes", + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 0, + "y": 90 + }, + "hiddenSeries": false, + "id": 280, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": true, + "min": true, + "rightSide": false, + "show": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 1, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "node_network_speed_bytes{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{ device }} - Speed", + "refId": "A", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Speed", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "decimals": 0, + "format": "bytes", + "label": "bytes", + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 12, + "y": 90 + }, + "hiddenSeries": false, + "id": 289, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": true, + "min": true, + "rightSide": false, + "show": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 1, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "node_network_transmit_queue_length{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{ device }} - Interface transmit queue length", + "refId": "A", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Queue Length", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "decimals": 0, + "format": "none", + "label": "packets", + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 0, + "y": 100 + }, + "hiddenSeries": false, + "id": 290, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "hideEmpty": false, + "hideZero": false, + "max": true, + "min": true, + "rightSide": false, + "show": true, + "sideWidth": 300, + "sort": "current", + "sortDesc": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "$$hashKey": "object:232", + "alias": "/.*Dropped.*/", + "transform": "negative-Y" + } + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "irate(node_softnet_processed_total{instance=\"$node\",job=\"$job\"}[5m])", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "CPU {{cpu}} - Processed", + "refId": "A", + "step": 4 + }, + { + "expr": "irate(node_softnet_dropped_total{instance=\"$node\",job=\"$job\"}[5m])", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "CPU {{cpu}} - Dropped", + "refId": "B", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Softnet Packets", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "$$hashKey": "object:207", + "format": "short", + "label": "packetes drop (-) / process (+)", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "$$hashKey": "object:208", + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 12, + "y": 100 + }, + "hiddenSeries": false, + "id": 310, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "hideEmpty": false, + "hideZero": false, + "max": true, + "min": true, + "rightSide": false, + "show": true, + "sideWidth": 300, + "sort": "current", + "sortDesc": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "irate(node_softnet_times_squeezed_total{instance=\"$node\",job=\"$job\"}[5m])", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "CPU {{cpu}} - Squeezed", + "refId": "A", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Softnet Out of Quota", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "$$hashKey": "object:207", + "format": "short", + "label": "counter", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "$$hashKey": "object:208", + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 0, + "y": 110 + }, + "hiddenSeries": false, + "id": 309, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "hideEmpty": false, + "hideZero": false, + "max": true, + "min": true, + "rightSide": false, + "show": true, + "sideWidth": 300, + "sort": "current", + "sortDesc": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "node_network_up{operstate=\"up\",instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{interface}} - Operational state UP", + "refId": "A", + "step": 4 + }, + { + "expr": "node_network_carrier{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "instant": false, + "legendFormat": "{{device}} - Physical link state", + "refId": "B" + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Network Operational Status", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "short", + "label": "counter", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + } + ], + "repeat": null, + "title": "Network Traffic", + "type": "row" + }, + { + "collapsed": true, + "datasource": "${DS_PROMETHEUS}", + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 31 + }, + "id": 273, + "panels": [ + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 0, + "y": 13 + }, + "hiddenSeries": false, + "id": 63, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "hideEmpty": false, + "hideZero": false, + "max": true, + "min": true, + "rightSide": false, + "show": true, + "sideWidth": 300, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "node_sockstat_TCP_alloc{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "TCP_alloc - Allocated sockets", + "refId": "A", + "step": 240 + }, + { + "expr": "node_sockstat_TCP_inuse{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "TCP_inuse - Tcp sockets currently in use", + "refId": "B", + "step": 240 + }, + { + "expr": "node_sockstat_TCP_mem{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "hide": true, + "interval": "", + "intervalFactor": 2, + "legendFormat": "TCP_mem - Used memory for tcp", + "refId": "C", + "step": 240 + }, + { + "expr": "node_sockstat_TCP_orphan{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "TCP_orphan - Orphan sockets", + "refId": "D", + "step": 240 + }, + { + "expr": "node_sockstat_TCP_tw{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "TCP_tw - Sockets wating close", + "refId": "E", + "step": 240 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Sockstat TCP", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "short", + "label": "counter", + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 12, + "y": 13 + }, + "hiddenSeries": false, + "id": 124, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "hideEmpty": false, + "hideZero": false, + "max": true, + "min": true, + "rightSide": false, + "show": true, + "sideWidth": 300, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "node_sockstat_UDPLITE_inuse{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "UDPLITE_inuse - Udplite sockets currently in use", + "refId": "A", + "step": 240 + }, + { + "expr": "node_sockstat_UDP_inuse{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "UDP_inuse - Udp sockets currently in use", + "refId": "B", + "step": 240 + }, + { + "expr": "node_sockstat_UDP_mem{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "UDP_mem - Used memory for udp", + "refId": "C", + "step": 240 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Sockstat UDP", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "short", + "label": "counter", + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 0, + "y": 23 + }, + "hiddenSeries": false, + "id": 126, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "hideEmpty": false, + "hideZero": false, + "max": true, + "min": true, + "rightSide": false, + "show": true, + "sideWidth": 300, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "node_sockstat_sockets_used{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "Sockets_used - Sockets currently in use", + "refId": "A", + "step": 240 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Sockstat Used", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "short", + "label": "sockets", + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 12, + "y": 23 + }, + "hiddenSeries": false, + "id": 220, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "hideEmpty": false, + "hideZero": false, + "max": true, + "min": true, + "rightSide": false, + "show": true, + "sideWidth": 300, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "node_sockstat_TCP_mem_bytes{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "mem_bytes - TCP sockets in that state", + "refId": "A", + "step": 240 + }, + { + "expr": "node_sockstat_UDP_mem_bytes{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "mem_bytes - UDP sockets in that state", + "refId": "B", + "step": 240 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Sockstat Memory Size", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "bytes", + "label": "bytes", + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 0, + "y": 33 + }, + "hiddenSeries": false, + "id": 125, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "hideEmpty": false, + "hideZero": false, + "max": true, + "min": true, + "rightSide": false, + "show": true, + "sideWidth": 300, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "node_sockstat_FRAG_inuse{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "FRAG_inuse - Frag sockets currently in use", + "refId": "A", + "step": 240 + }, + { + "expr": "node_sockstat_FRAG_memory{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "FRAG_memory - Used memory for frag", + "refId": "B", + "step": 240 + }, + { + "expr": "node_sockstat_RAW_inuse{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "RAW_inuse - Raw sockets currently in use", + "refId": "C", + "step": 240 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Sockstat FRAG / RAW", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "$$hashKey": "object:1572", + "format": "short", + "label": "counter", + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "$$hashKey": "object:1573", + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + } + ], + "repeat": null, + "title": "Network Sockstat", + "type": "row" + }, + { + "collapsed": true, + "datasource": "${DS_PROMETHEUS}", + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 32 + }, + "id": 274, + "panels": [ + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 0, + "y": 32 + }, + "height": "", + "hiddenSeries": false, + "id": 221, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "hideEmpty": false, + "hideZero": false, + "max": true, + "min": true, + "rightSide": false, + "show": true, + "sideWidth": 300, + "sort": "current", + "sortDesc": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "maxPerRow": 12, + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "$$hashKey": "object:1876", + "alias": "/.*Out.*/", + "transform": "negative-Y" + } + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "irate(node_netstat_IpExt_InOctets{instance=\"$node\",job=\"$job\"}[5m])", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "InOctets - Received octets", + "refId": "A", + "step": 4 + }, + { + "expr": "irate(node_netstat_IpExt_OutOctets{instance=\"$node\",job=\"$job\"}[5m])", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "OutOctets - Sent octets", + "refId": "B", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Netstat IP In / Out Octets", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "$$hashKey": "object:1889", + "format": "short", + "label": "octects out (-) / in (+)", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "$$hashKey": "object:1890", + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 12, + "y": 32 + }, + "height": "", + "hiddenSeries": false, + "id": 81, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "hideEmpty": false, + "hideZero": false, + "max": true, + "min": true, + "rightSide": false, + "show": true, + "sideWidth": 300, + "sort": "current", + "sortDesc": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "irate(node_netstat_Ip_Forwarding{instance=\"$node\",job=\"$job\"}[5m])", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "Forwarding - IP forwarding", + "refId": "A", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Netstat IP Forwarding", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "$$hashKey": "object:1957", + "format": "short", + "label": "datagrams", + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "$$hashKey": "object:1958", + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "decimals": null, + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 0, + "y": 42 + }, + "height": "", + "hiddenSeries": false, + "id": 115, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "hideZero": false, + "max": true, + "min": true, + "rightSide": false, + "show": true, + "sort": "current", + "sortDesc": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "maxPerRow": 12, + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "/.*Out.*/", + "transform": "negative-Y" + } + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "irate(node_netstat_Icmp_InMsgs{instance=\"$node\",job=\"$job\"}[5m])", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "InMsgs - Messages which the entity received. Note that this counter includes all those counted by icmpInErrors", + "refId": "A", + "step": 4 + }, + { + "expr": "irate(node_netstat_Icmp_OutMsgs{instance=\"$node\",job=\"$job\"}[5m])", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "OutMsgs - Messages which this entity attempted to send. Note that this counter includes all those counted by icmpOutErrors", + "refId": "B", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "ICMP In / Out", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "short", + "label": "messages out (-) / in (+)", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "decimals": null, + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 12, + "y": 42 + }, + "height": "", + "hiddenSeries": false, + "id": 50, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "hideZero": false, + "max": true, + "min": true, + "rightSide": false, + "show": true, + "sort": "current", + "sortDesc": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "maxPerRow": 12, + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "/.*Out.*/", + "transform": "negative-Y" + } + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "irate(node_netstat_Icmp_InErrors{instance=\"$node\",job=\"$job\"}[5m])", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "InErrors - Messages which the entity received but determined as having ICMP-specific errors (bad ICMP checksums, bad length, etc.)", + "refId": "A", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "ICMP Errors", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "short", + "label": "messages out (-) / in (+)", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "decimals": null, + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 0, + "y": 52 + }, + "height": "", + "hiddenSeries": false, + "id": 55, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "hideZero": false, + "max": true, + "min": true, + "rightSide": false, + "show": true, + "sort": "current", + "sortDesc": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "maxPerRow": 12, + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "/.*Out.*/", + "transform": "negative-Y" + }, + { + "alias": "/.*Snd.*/", + "transform": "negative-Y" + } + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "irate(node_netstat_Udp_InDatagrams{instance=\"$node\",job=\"$job\"}[5m])", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "InDatagrams - Datagrams received", + "refId": "A", + "step": 4 + }, + { + "expr": "irate(node_netstat_Udp_OutDatagrams{instance=\"$node\",job=\"$job\"}[5m])", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "OutDatagrams - Datagrams sent", + "refId": "B", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "UDP In / Out", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "short", + "label": "datagrams out (-) / in (+)", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 12, + "y": 52 + }, + "height": "", + "hiddenSeries": false, + "id": 109, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "hideZero": false, + "max": true, + "min": true, + "rightSide": false, + "show": true, + "sort": "current", + "sortDesc": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "maxPerRow": 12, + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "irate(node_netstat_Udp_InErrors{instance=\"$node\",job=\"$job\"}[5m])", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "InErrors - UDP Datagrams that could not be delivered to an application", + "refId": "A", + "step": 4 + }, + { + "expr": "irate(node_netstat_Udp_NoPorts{instance=\"$node\",job=\"$job\"}[5m])", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "NoPorts - UDP Datagrams received on a port with no listener", + "refId": "B", + "step": 4 + }, + { + "expr": "irate(node_netstat_UdpLite_InErrors{instance=\"$node\",job=\"$job\"}[5m])", + "interval": "", + "legendFormat": "InErrors Lite - UDPLite Datagrams that could not be delivered to an application", + "refId": "C" + }, + { + "expr": "irate(node_netstat_Udp_RcvbufErrors{instance=\"$node\",job=\"$job\"}[5m])", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "RcvbufErrors - UDP buffer errors received", + "refId": "D", + "step": 4 + }, + { + "expr": "irate(node_netstat_Udp_SndbufErrors{instance=\"$node\",job=\"$job\"}[5m])", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "SndbufErrors - UDP buffer errors send", + "refId": "E", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "UDP Errors", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "$$hashKey": "object:4232", + "format": "short", + "label": "datagrams", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "$$hashKey": "object:4233", + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "decimals": null, + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 0, + "y": 62 + }, + "height": "", + "hiddenSeries": false, + "id": 299, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "hideZero": false, + "max": true, + "min": true, + "rightSide": false, + "show": true, + "sort": "current", + "sortDesc": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "maxPerRow": 12, + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "/.*Out.*/", + "transform": "negative-Y" + }, + { + "alias": "/.*Snd.*/", + "transform": "negative-Y" + } + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "irate(node_netstat_Tcp_InSegs{instance=\"$node\",job=\"$job\"}[5m])", + "format": "time_series", + "instant": false, + "interval": "", + "intervalFactor": 2, + "legendFormat": "InSegs - Segments received, including those received in error. This count includes segments received on currently established connections", + "refId": "A", + "step": 4 + }, + { + "expr": "irate(node_netstat_Tcp_OutSegs{instance=\"$node\",job=\"$job\"}[5m])", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "OutSegs - Segments sent, including those on current connections but excluding those containing only retransmitted octets", + "refId": "B", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "TCP In / Out", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "short", + "label": "datagrams out (-) / in (+)", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "description": "", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 12, + "y": 62 + }, + "height": "", + "hiddenSeries": false, + "id": 104, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "hideEmpty": false, + "hideZero": false, + "max": true, + "min": true, + "rightSide": false, + "show": true, + "sort": "current", + "sortDesc": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "maxPerRow": 12, + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "irate(node_netstat_TcpExt_ListenOverflows{instance=\"$node\",job=\"$job\"}[5m])", + "format": "time_series", + "hide": false, + "interval": "", + "intervalFactor": 2, + "legendFormat": "ListenOverflows - Times the listen queue of a socket overflowed", + "refId": "A", + "step": 4 + }, + { + "expr": "irate(node_netstat_TcpExt_ListenDrops{instance=\"$node\",job=\"$job\"}[5m])", + "format": "time_series", + "hide": false, + "interval": "", + "intervalFactor": 2, + "legendFormat": "ListenDrops - SYNs to LISTEN sockets ignored", + "refId": "B", + "step": 4 + }, + { + "expr": "irate(node_netstat_TcpExt_TCPSynRetrans{instance=\"$node\",job=\"$job\"}[5m])", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "TCPSynRetrans - SYN-SYN/ACK retransmits to break down retransmissions in SYN, fast/timeout retransmits", + "refId": "C", + "step": 4 + }, + { + "expr": "irate(node_netstat_Tcp_RetransSegs{instance=\"$node\",job=\"$job\"}[5m])", + "interval": "", + "legendFormat": "RetransSegs - Segments retransmitted - that is, the number of TCP segments transmitted containing one or more previously transmitted octets", + "refId": "D" + }, + { + "expr": "irate(node_netstat_Tcp_InErrs{instance=\"$node\",job=\"$job\"}[5m])", + "interval": "", + "legendFormat": "InErrs - Segments received in error (e.g., bad TCP checksums)", + "refId": "E" + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "TCP Errors", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "short", + "label": "counter", + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 0, + "y": 72 + }, + "height": "", + "hiddenSeries": false, + "id": 85, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "hideZero": false, + "max": true, + "min": true, + "rightSide": false, + "show": true, + "sortDesc": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "maxPerRow": 12, + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "$$hashKey": "object:454", + "alias": "/.*MaxConn *./", + "color": "#890F02", + "fill": 0 + } + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "node_netstat_Tcp_CurrEstab{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "hide": false, + "interval": "", + "intervalFactor": 2, + "legendFormat": "CurrEstab - TCP connections for which the current state is either ESTABLISHED or CLOSE- WAIT", + "refId": "A", + "step": 4 + }, + { + "expr": "node_netstat_Tcp_MaxConn{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "hide": false, + "interval": "", + "intervalFactor": 2, + "legendFormat": "MaxConn - Limit on the total number of TCP connections the entity can support (Dinamic is \"-1\")", + "refId": "B", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "TCP Connections", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "$$hashKey": "object:469", + "format": "short", + "label": "connections", + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "$$hashKey": "object:470", + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "description": "", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 12, + "y": 72 + }, + "height": "", + "hiddenSeries": false, + "id": 91, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "hideEmpty": false, + "hideZero": false, + "max": true, + "min": true, + "rightSide": false, + "show": true, + "sort": "current", + "sortDesc": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "maxPerRow": 12, + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "/.*Sent.*/", + "transform": "negative-Y" + } + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "irate(node_netstat_TcpExt_SyncookiesFailed{instance=\"$node\",job=\"$job\"}[5m])", + "format": "time_series", + "hide": false, + "interval": "", + "intervalFactor": 2, + "legendFormat": "SyncookiesFailed - Invalid SYN cookies received", + "refId": "A", + "step": 4 + }, + { + "expr": "irate(node_netstat_TcpExt_SyncookiesRecv{instance=\"$node\",job=\"$job\"}[5m])", + "format": "time_series", + "hide": false, + "interval": "", + "intervalFactor": 2, + "legendFormat": "SyncookiesRecv - SYN cookies received", + "refId": "B", + "step": 4 + }, + { + "expr": "irate(node_netstat_TcpExt_SyncookiesSent{instance=\"$node\",job=\"$job\"}[5m])", + "format": "time_series", + "hide": false, + "interval": "", + "intervalFactor": 2, + "legendFormat": "SyncookiesSent - SYN cookies sent", + "refId": "C", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "TCP SynCookie", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "short", + "label": "counter out (-) / in (+)", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 0, + "y": 82 + }, + "height": "", + "hiddenSeries": false, + "id": 82, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "hideZero": false, + "max": true, + "min": true, + "rightSide": false, + "show": true, + "sortDesc": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "maxPerRow": 12, + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "irate(node_netstat_Tcp_ActiveOpens{instance=\"$node\",job=\"$job\"}[5m])", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "ActiveOpens - TCP connections that have made a direct transition to the SYN-SENT state from the CLOSED state", + "refId": "A", + "step": 4 + }, + { + "expr": "irate(node_netstat_Tcp_PassiveOpens{instance=\"$node\",job=\"$job\"}[5m])", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "PassiveOpens - TCP connections that have made a direct transition to the SYN-RCVD state from the LISTEN state", + "refId": "B", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "TCP Direct Transition", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "short", + "label": "connections", + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + } + ], + "repeat": null, + "title": "Network Netstat", + "type": "row" + }, + { + "collapsed": true, + "datasource": "${DS_PROMETHEUS}", + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 33 + }, + "id": 279, + "panels": [ + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "description": "", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 0, + "y": 54 + }, + "hiddenSeries": false, + "id": 40, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": true, + "min": true, + "show": true, + "sort": "current", + "sortDesc": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "node_scrape_collector_duration_seconds{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "hide": false, + "interval": "", + "intervalFactor": 2, + "legendFormat": "{{collector}} - Scrape duration", + "refId": "A", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Node Exporter Scrape Time", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "s", + "label": "seconds", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "description": "", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 12, + "y": 54 + }, + "hiddenSeries": false, + "id": 157, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": true, + "min": true, + "show": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "$$hashKey": "object:1969", + "alias": "/.*error.*/", + "color": "#F2495C", + "transform": "negative-Y" + } + ], + "spaceLength": 10, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "node_scrape_collector_success{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "hide": false, + "interval": "", + "intervalFactor": 2, + "legendFormat": "{{collector}} - Scrape success", + "refId": "A", + "step": 4 + }, + { + "expr": "node_textfile_scrape_error{instance=\"$node\",job=\"$job\"}", + "format": "time_series", + "hide": false, + "interval": "", + "intervalFactor": 2, + "legendFormat": "{{collector}} - Scrape textfile error (1 = true)", + "refId": "B", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Node Exporter Scrape", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "$$hashKey": "object:1484", + "format": "short", + "label": "counter", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "$$hashKey": "object:1485", + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + } + ], + "repeat": null, + "title": "Node Exporter", + "type": "row" + } + ], + "refresh": "1m", + "schemaVersion": 22, + "style": "dark", + "tags": [ + "linux" + ], + "templating": { + "list": [ + { + "current": { + "selected": false, + "text": "default", + "value": "default" + }, + "hide": 0, + "includeAll": false, + "label": "datasource", + "multi": false, + "name": "DS_PROMETHEUS", + "options": [], + "query": "prometheus", + "refresh": 1, + "regex": "", + "skipUrlSync": false, + "type": "datasource" + }, + { + "allValue": null, + "current": {}, + "datasource": "${DS_PROMETHEUS}", + "definition": "", + "hide": 0, + "includeAll": false, + "index": -1, + "label": "Job", + "multi": false, + "name": "job", + "options": [], + "query": "label_values(node_uname_info, job)", + "refresh": 1, + "regex": "", + "skipUrlSync": false, + "sort": 1, + "tagValuesQuery": "", + "tags": [], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": {}, + "datasource": "${DS_PROMETHEUS}", + "definition": "label_values(node_uname_info{job=\"$job\"}, instance)", + "hide": 0, + "includeAll": false, + "index": -1, + "label": "Host:", + "multi": false, + "name": "node", + "options": [], + "query": "label_values(node_uname_info{job=\"$job\"}, instance)", + "refresh": 1, + "regex": "", + "skipUrlSync": false, + "sort": 1, + "tagValuesQuery": "", + "tags": [], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + "selected": false, + "text": "[a-z]+|nvme[0-9]+n[0-9]+", + "value": "[a-z]+|nvme[0-9]+n[0-9]+" + }, + "hide": 2, + "includeAll": false, + "label": null, + "multi": false, + "name": "diskdevices", + "options": [ + { + "selected": true, + "text": "[a-z]+|nvme[0-9]+n[0-9]+", + "value": "[a-z]+|nvme[0-9]+n[0-9]+" + } + ], + "query": "[a-z]+|nvme[0-9]+n[0-9]+", + "skipUrlSync": false, + "type": "custom" + } + ] + }, + "time": { + "from": "now-4h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "browser", + "title": "Node Exporter", + "version": 1 +}
\ No newline at end of file diff --git a/terraform-ci-infra/1n_nmd/grafana/conf/nomad.json b/terraform-ci-infra/1n_nmd/grafana/conf/nomad.json new file mode 100644 index 0000000000..40ffeddf7b --- /dev/null +++ b/terraform-ci-infra/1n_nmd/grafana/conf/nomad.json @@ -0,0 +1,869 @@ +{ + "__inputs": [ + { + "name": "DS_PROMETHEUS", + "label": "Prometheus", + "description": "", + "type": "datasource", + "pluginId": "prometheus", + "pluginName": "Prometheus" + } + ], + "__requires": [ + { + "type": "grafana", + "id": "grafana", + "name": "Grafana", + "version": "5.3.2" + }, + { + "type": "panel", + "id": "graph", + "name": "Graph", + "version": "5.0.0" + }, + { + "type": "datasource", + "id": "prometheus", + "name": "Prometheus", + "version": "5.0.0" + }, + { + "type": "panel", + "id": "singlestat", + "name": "Singlestat", + "version": "5.0.0" + } + ], + "annotations": { + "list": [ + { + "builtIn": 1, + "datasource": "-- Grafana --", + "enable": true, + "hide": true, + "iconColor": "rgba(0, 211, 255, 1)", + "name": "Annotations & Alerts", + "type": "dashboard" + } + ] + }, + "description": "Nomad Jobs metrics", + "editable": true, + "gnetId": 12787, + "graphTooltip": 0, + "id": null, + "iteration": 1596708119930, + "links": [], + "panels": [ + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "#299c46", + "rgba(237, 129, 40, 0.89)", + "#d44a3a" + ], + "datasource": "${DS_PROMETHEUS}", + "decimals": null, + "format": "dtdurations", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + "h": 4, + "w": 4, + "x": 0, + "y": 0 + }, + "id": 16, + "interval": null, + "links": [], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "alias": "", + "expr": "max(nomad_client_uptime{instance=~\"$instance\"})", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "", + "rawSql": "SELECT\n UNIX_TIMESTAMP(<time_column>) as time_sec,\n <value column> as value,\n <series name column> as metric\nFROM <table name>\nWHERE $__timeFilter(time_column)\nORDER BY <time_column> ASC\n", + "refId": "A" + } + ], + "thresholds": "", + "title": "Uptime", + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "current" + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorPrefix": false, + "colorValue": false, + "colors": [ + "#7eb26d", + "rgba(237, 129, 40, 0.89)", + "#d44a3a" + ], + "datasource": "${DS_PROMETHEUS}", + "format": "none", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + "h": 4, + "w": 4, + "x": 4, + "y": 0 + }, + "id": 17, + "interval": null, + "links": [], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": true + }, + "tableColumn": "", + "targets": [ + { + "alias": "", + "expr": "count(sum(nomad_client_allocs_memory_cache) by (exported_job))", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "", + "rawSql": "SELECT\n UNIX_TIMESTAMP(<time_column>) as time_sec,\n <value column> as value,\n <series name column> as metric\nFROM <table name>\nWHERE $__timeFilter(time_column)\nORDER BY <time_column> ASC\n", + "refId": "A" + } + ], + "thresholds": "", + "title": "Jobs", + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "current" + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorPrefix": false, + "colorValue": false, + "colors": [ + "#7eb26d", + "rgba(237, 129, 40, 0.89)", + "#d44a3a" + ], + "datasource": "${DS_PROMETHEUS}", + "format": "none", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + "h": 4, + "w": 4, + "x": 8, + "y": 0 + }, + "id": 12, + "interval": null, + "links": [], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": true + }, + "tableColumn": "", + "targets": [ + { + "alias": "", + "expr": "sum(nomad_client_allocations_running{datacenter=\"$datacenter\",instance=~\"$instance\"})", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "", + "rawSql": "SELECT\n UNIX_TIMESTAMP(<time_column>) as time_sec,\n <value column> as value,\n <series name column> as metric\nFROM <table name>\nWHERE $__timeFilter(time_column)\nORDER BY <time_column> ASC\n", + "refId": "A" + } + ], + "thresholds": "", + "title": "Allocs", + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "current" + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "fill": 1, + "gridPos": { + "h": 4, + "w": 12, + "x": 12, + "y": 0 + }, + "id": 14, + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "alias": "", + "expr": "sum(nomad_client_allocations_blocked{datacenter=\"$datacenter\",instance=~\"$instance\"})", + "format": "time_series", + "hide": false, + "intervalFactor": 1, + "legendFormat": "Blocked", + "rawSql": "SELECT\n UNIX_TIMESTAMP(<time_column>) as time_sec,\n <value column> as value,\n <series name column> as metric\nFROM <table name>\nWHERE $__timeFilter(time_column)\nORDER BY <time_column> ASC\n", + "refId": "A" + }, + { + "expr": "sum(nomad_client_allocations_pending{datacenter=\"$datacenter\",instance=~\"$instance\"})", + "format": "time_series", + "hide": false, + "intervalFactor": 1, + "legendFormat": "Pending", + "refId": "B" + }, + { + "expr": "sum(nomad_client_allocations_restart{datacenter=\"$datacenter\",instance=~\"$instance\"})", + "format": "time_series", + "hide": false, + "intervalFactor": 1, + "legendFormat": "Restart ", + "refId": "C" + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "Block/Peding/Restart", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "fill": 1, + "gridPos": { + "h": 6, + "w": 12, + "x": 0, + "y": 13 + }, + "id": 2, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": "host", + "repeatDirection": "v", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "rate(nomad_client_allocs_cpu_total_percent[5m:10s]) > 1", + "format": "time_series", + "interval": "", + "intervalFactor": 1, + "legendFormat": "{{task}}", + "refId": "A" + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "CPU Usage Percent", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "decimals": 3, + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "fill": 1, + "gridPos": { + "h": 6, + "w": 12, + "x": 12, + "y": 13 + }, + "id": 3, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": "host", + "repeatDirection": "v", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "avg(nomad_client_allocs_cpu_total_ticks{instance=~\"$instance\"}) by(exported_job, task)", + "format": "time_series", + "interval": "", + "intervalFactor": 1, + "legendFormat": "{{task}}", + "refId": "A" + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "CPU Total Ticks", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "decimals": 3, + "format": "timeticks", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "fill": 1, + "gridPos": { + "h": 6, + "w": 12, + "x": 0, + "y": 19 + }, + "id": 6, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": "host", + "repeatDirection": "v", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "avg(nomad_client_allocs_memory_rss{instance=~\"$instance\"}) by(exported_job, task)", + "format": "time_series", + "interval": "", + "intervalFactor": 1, + "legendFormat": "{{task}}", + "refId": "A" + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "RSS", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "decimals": 3, + "format": "decbytes", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "fill": 1, + "gridPos": { + "h": 6, + "w": 12, + "x": 12, + "y": 19 + }, + "id": 7, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": "host", + "repeatDirection": "v", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "avg(nomad_client_allocs_memory_cache{instance=~\"$instance\"}) by(exported_job, task)", + "format": "time_series", + "interval": "", + "intervalFactor": 1, + "legendFormat": "{{task}}", + "refId": "A" + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "Memory Cache", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "decimals": 3, + "format": "decbytes", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + } + ], + "refresh": false, + "schemaVersion": 16, + "style": "dark", + "tags": [], + "templating": { + "list": [ + { + "current": { + "selected": false, + "text": "default", + "value": "default" + }, + "hide": 0, + "includeAll": false, + "label": "datasource", + "multi": false, + "name": "DS_PROMETHEUS", + "options": [], + "query": "prometheus", + "refresh": 1, + "regex": "", + "skipUrlSync": false, + "type": "datasource" + }, + { + "allValue": null, + "current": {}, + "datasource": "${DS_PROMETHEUS}", + "hide": 0, + "includeAll": false, + "label": "DC", + "multi": false, + "name": "datacenter", + "options": [], + "query": "label_values(nomad_client_uptime, datacenter)", + "refresh": 1, + "regex": "", + "skipUrlSync": false, + "sort": 0, + "tagValuesQuery": "", + "tags": [], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": {}, + "datasource": "${DS_PROMETHEUS}", + "hide": 0, + "includeAll": true, + "label": "Host", + "multi": true, + "name": "instance", + "options": [], + "query": "label_values(nomad_client_uptime{datacenter=~\"$datacenter\"}, instance)", + "refresh": 2, + "regex": "", + "skipUrlSync": false, + "sort": 0, + "tagValuesQuery": "", + "tags": [], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-4h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "browser", + "title": "Nomad", + "version": 1 +}
\ No newline at end of file diff --git a/terraform-ci-infra/1n_nmd/grafana/conf/nomad/grafana.hcl b/terraform-ci-infra/1n_nmd/grafana/conf/nomad/grafana.hcl new file mode 100644 index 0000000000..7325c6aef4 --- /dev/null +++ b/terraform-ci-infra/1n_nmd/grafana/conf/nomad/grafana.hcl @@ -0,0 +1,331 @@ +job "${job_name}" { + # The "region" parameter specifies the region in which to execute the job. + # If omitted, this inherits the default region name of "global". + # region = "global" + # + # The "datacenters" parameter specifies the list of datacenters which should + # be considered when placing this task. This must be provided. + datacenters = "${datacenters}" + + # The "type" parameter controls the type of job, which impacts the scheduler's + # decision on placement. This configuration is optional and defaults to + # "service". For a full list of job types and their differences, please see + # the online documentation. + # + # For more information, please see the online documentation at: + # + # https://www.nomadproject.io/docs/jobspec/schedulers + # + type = "service" + + update { + # The "max_parallel" parameter specifies the maximum number of updates to + # perform in parallel. In this case, this specifies to update a single task + # at a time. + max_parallel = 1 + + health_check = "checks" + + # The "min_healthy_time" parameter specifies the minimum time the allocation + # must be in the healthy state before it is marked as healthy and unblocks + # further allocations from being updated. + min_healthy_time = "10s" + + # The "healthy_deadline" parameter specifies the deadline in which the + # allocation must be marked as healthy after which the allocation is + # automatically transitioned to unhealthy. Transitioning to unhealthy will + # fail the deployment and potentially roll back the job if "auto_revert" is + # set to true. + healthy_deadline = "3m" + + # The "progress_deadline" parameter specifies the deadline in which an + # allocation must be marked as healthy. The deadline begins when the first + # allocation for the deployment is created and is reset whenever an allocation + # as part of the deployment transitions to a healthy state. If no allocation + # transitions to the healthy state before the progress deadline, the + # deployment is marked as failed. + progress_deadline = "10m" + +%{ if use_canary } + # The "canary" parameter specifies that changes to the job that would result + # in destructive updates should create the specified number of canaries + # without stopping any previous allocations. Once the operator determines the + # canaries are healthy, they can be promoted which unblocks a rolling update + # of the remaining allocations at a rate of "max_parallel". + # + # Further, setting "canary" equal to the count of the task group allows + # blue/green deployments. When the job is updated, a full set of the new + # version is deployed and upon promotion the old version is stopped. + canary = 1 + + # Specifies if the job should auto-promote to the canary version when all + # canaries become healthy during a deployment. Defaults to false which means + # canaries must be manually updated with the nomad deployment promote + # command. + auto_promote = true + + # The "auto_revert" parameter specifies if the job should auto-revert to the + # last stable job on deployment failure. A job is marked as stable if all the + # allocations as part of its deployment were marked healthy. + auto_revert = true +%{ endif } + } + + # The "group" stanza defines a series of tasks that should be co-located on + # the same Nomad client. Any task within a group will be placed on the same + # client. + # + # For more information and examples on the "group" stanza, please see + # the online documentation at: + # + # https://www.nomadproject.io/docs/job-specification/group + # + group "prod-group1-${service_name}" { + # The "count" parameter specifies the number of the task groups that should + # be running under this group. This value must be non-negative and defaults + # to 1. + count = ${group_count} + + + # The constraint allows restricting the set of eligible nodes. Constraints + # may filter on attributes or client metadata. + # + # For more information and examples on the "volume" stanza, please see + # the online documentation at: + # + # https://www.nomadproject.io/docs/job-specification/constraint + # + constraint { + attribute = "$${attr.cpu.arch}" + operator = "!=" + value = "arm64" + } + + # The "task" stanza creates an individual unit of work, such as a Docker + # container, web application, or batch processing. + # + # For more information and examples on the "task" stanza, please see + # the online documentation at: + # + # https://www.nomadproject.io/docs/job-specification/task + # + task "prod-task1-${service_name}" { + # The "driver" parameter specifies the task driver that should be used to + # run the task. + driver = "docker" + + # The "config" stanza specifies the driver configuration, which is passed + # directly to the driver to start the task. The details of configurations + # are specific to each driver, so please see specific driver + # documentation for more information. + config { + image = "${image}" + dns_servers = [ "$${attr.unique.network.ip-address}" ] + volumes = [ + "secrets/prometheus.yml:/etc/grafana/provisioning/datasources/prometheus.yml", + "secrets/dashboards.yml:/etc/grafana/provisioning/dashboards/dashboards.yml", + "secrets/grafana.ini:/etc/grafana/grafana.ini", + "secrets/node_exporter.json:/etc/grafana/provisioning/dashboards/node_exporter.json", + "secrets/docker_cadvisor.json:/etc/grafana/provisioning/dashboards/docker_cadvisor.json", + "secrets/nomad.json:/etc/grafana/provisioning/dashboards/nomad.json", + "secrets/consul.json:/etc/grafana/provisioning/dashboards/consul.json", + "secrets/prometheus.json:/etc/grafana/provisioning/dashboards/prometheus.json", + "secrets/blackbox_exporter_http.json:/etc/grafana/provisioning/dashboards/blackbox_exporter_http.json", + "secrets/blackbox_exporter_icmp.json:/etc/grafana/provisioning/dashboards/blackbox_exporter_icmp.json" + ] + } + + artifact { + # Prometheus Node Exporter + source = "https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/node_exporter.json" + destination = "secrets/" + } + + artifact { + # Docker cAdvisor + source = "https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/docker_cadvisor.json" + destination = "secrets/" + } + + artifact { + # Nomad + source = "https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/nomad.json" + destination = "secrets/" + } + + artifact { + # Consul + source = "https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/consul.json" + destination = "secrets/" + } + + artifact { + # Prometheus + source = "https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/prometheus.json" + destination = "secrets/" + } + + artifact { + # Prometheus Blackbox Exporter HTTP + source = "https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/blackbox_exporter_http.json" + destination = "secrets/" + } + + artifact { + # Prometheus Blackbox Exporter ICMP + source = "https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/blackbox_exporter_icmp.json" + destination = "secrets/" + } + + # The "template" stanza instructs Nomad to manage a template, such as + # a configuration file or script. This template can optionally pull data + # from Consul or Vault to populate runtime configuration data. + # + # For more information and examples on the "template" stanza, please see + # the online documentation at: + # + # https://www.nomadproject.io/docs/job-specification/template + # + template { + change_mode = "noop" + change_signal = "SIGINT" + destination = "secrets/prometheus.yml" + data = <<EOH +apiVersion: 1 +datasources: +- name: Prometheus + type: prometheus + access: direct + orgId: 1 + url: http://prometheus.service.consul:9090 + basicAuth: false + isDefault: true + version: 1 + editable: false +EOH + } + + template { + change_mode = "noop" + change_signal = "SIGINT" + destination = "secrets/dashboards.yml" + data = <<EOH +apiVersion: 1 +providers: +- name: dashboards + type: file + disableDeletion: false + updateIntervalSeconds: 10 + allowUiUpdates: false + options: + path: /etc/grafana/provisioning/dashboards + foldersFromFilesStructure: true +EOH + } + + template { + change_mode = "noop" + change_signal = "SIGINT" + destination = "secrets/grafana.ini" + data = <<EOH +app_mode = production + +[metrics] +enabled = true + +[server] +protocol = http +http_port = ${port} +root_url = http://${service_name}.service.consul:${port} +enable_gzip = true +;cert_file = +;cert_key = + +[security] +admin_user = grafanauser +admin_password = Grafana1234 +secret_key = SW2YcwTIb9zpOOhoPsMm + +[users] +allow_sign_up = false +allow_org_create = false +auto_assign_org = true +auto_assign_org_role = Viewer +default_theme = dark + +[auth.basic] +enabled = true + +[auth] +disable_login_form = false +disable_signout_menu = false + +[auth.anonymous] +enabled = false + +[log] +mode = console +level = info + +[log.console] +level = info +format = console +EOH + } + + # The service stanza instructs Nomad to register a service with Consul. + # + # For more information and examples on the "task" stanza, please see + # the online documentation at: + # + # https://www.nomadproject.io/docs/job-specification/service + # + service { + name = "${service_name}" + port = "${service_name}" + tags = [ "${service_name}$${NOMAD_ALLOC_INDEX}" ] + check { + name = "Grafana Check Live" + type = "http" + protocol = "http" + tls_skip_verify = true + path = "/api/health" + interval = "10s" + timeout = "2s" + } + } + + # The "resources" stanza describes the requirements a task needs to + # execute. Resource requirements include memory, network, cpu, and more. + # This ensures the task will execute on a machine that contains enough + # resource capacity. + # + # For more information and examples on the "resources" stanza, please see + # the online documentation at: + # + # https://www.nomadproject.io/docs/job-specification/resources + # + resources { + cpu = ${cpu} + memory = ${mem} + # The network stanza specifies the networking requirements for the task + # group, including the network mode and port allocations. When scheduling + # jobs in Nomad they are provisioned across your fleet of machines along + # with other jobs and services. Because you don't know in advance what host + # your job will be provisioned on, Nomad will provide your tasks with + # network configuration when they start up. + # + # For more information and examples on the "template" stanza, please see + # the online documentation at: + # + # https://www.nomadproject.io/docs/job-specification/network + # + network { + port "${service_name}" { + static = ${port} + } + } + } + } + } +}
\ No newline at end of file diff --git a/terraform-ci-infra/1n_nmd/grafana/conf/prometheus.json b/terraform-ci-infra/1n_nmd/grafana/conf/prometheus.json new file mode 100644 index 0000000000..0f07574b07 --- /dev/null +++ b/terraform-ci-infra/1n_nmd/grafana/conf/prometheus.json @@ -0,0 +1,3055 @@ +{ + "__inputs": [ + { + "name": "DS_PROMETHEUS", + "label": "prometheus", + "description": "A prometheus server with prometheus server metrics", + "type": "datasource", + "pluginId": "prometheus", + "pluginName": "Prometheus" + } + ], + "__requires": [ + { + "type": "grafana", + "id": "grafana", + "name": "Grafana", + "version": "4.5.0-beta1" + }, + { + "type": "panel", + "id": "graph", + "name": "Graph", + "version": "" + }, + { + "type": "datasource", + "id": "prometheus", + "name": "Prometheus", + "version": "1.0.0" + }, + { + "type": "panel", + "id": "singlestat", + "name": "Singlestat", + "version": "" + }, + { + "type": "panel", + "id": "table", + "name": "Table", + "version": "" + } + ], + "annotations": { + "list": [ + { + "datasource": "${DS_PROMETHEUS}", + "enable": true, + "expr": "sum(changes(prometheus_config_last_reload_success_timestamp_seconds{instance=~\"$instance\"}[10m])) by (instance)", + "hide": false, + "iconColor": "rgb(0, 96, 19)", + "limit": 100, + "name": "reloads", + "showIn": 0, + "step": "5m", + "type": "alert" + }, + { + "datasource": "${DS_PROMETHEUS}", + "enable": true, + "expr": "count(sum(up{instance=\"$instance\"}) by (instance) < 1)", + "hide": false, + "iconColor": "rgba(255, 96, 96, 1)", + "limit": 100, + "name": "down", + "showIn": 0, + "step": "5m", + "type": "alert" + } + ] + }, + "description": "Get started faster with Grafana Cloud then easily build these dashboards. https://grafana.com/products/cloud/\nOverview of metrics from Prometheus 2.0. \nUseful for using prometheus to monitor your prometheus.\nRevisions welcome!", + "editable": true, + "gnetId": 3662, + "graphTooltip": 0, + "hideControls": false, + "id": null, + "links": [], + "refresh": "30s", + "rows": [ + { + "collapse": false, + "height": 250, + "panels": [ + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": true, + "colors": [ + "rgba(245, 54, 54, 0.9)", + "rgba(237, 129, 40, 0.89)", + "rgba(50, 172, 45, 0.97)" + ], + "datasource": "${DS_PROMETHEUS}", + "decimals": 3, + "description": "Percentage of uptime during the most recent $interval period. Change the period with the 'interval' dropdown above.", + "format": "none", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": false + }, + "id": 2, + "interval": null, + "links": [], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "%", + "postfixFontSize": "100%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "span": 3, + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": true, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "avg(avg_over_time(up{instance=~\"$instance\",job=~\"$job\"}[$interval]) * 100)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 40 + } + ], + "thresholds": "90, 99", + "title": "Uptime [$interval]", + "type": "singlestat", + "valueFontSize": "100%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "current" + }, + { + "columns": [], + "datasource": "${DS_PROMETHEUS}", + "description": "Servers which are DOWN RIGHT NOW! \nFIX THEM!!", + "fontSize": "100%", + "hideTimeOverride": true, + "id": 25, + "links": [], + "pageSize": null, + "scroll": true, + "showHeader": true, + "sort": { + "col": 0, + "desc": true + }, + "span": 3, + "styles": [ + { + "alias": "Time", + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "pattern": "Time", + "type": "hidden" + }, + { + "alias": "", + "colorMode": null, + "colors": [ + "rgba(245, 54, 54, 0.9)", + "rgba(237, 129, 40, 0.89)", + "rgba(50, 172, 45, 0.97)" + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "/__name__|job|Value/", + "thresholds": [], + "type": "hidden", + "unit": "short" + }, + { + "alias": " ", + "colorMode": "cell", + "colors": [ + "rgba(255, 0, 0, 0.9)", + "rgba(237, 129, 40, 0.89)", + "rgba(255, 0, 0, 0.97)" + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "pattern": "instance", + "thresholds": [ + "", + "", + "" + ], + "type": "string", + "unit": "short" + } + ], + "targets": [ + { + "expr": "up{instance=~\"$instance\",job=~\"$job\"} < 1", + "format": "table", + "intervalFactor": 2, + "refId": "A", + "step": 2 + } + ], + "timeFrom": "1s", + "title": "Currently Down", + "transform": "table", + "type": "table" + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": true, + "colors": [ + "rgba(50, 172, 45, 0.97)", + "rgba(237, 129, 40, 0.89)", + "rgba(245, 54, 54, 0.9)" + ], + "datasource": "${DS_PROMETHEUS}", + "description": "Total number of time series in prometheus", + "format": "none", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "id": 12, + "interval": null, + "links": [], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "span": 3, + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": true, + "lineColor": "rgb(31, 120, 193)", + "show": true + }, + "tableColumn": "", + "targets": [ + { + "expr": "sum(prometheus_tsdb_head_series{job=~\"$job\",instance=~\"$instance\"})", + "format": "time_series", + "intervalFactor": 2, + "refId": "B", + "step": 40 + } + ], + "thresholds": "1000000,2000000", + "title": "Total Series", + "type": "singlestat", + "valueFontSize": "100%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "current" + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "rgba(245, 54, 54, 0.9)", + "rgba(237, 129, 40, 0.89)", + "rgba(50, 172, 45, 0.97)" + ], + "datasource": "${DS_PROMETHEUS}", + "format": "none", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "id": 14, + "interval": null, + "links": [], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "span": 3, + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": true, + "lineColor": "rgb(31, 120, 193)", + "show": true + }, + "tableColumn": "", + "targets": [ + { + "expr": "sum(prometheus_tsdb_head_chunks{job=~\"$job\",instance=~\"$instance\"})", + "format": "time_series", + "intervalFactor": 2, + "refId": "B", + "step": 40 + } + ], + "thresholds": "", + "title": "Memory Chunks", + "type": "singlestat", + "valueFontSize": "100%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "current" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "at a glance", + "titleSize": "h6" + }, + { + "collapse": false, + "height": 236, + "panels": [ + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": true, + "colors": [ + "rgba(50, 172, 45, 0.97)", + "rgba(237, 129, 40, 0.89)", + "rgba(245, 54, 54, 0.9)" + ], + "datasource": "${DS_PROMETHEUS}", + "description": "The total number of rule group evaluations missed due to slow rule group evaluation.", + "format": "none", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "id": 16, + "interval": null, + "links": [], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "span": 2, + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "sum(sum_over_time(prometheus_evaluator_iterations_missed_total{job=~\"$job\",instance=~\"$instance\"}[$interval]))", + "format": "time_series", + "intervalFactor": 2, + "refId": "A", + "step": 40 + } + ], + "thresholds": "1,10", + "title": "Missed Iterations [$interval]", + "type": "singlestat", + "valueFontSize": "100%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "current" + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": true, + "colors": [ + "rgba(50, 172, 45, 0.97)", + "rgba(237, 129, 40, 0.89)", + "rgba(245, 54, 54, 0.9)" + ], + "datasource": "${DS_PROMETHEUS}", + "description": "The total number of rule group evaluations skipped due to throttled metric storage.", + "format": "none", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "id": 18, + "interval": null, + "links": [], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "span": 2, + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "sum(sum_over_time(prometheus_evaluator_iterations_skipped_total{job=~\"$job\",instance=~\"$instance\"}[$interval]))", + "format": "time_series", + "intervalFactor": 2, + "refId": "A", + "step": 40 + } + ], + "thresholds": "1,10", + "title": "Skipped Iterations [$interval]", + "type": "singlestat", + "valueFontSize": "100%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "current" + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": true, + "colors": [ + "rgba(50, 172, 45, 0.97)", + "rgba(237, 129, 40, 0.89)", + "rgba(245, 54, 54, 0.9)" + ], + "datasource": "${DS_PROMETHEUS}", + "description": "Total number of scrapes that hit the sample limit and were rejected.", + "format": "none", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "id": 19, + "interval": null, + "links": [], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "span": 2, + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "sum(sum_over_time(prometheus_target_scrapes_exceeded_sample_limit_total{job=~\"$job\",instance=~\"$instance\"}[$interval]))", + "format": "time_series", + "intervalFactor": 2, + "refId": "A", + "step": 40 + } + ], + "thresholds": "1,10", + "title": "Tardy Scrapes [$interval]", + "type": "singlestat", + "valueFontSize": "100%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "current" + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": true, + "colors": [ + "rgba(50, 172, 45, 0.97)", + "rgba(237, 129, 40, 0.89)", + "rgba(245, 54, 54, 0.9)" + ], + "datasource": "${DS_PROMETHEUS}", + "description": "Number of times the database failed to reload block data from disk.", + "format": "none", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "id": 13, + "interval": null, + "links": [], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "span": 2, + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "sum(sum_over_time(prometheus_tsdb_reloads_failures_total{job=~\"$job\",instance=~\"$instance\"}[$interval]))", + "format": "time_series", + "intervalFactor": 2, + "refId": "A", + "step": 40 + } + ], + "thresholds": "1,10", + "title": "Reload Failures [$interval]", + "type": "singlestat", + "valueFontSize": "100%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "current" + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": true, + "colors": [ + "rgba(50, 172, 45, 0.97)", + "rgba(237, 129, 40, 0.89)", + "rgba(245, 54, 54, 0.9)" + ], + "datasource": "${DS_PROMETHEUS}", + "description": "Sum of all skipped scrapes", + "format": "none", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "id": 20, + "interval": null, + "links": [], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "span": 4, + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "sum(sum_over_time(prometheus_target_scrapes_exceeded_sample_limit_total{job=~\"$job\",instance=~\"$instance\"}[$interval])) + \nsum(sum_over_time(prometheus_target_scrapes_sample_duplicate_timestamp_total{job=~\"$job\",instance=~\"$instance\"}[$interval])) + \nsum(sum_over_time(prometheus_target_scrapes_sample_out_of_bounds_total{job=~\"$job\",instance=~\"$instance\"}[$interval])) + \nsum(sum_over_time(prometheus_target_scrapes_sample_out_of_order_total{job=~\"$job\",instance=~\"$instance\"}[$interval])) ", + "format": "time_series", + "intervalFactor": 2, + "refId": "A", + "step": 40 + } + ], + "thresholds": "1,10", + "title": "Skipped Scrapes [$interval]", + "type": "singlestat", + "valueFontSize": "100%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "current" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "quick numbers", + "titleSize": "h6" + }, + { + "collapse": false, + "height": 250, + "panels": [ + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "description": "All non-zero failures and errors", + "fill": 1, + "id": 33, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(increase(net_conntrack_dialer_conn_failed_total{instance=~\"$instance\"}[5m])) > 0", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Failed Connections", + "refId": "A", + "step": 2 + }, + { + "expr": "sum(increase(prometheus_evaluator_iterations_missed_total{instance=~\"$instance\"}[5m])) > 0", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Missed Iterations", + "refId": "B", + "step": 2 + }, + { + "expr": "sum(increase(prometheus_evaluator_iterations_skipped_total{instance=~\"$instance\"}[5m])) > 0", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Skipped Iterations", + "refId": "C", + "step": 2 + }, + { + "expr": "sum(increase(prometheus_rule_evaluation_failures_total{instance=~\"$instance\"}[5m])) > 0", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Evaluation", + "refId": "D", + "step": 2 + }, + { + "expr": "sum(increase(prometheus_sd_azure_refresh_failures_total{instance=~\"$instance\"}[5m])) > 0", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Azure Refresh", + "refId": "E", + "step": 2 + }, + { + "expr": "sum(increase(prometheus_sd_consul_rpc_failures_total{instance=~\"$instance\"}[5m])) > 0", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Consul RPC", + "refId": "F", + "step": 2 + }, + { + "expr": "sum(increase(prometheus_sd_dns_lookup_failures_total{instance=~\"$instance\"}[5m])) > 0", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "DNS Lookup", + "refId": "G", + "step": 2 + }, + { + "expr": "sum(increase(prometheus_sd_ec2_refresh_failures_total{instance=~\"$instance\"}[5m])) > 0", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "EC2 Refresh", + "refId": "H", + "step": 2 + }, + { + "expr": "sum(increase(prometheus_sd_gce_refresh_failures_total{instance=~\"$instance\"}[5m])) > 0", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "GCE Refresh", + "refId": "I", + "step": 2 + }, + { + "expr": "sum(increase(prometheus_sd_marathon_refresh_failures_total{instance=~\"$instance\"}[5m])) > 0", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Marathon Refresh", + "refId": "J", + "step": 2 + }, + { + "expr": "sum(increase(prometheus_sd_openstack_refresh_failures_total{instance=~\"$instance\"}[5m])) > 0", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Openstack Refresh", + "refId": "K", + "step": 2 + }, + { + "expr": "sum(increase(prometheus_sd_triton_refresh_failures_total{instance=~\"$instance\"}[5m])) > 0", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Triton Refresh", + "refId": "L", + "step": 2 + }, + { + "expr": "sum(increase(prometheus_target_scrapes_exceeded_sample_limit_total{instance=~\"$instance\"}[5m])) > 0", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Sample Limit", + "refId": "M", + "step": 2 + }, + { + "expr": "sum(increase(prometheus_target_scrapes_sample_duplicate_timestamp_total{instance=~\"$instance\"}[5m])) > 0", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Duplicate Timestamp", + "refId": "N", + "step": 2 + }, + { + "expr": "sum(increase(prometheus_target_scrapes_sample_out_of_bounds_total{instance=~\"$instance\"}[5m])) > 0", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Timestamp Out of Bounds", + "refId": "O", + "step": 2 + }, + { + "expr": "sum(increase(prometheus_target_scrapes_sample_out_of_order_total{instance=~\"$instance\"}[5m])) > 0", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Sample Out of Order", + "refId": "P", + "step": 2 + }, + { + "expr": "sum(increase(prometheus_treecache_zookeeper_failures_total{instance=~\"$instance\"}[5m])) > 0", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Zookeeper", + "refId": "Q", + "step": 2 + }, + { + "expr": "sum(increase(prometheus_tsdb_compactions_failed_total{instance=~\"$instance\"}[5m])) > 0", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "TSDB Compactions", + "refId": "R", + "step": 2 + }, + { + "expr": "sum(increase(prometheus_tsdb_head_series_not_found{instance=~\"$instance\"}[5m])) > 0", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Series Not Found", + "refId": "S", + "step": 2 + }, + { + "expr": "sum(increase(prometheus_tsdb_reloads_failures_total{instance=~\"$instance\"}[5m])) > 0", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Reload", + "refId": "T", + "step": 2 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "Failures and Errors", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "short", + "label": "Errors", + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "errors", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "fill": 1, + "id": 1, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "up{instance=~\"$instance\",job=~\"$job\"}", + "format": "time_series", + "interval": "", + "intervalFactor": 1, + "legendFormat": "{{instance}}", + "refId": "A", + "step": 2 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "Upness (stacked)", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "decimals": 0, + "format": "none", + "label": "Up", + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "fill": 1, + "id": 5, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "prometheus_tsdb_head_chunks{job=~\"$job\",instance=~\"$instance\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{instance}}", + "refId": "A", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "Storage Memory Chunks", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "short", + "label": "Chunks", + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "up", + "titleSize": "h6" + }, + { + "collapse": false, + "height": 250, + "panels": [ + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "fill": 1, + "id": 3, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "prometheus_tsdb_head_series{job=~\"$job\",instance=~\"$instance\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{instance}}", + "refId": "A", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "Series Count", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "short", + "label": "Series", + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "fill": 1, + "id": 32, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "removed", + "transform": "negative-Y" + } + ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum( increase(prometheus_tsdb_head_series_created_total{instance=~\"$instance\"}[5m]) )", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "created", + "refId": "A", + "step": 4 + }, + { + "expr": "sum( increase(prometheus_tsdb_head_series_removed_total{instance=~\"$instance\"}[5m]) )", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "removed", + "refId": "B", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "Series Created / Removed", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "short", + "label": "Series Count", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "series", + "titleSize": "h6" + }, + { + "collapse": false, + "height": 250, + "panels": [ + { + "aliasColors": { + "10.58.3.10:80": "#BA43A9" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "description": "Rate of total number of appended samples", + "fill": 1, + "id": 4, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "rate(prometheus_tsdb_head_samples_appended_total{job=~\"$job\",instance=~\"$instance\"}[1m])", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{instance}}", + "refId": "A", + "step": 2 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "Appended Samples per Second", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "short", + "label": "Samples / Second", + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "appended samples", + "titleSize": "h6" + }, + { + "collapse": false, + "height": 250, + "panels": [ + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "description": "Total number of syncs that were executed on a scrape pool.", + "fill": 1, + "id": 6, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(prometheus_target_scrape_pool_sync_total{job=~\"$job\",instance=~\"$instance\"}) by (scrape_job)", + "format": "time_series", + "hide": false, + "intervalFactor": 2, + "legendFormat": "{{scrape_job}}", + "refId": "B", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "Scrape Sync Total", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "short", + "label": "Syncs", + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "description": "Actual interval to sync the scrape pool.", + "fill": 1, + "id": 21, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(prometheus_target_sync_length_seconds_sum{job=~\"$job\",instance=~\"$instance\"}[2m])) by (scrape_job) * 1000", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{scrape_job}}", + "refId": "A", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "Target Sync", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "short", + "label": "Milliseconds", + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "sync", + "titleSize": "h6" + }, + { + "collapse": false, + "height": 250, + "panels": [ + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "fill": 1, + "id": 29, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "scrape_duration_seconds{instance=~\"$instance\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{instance}}", + "refId": "A", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "Scrape Duration", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "short", + "label": "Seconds", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "description": "Total number of rejected scrapes", + "fill": 1, + "id": 30, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(prometheus_target_scrapes_exceeded_sample_limit_total{job=~\"$job\",instance=~\"$instance\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "exceeded sample limit", + "refId": "A", + "step": 4 + }, + { + "expr": "sum(prometheus_target_scrapes_sample_duplicate_timestamp_total{job=~\"$job\",instance=~\"$instance\"})", + "format": "time_series", + "hide": false, + "intervalFactor": 2, + "legendFormat": "duplicate timestamp", + "refId": "B", + "step": 4 + }, + { + "expr": "sum(prometheus_target_scrapes_sample_out_of_bounds_total{job=~\"$job\",instance=~\"$instance\"})", + "format": "time_series", + "hide": false, + "intervalFactor": 2, + "legendFormat": "out of bounds", + "refId": "C", + "step": 4 + }, + { + "expr": "sum(prometheus_target_scrapes_sample_out_of_order_total{job=~\"$job\",instance=~\"$instance\"}) ", + "format": "time_series", + "hide": false, + "intervalFactor": 2, + "legendFormat": "out of order", + "refId": "D", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "Rejected Scrapes", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "decimals": 0, + "format": "short", + "label": "Scrapes", + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "scrapes", + "titleSize": "h6" + }, + { + "collapse": false, + "height": 250, + "panels": [ + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "description": "The duration of rule group evaluations", + "fill": 1, + "id": 10, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "1000 * rate(prometheus_evaluator_duration_seconds_sum{job=~\"$job\", instance=~\"$instance\"}[5m]) / rate(prometheus_evaluator_duration_seconds_count{job=~\"$job\", instance=~\"$instance\"}[5m])", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{instance}}", + "refId": "E", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "Average Rule Evaluation Duration", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "short", + "label": "Milliseconds", + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "fill": 1, + "id": 11, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(http_request_duration_microseconds_count{job=~\"$job\",instance=~\"$instance\"}[1m])) by (handler) > 0", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{handler}}", + "refId": "A", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "HTTP Request Duration", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "short", + "label": "Microseconds", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "fill": 1, + "id": 15, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(prometheus_engine_query_duration_seconds_sum{job=~\"$job\",instance=~\"$instance\"}) by (slice)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{slice}}", + "refId": "A", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "Prometheus Engine Query Duration Seconds", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "short", + "label": "Seconds", + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "description": "Rule-group evaluations \n - total\n - missed due to slow rule group evaluation\n - skipped due to throttled metric storage", + "fill": 1, + "id": 31, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(prometheus_evaluator_iterations_total{job=~\"$job\", instance=~\"$instance\"}[5m]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Total", + "refId": "B", + "step": 4 + }, + { + "expr": "sum(rate(prometheus_evaluator_iterations_missed_total{job=~\"$job\", instance=~\"$instance\"}[5m]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Missed", + "refId": "A", + "step": 4 + }, + { + "expr": "sum(rate(prometheus_evaluator_iterations_skipped_total{job=~\"$job\", instance=~\"$instance\"}[5m]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Skipped", + "refId": "C", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "Rule Evaluator Iterations", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "short", + "label": "iterations", + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "durations", + "titleSize": "h6" + }, + { + "collapse": false, + "height": 250, + "panels": [ + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "fill": 1, + "id": 22, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "rate(prometheus_notifications_sent_total[5m])", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{instance}}", + "refId": "A", + "step": 2 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "Notifications Sent", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "short", + "label": "Notifications", + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "notifications", + "titleSize": "h6" + }, + { + "collapse": false, + "height": 250, + "panels": [ + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "fill": 1, + "id": 23, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "(time() - prometheus_config_last_reload_success_timestamp_seconds{job=~\"$job\",instance=~\"$instance\"}) / 60", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{instance}}", + "refId": "A", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "Minutes Since Successful Config Reload", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "short", + "label": "Minutes", + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "fill": 1, + "id": 24, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "prometheus_config_last_reload_successful{job=~\"$job\",instance=~\"$instance\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{instance}}", + "refId": "A", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "Successful Config Reload", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "decimals": 0, + "format": "short", + "label": "Success", + "logBase": 1, + "max": "1", + "min": "0", + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "config", + "titleSize": "h6" + }, + { + "collapse": false, + "height": 250, + "panels": [ + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "description": "GC invocation durations", + "fill": 1, + "id": 28, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(go_gc_duration_seconds_sum{instance=~\"$instance\",job=~\"$job\"}[2m])) by (instance)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{instance}}", + "refId": "A", + "step": 2 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "GC Rate / 2m", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "garbage collection", + "titleSize": "h6" + }, + { + "collapse": true, + "height": 250, + "panels": [ + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "description": "This is probably wrong! Please help.", + "fill": 1, + "id": 26, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "allocated", + "stack": false + } + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(go_memstats_alloc_bytes_total{job=~\"$job\", instance=~\"$instance\"})", + "format": "time_series", + "hide": true, + "intervalFactor": 2, + "legendFormat": "alloc_bytes_total", + "refId": "A", + "step": 10 + }, + { + "expr": "sum(go_memstats_alloc_bytes{job=~\"$job\", instance=~\"$instance\"})", + "format": "time_series", + "hide": false, + "intervalFactor": 2, + "legendFormat": "allocated", + "refId": "B", + "step": 10 + }, + { + "expr": "sum(go_memstats_buck_hash_sys_bytes{job=~\"$job\", instance=~\"$instance\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "profiling bucket hash table", + "refId": "C", + "step": 10 + }, + { + "expr": "sum(go_memstats_gc_sys_bytes{job=~\"$job\", instance=~\"$instance\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "GC metadata", + "refId": "D", + "step": 10 + }, + { + "expr": "sum(go_memstats_heap_alloc_bytes{job=~\"$job\", instance=~\"$instance\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "heap in-use", + "refId": "E", + "step": 10 + }, + { + "expr": "sum(go_memstats_heap_idle_bytes{job=~\"$job\", instance=~\"$instance\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "heap idle", + "refId": "F", + "step": 10 + }, + { + "expr": "sum(go_memstats_heap_inuse_bytes{job=~\"$job\", instance=~\"$instance\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "heap in use", + "refId": "G", + "step": 10 + }, + { + "expr": "sum(go_memstats_heap_released_bytes{job=~\"$job\", instance=~\"$instance\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "heap released", + "refId": "H", + "step": 10 + }, + { + "expr": "sum(go_memstats_heap_sys_bytes{job=~\"$job\", instance=~\"$instance\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "heap system", + "refId": "I", + "step": 10 + }, + { + "expr": "sum(go_memstats_mcache_inuse_bytes{job=~\"$job\", instance=~\"$instance\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "mcache in use", + "refId": "J", + "step": 10 + }, + { + "expr": "sum(go_memstats_mcache_sys_bytes{job=~\"$job\", instance=~\"$instance\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "mcache sys", + "refId": "K", + "step": 10 + }, + { + "expr": "sum(go_memstats_mspan_inuse_bytes{job=~\"$job\", instance=~\"$instance\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "mspan in use", + "refId": "L", + "step": 10 + }, + { + "expr": "sum(go_memstats_mspan_sys_bytes{job=~\"$job\", instance=~\"$instance\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "mspan sys", + "refId": "M", + "step": 10 + }, + { + "expr": "sum(go_memstats_next_gc_bytes{job=~\"$job\", instance=~\"$instance\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "heap next gc", + "refId": "N", + "step": 10 + }, + { + "expr": "sum(go_memstats_other_sys_bytes{job=~\"$job\", instance=~\"$instance\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "other sys", + "refId": "O", + "step": 10 + }, + { + "expr": "sum(go_memstats_stack_inuse_bytes{job=~\"$job\", instance=~\"$instance\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "stack in use", + "refId": "P", + "step": 10 + }, + { + "expr": "sum(go_memstats_stack_sys_bytes{job=~\"$job\", instance=~\"$instance\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "stack sys", + "refId": "Q", + "step": 10 + }, + { + "expr": "sum(go_memstats_sys_bytes{job=~\"$job\", instance=~\"$instance\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "sys", + "refId": "R", + "step": 10 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "Go Memory Usage (FIXME)", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "fill": 1, + "id": 9, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "prometheus_target_interval_length_seconds{instance=~\"$instance\", job=~\"$job\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{quantile}} {{interval}}", + "refId": "A", + "step": 20 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "Scrape Duration", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "short", + "label": "Seconds", + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "fill": 1, + "id": 7, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(prometheus_target_interval_length_seconds_count{job=~\"$job\",instance=~\"$instance\"}[5m])) by (interval)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{interval}}", + "refId": "A", + "step": 20 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "Target Scrapes / 5m", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "short", + "label": "Scrapes", + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Broken, ignore", + "titleSize": "h6" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [], + "templating": { + "list": [ + { + "current": { + "selected": false, + "text": "default", + "value": "default" + }, + "hide": 0, + "includeAll": false, + "label": "datasource", + "multi": false, + "name": "DS_PROMETHEUS", + "options": [], + "query": "prometheus", + "refresh": 1, + "regex": "", + "skipUrlSync": false, + "type": "datasource" + }, + { + "allValue": null, + "current": {}, + "datasource": "${DS_PROMETHEUS}", + "hide": 0, + "includeAll": true, + "label": null, + "multi": true, + "name": "job", + "options": [], + "query": "query_result(prometheus_tsdb_head_samples_appended_total)", + "refresh": 2, + "regex": "/.*job=\"([^\"]+)/", + "sort": 1, + "tagValuesQuery": "", + "tags": [], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": {}, + "datasource": "${DS_PROMETHEUS}", + "hide": 0, + "includeAll": true, + "label": null, + "multi": true, + "name": "instance", + "options": [], + "query": "query_result(up{job=~\"$job\"})", + "refresh": 2, + "regex": "/.*instance=\"([^\"]+).*/", + "sort": 0, + "tagValuesQuery": "", + "tags": [], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + "selected": true, + "text": "1h", + "value": "1h" + }, + "hide": 0, + "includeAll": false, + "label": null, + "multi": false, + "name": "interval", + "options": [ + { + "selected": true, + "text": "1h", + "value": "1h" + }, + { + "selected": false, + "text": "3h", + "value": "3h" + }, + { + "selected": false, + "text": "6h", + "value": "6h" + }, + { + "selected": false, + "text": "12h", + "value": "12h" + }, + { + "selected": false, + "text": "1d", + "value": "1d" + }, + { + "selected": false, + "text": "2d", + "value": "2d" + }, + { + "selected": false, + "text": "7d", + "value": "7d" + }, + { + "selected": false, + "text": "30d", + "value": "30d" + }, + { + "selected": false, + "text": "90d", + "value": "90d" + }, + { + "selected": false, + "text": "180d", + "value": "180d" + } + ], + "query": "1h, 3h, 6h, 12h, 1d, 2d, 7d, 30d, 90d, 180d", + "type": "custom" + } + ] + }, + "time": { + "from": "now-4h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "browser", + "title": "Prometheus", + "version": 1 +} diff --git a/terraform-ci-infra/1n_nmd/grafana/main.tf b/terraform-ci-infra/1n_nmd/grafana/main.tf new file mode 100644 index 0000000000..b67ba03985 --- /dev/null +++ b/terraform-ci-infra/1n_nmd/grafana/main.tf @@ -0,0 +1,24 @@ +locals { + datacenters = join(",", var.nomad_datacenters) +} + +data "template_file" "nomad_job_grafana" { + template = file("${path.module}/conf/nomad/grafana.hcl") + vars = { + datacenters = local.datacenters + job_name = var.grafana_job_name + use_canary = var.grafana_use_canary + group_count = var.grafana_group_count + service_name = var.grafana_service_name + use_vault_provider = var.grafana_vault_secret.use_vault_provider + image = var.grafana_container_image + cpu = var.grafana_cpu + mem = var.grafana_mem + port = var.grafana_port + } +} + +resource "nomad_job" "nomad_job_grafana" { + jobspec = data.template_file.nomad_job_grafana.rendered + detach = false +}
\ No newline at end of file diff --git a/terraform-ci-infra/1n_nmd/grafana/variables.tf b/terraform-ci-infra/1n_nmd/grafana/variables.tf new file mode 100644 index 0000000000..0c2382b16a --- /dev/null +++ b/terraform-ci-infra/1n_nmd/grafana/variables.tf @@ -0,0 +1,66 @@ +# Nomad +variable "nomad_datacenters" { + description = "Nomad data centers" + type = list(string) + default = [ "dc1" ] +} + +# Grafana +variable "grafana_job_name" { + description = "Grafana job name" + type = string + default = "grafana" +} + +variable "grafana_group_count" { + description = "Number of grafana group instances" + type = number + default = 1 +} + +variable "grafana_service_name" { + description = "Grafana service name" + type = string + default = "grafana" +} + +variable "grafana_container_image" { + description = "Grafana docker image" + type = string + default = "grafana/grafana:7.3.7" +} + +variable "grafana_use_canary" { + description = "Uses canary deployment" + type = bool + default = false +} + +variable "grafana_vault_secret" { + description = "Set of properties to be able to fetch secret from vault" + type = object({ + use_vault_provider = bool, + vault_kv_policy_name = string, + vault_kv_path = string, + vault_kv_field_access_key = string, + vault_kv_field_secret_key = string + }) +} + +variable "grafana_cpu" { + description = "Grafana CPU allocation" + type = number + default = 2000 +} + +variable "grafana_mem" { + description = "Grafana RAM allocation" + type = number + default = 8192 +} + +variable "grafana_port" { + description = "Grafana TCP allocation" + type = number + default = 3000 +}
\ No newline at end of file diff --git a/terraform-ci-infra/1n_nmd/main.tf b/terraform-ci-infra/1n_nmd/main.tf index 4da8929e8d..4e0b7537c4 100644 --- a/terraform-ci-infra/1n_nmd/main.tf +++ b/terraform-ci-infra/1n_nmd/main.tf @@ -4,64 +4,182 @@ # and downstream modules can simply declare resources for that provider # and have them automatically associated with the root provider # configurations. +module "alertmanager" { + source = "./alertmanager" + providers = { + nomad = nomad.yul1 + } + + # nomad + nomad_datacenters = [ "yul1" ] + + # alertmanager + alertmanager_job_name = "prod-alertmanager" + alertmanager_use_canary = true + alertmanager_group_count = 1 + alertmanager_vault_secret = { + use_vault_provider = false, + vault_kv_policy_name = "kv-secret", + vault_kv_path = "secret/data/prometheus", + vault_kv_field_access_key = "access_key", + vault_kv_field_secret_key = "secret_key" + } + alertmanager_version = "0.21.0" + alertmanager_cpu = 1000 + alertmanager_mem = 1024 + alertmanager_port = 9093 + alertmanager_slack_api_url = "https://hooks.slack.com/services/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" + alertmanager_slack_channel = "fdio-infra-monitoring" +} + +module "exporter" { + source = "./exporter" + providers = { + nomad = nomad.yul1 + } + + # nomad + nomad_datacenters = [ "yul1" ] + + # exporter + exporter_job_name = "prod-exporter" + exporter_use_canary = false + + # node + node_version = "1.0.1" + node_port = 9100 + + # blackbox + blackbox_version = "0.18.0" + blackbox_port = 9115 + + # cadvisor + cadvisor_image = "gcr.io/cadvisor/cadvisor:latest" + cadvisor_port = 8080 +} + +module "grafana" { + source = "./grafana" + providers = { + nomad = nomad.yul1 + } + + # nomad + nomad_datacenters = [ "yul1" ] + + # grafana + grafana_job_name = "prod-grafana" + grafana_use_canary = true + grafana_group_count = 1 + grafana_vault_secret = { + use_vault_provider = false, + vault_kv_policy_name = "kv-secret", + vault_kv_path = "secret/data/prometheus", + vault_kv_field_access_key = "access_key", + vault_kv_field_secret_key = "secret_key" + } + grafana_container_image = "grafana/grafana:7.3.7" + grafana_cpu = 2000 + grafana_mem = 2048 + grafana_port = 3000 +} + module "minio" { - source = "./minio" - providers = { + source = "./minio" + providers = { nomad = nomad.yul1 } # nomad - nomad_datacenters = [ "yul1" ] - nomad_host_volume = "prod-volume-data1-1" + nomad_datacenters = [ "yul1" ] + nomad_host_volume = "prod-volume-data1-1" # minio - minio_job_name = "prod-minio" - minio_group_count = 4 - minio_service_name = "storage" - minio_host = "http://10.32.8.1{4...7}" - minio_port = 9000 - minio_container_image = "minio/minio:RELEASE.2020-12-03T05-49-24Z" - minio_vault_secret = { - use_vault_provider = false, - vault_kv_policy_name = "kv-secret", - vault_kv_path = "secret/data/minio", - vault_kv_field_access_key = "access_key", - vault_kv_field_secret_key = "secret_key" + minio_job_name = "prod-minio" + minio_group_count = 4 + minio_service_name = "storage" + minio_host = "http://10.32.8.1{4...7}" + minio_port = 9000 + minio_container_image = "minio/minio:RELEASE.2020-12-03T05-49-24Z" + minio_vault_secret = { + use_vault_provider = false, + vault_kv_policy_name = "kv-secret", + vault_kv_path = "secret/data/minio", + vault_kv_field_access_key = "access_key", + vault_kv_field_secret_key = "secret_key" } - minio_data_dir = "/data/" - minio_use_host_volume = true - minio_use_canary = true - minio_envs = [ "MINIO_BROWSER=\"off\"" ] + minio_data_dir = "/data/" + minio_use_host_volume = true + minio_use_canary = true + minio_envs = [ "MINIO_BROWSER=\"off\"" ] # minio client - mc_job_name = "prod-mc" - mc_container_image = "minio/mc:RELEASE.2020-12-10T01-26-17Z" - mc_extra_commands = [ + mc_job_name = "prod-mc" + mc_container_image = "minio/mc:RELEASE.2020-12-10T01-26-17Z" + mc_extra_commands = [ "mc policy set public LOCALMINIO/logs.fd.io", "mc policy set public LOCALMINIO/docs.fd.io", "mc ilm add --expiry-days '180' LOCALMINIO/logs.fd.io", "mc admin user add LOCALMINIO storage Storage1234", "mc admin policy set LOCALMINIO writeonly user=storage" ] - minio_buckets = [ "logs.fd.io", "docs.fd.io" ] + minio_buckets = [ "logs.fd.io", "docs.fd.io" ] } module "nginx" { - source = "./nginx" - providers = { + source = "./nginx" + providers = { nomad = nomad.yul1 } # nomad - nomad_datacenters = [ "yul1" ] + nomad_datacenters = [ "yul1" ] # nginx - nginx_job_name = "prod-nginx" + nginx_job_name = "prod-nginx" } -#module "vpp_device" { -# source = "./vpp_device" -# providers = { -# nomad = nomad.yul1 -# } -#}
\ No newline at end of file +module "prometheus" { + source = "./prometheus" + providers = { + nomad = nomad.yul1 + } + + # nomad + nomad_datacenters = [ "yul1" ] + nomad_host_volume = "prod-volume-data1-1" + + # prometheus + prometheus_job_name = "prod-prometheus" + prometheus_use_canary = true + prometheus_group_count = 4 + prometheus_vault_secret = { + use_vault_provider = false, + vault_kv_policy_name = "kv-secret", + vault_kv_path = "secret/data/prometheus", + vault_kv_field_access_key = "access_key", + vault_kv_field_secret_key = "secret_key" + } + prometheus_data_dir = "/data/" + prometheus_use_host_volume = true + prometheus_version = "2.24.0" + prometheus_cpu = 2000 + prometheus_mem = 8192 + prometheus_port = 9090 +} + +module "vpp_device" { + source = "./vpp_device" + providers = { + nomad = nomad.yul1 + } + + # nomad + nomad_datacenters = [ "yul1" ] + + # csit_shim + csit_shim_job_name = "prod-device-csit-shim" + csit_shim_group_count = "1" + csit_shim_cpu = "1000" + csit_shim_mem = "5000" +}
\ No newline at end of file diff --git a/terraform-ci-infra/1n_nmd/prometheus/conf/nomad/prometheus.hcl b/terraform-ci-infra/1n_nmd/prometheus/conf/nomad/prometheus.hcl new file mode 100644 index 0000000000..2d74662f31 --- /dev/null +++ b/terraform-ci-infra/1n_nmd/prometheus/conf/nomad/prometheus.hcl @@ -0,0 +1,569 @@ +job "${job_name}" { + # The "region" parameter specifies the region in which to execute the job. + # If omitted, this inherits the default region name of "global". + # region = "global" + # + # The "datacenters" parameter specifies the list of datacenters which should + # be considered when placing this task. This must be provided. + datacenters = "${datacenters}" + + # The "type" parameter controls the type of job, which impacts the scheduler's + # decision on placement. This configuration is optional and defaults to + # "service". For a full list of job types and their differences, please see + # the online documentation. + # + # For more information, please see the online documentation at: + # + # https://www.nomadproject.io/docs/jobspec/schedulers + # + type = "service" + + update { + # The "max_parallel" parameter specifies the maximum number of updates to + # perform in parallel. In this case, this specifies to update a single task + # at a time. + max_parallel = 1 + + health_check = "checks" + + # The "min_healthy_time" parameter specifies the minimum time the allocation + # must be in the healthy state before it is marked as healthy and unblocks + # further allocations from being updated. + min_healthy_time = "10s" + + # The "healthy_deadline" parameter specifies the deadline in which the + # allocation must be marked as healthy after which the allocation is + # automatically transitioned to unhealthy. Transitioning to unhealthy will + # fail the deployment and potentially roll back the job if "auto_revert" is + # set to true. + healthy_deadline = "3m" + + # The "progress_deadline" parameter specifies the deadline in which an + # allocation must be marked as healthy. The deadline begins when the first + # allocation for the deployment is created and is reset whenever an allocation + # as part of the deployment transitions to a healthy state. If no allocation + # transitions to the healthy state before the progress deadline, the + # deployment is marked as failed. + progress_deadline = "10m" + +%{ if use_canary } + # The "canary" parameter specifies that changes to the job that would result + # in destructive updates should create the specified number of canaries + # without stopping any previous allocations. Once the operator determines the + # canaries are healthy, they can be promoted which unblocks a rolling update + # of the remaining allocations at a rate of "max_parallel". + # + # Further, setting "canary" equal to the count of the task group allows + # blue/green deployments. When the job is updated, a full set of the new + # version is deployed and upon promotion the old version is stopped. + canary = 1 + + # Specifies if the job should auto-promote to the canary version when all + # canaries become healthy during a deployment. Defaults to false which means + # canaries must be manually updated with the nomad deployment promote + # command. + auto_promote = true + + # The "auto_revert" parameter specifies if the job should auto-revert to the + # last stable job on deployment failure. A job is marked as stable if all the + # allocations as part of its deployment were marked healthy. + auto_revert = true +%{ endif } + } + + # The "group" stanza defines a series of tasks that should be co-located on + # the same Nomad client. Any task within a group will be placed on the same + # client. + # + # For more information and examples on the "group" stanza, please see + # the online documentation at: + # + # https://www.nomadproject.io/docs/job-specification/group + # + group "prod-group1-${service_name}" { + # The "count" parameter specifies the number of the task groups that should + # be running under this group. This value must be non-negative and defaults + # to 1. + count = ${group_count} + + # The volume stanza allows the group to specify that it requires a given + # volume from the cluster. + # + # For more information and examples on the "volume" stanza, please see + # the online documentation at: + # + # https://www.nomadproject.io/docs/job-specification/volume + # + %{ if use_host_volume } + volume "prod-volume1-${service_name}" { + type = "host" + read_only = false + source = "${host_volume}" + } + %{ endif } + + # The constraint allows restricting the set of eligible nodes. Constraints + # may filter on attributes or client metadata. + # + # For more information and examples on the "volume" stanza, please see + # the online documentation at: + # + # https://www.nomadproject.io/docs/job-specification/constraint + # + constraint { + attribute = "$${attr.cpu.arch}" + operator = "!=" + value = "arm64" + } + + # The "task" stanza creates an individual unit of work, such as a Docker + # container, web application, or batch processing. + # + # For more information and examples on the "task" stanza, please see + # the online documentation at: + # + # https://www.nomadproject.io/docs/job-specification/task + # + task "prod-task1-${service_name}" { + # The "driver" parameter specifies the task driver that should be used to + # run the task. + driver = "exec" + + %{ if use_host_volume } + volume_mount { + volume = "prod-volume1-${service_name}" + destination = "${data_dir}" + read_only = false + } + %{ endif } + + %{ if use_vault_provider } + vault { + policies = "${vault_kv_policy_name}" + } + %{ endif } + + # The "config" stanza specifies the driver configuration, which is passed + # directly to the driver to start the task. The details of configurations + # are specific to each driver, so please see specific driver + # documentation for more information. + config { + command = "local/prometheus-${version}.linux-amd64/prometheus" + args = [ + "--config.file=secrets/prometheus.yml", + "--storage.tsdb.path=${data_dir}prometheus/", + "--storage.tsdb.retention.time=15d" + ] + } + + # The artifact stanza instructs Nomad to fetch and unpack a remote resource, + # such as a file, tarball, or binary. Nomad downloads artifacts using the + # popular go-getter library, which permits downloading artifacts from a + # variety of locations using a URL as the input source. + # + # For more information and examples on the "artifact" stanza, please see + # the online documentation at: + # + # https://www.nomadproject.io/docs/job-specification/artifact + # + artifact { + source = "${url}" + } + + # The "template" stanza instructs Nomad to manage a template, such as + # a configuration file or script. This template can optionally pull data + # from Consul or Vault to populate runtime configuration data. + # + # For more information and examples on the "template" stanza, please see + # the online documentation at: + # + # https://www.nomadproject.io/docs/job-specification/template + # + template { + change_mode = "noop" + change_signal = "SIGINT" + destination = "secrets/alerts.yml" + left_delimiter = "{{{" + right_delimiter = "}}}" + data = <<EOH +--- +groups: +- name: "Consul" + rules: + - alert: ConsulServiceHealthcheckFailed + expr: consul_catalog_service_node_healthy == 0 + for: 0m + labels: + severity: critical + annotations: + summary: "Consul service healthcheck failed (instance {{ $labels.instance }})." + description: "Service: `{{ $labels.service_name }}` Healthcheck: `{{ $labels.service_id }}`." + - alert: ConsulMissingMasterNode + expr: consul_raft_peers < 3 + for: 0m + labels: + severity: critical + annotations: + summary: "Consul missing master node (instance {{ $labels.instance }})." + description: "Numbers of consul raft peers should be 3, in order to preserve quorum." + - alert: ConsulAgentUnhealthy + expr: consul_health_node_status{status="critical"} == 1 + for: 0m + labels: + severity: critical + annotations: + summary: "Consul agent unhealthy (instance {{ $labels.instance }})." + description: "A Consul agent is down." +- name: "Hosts" + rules: + - alert: NodeDown + expr: up == 0 + for: 0m + labels: + severity: critical + annotations: + summary: "Prometheus target missing (instance {{ $labels.instance }})." + description: "A Prometheus target has disappeared. An exporter might be crashed." + - alert: HostHighCpuLoad + expr: 100 - (avg by(instance) (rate(node_cpu_seconds_total{mode="idle"}[2m])) * 100) > 80 + for: 0m + labels: + severity: warning + annotations: + summary: "Host high CPU load (instance {{ $labels.instance }})." + description: "CPU load is > 80%." + - alert: HostOutOfMemory + expr: node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes * 100 < 10 + for: 2m + labels: + severity: warning + annotations: + summary: "Host out of memory (instance {{ $labels.instance }})." + description: "Node memory is filling up (< 10% left)." + - alert: HostOomKillDetected + expr: increase(node_vmstat_oom_kill[1m]) > 0 + for: 0m + labels: + severity: warning + annotations: + summary: "Host OOM kill detected (instance {{ $labels.instance }})." + description: "OOM kill detected." + - alert: HostMemoryUnderMemoryPressure + expr: rate(node_vmstat_pgmajfault[1m]) > 1000 + for: 2m + labels: + severity: warning + annotations: + summary: "Host memory under memory pressure (instance {{ $labels.instance }})." + description: "The node is under heavy memory pressure. High rate of major page faults." + - alert: HostOutOfDiskSpace + expr: (node_filesystem_avail_bytes * 100) / node_filesystem_size_bytes < 10 and ON (instance, device, mountpoint) node_filesystem_readonly == 0 + for: 2m + labels: + severity: warning + annotations: + summary: "Host out of disk space (instance {{ $labels.instance }})." + description: "Disk is almost full (< 10% left)." + - alert: HostRaidDiskFailure + expr: node_md_disks{state="failed"} > 0 + for: 2m + labels: + severity: warning + annotations: + summary: "Host RAID disk failure (instance {{ $labels.instance }})." + description: "At least one device in RAID array on {{ $labels.instance }} failed. Array {{ $labels.md_device }} needs attention and possibly a disk swap." + - alert: HostConntrackLimit + expr: node_nf_conntrack_entries / node_nf_conntrack_entries_limit > 0.8 + for: 5m + labels: + severity: warning + annotations: + summary: "Host conntrack limit (instance {{ $labels.instance }})." + description: "The number of conntrack is approching limit." + - alert: HostNetworkInterfaceSaturated + expr: (rate(node_network_receive_bytes_total{device!~"^tap.*"}[1m]) + rate(node_network_transmit_bytes_total{device!~"^tap.*"}[1m])) / node_network_speed_bytes{device!~"^tap.*"} > 0.8 + for: 1m + labels: + severity: warning + annotations: + summary: "Host Network Interface Saturated (instance {{ $labels.instance }})." + description: "The network interface {{ $labels.interface }} on {{ $labels.instance }} is getting overloaded." + - alert: HostSystemdServiceCrashed + expr: node_systemd_unit_state{state="failed"} == 1 + for: 0m + labels: + severity: warning + annotations: + summary: "Host SystemD service crashed (instance {{ $labels.instance }})." + description: "SystemD service crashed." + - alert: HostEdacCorrectableErrorsDetected + expr: increase(node_edac_correctable_errors_total[1m]) > 0 + for: 0m + labels: + severity: info + annotations: + summary: "Host EDAC Correctable Errors detected (instance {{ $labels.instance }})." + description: '{{ $labels.instance }} has had {{ printf "%.0f" $value }} correctable memory errors reported by EDAC in the last 5 minutes.' + - alert: HostEdacUncorrectableErrorsDetected + expr: node_edac_uncorrectable_errors_total > 0 + for: 0m + labels: + severity: warning + annotations: + summary: "Host EDAC Uncorrectable Errors detected (instance {{ $labels.instance }})." + description: '{{ $labels.instance }} has had {{ printf "%.0f" $value }} uncorrectable memory errors reported by EDAC in the last 5 minutes.' +- name: "Min.io" + rules: + - alert: MinioDiskOffline + expr: minio_offline_disks > 0 + for: 0m + labels: + severity: critical + annotations: + summary: "Minio disk offline (instance {{ $labels.instance }})" + description: "Minio disk is offline." + - alert: MinioStorageSpaceExhausted + expr: minio_disk_storage_free_bytes / 1024 / 1024 / 1024 < 10 + for: 2m + labels: + severity: warning + annotations: + summary: "Minio storage space exhausted (instance {{ $labels.instance }})." + description: "Minio storage space is low (< 10 GB)." +- name: "Prometheus" + rules: + - alert: PrometheusConfigurationReloadFailure + expr: prometheus_config_last_reload_successful != 1 + for: 0m + labels: + severity: warning + annotations: + summary: "Prometheus configuration reload failure (instance {{ $labels.instance }})." + description: "Prometheus configuration reload error." + - alert: PrometheusTooManyRestarts + expr: changes(process_start_time_seconds{job=~"prometheus|pushgateway|alertmanager"}[15m]) > 2 + for: 0m + labels: + severity: warning + annotations: + summary: "Prometheus too many restarts (instance {{ $labels.instance }})." + description: "Prometheus has restarted more than twice in the last 15 minutes. It might be crashlooping." + - alert: PrometheusAlertmanagerConfigurationReloadFailure + expr: alertmanager_config_last_reload_successful != 1 + for: 0m + labels: + severity: warning + annotations: + summary: "Prometheus AlertManager configuration reload failure (instance {{ $labels.instance }})." + description: "AlertManager configuration reload error." + - alert: PrometheusRuleEvaluationFailures + expr: increase(prometheus_rule_evaluation_failures_total[3m]) > 0 + for: 0m + labels: + severity: critical + annotations: + summary: "Prometheus rule evaluation failures (instance {{ $labels.instance }})." + description: "Prometheus encountered {{ $value }} rule evaluation failures, leading to potentially ignored alerts." + - alert: PrometheusTargetScrapingSlow + expr: prometheus_target_interval_length_seconds{quantile="0.9"} > 60 + for: 5m + labels: + severity: warning + annotations: + summary: "Prometheus target scraping slow (instance {{ $labels.instance }})." + description: "Prometheus is scraping exporters slowly." + - alert: PrometheusTsdbCompactionsFailed + expr: increase(prometheus_tsdb_compactions_failed_total[1m]) > 0 + for: 0m + labels: + severity: critical + annotations: + summary: "Prometheus TSDB compactions failed (instance {{ $labels.instance }})." + description: "Prometheus encountered {{ $value }} TSDB compactions failures." + - alert: PrometheusTsdbHeadTruncationsFailed + expr: increase(prometheus_tsdb_head_truncations_failed_total[1m]) > 0 + for: 0m + labels: + severity: critical + annotations: + summary: "Prometheus TSDB head truncations failed (instance {{ $labels.instance }})." + description: "Prometheus encountered {{ $value }} TSDB head truncation failures." + - alert: PrometheusTsdbWalCorruptions + expr: increase(prometheus_tsdb_wal_corruptions_total[1m]) > 0 + for: 0m + labels: + severity: critical + annotations: + summary: "Prometheus TSDB WAL corruptions (instance {{ $labels.instance }})." + description: "Prometheus encountered {{ $value }} TSDB WAL corruptions." + - alert: PrometheusTsdbWalTruncationsFailed + expr: increase(prometheus_tsdb_wal_truncations_failed_total[1m]) > 0 + for: 0m + labels: + severity: critical + annotations: + summary: "Prometheus TSDB WAL truncations failed (instance {{ $labels.instance }})." + description: "Prometheus encountered {{ $value }} TSDB WAL truncation failures." +EOH + } + + template { + change_mode = "noop" + change_signal = "SIGINT" + destination = "secrets/prometheus.yml" + data = <<EOH +--- +global: + scrape_interval: 5s + scrape_timeout: 5s + evaluation_interval: 5s + +alerting: + alertmanagers: + - consul_sd_configs: + - server: '{{ env "NOMAD_IP_prometheus" }}:8500' + services: [ 'alertmanager' ] + +rule_files: + - 'alerts.yml' + +scrape_configs: + + - job_name: 'Nomad Cluster' + consul_sd_configs: + - server: '{{ env "NOMAD_IP_prometheus" }}:8500' + services: [ 'nomad-client', 'nomad' ] + relabel_configs: + - source_labels: [__meta_consul_tags] + regex: '(.*)http(.*)' + action: keep + metrics_path: /v1/metrics + params: + format: [ 'prometheus' ] + + - job_name: 'Consul Cluster' + static_configs: + - targets: [ '10.30.51.30:8500', '10.30.51.32:8500', '10.30.51.33:8500' ] + metrics_path: /v1/agent/metrics + params: + format: [ 'prometheus' ] + + - job_name: 'Alertmanager' + consul_sd_configs: + - server: '{{ env "NOMAD_IP_prometheus" }}:8500' + services: [ 'alertmanager' ] + + - job_name: 'Blackbox Exporter (icmp)' + static_configs: + - targets: [ 'gerrit.fd.io' ] + - targets: [ 'jenkins.fd.io' ] + - targets: [ '10.30.51.32' ] + params: + module: [ 'icmp_v4' ] + relabel_configs: + - source_labels: [__address__] + target_label: __param_target + - source_labels: [__param_target] + target_label: instance + - target_label: __address__ + replacement: localhost:9115 + metrics_path: /probe + + - job_name: 'Blackbox Exporter (http)' + static_configs: + - targets: [ 'gerrit.fd.io' ] + - targets: [ 'jenkins.fd.io' ] + params: + module: [ 'http_2xx' ] + relabel_configs: + - source_labels: [__address__] + target_label: __param_target + - source_labels: [__param_target] + target_label: instance + - target_label: __address__ + replacement: localhost:9115 + metrics_path: /probe + + - job_name: 'cAdvisor Exporter' + consul_sd_configs: + - server: '{{ env "NOMAD_IP_prometheus" }}:8500' + services: [ 'cadvisorexporter' ] + + - job_name: 'Grafana' + consul_sd_configs: + - server: '{{ env "NOMAD_IP_prometheus" }}:8500' + services: [ 'grafana' ] + + - job_name: 'Node Exporter' + consul_sd_configs: + - server: '{{ env "NOMAD_IP_prometheus" }}:8500' + services: [ 'nodeexporter' ] + + - job_name: 'Prometheus' + consul_sd_configs: + - server: '{{ env "NOMAD_IP_prometheus" }}:8500' + services: [ 'prometheus' ] + + - job_name: 'Minio' + bearer_token: eyJhbGciOiJIUzUxMiIsInR5cCI6IkpXVCJ9.eyJleHAiOjQ3NjQ1ODEzMzcsImlzcyI6InByb21ldGhldXMiLCJzdWIiOiJtaW5pbyJ9.oeTw3EIaiFmlDikrHXWiWXMH2vxLfDLkfjEC7G2N3M_keH_xyA_l2ofLLNYtopa_3GCEZnxLQdPuFZrmgpkDWg + consul_sd_configs: + - server: '{{ env "NOMAD_IP_prometheus" }}:8500' + services: [ 'storage' ] + metrics_path: /minio/prometheus/metrics +EOH + } + + # The service stanza instructs Nomad to register a service with Consul. + # + # For more information and examples on the "task" stanza, please see + # the online documentation at: + # + # https://www.nomadproject.io/docs/job-specification/service + # + service { + name = "${service_name}" + port = "${service_name}" + tags = [ "${service_name}$${NOMAD_ALLOC_INDEX}" ] + check { + name = "Prometheus Check Live" + type = "http" + path = "/-/healthy" + interval = "10s" + timeout = "2s" + } + } + + # The "resources" stanza describes the requirements a task needs to + # execute. Resource requirements include memory, network, cpu, and more. + # This ensures the task will execute on a machine that contains enough + # resource capacity. + # + # For more information and examples on the "resources" stanza, please see + # the online documentation at: + # + # https://www.nomadproject.io/docs/job-specification/resources + # + resources { + cpu = ${cpu} + memory = ${mem} + # The network stanza specifies the networking requirements for the task + # group, including the network mode and port allocations. When scheduling + # jobs in Nomad they are provisioned across your fleet of machines along + # with other jobs and services. Because you don't know in advance what host + # your job will be provisioned on, Nomad will provide your tasks with + # network configuration when they start up. + # + # For more information and examples on the "template" stanza, please see + # the online documentation at: + # + # https://www.nomadproject.io/docs/job-specification/network + # + network { + port "${service_name}" { + static = ${port} + } + } + } + } + } +}
\ No newline at end of file diff --git a/terraform-ci-infra/1n_nmd/prometheus/main.tf b/terraform-ci-infra/1n_nmd/prometheus/main.tf new file mode 100644 index 0000000000..9506ba3941 --- /dev/null +++ b/terraform-ci-infra/1n_nmd/prometheus/main.tf @@ -0,0 +1,37 @@ +locals { + datacenters = join(",", var.nomad_datacenters) + + prometheus_url = join("", + [ + "https://github.com", + "/prometheus/prometheus/releases/download/", + "v${var.prometheus_version}/", + "prometheus-${var.prometheus_version}.linux-amd64.tar.gz" + ] + ) +} + +data "template_file" "nomad_job_prometheus" { + template = file("${path.module}/conf/nomad/prometheus.hcl") + vars = { + datacenters = local.datacenters + url = local.prometheus_url + job_name = var.prometheus_job_name + use_canary = var.prometheus_use_canary + group_count = var.prometheus_group_count + use_host_volume = var.prometheus_use_host_volume + host_volume = var.nomad_host_volume + data_dir = var.prometheus_data_dir + service_name = var.prometheus_service_name + use_vault_provider = var.prometheus_vault_secret.use_vault_provider + version = var.prometheus_version + cpu = var.prometheus_cpu + mem = var.prometheus_mem + port = var.prometheus_port + } +} + +resource "nomad_job" "nomad_job_prometheus" { + jobspec = data.template_file.nomad_job_prometheus.rendered + detach = false +}
\ No newline at end of file diff --git a/terraform-ci-infra/1n_nmd/prometheus/variables.tf b/terraform-ci-infra/1n_nmd/prometheus/variables.tf new file mode 100644 index 0000000000..a509533ccd --- /dev/null +++ b/terraform-ci-infra/1n_nmd/prometheus/variables.tf @@ -0,0 +1,84 @@ +# Nomad +variable "nomad_datacenters" { + description = "Nomad data centers" + type = list(string) + default = [ "dc1" ] +} + +variable "nomad_host_volume" { + description = "Nomad Host Volume" + type = string + default = "persistence" +} + +# Prometheus +variable "prometheus_job_name" { + description = "Prometheus job name" + type = string + default = "prometheus" +} + +variable "prometheus_group_count" { + description = "Number of prometheus group instances" + type = number + default = 1 +} + +variable "prometheus_service_name" { + description = "Prometheus service name" + type = string + default = "prometheus" +} + +variable "prometheus_version" { + description = "Prometheus version" + type = string + default = "v2.24.0" +} + +variable "prometheus_use_canary" { + description = "Uses canary deployment" + type = bool + default = false +} + +variable "prometheus_vault_secret" { + description = "Set of properties to be able to fetch secret from vault" + type = object({ + use_vault_provider = bool, + vault_kv_policy_name = string, + vault_kv_path = string, + vault_kv_field_access_key = string, + vault_kv_field_secret_key = string + }) +} + +variable "prometheus_cpu" { + description = "Prometheus CPU allocation" + type = number + default = 2000 +} + +variable "prometheus_mem" { + description = "Prometheus RAM allocation" + type = number + default = 8192 +} + +variable "prometheus_port" { + description = "Prometheus TCP allocation" + type = number + default = 9200 +} + +variable "prometheus_data_dir" { + description = "Prometheus DISK allocation" + type = string + default = "/data" +} + +variable "prometheus_use_host_volume" { + description = "Use Nomad host volume feature" + type = bool + default = false +}
\ No newline at end of file diff --git a/terraform-ci-infra/1n_nmd/terraform.tfstate b/terraform-ci-infra/1n_nmd/terraform.tfstate index 21cc9738db..5d33863ff0 100644 --- a/terraform-ci-infra/1n_nmd/terraform.tfstate +++ b/terraform-ci-infra/1n_nmd/terraform.tfstate @@ -1,11 +1,340 @@ { "version": 4, - "terraform_version": "0.14.2", - "serial": 223, + "terraform_version": "0.14.5", + "serial": 1030, "lineage": "e4e7f30a-652d-7a31-e31c-5e3a3388c9b9", "outputs": {}, "resources": [ { + "module": "module.alertmanager", + "mode": "data", + "type": "template_file", + "name": "nomad_job_alertmanager", + "provider": "provider[\"registry.terraform.io/hashicorp/template\"]", + "instances": [ + { + "schema_version": 0, + "attributes": { + "filename": null, + "id": "ae09d392c808970a05f2423cd8dbf158f6cb6d3ae50260cd7d16f1575ce43871", + "rendered": "job \"prod-alertmanager\" {\n # The \"region\" parameter specifies the region in which to execute the job.\n # If omitted, this inherits the default region name of \"global\".\n # region = \"global\"\n #\n # The \"datacenters\" parameter specifies the list of datacenters which should\n # be considered when placing this task. This must be provided.\n datacenters = \"yul1\"\n\n # The \"type\" parameter controls the type of job, which impacts the scheduler's\n # decision on placement. This configuration is optional and defaults to\n # \"service\". For a full list of job types and their differences, please see\n # the online documentation.\n #\n # For more information, please see the online documentation at:\n #\n # https://www.nomadproject.io/docs/jobspec/schedulers\n #\n type = \"service\"\n\n update {\n # The \"max_parallel\" parameter specifies the maximum number of updates to\n # perform in parallel. In this case, this specifies to update a single task\n # at a time.\n max_parallel = 1\n\n health_check = \"checks\"\n\n # The \"min_healthy_time\" parameter specifies the minimum time the allocation\n # must be in the healthy state before it is marked as healthy and unblocks\n # further allocations from being updated.\n min_healthy_time = \"10s\"\n\n # The \"healthy_deadline\" parameter specifies the deadline in which the\n # allocation must be marked as healthy after which the allocation is\n # automatically transitioned to unhealthy. Transitioning to unhealthy will\n # fail the deployment and potentially roll back the job if \"auto_revert\" is\n # set to true.\n healthy_deadline = \"3m\"\n\n # The \"progress_deadline\" parameter specifies the deadline in which an\n # allocation must be marked as healthy. The deadline begins when the first\n # allocation for the deployment is created and is reset whenever an allocation\n # as part of the deployment transitions to a healthy state. If no allocation\n # transitions to the healthy state before the progress deadline, the\n # deployment is marked as failed.\n progress_deadline = \"10m\"\n\n\n # The \"canary\" parameter specifies that changes to the job that would result\n # in destructive updates should create the specified number of canaries\n # without stopping any previous allocations. Once the operator determines the\n # canaries are healthy, they can be promoted which unblocks a rolling update\n # of the remaining allocations at a rate of \"max_parallel\".\n #\n # Further, setting \"canary\" equal to the count of the task group allows\n # blue/green deployments. When the job is updated, a full set of the new\n # version is deployed and upon promotion the old version is stopped.\n canary = 1\n\n # Specifies if the job should auto-promote to the canary version when all\n # canaries become healthy during a deployment. Defaults to false which means\n # canaries must be manually updated with the nomad deployment promote\n # command.\n auto_promote = true\n\n # The \"auto_revert\" parameter specifies if the job should auto-revert to the\n # last stable job on deployment failure. A job is marked as stable if all the\n # allocations as part of its deployment were marked healthy.\n auto_revert = true\n\n }\n\n # The \"group\" stanza defines a series of tasks that should be co-located on\n # the same Nomad client. Any task within a group will be placed on the same\n # client.\n #\n # For more information and examples on the \"group\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/group\n #\n group \"prod-group1-alertmanager\" {\n # The \"count\" parameter specifies the number of the task groups that should\n # be running under this group. This value must be non-negative and defaults\n # to 1.\n count = 1\n\n # The constraint allows restricting the set of eligible nodes. Constraints\n # may filter on attributes or client metadata.\n #\n # For more information and examples on the \"volume\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/constraint\n #\n constraint {\n attribute = \"${attr.cpu.arch}\"\n operator = \"!=\"\n value = \"arm64\"\n }\n\n # The \"task\" stanza creates an individual unit of work, such as a Docker\n # container, web application, or batch processing.\n #\n # For more information and examples on the \"task\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/task\n #\n task \"prod-task1-alertmanager\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"exec\"\n\n \n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n command = \"local/alertmanager-0.21.0.linux-amd64/alertmanager\"\n args = [\n \"--config.file=secrets/alertmanager.yml\"\n ]\n }\n\n # The artifact stanza instructs Nomad to fetch and unpack a remote resource,\n # such as a file, tarball, or binary. Nomad downloads artifacts using the\n # popular go-getter library, which permits downloading artifacts from a\n # variety of locations using a URL as the input source.\n #\n # For more information and examples on the \"artifact\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/artifact\n #\n artifact {\n source = \"https://github.com/prometheus/alertmanager/releases/download/v0.21.0/alertmanager-0.21.0.linux-amd64.tar.gz\"\n }\n\n # The \"template\" stanza instructs Nomad to manage a template, such as\n # a configuration file or script. This template can optionally pull data\n # from Consul or Vault to populate runtime configuration data.\n #\n # For more information and examples on the \"template\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/template\n #\n template {\n change_mode = \"noop\"\n change_signal = \"SIGINT\"\n destination = \"secrets/alertmanager.yml\"\n left_delimiter = \"{{{\"\n right_delimiter = \"}}}\"\n data = \u003c\u003cEOH\nglobal:\n # The API URL to use for Slack notifications.\n slack_api_url: 'https://hooks.slack.com/services/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'\n\n# The directory from which notification templates are read.\ntemplates:\n- '/etc/alertmanager/template/*.tmpl'\n\n#tls_config:\n# # CA certificate to validate the server certificate with.\n# ca_file: \u003cfilepath\u003e ]\n#\n# # Certificate and key files for client cert authentication to the server.\n# cert_file: \u003cfilepath\u003e\n# key_file: \u003cfilepath\u003e\n#\n# # ServerName extension to indicate the name of the server.\n# # http://tools.ietf.org/html/rfc4366#section-3.1\n# server_name: \u003cstring\u003e\n#\n# # Disable validation of the server certificate.\n# insecure_skip_verify: true\n\n# The root route on which each incoming alert enters.\nroute:\n receiver: 'default-receiver'\n\n # The labels by which incoming alerts are grouped together. For example,\n # multiple alerts coming in for cluster=A and alertname=LatencyHigh would\n # be batched into a single group.\n #\n # To aggregate by all possible labels use '...' as the sole label name.\n # This effectively disables aggregation entirely, passing through all\n # alerts as-is. This is unlikely to be what you want, unless you have\n # a very low alert volume or your upstream notification system performs\n # its own grouping. Example: group_by: [...]\n group_by: ['alertname', 'cluster', 'service']\n\n # When a new group of alerts is created by an incoming alert, wait at\n # least 'group_wait' to send the initial notification.\n # This way ensures that you get multiple alerts for the same group that start\n # firing shortly after another are batched together on the first\n # notification.\n group_wait: 30s\n\n # When the first notification was sent, wait 'group_interval' to send a batch\n # of new alerts that started firing for that group.\n group_interval: 5m\n\n # If an alert has successfully been sent, wait 'repeat_interval' to\n # resend them.\n repeat_interval: 3h\n\n # All the above attributes are inherited by all child routes and can\n # overwritten on each.\n # The child route trees.\n routes:\n # This routes performs a regular expression match on alert labels to\n # catch alerts that are related to a list of services.\n - match_re:\n service: .*\n receiver: default-receiver\n # The service has a sub-route for critical alerts, any alerts\n # that do not match, i.e. severity != critical, fall-back to the\n # parent node and are sent to 'team-X-mails'\n routes:\n - match:\n severity: critical\n receiver: 'default-receiver'\n\n# Inhibition rules allow to mute a set of alerts given that another alert is\n# firing.\n# We use this to mute any warning-level notifications if the same alert is\n# already critical.\ninhibit_rules:\n- source_match:\n severity: 'critical'\n target_match:\n severity: 'warning'\n # Apply inhibition if the alertname is the same.\n # CAUTION:\n # If all label names listed in `equal` are missing\n # from both the source and target alerts,\n # the inhibition rule will apply!\n equal: ['alertname', 'cluster', 'service']\n\nreceivers:\n- name: 'default-receiver'\n slack_configs:\n - channel: '#fdio-infra-monitoring'\n send_resolved: true\n icon_url: https://avatars3.githubusercontent.com/u/3380462\n title: |-\n [{{ .Status | toUpper }}{{ if eq .Status \"firing\" }}:{{ .Alerts.Firing | len }}{{ end }}] {{ .CommonLabels.alertname }} for {{ .CommonLabels.job }}\n {{- if gt (len .CommonLabels) (len .GroupLabels) -}}\n {{\" \"}}(\n {{- with .CommonLabels.Remove .GroupLabels.Names }}\n {{- range $index, $label := .SortedPairs -}}\n {{ if $index }}, {{ end }}\n {{- $label.Name }}=\"{{ $label.Value -}}\"\n {{- end }}\n {{- end -}}\n )\n {{- end }}\n text: \u003e-\n {{ range .Alerts -}}\n *Alert:* {{ .Annotations.summary }}{{ if .Labels.severity }} - `{{ .Labels.severity }}`{{ end }}\n\n *Description:* {{ .Annotations.description }}\n\n *Details:*\n {{ range .Labels.SortedPairs }} • *{{ .Name }}:* `{{ .Value }}`\n {{ end }}\n {{ end }}\nEOH\n }\n\n # The service stanza instructs Nomad to register a service with Consul.\n #\n # For more information and examples on the \"task\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/service\n #\n service {\n name = \"alertmanager\"\n port = \"alertmanager\"\n tags = [ \"alertmanager${NOMAD_ALLOC_INDEX}\" ]\n check {\n name = \"Alertmanager Check Live\"\n type = \"http\"\n path = \"/-/healthy\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # For more information and examples on the \"resources\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/resources\n #\n resources {\n cpu = 1000\n memory = 1024\n # The network stanza specifies the networking requirements for the task\n # group, including the network mode and port allocations. When scheduling\n # jobs in Nomad they are provisioned across your fleet of machines along\n # with other jobs and services. Because you don't know in advance what host\n # your job will be provisioned on, Nomad will provide your tasks with\n # network configuration when they start up.\n #\n # For more information and examples on the \"template\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/network\n #\n network {\n port \"alertmanager\" {\n static = 9093\n }\n }\n }\n }\n }\n}", + "template": "job \"${job_name}\" {\n # The \"region\" parameter specifies the region in which to execute the job.\n # If omitted, this inherits the default region name of \"global\".\n # region = \"global\"\n #\n # The \"datacenters\" parameter specifies the list of datacenters which should\n # be considered when placing this task. This must be provided.\n datacenters = \"${datacenters}\"\n\n # The \"type\" parameter controls the type of job, which impacts the scheduler's\n # decision on placement. This configuration is optional and defaults to\n # \"service\". For a full list of job types and their differences, please see\n # the online documentation.\n #\n # For more information, please see the online documentation at:\n #\n # https://www.nomadproject.io/docs/jobspec/schedulers\n #\n type = \"service\"\n\n update {\n # The \"max_parallel\" parameter specifies the maximum number of updates to\n # perform in parallel. In this case, this specifies to update a single task\n # at a time.\n max_parallel = 1\n\n health_check = \"checks\"\n\n # The \"min_healthy_time\" parameter specifies the minimum time the allocation\n # must be in the healthy state before it is marked as healthy and unblocks\n # further allocations from being updated.\n min_healthy_time = \"10s\"\n\n # The \"healthy_deadline\" parameter specifies the deadline in which the\n # allocation must be marked as healthy after which the allocation is\n # automatically transitioned to unhealthy. Transitioning to unhealthy will\n # fail the deployment and potentially roll back the job if \"auto_revert\" is\n # set to true.\n healthy_deadline = \"3m\"\n\n # The \"progress_deadline\" parameter specifies the deadline in which an\n # allocation must be marked as healthy. The deadline begins when the first\n # allocation for the deployment is created and is reset whenever an allocation\n # as part of the deployment transitions to a healthy state. If no allocation\n # transitions to the healthy state before the progress deadline, the\n # deployment is marked as failed.\n progress_deadline = \"10m\"\n\n%{ if use_canary }\n # The \"canary\" parameter specifies that changes to the job that would result\n # in destructive updates should create the specified number of canaries\n # without stopping any previous allocations. Once the operator determines the\n # canaries are healthy, they can be promoted which unblocks a rolling update\n # of the remaining allocations at a rate of \"max_parallel\".\n #\n # Further, setting \"canary\" equal to the count of the task group allows\n # blue/green deployments. When the job is updated, a full set of the new\n # version is deployed and upon promotion the old version is stopped.\n canary = 1\n\n # Specifies if the job should auto-promote to the canary version when all\n # canaries become healthy during a deployment. Defaults to false which means\n # canaries must be manually updated with the nomad deployment promote\n # command.\n auto_promote = true\n\n # The \"auto_revert\" parameter specifies if the job should auto-revert to the\n # last stable job on deployment failure. A job is marked as stable if all the\n # allocations as part of its deployment were marked healthy.\n auto_revert = true\n%{ endif }\n }\n\n # The \"group\" stanza defines a series of tasks that should be co-located on\n # the same Nomad client. Any task within a group will be placed on the same\n # client.\n #\n # For more information and examples on the \"group\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/group\n #\n group \"prod-group1-${service_name}\" {\n # The \"count\" parameter specifies the number of the task groups that should\n # be running under this group. This value must be non-negative and defaults\n # to 1.\n count = ${group_count}\n\n # The constraint allows restricting the set of eligible nodes. Constraints\n # may filter on attributes or client metadata.\n #\n # For more information and examples on the \"volume\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/constraint\n #\n constraint {\n attribute = \"$${attr.cpu.arch}\"\n operator = \"!=\"\n value = \"arm64\"\n }\n\n # The \"task\" stanza creates an individual unit of work, such as a Docker\n # container, web application, or batch processing.\n #\n # For more information and examples on the \"task\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/task\n #\n task \"prod-task1-${service_name}\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"exec\"\n\n %{ if use_vault_provider }\n vault {\n policies = \"${vault_kv_policy_name}\"\n }\n %{ endif }\n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n command = \"local/alertmanager-${version}.linux-amd64/alertmanager\"\n args = [\n \"--config.file=secrets/alertmanager.yml\"\n ]\n }\n\n # The artifact stanza instructs Nomad to fetch and unpack a remote resource,\n # such as a file, tarball, or binary. Nomad downloads artifacts using the\n # popular go-getter library, which permits downloading artifacts from a\n # variety of locations using a URL as the input source.\n #\n # For more information and examples on the \"artifact\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/artifact\n #\n artifact {\n source = \"${url}\"\n }\n\n # The \"template\" stanza instructs Nomad to manage a template, such as\n # a configuration file or script. This template can optionally pull data\n # from Consul or Vault to populate runtime configuration data.\n #\n # For more information and examples on the \"template\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/template\n #\n template {\n change_mode = \"noop\"\n change_signal = \"SIGINT\"\n destination = \"secrets/alertmanager.yml\"\n left_delimiter = \"{{{\"\n right_delimiter = \"}}}\"\n data = \u003c\u003cEOH\nglobal:\n # The API URL to use for Slack notifications.\n slack_api_url: '${slack_api_url}'\n\n# The directory from which notification templates are read.\ntemplates:\n- '/etc/alertmanager/template/*.tmpl'\n\n#tls_config:\n# # CA certificate to validate the server certificate with.\n# ca_file: \u003cfilepath\u003e ]\n#\n# # Certificate and key files for client cert authentication to the server.\n# cert_file: \u003cfilepath\u003e\n# key_file: \u003cfilepath\u003e\n#\n# # ServerName extension to indicate the name of the server.\n# # http://tools.ietf.org/html/rfc4366#section-3.1\n# server_name: \u003cstring\u003e\n#\n# # Disable validation of the server certificate.\n# insecure_skip_verify: true\n\n# The root route on which each incoming alert enters.\nroute:\n receiver: '${default_receiver}'\n\n # The labels by which incoming alerts are grouped together. For example,\n # multiple alerts coming in for cluster=A and alertname=LatencyHigh would\n # be batched into a single group.\n #\n # To aggregate by all possible labels use '...' as the sole label name.\n # This effectively disables aggregation entirely, passing through all\n # alerts as-is. This is unlikely to be what you want, unless you have\n # a very low alert volume or your upstream notification system performs\n # its own grouping. Example: group_by: [...]\n group_by: ['alertname', 'cluster', 'service']\n\n # When a new group of alerts is created by an incoming alert, wait at\n # least 'group_wait' to send the initial notification.\n # This way ensures that you get multiple alerts for the same group that start\n # firing shortly after another are batched together on the first\n # notification.\n group_wait: 30s\n\n # When the first notification was sent, wait 'group_interval' to send a batch\n # of new alerts that started firing for that group.\n group_interval: 5m\n\n # If an alert has successfully been sent, wait 'repeat_interval' to\n # resend them.\n repeat_interval: 3h\n\n # All the above attributes are inherited by all child routes and can\n # overwritten on each.\n # The child route trees.\n routes:\n # This routes performs a regular expression match on alert labels to\n # catch alerts that are related to a list of services.\n - match_re:\n service: .*\n receiver: ${default_receiver}\n # The service has a sub-route for critical alerts, any alerts\n # that do not match, i.e. severity != critical, fall-back to the\n # parent node and are sent to 'team-X-mails'\n routes:\n - match:\n severity: critical\n receiver: '${default_receiver}'\n\n# Inhibition rules allow to mute a set of alerts given that another alert is\n# firing.\n# We use this to mute any warning-level notifications if the same alert is\n# already critical.\ninhibit_rules:\n- source_match:\n severity: 'critical'\n target_match:\n severity: 'warning'\n # Apply inhibition if the alertname is the same.\n # CAUTION:\n # If all label names listed in `equal` are missing\n # from both the source and target alerts,\n # the inhibition rule will apply!\n equal: ['alertname', 'cluster', 'service']\n\nreceivers:\n- name: '${default_receiver}'\n slack_configs:\n - channel: '#${slack_channel}'\n send_resolved: true\n icon_url: https://avatars3.githubusercontent.com/u/3380462\n title: |-\n [{{ .Status | toUpper }}{{ if eq .Status \"firing\" }}:{{ .Alerts.Firing | len }}{{ end }}] {{ .CommonLabels.alertname }} for {{ .CommonLabels.job }}\n {{- if gt (len .CommonLabels) (len .GroupLabels) -}}\n {{\" \"}}(\n {{- with .CommonLabels.Remove .GroupLabels.Names }}\n {{- range $index, $label := .SortedPairs -}}\n {{ if $index }}, {{ end }}\n {{- $label.Name }}=\"{{ $label.Value -}}\"\n {{- end }}\n {{- end -}}\n )\n {{- end }}\n text: \u003e-\n {{ range .Alerts -}}\n *Alert:* {{ .Annotations.summary }}{{ if .Labels.severity }} - `{{ .Labels.severity }}`{{ end }}\n\n *Description:* {{ .Annotations.description }}\n\n *Details:*\n {{ range .Labels.SortedPairs }} • *{{ .Name }}:* `{{ .Value }}`\n {{ end }}\n {{ end }}\nEOH\n }\n\n # The service stanza instructs Nomad to register a service with Consul.\n #\n # For more information and examples on the \"task\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/service\n #\n service {\n name = \"${service_name}\"\n port = \"${service_name}\"\n tags = [ \"${service_name}$${NOMAD_ALLOC_INDEX}\" ]\n check {\n name = \"Alertmanager Check Live\"\n type = \"http\"\n path = \"/-/healthy\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # For more information and examples on the \"resources\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/resources\n #\n resources {\n cpu = ${cpu}\n memory = ${mem}\n # The network stanza specifies the networking requirements for the task\n # group, including the network mode and port allocations. When scheduling\n # jobs in Nomad they are provisioned across your fleet of machines along\n # with other jobs and services. Because you don't know in advance what host\n # your job will be provisioned on, Nomad will provide your tasks with\n # network configuration when they start up.\n #\n # For more information and examples on the \"template\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/network\n #\n network {\n port \"${service_name}\" {\n static = ${port}\n }\n }\n }\n }\n }\n}", + "vars": { + "cpu": "1000", + "datacenters": "yul1", + "default_receiver": "default-receiver", + "group_count": "1", + "job_name": "prod-alertmanager", + "mem": "1024", + "port": "9093", + "service_name": "alertmanager", + "slack_api_url": "https://hooks.slack.com/services/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", + "slack_channel": "fdio-infra-monitoring", + "url": "https://github.com/prometheus/alertmanager/releases/download/v0.21.0/alertmanager-0.21.0.linux-amd64.tar.gz", + "use_canary": "true", + "use_vault_provider": "false", + "version": "0.21.0" + } + }, + "sensitive_attributes": [] + } + ] + }, + { + "module": "module.alertmanager", + "mode": "managed", + "type": "nomad_job", + "name": "nomad_job_alertmanager", + "provider": "provider[\"registry.terraform.io/hashicorp/nomad\"].yul1", + "instances": [ + { + "schema_version": 0, + "attributes": { + "allocation_ids": [ + "464144d9-8c27-dc03-71bb-6f8d525bc486" + ], + "datacenters": [ + "yul1" + ], + "deployment_id": "d69d73a6-2a1b-ebf6-e421-30ce1f34f519", + "deployment_status": "successful", + "deregister_on_destroy": true, + "deregister_on_id_change": true, + "detach": false, + "id": "prod-alertmanager", + "jobspec": "job \"prod-alertmanager\" {\n # The \"region\" parameter specifies the region in which to execute the job.\n # If omitted, this inherits the default region name of \"global\".\n # region = \"global\"\n #\n # The \"datacenters\" parameter specifies the list of datacenters which should\n # be considered when placing this task. This must be provided.\n datacenters = \"yul1\"\n\n # The \"type\" parameter controls the type of job, which impacts the scheduler's\n # decision on placement. This configuration is optional and defaults to\n # \"service\". For a full list of job types and their differences, please see\n # the online documentation.\n #\n # For more information, please see the online documentation at:\n #\n # https://www.nomadproject.io/docs/jobspec/schedulers\n #\n type = \"service\"\n\n update {\n # The \"max_parallel\" parameter specifies the maximum number of updates to\n # perform in parallel. In this case, this specifies to update a single task\n # at a time.\n max_parallel = 1\n\n health_check = \"checks\"\n\n # The \"min_healthy_time\" parameter specifies the minimum time the allocation\n # must be in the healthy state before it is marked as healthy and unblocks\n # further allocations from being updated.\n min_healthy_time = \"10s\"\n\n # The \"healthy_deadline\" parameter specifies the deadline in which the\n # allocation must be marked as healthy after which the allocation is\n # automatically transitioned to unhealthy. Transitioning to unhealthy will\n # fail the deployment and potentially roll back the job if \"auto_revert\" is\n # set to true.\n healthy_deadline = \"3m\"\n\n # The \"progress_deadline\" parameter specifies the deadline in which an\n # allocation must be marked as healthy. The deadline begins when the first\n # allocation for the deployment is created and is reset whenever an allocation\n # as part of the deployment transitions to a healthy state. If no allocation\n # transitions to the healthy state before the progress deadline, the\n # deployment is marked as failed.\n progress_deadline = \"10m\"\n\n\n # The \"canary\" parameter specifies that changes to the job that would result\n # in destructive updates should create the specified number of canaries\n # without stopping any previous allocations. Once the operator determines the\n # canaries are healthy, they can be promoted which unblocks a rolling update\n # of the remaining allocations at a rate of \"max_parallel\".\n #\n # Further, setting \"canary\" equal to the count of the task group allows\n # blue/green deployments. When the job is updated, a full set of the new\n # version is deployed and upon promotion the old version is stopped.\n canary = 1\n\n # Specifies if the job should auto-promote to the canary version when all\n # canaries become healthy during a deployment. Defaults to false which means\n # canaries must be manually updated with the nomad deployment promote\n # command.\n auto_promote = true\n\n # The \"auto_revert\" parameter specifies if the job should auto-revert to the\n # last stable job on deployment failure. A job is marked as stable if all the\n # allocations as part of its deployment were marked healthy.\n auto_revert = true\n\n }\n\n # The \"group\" stanza defines a series of tasks that should be co-located on\n # the same Nomad client. Any task within a group will be placed on the same\n # client.\n #\n # For more information and examples on the \"group\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/group\n #\n group \"prod-group1-alertmanager\" {\n # The \"count\" parameter specifies the number of the task groups that should\n # be running under this group. This value must be non-negative and defaults\n # to 1.\n count = 1\n\n # The constraint allows restricting the set of eligible nodes. Constraints\n # may filter on attributes or client metadata.\n #\n # For more information and examples on the \"volume\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/constraint\n #\n constraint {\n attribute = \"${attr.cpu.arch}\"\n operator = \"!=\"\n value = \"arm64\"\n }\n\n # The \"task\" stanza creates an individual unit of work, such as a Docker\n # container, web application, or batch processing.\n #\n # For more information and examples on the \"task\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/task\n #\n task \"prod-task1-alertmanager\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"exec\"\n\n \n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n command = \"local/alertmanager-0.21.0.linux-amd64/alertmanager\"\n args = [\n \"--config.file=secrets/alertmanager.yml\"\n ]\n }\n\n # The artifact stanza instructs Nomad to fetch and unpack a remote resource,\n # such as a file, tarball, or binary. Nomad downloads artifacts using the\n # popular go-getter library, which permits downloading artifacts from a\n # variety of locations using a URL as the input source.\n #\n # For more information and examples on the \"artifact\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/artifact\n #\n artifact {\n source = \"https://github.com/prometheus/alertmanager/releases/download/v0.21.0/alertmanager-0.21.0.linux-amd64.tar.gz\"\n }\n\n # The \"template\" stanza instructs Nomad to manage a template, such as\n # a configuration file or script. This template can optionally pull data\n # from Consul or Vault to populate runtime configuration data.\n #\n # For more information and examples on the \"template\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/template\n #\n template {\n change_mode = \"noop\"\n change_signal = \"SIGINT\"\n destination = \"secrets/alertmanager.yml\"\n left_delimiter = \"{{{\"\n right_delimiter = \"}}}\"\n data = \u003c\u003cEOH\nglobal:\n # The API URL to use for Slack notifications.\n slack_api_url: 'https://hooks.slack.com/services/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'\n\n# The directory from which notification templates are read.\ntemplates:\n- '/etc/alertmanager/template/*.tmpl'\n\n#tls_config:\n# # CA certificate to validate the server certificate with.\n# ca_file: \u003cfilepath\u003e ]\n#\n# # Certificate and key files for client cert authentication to the server.\n# cert_file: \u003cfilepath\u003e\n# key_file: \u003cfilepath\u003e\n#\n# # ServerName extension to indicate the name of the server.\n# # http://tools.ietf.org/html/rfc4366#section-3.1\n# server_name: \u003cstring\u003e\n#\n# # Disable validation of the server certificate.\n# insecure_skip_verify: true\n\n# The root route on which each incoming alert enters.\nroute:\n receiver: 'default-receiver'\n\n # The labels by which incoming alerts are grouped together. For example,\n # multiple alerts coming in for cluster=A and alertname=LatencyHigh would\n # be batched into a single group.\n #\n # To aggregate by all possible labels use '...' as the sole label name.\n # This effectively disables aggregation entirely, passing through all\n # alerts as-is. This is unlikely to be what you want, unless you have\n # a very low alert volume or your upstream notification system performs\n # its own grouping. Example: group_by: [...]\n group_by: ['alertname', 'cluster', 'service']\n\n # When a new group of alerts is created by an incoming alert, wait at\n # least 'group_wait' to send the initial notification.\n # This way ensures that you get multiple alerts for the same group that start\n # firing shortly after another are batched together on the first\n # notification.\n group_wait: 30s\n\n # When the first notification was sent, wait 'group_interval' to send a batch\n # of new alerts that started firing for that group.\n group_interval: 5m\n\n # If an alert has successfully been sent, wait 'repeat_interval' to\n # resend them.\n repeat_interval: 3h\n\n # All the above attributes are inherited by all child routes and can\n # overwritten on each.\n # The child route trees.\n routes:\n # This routes performs a regular expression match on alert labels to\n # catch alerts that are related to a list of services.\n - match_re:\n service: .*\n receiver: default-receiver\n # The service has a sub-route for critical alerts, any alerts\n # that do not match, i.e. severity != critical, fall-back to the\n # parent node and are sent to 'team-X-mails'\n routes:\n - match:\n severity: critical\n receiver: 'default-receiver'\n\n# Inhibition rules allow to mute a set of alerts given that another alert is\n# firing.\n# We use this to mute any warning-level notifications if the same alert is\n# already critical.\ninhibit_rules:\n- source_match:\n severity: 'critical'\n target_match:\n severity: 'warning'\n # Apply inhibition if the alertname is the same.\n # CAUTION:\n # If all label names listed in `equal` are missing\n # from both the source and target alerts,\n # the inhibition rule will apply!\n equal: ['alertname', 'cluster', 'service']\n\nreceivers:\n- name: 'default-receiver'\n slack_configs:\n - channel: '#fdio-infra-monitoring'\n send_resolved: true\n icon_url: https://avatars3.githubusercontent.com/u/3380462\n title: |-\n [{{ .Status | toUpper }}{{ if eq .Status \"firing\" }}:{{ .Alerts.Firing | len }}{{ end }}] {{ .CommonLabels.alertname }} for {{ .CommonLabels.job }}\n {{- if gt (len .CommonLabels) (len .GroupLabels) -}}\n {{\" \"}}(\n {{- with .CommonLabels.Remove .GroupLabels.Names }}\n {{- range $index, $label := .SortedPairs -}}\n {{ if $index }}, {{ end }}\n {{- $label.Name }}=\"{{ $label.Value -}}\"\n {{- end }}\n {{- end -}}\n )\n {{- end }}\n text: \u003e-\n {{ range .Alerts -}}\n *Alert:* {{ .Annotations.summary }}{{ if .Labels.severity }} - `{{ .Labels.severity }}`{{ end }}\n\n *Description:* {{ .Annotations.description }}\n\n *Details:*\n {{ range .Labels.SortedPairs }} • *{{ .Name }}:* `{{ .Value }}`\n {{ end }}\n {{ end }}\nEOH\n }\n\n # The service stanza instructs Nomad to register a service with Consul.\n #\n # For more information and examples on the \"task\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/service\n #\n service {\n name = \"alertmanager\"\n port = \"alertmanager\"\n tags = [ \"alertmanager${NOMAD_ALLOC_INDEX}\" ]\n check {\n name = \"Alertmanager Check Live\"\n type = \"http\"\n path = \"/-/healthy\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # For more information and examples on the \"resources\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/resources\n #\n resources {\n cpu = 1000\n memory = 1024\n # The network stanza specifies the networking requirements for the task\n # group, including the network mode and port allocations. When scheduling\n # jobs in Nomad they are provisioned across your fleet of machines along\n # with other jobs and services. Because you don't know in advance what host\n # your job will be provisioned on, Nomad will provide your tasks with\n # network configuration when they start up.\n #\n # For more information and examples on the \"template\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/network\n #\n network {\n port \"alertmanager\" {\n static = 9093\n }\n }\n }\n }\n }\n}", + "json": null, + "modify_index": "7147924", + "name": "prod-alertmanager", + "namespace": "default", + "policy_override": null, + "purge_on_destroy": null, + "region": "global", + "task_groups": [ + { + "count": 1, + "meta": {}, + "name": "prod-group1-alertmanager", + "task": [ + { + "driver": "exec", + "meta": {}, + "name": "prod-task1-alertmanager", + "volume_mounts": [] + } + ], + "volumes": [] + } + ], + "type": "service" + }, + "sensitive_attributes": [], + "private": "bnVsbA==", + "dependencies": [ + "module.alertmanager.data.template_file.nomad_job_alertmanager" + ] + } + ] + }, + { + "module": "module.exporter", + "mode": "data", + "type": "template_file", + "name": "nomad_job_exporter", + "provider": "provider[\"registry.terraform.io/hashicorp/template\"]", + "instances": [ + { + "schema_version": 0, + "attributes": { + "filename": null, + "id": "28db119a83617686c94496ed114455041d4fc500d93c4de8f8b8cfbe7d4c1db2", + "rendered": "job \"prod-exporter\" {\n # The \"region\" parameter specifies the region in which to execute the job.\n # If omitted, this inherits the default region name of \"global\".\n # region = \"global\"\n #\n # The \"datacenters\" parameter specifies the list of datacenters which should\n # be considered when placing this task. This must be provided.\n datacenters = \"yul1\"\n\n # The \"type\" parameter controls the type of job, which impacts the scheduler's\n # decision on placement. This configuration is optional and defaults to\n # \"service\". For a full list of job types and their differences, please see\n # the online documentation.\n #\n # https://www.nomadproject.io/docs/jobspec/schedulers\n #\n type = \"system\"\n\n update {\n # The \"max_parallel\" parameter specifies the maximum number of updates to\n # perform in parallel. In this case, this specifies to update a single task\n # at a time.\n max_parallel = 1\n\n health_check = \"checks\"\n\n # The \"min_healthy_time\" parameter specifies the minimum time the allocation\n # must be in the healthy state before it is marked as healthy and unblocks\n # further allocations from being updated.\n min_healthy_time = \"10s\"\n\n # The \"healthy_deadline\" parameter specifies the deadline in which the\n # allocation must be marked as healthy after which the allocation is\n # automatically transitioned to unhealthy. Transitioning to unhealthy will\n # fail the deployment and potentially roll back the job if \"auto_revert\" is\n # set to true.\n healthy_deadline = \"3m\"\n\n # The \"progress_deadline\" parameter specifies the deadline in which an\n # allocation must be marked as healthy. The deadline begins when the first\n # allocation for the deployment is created and is reset whenever an allocation\n # as part of the deployment transitions to a healthy state. If no allocation\n # transitions to the healthy state before the progress deadline, the\n # deployment is marked as failed.\n progress_deadline = \"10m\"\n\n\n }\n\n # The \"group\" stanza defines a series of tasks that should be co-located on\n # the same Nomad client. Any task within a group will be placed on the same\n # client.\n #\n # https://www.nomadproject.io/docs/job-specification/group\n #\n group \"prod-group1-exporter-amd64\" {\n # The constraint allows restricting the set of eligible nodes. Constraints\n # may filter on attributes or client metadata.\n #\n # https://www.nomadproject.io/docs/job-specification/constraint\n #\n constraint {\n attribute = \"${attr.cpu.arch}\"\n operator = \"!=\"\n value = \"arm64\"\n }\n\n # The \"task\" stanza creates an individual unit of work, such as a Docker\n # container, web application, or batch processing.\n #\n # https://www.nomadproject.io/docs/job-specification/task\n #\n task \"prod-task1-nodeexporter-amd64\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"raw_exec\"\n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n command = \"local/node_exporter-1.0.1.linux-amd64/node_exporter\"\n }\n\n # The artifact stanza instructs Nomad to fetch and unpack a remote resource,\n # such as a file, tarball, or binary. Nomad downloads artifacts using the\n # popular go-getter library, which permits downloading artifacts from a\n # variety of locations using a URL as the input source.\n #\n # https://www.nomadproject.io/docs/job-specification/artifact\n #\n artifact {\n source = \"https://github.com/prometheus/node_exporter/releases/download/v1.0.1/node_exporter-1.0.1.linux-amd64.tar.gz\"\n }\n\n # The service stanza instructs Nomad to register a service with Consul.\n #\n # https://www.nomadproject.io/docs/job-specification/service\n #\n service {\n name = \"nodeexporter\"\n port = \"nodeexporter\"\n check {\n name = \"Node Exporter Check Live\"\n type = \"http\"\n path = \"/metrics\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # https://www.nomadproject.io/docs/job-specification/resources\n #\n resources {\n cpu = 500\n # The network stanza specifies the networking requirements for the task\n # group, including the network mode and port allocations. When scheduling\n # jobs in Nomad they are provisioned across your fleet of machines along\n # with other jobs and services. Because you don't know in advance what host\n # your job will be provisioned on, Nomad will provide your tasks with\n # network configuration when they start up.\n #\n # https://www.nomadproject.io/docs/job-specification/network\n #\n network {\n port \"nodeexporter\" {\n static = 9100\n }\n }\n }\n }\n task \"prod-task2-blackboxexporter-amd64\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"exec\"\n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n command = \"local/blackbox_exporter-0.18.0.linux-amd64/blackbox_exporter\"\n args = [\n \"--config.file=secrets/blackbox.yml\"\n ]\n }\n\n # The \"template\" stanza instructs Nomad to manage a template, such as\n # a configuration file or script. This template can optionally pull data\n # from Consul or Vault to populate runtime configuration data.\n #\n # https://www.nomadproject.io/docs/job-specification/template\n #\n template {\n change_mode = \"noop\"\n change_signal = \"SIGINT\"\n destination = \"secrets/blackbox.yml\"\n data = \u003c\u003cEOH\nmodules:\n http_2xx:\n prober: http\n timeout: 5s\n http:\n valid_http_versions: [\"HTTP/1.1\", \"HTTP/2.0\"]\n no_follow_redirects: false\n fail_if_ssl: false\n fail_if_not_ssl: true\n tls_config:\n insecure_skip_verify: false\n preferred_ip_protocol: \"ip4\"\n icmp_v4:\n prober: icmp\n timeout: 5s\n icmp:\n preferred_ip_protocol: \"ip4\"\n dns_udp:\n prober: dns\n timeout: 5s\n dns:\n query_name: \"jenkins.fd.io\"\n query_type: \"A\"\n valid_rcodes:\n - NOERROR\nEOH\n }\n\n # The artifact stanza instructs Nomad to fetch and unpack a remote resource,\n # such as a file, tarball, or binary. Nomad downloads artifacts using the\n # popular go-getter library, which permits downloading artifacts from a\n # variety of locations using a URL as the input source.\n #\n # https://www.nomadproject.io/docs/job-specification/artifact\n #\n artifact {\n source = \"https://github.com/prometheus/blackbox_exporter/releases/download/v0.18.0/blackbox_exporter-0.18.0.linux-amd64.tar.gz\"\n }\n\n # The service stanza instructs Nomad to register a service with Consul.\n #\n # https://www.nomadproject.io/docs/job-specification/service\n #\n service {\n name = \"blackboxexporter\"\n port = \"blackboxexporter\"\n tags = [ \"blackboxexporter${NOMAD_ALLOC_INDEX}\" ]\n check {\n name = \"Blackbox Exporter Check Live\"\n type = \"http\"\n path = \"/metrics\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # https://www.nomadproject.io/docs/job-specification/resources\n #\n resources {\n cpu = 500\n # The network stanza specifies the networking requirements for the task\n # group, including the network mode and port allocations. When scheduling\n # jobs in Nomad they are provisioned across your fleet of machines along\n # with other jobs and services. Because you don't know in advance what host\n # your job will be provisioned on, Nomad will provide your tasks with\n # network configuration when they start up.\n #\n # https://www.nomadproject.io/docs/job-specification/network\n #\n network {\n port \"blackboxexporter\" {\n static = 9115\n }\n }\n }\n }\n\n task \"prod-task3-cadvisorexporter-amd64\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"docker\"\n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n image = \"gcr.io/cadvisor/cadvisor:latest\"\n volumes = [\n \"/:/rootfs:ro\",\n \"/var/run:/var/run:rw\",\n \"/sys:/sys:ro\",\n \"/var/lib/docker/:/var/lib/docker:ro\",\n \"/cgroup:/cgroup:ro\"\n ]\n }\n\n # The service stanza instructs Nomad to register a service with Consul.\n #\n # https://www.nomadproject.io/docs/job-specification/service\n #\n service {\n name = \"cadvisorexporter\"\n port = \"cadvisorexporter\"\n check {\n name = \"cAdvisor Check Live\"\n type = \"http\"\n path = \"/metrics\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # https://www.nomadproject.io/docs/job-specification/resources\n #\n resources {\n cpu = 500\n # The network stanza specifies the networking requirements for the task\n # group, including the network mode and port allocations. When scheduling\n # jobs in Nomad they are provisioned across your fleet of machines along\n # with other jobs and services. Because you don't know in advance what host\n # your job will be provisioned on, Nomad will provide your tasks with\n # network configuration when they start up.\n #\n # https://www.nomadproject.io/docs/job-specification/network\n #\n network {\n port \"cadvisorexporter\" {\n static = 8080\n }\n }\n }\n }\n }\n\n group \"prod-group1-exporter-arm64\" {\n # The constraint allows restricting the set of eligible nodes. Constraints\n # may filter on attributes or client metadata.\n #\n # https://www.nomadproject.io/docs/job-specification/constraint\n #\n constraint {\n attribute = \"${attr.cpu.arch}\"\n operator = \"==\"\n value = \"arm64\"\n }\n\n # The \"task\" stanza creates an individual unit of work, such as a Docker\n # container, web application, or batch processing.\n #\n # https://www.nomadproject.io/docs/job-specification/task\n #\n task \"prod-task1-nodeexporter-arm64\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"raw_exec\"\n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n command = \"local/node_exporter-1.0.1.linux-arm64/node_exporter\"\n }\n\n # The artifact stanza instructs Nomad to fetch and unpack a remote resource,\n # such as a file, tarball, or binary. Nomad downloads artifacts using the\n # popular go-getter library, which permits downloading artifacts from a\n # variety of locations using a URL as the input source.\n #\n # https://www.nomadproject.io/docs/job-specification/artifact\n #\n artifact {\n source = \"https://github.com/prometheus/node_exporter/releases/download/v1.0.1/node_exporter-1.0.1.linux-arm64.tar.gz\"\n }\n\n # The service stanza instructs Nomad to register a service with Consul.\n #\n # https://www.nomadproject.io/docs/job-specification/service\n #\n service {\n name = \"nodeexporter\"\n port = \"nodeexporter\"\n check {\n name = \"Node Exporter Check Live\"\n type = \"http\"\n path = \"/metrics\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # https://www.nomadproject.io/docs/job-specification/resources\n #\n resources {\n cpu = 500\n # The network stanza specifies the networking requirements for the task\n # group, including the network mode and port allocations. When scheduling\n # jobs in Nomad they are provisioned across your fleet of machines along\n # with other jobs and services. Because you don't know in advance what host\n # your job will be provisioned on, Nomad will provide your tasks with\n # network configuration when they start up.\n #\n # https://www.nomadproject.io/docs/job-specification/network\n #\n network {\n port \"nodeexporter\" {\n static = 9100\n }\n }\n }\n }\n\n task \"prod-task2-blackboxexporter-arm64\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"exec\"\n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n command = \"local/blackbox_exporter-0.18.0.linux-arm64/blackbox_exporter\"\n args = [\n \"--config.file=secrets/blackbox.yml\"\n ]\n }\n\n # The \"template\" stanza instructs Nomad to manage a template, such as\n # a configuration file or script. This template can optionally pull data\n # from Consul or Vault to populate runtime configuration data.\n #\n # https://www.nomadproject.io/docs/job-specification/template\n #\n template {\n change_mode = \"noop\"\n change_signal = \"SIGINT\"\n destination = \"secrets/blackbox.yml\"\n data = \u003c\u003cEOH\nmodules:\n http_2xx:\n prober: http\n timeout: 5s\n http:\n valid_http_versions: [\"HTTP/1.1\", \"HTTP/2.0\"]\n no_follow_redirects: false\n fail_if_ssl: false\n fail_if_not_ssl: true\n tls_config:\n insecure_skip_verify: false\n preferred_ip_protocol: \"ip4\"\n icmp_v4:\n prober: icmp\n timeout: 5s\n icmp:\n preferred_ip_protocol: \"ip4\"\n dns_udp:\n prober: dns\n timeout: 5s\n dns:\n query_name: \"jenkins.fd.io\"\n query_type: \"A\"\n valid_rcodes:\n - NOERROR\nEOH\n }\n\n # The artifact stanza instructs Nomad to fetch and unpack a remote resource,\n # such as a file, tarball, or binary. Nomad downloads artifacts using the\n # popular go-getter library, which permits downloading artifacts from a\n # variety of locations using a URL as the input source.\n #\n # https://www.nomadproject.io/docs/job-specification/artifact\n #\n artifact {\n source = \"https://github.com/prometheus/blackbox_exporter/releases/download/v0.18.0/blackbox_exporter-0.18.0.linux-arm64.tar.gz\"\n }\n\n # The service stanza instructs Nomad to register a service with Consul.\n #\n # https://www.nomadproject.io/docs/job-specification/service\n #\n service {\n name = \"blackboxexporter\"\n port = \"blackboxexporter\"\n tags = [ \"blackboxexporter${NOMAD_ALLOC_INDEX}\" ]\n check {\n name = \"Blackbox Exporter Check Live\"\n type = \"http\"\n path = \"/metrics\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # https://www.nomadproject.io/docs/job-specification/resources\n #\n resources {\n cpu = 500\n # The network stanza specifies the networking requirements for the task\n # group, including the network mode and port allocations. When scheduling\n # jobs in Nomad they are provisioned across your fleet of machines along\n # with other jobs and services. Because you don't know in advance what host\n # your job will be provisioned on, Nomad will provide your tasks with\n # network configuration when they start up.\n #\n # https://www.nomadproject.io/docs/job-specification/network\n #\n network {\n port \"blackboxexporter\" {\n static = 9115\n }\n }\n }\n }\n\n task \"prod-task3-cadvisorexporter-arm64\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"docker\"\n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n # There is currently no official release for arm yet...using community.\n image = \"zcube/cadvisor:latest\"\n volumes = [\n \"/:/rootfs:ro\",\n \"/var/run:/var/run:rw\",\n \"/sys:/sys:ro\",\n \"/var/lib/docker/:/var/lib/docker:ro\",\n \"/cgroup:/cgroup:ro\"\n ]\n }\n\n # The service stanza instructs Nomad to register a service with Consul.\n #\n # https://www.nomadproject.io/docs/job-specification/service\n #\n service {\n name = \"cadvisorexporter\"\n port = \"cadvisorexporter\"\n check {\n name = \"cAdvisor Check Live\"\n type = \"http\"\n path = \"/metrics\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # https://www.nomadproject.io/docs/job-specification/resources\n #\n resources {\n cpu = 500\n # The network stanza specifies the networking requirements for the task\n # group, including the network mode and port allocations. When scheduling\n # jobs in Nomad they are provisioned across your fleet of machines along\n # with other jobs and services. Because you don't know in advance what host\n # your job will be provisioned on, Nomad will provide your tasks with\n # network configuration when they start up.\n #\n # https://www.nomadproject.io/docs/job-specification/network\n #\n network {\n port \"cadvisorexporter\" {\n static = 8080\n }\n }\n }\n }\n }\n}", + "template": "job \"${job_name}\" {\n # The \"region\" parameter specifies the region in which to execute the job.\n # If omitted, this inherits the default region name of \"global\".\n # region = \"global\"\n #\n # The \"datacenters\" parameter specifies the list of datacenters which should\n # be considered when placing this task. This must be provided.\n datacenters = \"${datacenters}\"\n\n # The \"type\" parameter controls the type of job, which impacts the scheduler's\n # decision on placement. This configuration is optional and defaults to\n # \"service\". For a full list of job types and their differences, please see\n # the online documentation.\n #\n # https://www.nomadproject.io/docs/jobspec/schedulers\n #\n type = \"system\"\n\n update {\n # The \"max_parallel\" parameter specifies the maximum number of updates to\n # perform in parallel. In this case, this specifies to update a single task\n # at a time.\n max_parallel = 1\n\n health_check = \"checks\"\n\n # The \"min_healthy_time\" parameter specifies the minimum time the allocation\n # must be in the healthy state before it is marked as healthy and unblocks\n # further allocations from being updated.\n min_healthy_time = \"10s\"\n\n # The \"healthy_deadline\" parameter specifies the deadline in which the\n # allocation must be marked as healthy after which the allocation is\n # automatically transitioned to unhealthy. Transitioning to unhealthy will\n # fail the deployment and potentially roll back the job if \"auto_revert\" is\n # set to true.\n healthy_deadline = \"3m\"\n\n # The \"progress_deadline\" parameter specifies the deadline in which an\n # allocation must be marked as healthy. The deadline begins when the first\n # allocation for the deployment is created and is reset whenever an allocation\n # as part of the deployment transitions to a healthy state. If no allocation\n # transitions to the healthy state before the progress deadline, the\n # deployment is marked as failed.\n progress_deadline = \"10m\"\n\n%{ if use_canary }\n # The \"canary\" parameter specifies that changes to the job that would result\n # in destructive updates should create the specified number of canaries\n # without stopping any previous allocations. Once the operator determines the\n # canaries are healthy, they can be promoted which unblocks a rolling update\n # of the remaining allocations at a rate of \"max_parallel\".\n #\n # Further, setting \"canary\" equal to the count of the task group allows\n # blue/green deployments. When the job is updated, a full set of the new\n # version is deployed and upon promotion the old version is stopped.\n canary = 1\n\n # Specifies if the job should auto-promote to the canary version when all\n # canaries become healthy during a deployment. Defaults to false which means\n # canaries must be manually updated with the nomad deployment promote\n # command.\n auto_promote = true\n\n # The \"auto_revert\" parameter specifies if the job should auto-revert to the\n # last stable job on deployment failure. A job is marked as stable if all the\n # allocations as part of its deployment were marked healthy.\n auto_revert = true\n%{ endif }\n }\n\n # The \"group\" stanza defines a series of tasks that should be co-located on\n # the same Nomad client. Any task within a group will be placed on the same\n # client.\n #\n # https://www.nomadproject.io/docs/job-specification/group\n #\n group \"prod-group1-exporter-amd64\" {\n # The constraint allows restricting the set of eligible nodes. Constraints\n # may filter on attributes or client metadata.\n #\n # https://www.nomadproject.io/docs/job-specification/constraint\n #\n constraint {\n attribute = \"$${attr.cpu.arch}\"\n operator = \"!=\"\n value = \"arm64\"\n }\n\n # The \"task\" stanza creates an individual unit of work, such as a Docker\n # container, web application, or batch processing.\n #\n # https://www.nomadproject.io/docs/job-specification/task\n #\n task \"prod-task1-${node_service_name}-amd64\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"raw_exec\"\n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n command = \"local/node_exporter-${node_version}.linux-amd64/node_exporter\"\n }\n\n # The artifact stanza instructs Nomad to fetch and unpack a remote resource,\n # such as a file, tarball, or binary. Nomad downloads artifacts using the\n # popular go-getter library, which permits downloading artifacts from a\n # variety of locations using a URL as the input source.\n #\n # https://www.nomadproject.io/docs/job-specification/artifact\n #\n artifact {\n source = \"${node_url_amd64}\"\n }\n\n # The service stanza instructs Nomad to register a service with Consul.\n #\n # https://www.nomadproject.io/docs/job-specification/service\n #\n service {\n name = \"${node_service_name}\"\n port = \"${node_service_name}\"\n check {\n name = \"Node Exporter Check Live\"\n type = \"http\"\n path = \"/metrics\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # https://www.nomadproject.io/docs/job-specification/resources\n #\n resources {\n cpu = 500\n # The network stanza specifies the networking requirements for the task\n # group, including the network mode and port allocations. When scheduling\n # jobs in Nomad they are provisioned across your fleet of machines along\n # with other jobs and services. Because you don't know in advance what host\n # your job will be provisioned on, Nomad will provide your tasks with\n # network configuration when they start up.\n #\n # https://www.nomadproject.io/docs/job-specification/network\n #\n network {\n port \"${node_service_name}\" {\n static = ${node_port}\n }\n }\n }\n }\n task \"prod-task2-${blackbox_service_name}-amd64\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"exec\"\n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n command = \"local/blackbox_exporter-${blackbox_version}.linux-amd64/blackbox_exporter\"\n args = [\n \"--config.file=secrets/blackbox.yml\"\n ]\n }\n\n # The \"template\" stanza instructs Nomad to manage a template, such as\n # a configuration file or script. This template can optionally pull data\n # from Consul or Vault to populate runtime configuration data.\n #\n # https://www.nomadproject.io/docs/job-specification/template\n #\n template {\n change_mode = \"noop\"\n change_signal = \"SIGINT\"\n destination = \"secrets/blackbox.yml\"\n data = \u003c\u003cEOH\nmodules:\n http_2xx:\n prober: http\n timeout: 5s\n http:\n valid_http_versions: [\"HTTP/1.1\", \"HTTP/2.0\"]\n no_follow_redirects: false\n fail_if_ssl: false\n fail_if_not_ssl: true\n tls_config:\n insecure_skip_verify: false\n preferred_ip_protocol: \"ip4\"\n icmp_v4:\n prober: icmp\n timeout: 5s\n icmp:\n preferred_ip_protocol: \"ip4\"\n dns_udp:\n prober: dns\n timeout: 5s\n dns:\n query_name: \"jenkins.fd.io\"\n query_type: \"A\"\n valid_rcodes:\n - NOERROR\nEOH\n }\n\n # The artifact stanza instructs Nomad to fetch and unpack a remote resource,\n # such as a file, tarball, or binary. Nomad downloads artifacts using the\n # popular go-getter library, which permits downloading artifacts from a\n # variety of locations using a URL as the input source.\n #\n # https://www.nomadproject.io/docs/job-specification/artifact\n #\n artifact {\n source = \"${blackbox_url_amd64}\"\n }\n\n # The service stanza instructs Nomad to register a service with Consul.\n #\n # https://www.nomadproject.io/docs/job-specification/service\n #\n service {\n name = \"${blackbox_service_name}\"\n port = \"${blackbox_service_name}\"\n tags = [ \"${blackbox_service_name}$${NOMAD_ALLOC_INDEX}\" ]\n check {\n name = \"Blackbox Exporter Check Live\"\n type = \"http\"\n path = \"/metrics\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # https://www.nomadproject.io/docs/job-specification/resources\n #\n resources {\n cpu = 500\n # The network stanza specifies the networking requirements for the task\n # group, including the network mode and port allocations. When scheduling\n # jobs in Nomad they are provisioned across your fleet of machines along\n # with other jobs and services. Because you don't know in advance what host\n # your job will be provisioned on, Nomad will provide your tasks with\n # network configuration when they start up.\n #\n # https://www.nomadproject.io/docs/job-specification/network\n #\n network {\n port \"${blackbox_service_name}\" {\n static = ${blackbox_port}\n }\n }\n }\n }\n\n task \"prod-task3-${cadvisor_service_name}-amd64\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"docker\"\n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n image = \"${cadvisor_image}\"\n volumes = [\n \"/:/rootfs:ro\",\n \"/var/run:/var/run:rw\",\n \"/sys:/sys:ro\",\n \"/var/lib/docker/:/var/lib/docker:ro\",\n \"/cgroup:/cgroup:ro\"\n ]\n }\n\n # The service stanza instructs Nomad to register a service with Consul.\n #\n # https://www.nomadproject.io/docs/job-specification/service\n #\n service {\n name = \"${cadvisor_service_name}\"\n port = \"${cadvisor_service_name}\"\n check {\n name = \"cAdvisor Check Live\"\n type = \"http\"\n path = \"/metrics\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # https://www.nomadproject.io/docs/job-specification/resources\n #\n resources {\n cpu = 500\n # The network stanza specifies the networking requirements for the task\n # group, including the network mode and port allocations. When scheduling\n # jobs in Nomad they are provisioned across your fleet of machines along\n # with other jobs and services. Because you don't know in advance what host\n # your job will be provisioned on, Nomad will provide your tasks with\n # network configuration when they start up.\n #\n # https://www.nomadproject.io/docs/job-specification/network\n #\n network {\n port \"${cadvisor_service_name}\" {\n static = ${cadvisor_port}\n }\n }\n }\n }\n }\n\n group \"prod-group1-exporter-arm64\" {\n # The constraint allows restricting the set of eligible nodes. Constraints\n # may filter on attributes or client metadata.\n #\n # https://www.nomadproject.io/docs/job-specification/constraint\n #\n constraint {\n attribute = \"$${attr.cpu.arch}\"\n operator = \"==\"\n value = \"arm64\"\n }\n\n # The \"task\" stanza creates an individual unit of work, such as a Docker\n # container, web application, or batch processing.\n #\n # https://www.nomadproject.io/docs/job-specification/task\n #\n task \"prod-task1-${node_service_name}-arm64\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"raw_exec\"\n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n command = \"local/node_exporter-${node_version}.linux-arm64/node_exporter\"\n }\n\n # The artifact stanza instructs Nomad to fetch and unpack a remote resource,\n # such as a file, tarball, or binary. Nomad downloads artifacts using the\n # popular go-getter library, which permits downloading artifacts from a\n # variety of locations using a URL as the input source.\n #\n # https://www.nomadproject.io/docs/job-specification/artifact\n #\n artifact {\n source = \"${node_url_arm64}\"\n }\n\n # The service stanza instructs Nomad to register a service with Consul.\n #\n # https://www.nomadproject.io/docs/job-specification/service\n #\n service {\n name = \"${node_service_name}\"\n port = \"${node_service_name}\"\n check {\n name = \"Node Exporter Check Live\"\n type = \"http\"\n path = \"/metrics\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # https://www.nomadproject.io/docs/job-specification/resources\n #\n resources {\n cpu = 500\n # The network stanza specifies the networking requirements for the task\n # group, including the network mode and port allocations. When scheduling\n # jobs in Nomad they are provisioned across your fleet of machines along\n # with other jobs and services. Because you don't know in advance what host\n # your job will be provisioned on, Nomad will provide your tasks with\n # network configuration when they start up.\n #\n # https://www.nomadproject.io/docs/job-specification/network\n #\n network {\n port \"${node_service_name}\" {\n static = ${node_port}\n }\n }\n }\n }\n\n task \"prod-task2-${blackbox_service_name}-arm64\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"exec\"\n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n command = \"local/blackbox_exporter-${blackbox_version}.linux-arm64/blackbox_exporter\"\n args = [\n \"--config.file=secrets/blackbox.yml\"\n ]\n }\n\n # The \"template\" stanza instructs Nomad to manage a template, such as\n # a configuration file or script. This template can optionally pull data\n # from Consul or Vault to populate runtime configuration data.\n #\n # https://www.nomadproject.io/docs/job-specification/template\n #\n template {\n change_mode = \"noop\"\n change_signal = \"SIGINT\"\n destination = \"secrets/blackbox.yml\"\n data = \u003c\u003cEOH\nmodules:\n http_2xx:\n prober: http\n timeout: 5s\n http:\n valid_http_versions: [\"HTTP/1.1\", \"HTTP/2.0\"]\n no_follow_redirects: false\n fail_if_ssl: false\n fail_if_not_ssl: true\n tls_config:\n insecure_skip_verify: false\n preferred_ip_protocol: \"ip4\"\n icmp_v4:\n prober: icmp\n timeout: 5s\n icmp:\n preferred_ip_protocol: \"ip4\"\n dns_udp:\n prober: dns\n timeout: 5s\n dns:\n query_name: \"jenkins.fd.io\"\n query_type: \"A\"\n valid_rcodes:\n - NOERROR\nEOH\n }\n\n # The artifact stanza instructs Nomad to fetch and unpack a remote resource,\n # such as a file, tarball, or binary. Nomad downloads artifacts using the\n # popular go-getter library, which permits downloading artifacts from a\n # variety of locations using a URL as the input source.\n #\n # https://www.nomadproject.io/docs/job-specification/artifact\n #\n artifact {\n source = \"${blackbox_url_arm64}\"\n }\n\n # The service stanza instructs Nomad to register a service with Consul.\n #\n # https://www.nomadproject.io/docs/job-specification/service\n #\n service {\n name = \"${blackbox_service_name}\"\n port = \"${blackbox_service_name}\"\n tags = [ \"${blackbox_service_name}$${NOMAD_ALLOC_INDEX}\" ]\n check {\n name = \"Blackbox Exporter Check Live\"\n type = \"http\"\n path = \"/metrics\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # https://www.nomadproject.io/docs/job-specification/resources\n #\n resources {\n cpu = 500\n # The network stanza specifies the networking requirements for the task\n # group, including the network mode and port allocations. When scheduling\n # jobs in Nomad they are provisioned across your fleet of machines along\n # with other jobs and services. Because you don't know in advance what host\n # your job will be provisioned on, Nomad will provide your tasks with\n # network configuration when they start up.\n #\n # https://www.nomadproject.io/docs/job-specification/network\n #\n network {\n port \"${blackbox_service_name}\" {\n static = ${blackbox_port}\n }\n }\n }\n }\n\n task \"prod-task3-${cadvisor_service_name}-arm64\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"docker\"\n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n # There is currently no official release for arm yet...using community.\n image = \"zcube/cadvisor:latest\"\n volumes = [\n \"/:/rootfs:ro\",\n \"/var/run:/var/run:rw\",\n \"/sys:/sys:ro\",\n \"/var/lib/docker/:/var/lib/docker:ro\",\n \"/cgroup:/cgroup:ro\"\n ]\n }\n\n # The service stanza instructs Nomad to register a service with Consul.\n #\n # https://www.nomadproject.io/docs/job-specification/service\n #\n service {\n name = \"${cadvisor_service_name}\"\n port = \"${cadvisor_service_name}\"\n check {\n name = \"cAdvisor Check Live\"\n type = \"http\"\n path = \"/metrics\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # https://www.nomadproject.io/docs/job-specification/resources\n #\n resources {\n cpu = 500\n # The network stanza specifies the networking requirements for the task\n # group, including the network mode and port allocations. When scheduling\n # jobs in Nomad they are provisioned across your fleet of machines along\n # with other jobs and services. Because you don't know in advance what host\n # your job will be provisioned on, Nomad will provide your tasks with\n # network configuration when they start up.\n #\n # https://www.nomadproject.io/docs/job-specification/network\n #\n network {\n port \"${cadvisor_service_name}\" {\n static = ${cadvisor_port}\n }\n }\n }\n }\n }\n}", + "vars": { + "blackbox_port": "9115", + "blackbox_service_name": "blackboxexporter", + "blackbox_url_amd64": "https://github.com/prometheus/blackbox_exporter/releases/download/v0.18.0/blackbox_exporter-0.18.0.linux-amd64.tar.gz", + "blackbox_url_arm64": "https://github.com/prometheus/blackbox_exporter/releases/download/v0.18.0/blackbox_exporter-0.18.0.linux-arm64.tar.gz", + "blackbox_version": "0.18.0", + "cadvisor_image": "gcr.io/cadvisor/cadvisor:latest", + "cadvisor_port": "8080", + "cadvisor_service_name": "cadvisorexporter", + "datacenters": "yul1", + "job_name": "prod-exporter", + "node_port": "9100", + "node_service_name": "nodeexporter", + "node_url_amd64": "https://github.com/prometheus/node_exporter/releases/download/v1.0.1/node_exporter-1.0.1.linux-amd64.tar.gz", + "node_url_arm64": "https://github.com/prometheus/node_exporter/releases/download/v1.0.1/node_exporter-1.0.1.linux-arm64.tar.gz", + "node_version": "1.0.1", + "use_canary": "false" + } + }, + "sensitive_attributes": [] + } + ] + }, + { + "module": "module.exporter", + "mode": "managed", + "type": "nomad_job", + "name": "nomad_job_exporter", + "provider": "provider[\"registry.terraform.io/hashicorp/nomad\"].yul1", + "instances": [ + { + "schema_version": 0, + "attributes": { + "allocation_ids": [ + "e11d14cf-0b12-7f11-f982-e75abb2fa245", + "be1d7792-8b38-0769-1899-4d78ac17d775", + "33190f8d-6b97-5a79-32c3-c2a48eb33cab", + "7b9a89f3-3094-73aa-de9e-b674cdf3962b", + "1b730294-e8c6-d330-72a6-7502ef6d8195", + "3b3932ce-d57e-d0c6-0d36-b32724d83a0f", + "d07855d6-29a8-dba5-92a8-bed5673c3b81", + "4ea7fa69-4819-5050-37ea-bbce995e994d", + "2c694f1a-fb0e-67b9-407a-dd5f1d72daa0", + "52e828d4-79a7-9e43-2cdb-1ba6088f3257", + "e23fc3eb-1699-e1e8-629b-82a21b72ecf4", + "6f83b8c0-4313-eb5a-9c22-e8db2226e832", + "15ee749c-07f0-2864-f907-919faa62cee2", + "12025e7c-4a27-9a9b-b0aa-a205179139eb", + "a6234b96-8c7b-1fd4-e85f-d361774d3005", + "fadf8b49-0e1c-98ea-42b5-119667fa092e", + "2cb8905c-3d36-878d-917e-493f8a982970", + "a1426c7b-a4a1-0f19-cc11-162b396e9ce9", + "f24eee7b-e480-3386-9a6e-357edb9ae137", + "7b7c32b2-9cc9-bb99-b203-2842e4495f5c" + ], + "datacenters": [ + "yul1" + ], + "deployment_id": "", + "deployment_status": "", + "deregister_on_destroy": true, + "deregister_on_id_change": true, + "detach": false, + "id": "prod-exporter", + "jobspec": "job \"prod-exporter\" {\n # The \"region\" parameter specifies the region in which to execute the job.\n # If omitted, this inherits the default region name of \"global\".\n # region = \"global\"\n #\n # The \"datacenters\" parameter specifies the list of datacenters which should\n # be considered when placing this task. This must be provided.\n datacenters = \"yul1\"\n\n # The \"type\" parameter controls the type of job, which impacts the scheduler's\n # decision on placement. This configuration is optional and defaults to\n # \"service\". For a full list of job types and their differences, please see\n # the online documentation.\n #\n # https://www.nomadproject.io/docs/jobspec/schedulers\n #\n type = \"system\"\n\n update {\n # The \"max_parallel\" parameter specifies the maximum number of updates to\n # perform in parallel. In this case, this specifies to update a single task\n # at a time.\n max_parallel = 1\n\n health_check = \"checks\"\n\n # The \"min_healthy_time\" parameter specifies the minimum time the allocation\n # must be in the healthy state before it is marked as healthy and unblocks\n # further allocations from being updated.\n min_healthy_time = \"10s\"\n\n # The \"healthy_deadline\" parameter specifies the deadline in which the\n # allocation must be marked as healthy after which the allocation is\n # automatically transitioned to unhealthy. Transitioning to unhealthy will\n # fail the deployment and potentially roll back the job if \"auto_revert\" is\n # set to true.\n healthy_deadline = \"3m\"\n\n # The \"progress_deadline\" parameter specifies the deadline in which an\n # allocation must be marked as healthy. The deadline begins when the first\n # allocation for the deployment is created and is reset whenever an allocation\n # as part of the deployment transitions to a healthy state. If no allocation\n # transitions to the healthy state before the progress deadline, the\n # deployment is marked as failed.\n progress_deadline = \"10m\"\n\n\n }\n\n # The \"group\" stanza defines a series of tasks that should be co-located on\n # the same Nomad client. Any task within a group will be placed on the same\n # client.\n #\n # https://www.nomadproject.io/docs/job-specification/group\n #\n group \"prod-group1-exporter-amd64\" {\n # The constraint allows restricting the set of eligible nodes. Constraints\n # may filter on attributes or client metadata.\n #\n # https://www.nomadproject.io/docs/job-specification/constraint\n #\n constraint {\n attribute = \"${attr.cpu.arch}\"\n operator = \"!=\"\n value = \"arm64\"\n }\n\n # The \"task\" stanza creates an individual unit of work, such as a Docker\n # container, web application, or batch processing.\n #\n # https://www.nomadproject.io/docs/job-specification/task\n #\n task \"prod-task1-nodeexporter-amd64\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"raw_exec\"\n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n command = \"local/node_exporter-1.0.1.linux-amd64/node_exporter\"\n }\n\n # The artifact stanza instructs Nomad to fetch and unpack a remote resource,\n # such as a file, tarball, or binary. Nomad downloads artifacts using the\n # popular go-getter library, which permits downloading artifacts from a\n # variety of locations using a URL as the input source.\n #\n # https://www.nomadproject.io/docs/job-specification/artifact\n #\n artifact {\n source = \"https://github.com/prometheus/node_exporter/releases/download/v1.0.1/node_exporter-1.0.1.linux-amd64.tar.gz\"\n }\n\n # The service stanza instructs Nomad to register a service with Consul.\n #\n # https://www.nomadproject.io/docs/job-specification/service\n #\n service {\n name = \"nodeexporter\"\n port = \"nodeexporter\"\n check {\n name = \"Node Exporter Check Live\"\n type = \"http\"\n path = \"/metrics\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # https://www.nomadproject.io/docs/job-specification/resources\n #\n resources {\n cpu = 500\n # The network stanza specifies the networking requirements for the task\n # group, including the network mode and port allocations. When scheduling\n # jobs in Nomad they are provisioned across your fleet of machines along\n # with other jobs and services. Because you don't know in advance what host\n # your job will be provisioned on, Nomad will provide your tasks with\n # network configuration when they start up.\n #\n # https://www.nomadproject.io/docs/job-specification/network\n #\n network {\n port \"nodeexporter\" {\n static = 9100\n }\n }\n }\n }\n task \"prod-task2-blackboxexporter-amd64\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"exec\"\n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n command = \"local/blackbox_exporter-0.18.0.linux-amd64/blackbox_exporter\"\n args = [\n \"--config.file=secrets/blackbox.yml\"\n ]\n }\n\n # The \"template\" stanza instructs Nomad to manage a template, such as\n # a configuration file or script. This template can optionally pull data\n # from Consul or Vault to populate runtime configuration data.\n #\n # https://www.nomadproject.io/docs/job-specification/template\n #\n template {\n change_mode = \"noop\"\n change_signal = \"SIGINT\"\n destination = \"secrets/blackbox.yml\"\n data = \u003c\u003cEOH\nmodules:\n http_2xx:\n prober: http\n timeout: 5s\n http:\n valid_http_versions: [\"HTTP/1.1\", \"HTTP/2.0\"]\n no_follow_redirects: false\n fail_if_ssl: false\n fail_if_not_ssl: true\n tls_config:\n insecure_skip_verify: false\n preferred_ip_protocol: \"ip4\"\n icmp_v4:\n prober: icmp\n timeout: 5s\n icmp:\n preferred_ip_protocol: \"ip4\"\n dns_udp:\n prober: dns\n timeout: 5s\n dns:\n query_name: \"jenkins.fd.io\"\n query_type: \"A\"\n valid_rcodes:\n - NOERROR\nEOH\n }\n\n # The artifact stanza instructs Nomad to fetch and unpack a remote resource,\n # such as a file, tarball, or binary. Nomad downloads artifacts using the\n # popular go-getter library, which permits downloading artifacts from a\n # variety of locations using a URL as the input source.\n #\n # https://www.nomadproject.io/docs/job-specification/artifact\n #\n artifact {\n source = \"https://github.com/prometheus/blackbox_exporter/releases/download/v0.18.0/blackbox_exporter-0.18.0.linux-amd64.tar.gz\"\n }\n\n # The service stanza instructs Nomad to register a service with Consul.\n #\n # https://www.nomadproject.io/docs/job-specification/service\n #\n service {\n name = \"blackboxexporter\"\n port = \"blackboxexporter\"\n tags = [ \"blackboxexporter${NOMAD_ALLOC_INDEX}\" ]\n check {\n name = \"Blackbox Exporter Check Live\"\n type = \"http\"\n path = \"/metrics\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # https://www.nomadproject.io/docs/job-specification/resources\n #\n resources {\n cpu = 500\n # The network stanza specifies the networking requirements for the task\n # group, including the network mode and port allocations. When scheduling\n # jobs in Nomad they are provisioned across your fleet of machines along\n # with other jobs and services. Because you don't know in advance what host\n # your job will be provisioned on, Nomad will provide your tasks with\n # network configuration when they start up.\n #\n # https://www.nomadproject.io/docs/job-specification/network\n #\n network {\n port \"blackboxexporter\" {\n static = 9115\n }\n }\n }\n }\n\n task \"prod-task3-cadvisorexporter-amd64\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"docker\"\n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n image = \"gcr.io/cadvisor/cadvisor:latest\"\n volumes = [\n \"/:/rootfs:ro\",\n \"/var/run:/var/run:rw\",\n \"/sys:/sys:ro\",\n \"/var/lib/docker/:/var/lib/docker:ro\",\n \"/cgroup:/cgroup:ro\"\n ]\n }\n\n # The service stanza instructs Nomad to register a service with Consul.\n #\n # https://www.nomadproject.io/docs/job-specification/service\n #\n service {\n name = \"cadvisorexporter\"\n port = \"cadvisorexporter\"\n check {\n name = \"cAdvisor Check Live\"\n type = \"http\"\n path = \"/metrics\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # https://www.nomadproject.io/docs/job-specification/resources\n #\n resources {\n cpu = 500\n # The network stanza specifies the networking requirements for the task\n # group, including the network mode and port allocations. When scheduling\n # jobs in Nomad they are provisioned across your fleet of machines along\n # with other jobs and services. Because you don't know in advance what host\n # your job will be provisioned on, Nomad will provide your tasks with\n # network configuration when they start up.\n #\n # https://www.nomadproject.io/docs/job-specification/network\n #\n network {\n port \"cadvisorexporter\" {\n static = 8080\n }\n }\n }\n }\n }\n\n group \"prod-group1-exporter-arm64\" {\n # The constraint allows restricting the set of eligible nodes. Constraints\n # may filter on attributes or client metadata.\n #\n # https://www.nomadproject.io/docs/job-specification/constraint\n #\n constraint {\n attribute = \"${attr.cpu.arch}\"\n operator = \"==\"\n value = \"arm64\"\n }\n\n # The \"task\" stanza creates an individual unit of work, such as a Docker\n # container, web application, or batch processing.\n #\n # https://www.nomadproject.io/docs/job-specification/task\n #\n task \"prod-task1-nodeexporter-arm64\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"raw_exec\"\n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n command = \"local/node_exporter-1.0.1.linux-arm64/node_exporter\"\n }\n\n # The artifact stanza instructs Nomad to fetch and unpack a remote resource,\n # such as a file, tarball, or binary. Nomad downloads artifacts using the\n # popular go-getter library, which permits downloading artifacts from a\n # variety of locations using a URL as the input source.\n #\n # https://www.nomadproject.io/docs/job-specification/artifact\n #\n artifact {\n source = \"https://github.com/prometheus/node_exporter/releases/download/v1.0.1/node_exporter-1.0.1.linux-arm64.tar.gz\"\n }\n\n # The service stanza instructs Nomad to register a service with Consul.\n #\n # https://www.nomadproject.io/docs/job-specification/service\n #\n service {\n name = \"nodeexporter\"\n port = \"nodeexporter\"\n check {\n name = \"Node Exporter Check Live\"\n type = \"http\"\n path = \"/metrics\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # https://www.nomadproject.io/docs/job-specification/resources\n #\n resources {\n cpu = 500\n # The network stanza specifies the networking requirements for the task\n # group, including the network mode and port allocations. When scheduling\n # jobs in Nomad they are provisioned across your fleet of machines along\n # with other jobs and services. Because you don't know in advance what host\n # your job will be provisioned on, Nomad will provide your tasks with\n # network configuration when they start up.\n #\n # https://www.nomadproject.io/docs/job-specification/network\n #\n network {\n port \"nodeexporter\" {\n static = 9100\n }\n }\n }\n }\n\n task \"prod-task2-blackboxexporter-arm64\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"exec\"\n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n command = \"local/blackbox_exporter-0.18.0.linux-arm64/blackbox_exporter\"\n args = [\n \"--config.file=secrets/blackbox.yml\"\n ]\n }\n\n # The \"template\" stanza instructs Nomad to manage a template, such as\n # a configuration file or script. This template can optionally pull data\n # from Consul or Vault to populate runtime configuration data.\n #\n # https://www.nomadproject.io/docs/job-specification/template\n #\n template {\n change_mode = \"noop\"\n change_signal = \"SIGINT\"\n destination = \"secrets/blackbox.yml\"\n data = \u003c\u003cEOH\nmodules:\n http_2xx:\n prober: http\n timeout: 5s\n http:\n valid_http_versions: [\"HTTP/1.1\", \"HTTP/2.0\"]\n no_follow_redirects: false\n fail_if_ssl: false\n fail_if_not_ssl: true\n tls_config:\n insecure_skip_verify: false\n preferred_ip_protocol: \"ip4\"\n icmp_v4:\n prober: icmp\n timeout: 5s\n icmp:\n preferred_ip_protocol: \"ip4\"\n dns_udp:\n prober: dns\n timeout: 5s\n dns:\n query_name: \"jenkins.fd.io\"\n query_type: \"A\"\n valid_rcodes:\n - NOERROR\nEOH\n }\n\n # The artifact stanza instructs Nomad to fetch and unpack a remote resource,\n # such as a file, tarball, or binary. Nomad downloads artifacts using the\n # popular go-getter library, which permits downloading artifacts from a\n # variety of locations using a URL as the input source.\n #\n # https://www.nomadproject.io/docs/job-specification/artifact\n #\n artifact {\n source = \"https://github.com/prometheus/blackbox_exporter/releases/download/v0.18.0/blackbox_exporter-0.18.0.linux-arm64.tar.gz\"\n }\n\n # The service stanza instructs Nomad to register a service with Consul.\n #\n # https://www.nomadproject.io/docs/job-specification/service\n #\n service {\n name = \"blackboxexporter\"\n port = \"blackboxexporter\"\n tags = [ \"blackboxexporter${NOMAD_ALLOC_INDEX}\" ]\n check {\n name = \"Blackbox Exporter Check Live\"\n type = \"http\"\n path = \"/metrics\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # https://www.nomadproject.io/docs/job-specification/resources\n #\n resources {\n cpu = 500\n # The network stanza specifies the networking requirements for the task\n # group, including the network mode and port allocations. When scheduling\n # jobs in Nomad they are provisioned across your fleet of machines along\n # with other jobs and services. Because you don't know in advance what host\n # your job will be provisioned on, Nomad will provide your tasks with\n # network configuration when they start up.\n #\n # https://www.nomadproject.io/docs/job-specification/network\n #\n network {\n port \"blackboxexporter\" {\n static = 9115\n }\n }\n }\n }\n\n task \"prod-task3-cadvisorexporter-arm64\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"docker\"\n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n # There is currently no official release for arm yet...using community.\n image = \"zcube/cadvisor:latest\"\n volumes = [\n \"/:/rootfs:ro\",\n \"/var/run:/var/run:rw\",\n \"/sys:/sys:ro\",\n \"/var/lib/docker/:/var/lib/docker:ro\",\n \"/cgroup:/cgroup:ro\"\n ]\n }\n\n # The service stanza instructs Nomad to register a service with Consul.\n #\n # https://www.nomadproject.io/docs/job-specification/service\n #\n service {\n name = \"cadvisorexporter\"\n port = \"cadvisorexporter\"\n check {\n name = \"cAdvisor Check Live\"\n type = \"http\"\n path = \"/metrics\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # https://www.nomadproject.io/docs/job-specification/resources\n #\n resources {\n cpu = 500\n # The network stanza specifies the networking requirements for the task\n # group, including the network mode and port allocations. When scheduling\n # jobs in Nomad they are provisioned across your fleet of machines along\n # with other jobs and services. Because you don't know in advance what host\n # your job will be provisioned on, Nomad will provide your tasks with\n # network configuration when they start up.\n #\n # https://www.nomadproject.io/docs/job-specification/network\n #\n network {\n port \"cadvisorexporter\" {\n static = 8080\n }\n }\n }\n }\n }\n}", + "json": null, + "modify_index": "7147927", + "name": "prod-exporter", + "namespace": "default", + "policy_override": null, + "purge_on_destroy": null, + "region": "global", + "task_groups": [ + { + "count": 1, + "meta": {}, + "name": "prod-group1-exporter-amd64", + "task": [ + { + "driver": "raw_exec", + "meta": {}, + "name": "prod-task1-nodeexporter-amd64", + "volume_mounts": [] + }, + { + "driver": "exec", + "meta": {}, + "name": "prod-task2-blackboxexporter-amd64", + "volume_mounts": [] + }, + { + "driver": "docker", + "meta": {}, + "name": "prod-task3-cadvisorexporter-amd64", + "volume_mounts": [] + } + ], + "volumes": [] + }, + { + "count": 1, + "meta": {}, + "name": "prod-group1-exporter-arm64", + "task": [ + { + "driver": "raw_exec", + "meta": {}, + "name": "prod-task1-nodeexporter-arm64", + "volume_mounts": [] + }, + { + "driver": "exec", + "meta": {}, + "name": "prod-task2-blackboxexporter-arm64", + "volume_mounts": [] + }, + { + "driver": "docker", + "meta": {}, + "name": "prod-task3-cadvisorexporter-arm64", + "volume_mounts": [] + } + ], + "volumes": [] + } + ], + "type": "system" + }, + "sensitive_attributes": [], + "private": "bnVsbA==", + "dependencies": [ + "module.exporter.data.template_file.nomad_job_exporter" + ] + } + ] + }, + { + "module": "module.grafana", + "mode": "data", + "type": "template_file", + "name": "nomad_job_grafana", + "provider": "provider[\"registry.terraform.io/hashicorp/template\"]", + "instances": [ + { + "schema_version": 0, + "attributes": { + "filename": null, + "id": "080a6dd88248c6a78ec3025a0ec9e471aed9acde495ca47db868b0893b4446b7", + "rendered": "job \"prod-grafana\" {\n # The \"region\" parameter specifies the region in which to execute the job.\n # If omitted, this inherits the default region name of \"global\".\n # region = \"global\"\n #\n # The \"datacenters\" parameter specifies the list of datacenters which should\n # be considered when placing this task. This must be provided.\n datacenters = \"yul1\"\n\n # The \"type\" parameter controls the type of job, which impacts the scheduler's\n # decision on placement. This configuration is optional and defaults to\n # \"service\". For a full list of job types and their differences, please see\n # the online documentation.\n #\n # For more information, please see the online documentation at:\n #\n # https://www.nomadproject.io/docs/jobspec/schedulers\n #\n type = \"service\"\n\n update {\n # The \"max_parallel\" parameter specifies the maximum number of updates to\n # perform in parallel. In this case, this specifies to update a single task\n # at a time.\n max_parallel = 1\n\n health_check = \"checks\"\n\n # The \"min_healthy_time\" parameter specifies the minimum time the allocation\n # must be in the healthy state before it is marked as healthy and unblocks\n # further allocations from being updated.\n min_healthy_time = \"10s\"\n\n # The \"healthy_deadline\" parameter specifies the deadline in which the\n # allocation must be marked as healthy after which the allocation is\n # automatically transitioned to unhealthy. Transitioning to unhealthy will\n # fail the deployment and potentially roll back the job if \"auto_revert\" is\n # set to true.\n healthy_deadline = \"3m\"\n\n # The \"progress_deadline\" parameter specifies the deadline in which an\n # allocation must be marked as healthy. The deadline begins when the first\n # allocation for the deployment is created and is reset whenever an allocation\n # as part of the deployment transitions to a healthy state. If no allocation\n # transitions to the healthy state before the progress deadline, the\n # deployment is marked as failed.\n progress_deadline = \"10m\"\n\n\n # The \"canary\" parameter specifies that changes to the job that would result\n # in destructive updates should create the specified number of canaries\n # without stopping any previous allocations. Once the operator determines the\n # canaries are healthy, they can be promoted which unblocks a rolling update\n # of the remaining allocations at a rate of \"max_parallel\".\n #\n # Further, setting \"canary\" equal to the count of the task group allows\n # blue/green deployments. When the job is updated, a full set of the new\n # version is deployed and upon promotion the old version is stopped.\n canary = 1\n\n # Specifies if the job should auto-promote to the canary version when all\n # canaries become healthy during a deployment. Defaults to false which means\n # canaries must be manually updated with the nomad deployment promote\n # command.\n auto_promote = true\n\n # The \"auto_revert\" parameter specifies if the job should auto-revert to the\n # last stable job on deployment failure. A job is marked as stable if all the\n # allocations as part of its deployment were marked healthy.\n auto_revert = true\n\n }\n\n # The \"group\" stanza defines a series of tasks that should be co-located on\n # the same Nomad client. Any task within a group will be placed on the same\n # client.\n #\n # For more information and examples on the \"group\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/group\n #\n group \"prod-group1-grafana\" {\n # The \"count\" parameter specifies the number of the task groups that should\n # be running under this group. This value must be non-negative and defaults\n # to 1.\n count = 1\n\n\n # The constraint allows restricting the set of eligible nodes. Constraints\n # may filter on attributes or client metadata.\n #\n # For more information and examples on the \"volume\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/constraint\n #\n constraint {\n attribute = \"${attr.cpu.arch}\"\n operator = \"!=\"\n value = \"arm64\"\n }\n\n # The \"task\" stanza creates an individual unit of work, such as a Docker\n # container, web application, or batch processing.\n #\n # For more information and examples on the \"task\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/task\n #\n task \"prod-task1-grafana\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"docker\"\n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n image = \"grafana/grafana:7.3.7\"\n dns_servers = [ \"${attr.unique.network.ip-address}\" ]\n volumes = [\n \"secrets/prometheus.yml:/etc/grafana/provisioning/datasources/prometheus.yml\",\n \"secrets/dashboards.yml:/etc/grafana/provisioning/dashboards/dashboards.yml\",\n \"secrets/grafana.ini:/etc/grafana/grafana.ini\",\n \"secrets/node_exporter.json:/etc/grafana/provisioning/dashboards/node_exporter.json\",\n \"secrets/docker_cadvisor.json:/etc/grafana/provisioning/dashboards/docker_cadvisor.json\",\n \"secrets/nomad.json:/etc/grafana/provisioning/dashboards/nomad.json\",\n \"secrets/consul.json:/etc/grafana/provisioning/dashboards/consul.json\",\n \"secrets/prometheus.json:/etc/grafana/provisioning/dashboards/prometheus.json\",\n \"secrets/blackbox_exporter_http.json:/etc/grafana/provisioning/dashboards/blackbox_exporter_http.json\",\n \"secrets/blackbox_exporter_icmp.json:/etc/grafana/provisioning/dashboards/blackbox_exporter_icmp.json\"\n ]\n }\n\n artifact {\n # Prometheus Node Exporter\n source = \"https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/node_exporter.json\"\n destination = \"secrets/\"\n }\n\n artifact {\n # Docker cAdvisor\n source = \"https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/docker_cadvisor.json\"\n destination = \"secrets/\"\n }\n\n artifact {\n # Nomad\n source = \"https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/nomad.json\"\n destination = \"secrets/\"\n }\n\n artifact {\n # Consul\n source = \"https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/consul.json\"\n destination = \"secrets/\"\n }\n\n artifact {\n # Prometheus\n source = \"https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/prometheus.json\"\n destination = \"secrets/\"\n }\n\n artifact {\n # Prometheus Blackbox Exporter ICMP\n source = \"https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/blackbox_exporter_icmp.json\"\n destination = \"secrets/\"\n }\n\n artifact {\n # Prometheus Blackbox Exporter HTTP\n source = \"https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/blackbox_exporter_http.json\"\n destination = \"secrets/\"\n }\n\n # The \"template\" stanza instructs Nomad to manage a template, such as\n # a configuration file or script. This template can optionally pull data\n # from Consul or Vault to populate runtime configuration data.\n #\n # For more information and examples on the \"template\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/template\n #\n template {\n change_mode = \"noop\"\n change_signal = \"SIGINT\"\n destination = \"secrets/prometheus.yml\"\n data = \u003c\u003cEOH\napiVersion: 1\ndatasources:\n- name: Prometheus\n type: prometheus\n access: direct\n orgId: 1\n url: http://prometheus.service.consul:9090\n basicAuth: false\n isDefault: true\n version: 1\n editable: false\nEOH\n }\n\n template {\n change_mode = \"noop\"\n change_signal = \"SIGINT\"\n destination = \"secrets/dashboards.yml\"\n data = \u003c\u003cEOH\napiVersion: 1\nproviders:\n- name: dashboards\n type: file\n disableDeletion: false\n updateIntervalSeconds: 10\n allowUiUpdates: false\n options:\n path: /etc/grafana/provisioning/dashboards\n foldersFromFilesStructure: true\nEOH\n }\n\n template {\n change_mode = \"noop\"\n change_signal = \"SIGINT\"\n destination = \"secrets/grafana.ini\"\n data = \u003c\u003cEOH\napp_mode = production\n\n[metrics]\nenabled = true\n\n[server]\nprotocol = http\nhttp_port = 3000\nroot_url = http://grafana.service.consul:3000\nenable_gzip = true\n;cert_file =\n;cert_key =\n\n[security]\nadmin_user = grafanauser\nadmin_password = Grafana1234\nsecret_key = SW2YcwTIb9zpOOhoPsMm\n\n[users]\nallow_sign_up = false\nallow_org_create = false\nauto_assign_org = true\nauto_assign_org_role = Viewer\ndefault_theme = dark\n\n[auth.basic]\nenabled = true\n\n[auth]\ndisable_login_form = false\ndisable_signout_menu = false\n\n[auth.anonymous]\nenabled = false\n\n[log]\nmode = console\nlevel = info\n\n[log.console]\nlevel = info\nformat = console\nEOH\n }\n\n # The service stanza instructs Nomad to register a service with Consul.\n #\n # For more information and examples on the \"task\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/service\n #\n service {\n name = \"grafana\"\n port = \"grafana\"\n tags = [ \"grafana${NOMAD_ALLOC_INDEX}\" ]\n check {\n name = \"Grafana Check Live\"\n type = \"http\"\n protocol = \"http\"\n tls_skip_verify = true\n path = \"/api/health\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # For more information and examples on the \"resources\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/resources\n #\n resources {\n cpu = 2000\n memory = 2048\n # The network stanza specifies the networking requirements for the task\n # group, including the network mode and port allocations. When scheduling\n # jobs in Nomad they are provisioned across your fleet of machines along\n # with other jobs and services. Because you don't know in advance what host\n # your job will be provisioned on, Nomad will provide your tasks with\n # network configuration when they start up.\n #\n # For more information and examples on the \"template\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/network\n #\n network {\n port \"grafana\" {\n static = 3000\n }\n }\n }\n }\n }\n}", + "template": "job \"${job_name}\" {\n # The \"region\" parameter specifies the region in which to execute the job.\n # If omitted, this inherits the default region name of \"global\".\n # region = \"global\"\n #\n # The \"datacenters\" parameter specifies the list of datacenters which should\n # be considered when placing this task. This must be provided.\n datacenters = \"${datacenters}\"\n\n # The \"type\" parameter controls the type of job, which impacts the scheduler's\n # decision on placement. This configuration is optional and defaults to\n # \"service\". For a full list of job types and their differences, please see\n # the online documentation.\n #\n # For more information, please see the online documentation at:\n #\n # https://www.nomadproject.io/docs/jobspec/schedulers\n #\n type = \"service\"\n\n update {\n # The \"max_parallel\" parameter specifies the maximum number of updates to\n # perform in parallel. In this case, this specifies to update a single task\n # at a time.\n max_parallel = 1\n\n health_check = \"checks\"\n\n # The \"min_healthy_time\" parameter specifies the minimum time the allocation\n # must be in the healthy state before it is marked as healthy and unblocks\n # further allocations from being updated.\n min_healthy_time = \"10s\"\n\n # The \"healthy_deadline\" parameter specifies the deadline in which the\n # allocation must be marked as healthy after which the allocation is\n # automatically transitioned to unhealthy. Transitioning to unhealthy will\n # fail the deployment and potentially roll back the job if \"auto_revert\" is\n # set to true.\n healthy_deadline = \"3m\"\n\n # The \"progress_deadline\" parameter specifies the deadline in which an\n # allocation must be marked as healthy. The deadline begins when the first\n # allocation for the deployment is created and is reset whenever an allocation\n # as part of the deployment transitions to a healthy state. If no allocation\n # transitions to the healthy state before the progress deadline, the\n # deployment is marked as failed.\n progress_deadline = \"10m\"\n\n%{ if use_canary }\n # The \"canary\" parameter specifies that changes to the job that would result\n # in destructive updates should create the specified number of canaries\n # without stopping any previous allocations. Once the operator determines the\n # canaries are healthy, they can be promoted which unblocks a rolling update\n # of the remaining allocations at a rate of \"max_parallel\".\n #\n # Further, setting \"canary\" equal to the count of the task group allows\n # blue/green deployments. When the job is updated, a full set of the new\n # version is deployed and upon promotion the old version is stopped.\n canary = 1\n\n # Specifies if the job should auto-promote to the canary version when all\n # canaries become healthy during a deployment. Defaults to false which means\n # canaries must be manually updated with the nomad deployment promote\n # command.\n auto_promote = true\n\n # The \"auto_revert\" parameter specifies if the job should auto-revert to the\n # last stable job on deployment failure. A job is marked as stable if all the\n # allocations as part of its deployment were marked healthy.\n auto_revert = true\n%{ endif }\n }\n\n # The \"group\" stanza defines a series of tasks that should be co-located on\n # the same Nomad client. Any task within a group will be placed on the same\n # client.\n #\n # For more information and examples on the \"group\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/group\n #\n group \"prod-group1-${service_name}\" {\n # The \"count\" parameter specifies the number of the task groups that should\n # be running under this group. This value must be non-negative and defaults\n # to 1.\n count = ${group_count}\n\n\n # The constraint allows restricting the set of eligible nodes. Constraints\n # may filter on attributes or client metadata.\n #\n # For more information and examples on the \"volume\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/constraint\n #\n constraint {\n attribute = \"$${attr.cpu.arch}\"\n operator = \"!=\"\n value = \"arm64\"\n }\n\n # The \"task\" stanza creates an individual unit of work, such as a Docker\n # container, web application, or batch processing.\n #\n # For more information and examples on the \"task\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/task\n #\n task \"prod-task1-${service_name}\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"docker\"\n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n image = \"${image}\"\n dns_servers = [ \"$${attr.unique.network.ip-address}\" ]\n volumes = [\n \"secrets/prometheus.yml:/etc/grafana/provisioning/datasources/prometheus.yml\",\n \"secrets/dashboards.yml:/etc/grafana/provisioning/dashboards/dashboards.yml\",\n \"secrets/grafana.ini:/etc/grafana/grafana.ini\",\n \"secrets/node_exporter.json:/etc/grafana/provisioning/dashboards/node_exporter.json\",\n \"secrets/docker_cadvisor.json:/etc/grafana/provisioning/dashboards/docker_cadvisor.json\",\n \"secrets/nomad.json:/etc/grafana/provisioning/dashboards/nomad.json\",\n \"secrets/consul.json:/etc/grafana/provisioning/dashboards/consul.json\",\n \"secrets/prometheus.json:/etc/grafana/provisioning/dashboards/prometheus.json\",\n \"secrets/blackbox_exporter_http.json:/etc/grafana/provisioning/dashboards/blackbox_exporter_http.json\",\n \"secrets/blackbox_exporter_icmp.json:/etc/grafana/provisioning/dashboards/blackbox_exporter_icmp.json\"\n ]\n }\n\n artifact {\n # Prometheus Node Exporter\n source = \"https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/node_exporter.json\"\n destination = \"secrets/\"\n }\n\n artifact {\n # Docker cAdvisor\n source = \"https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/docker_cadvisor.json\"\n destination = \"secrets/\"\n }\n\n artifact {\n # Nomad\n source = \"https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/nomad.json\"\n destination = \"secrets/\"\n }\n\n artifact {\n # Consul\n source = \"https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/consul.json\"\n destination = \"secrets/\"\n }\n\n artifact {\n # Prometheus\n source = \"https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/prometheus.json\"\n destination = \"secrets/\"\n }\n\n artifact {\n # Prometheus Blackbox Exporter ICMP\n source = \"https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/blackbox_exporter_icmp.json\"\n destination = \"secrets/\"\n }\n\n artifact {\n # Prometheus Blackbox Exporter HTTP\n source = \"https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/blackbox_exporter_http.json\"\n destination = \"secrets/\"\n }\n\n # The \"template\" stanza instructs Nomad to manage a template, such as\n # a configuration file or script. This template can optionally pull data\n # from Consul or Vault to populate runtime configuration data.\n #\n # For more information and examples on the \"template\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/template\n #\n template {\n change_mode = \"noop\"\n change_signal = \"SIGINT\"\n destination = \"secrets/prometheus.yml\"\n data = \u003c\u003cEOH\napiVersion: 1\ndatasources:\n- name: Prometheus\n type: prometheus\n access: direct\n orgId: 1\n url: http://prometheus.service.consul:9090\n basicAuth: false\n isDefault: true\n version: 1\n editable: false\nEOH\n }\n\n template {\n change_mode = \"noop\"\n change_signal = \"SIGINT\"\n destination = \"secrets/dashboards.yml\"\n data = \u003c\u003cEOH\napiVersion: 1\nproviders:\n- name: dashboards\n type: file\n disableDeletion: false\n updateIntervalSeconds: 10\n allowUiUpdates: false\n options:\n path: /etc/grafana/provisioning/dashboards\n foldersFromFilesStructure: true\nEOH\n }\n\n template {\n change_mode = \"noop\"\n change_signal = \"SIGINT\"\n destination = \"secrets/grafana.ini\"\n data = \u003c\u003cEOH\napp_mode = production\n\n[metrics]\nenabled = true\n\n[server]\nprotocol = http\nhttp_port = ${port}\nroot_url = http://${service_name}.service.consul:${port}\nenable_gzip = true\n;cert_file =\n;cert_key =\n\n[security]\nadmin_user = grafanauser\nadmin_password = Grafana1234\nsecret_key = SW2YcwTIb9zpOOhoPsMm\n\n[users]\nallow_sign_up = false\nallow_org_create = false\nauto_assign_org = true\nauto_assign_org_role = Viewer\ndefault_theme = dark\n\n[auth.basic]\nenabled = true\n\n[auth]\ndisable_login_form = false\ndisable_signout_menu = false\n\n[auth.anonymous]\nenabled = false\n\n[log]\nmode = console\nlevel = info\n\n[log.console]\nlevel = info\nformat = console\nEOH\n }\n\n # The service stanza instructs Nomad to register a service with Consul.\n #\n # For more information and examples on the \"task\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/service\n #\n service {\n name = \"${service_name}\"\n port = \"${service_name}\"\n tags = [ \"${service_name}$${NOMAD_ALLOC_INDEX}\" ]\n check {\n name = \"Grafana Check Live\"\n type = \"http\"\n protocol = \"http\"\n tls_skip_verify = true\n path = \"/api/health\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # For more information and examples on the \"resources\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/resources\n #\n resources {\n cpu = ${cpu}\n memory = ${mem}\n # The network stanza specifies the networking requirements for the task\n # group, including the network mode and port allocations. When scheduling\n # jobs in Nomad they are provisioned across your fleet of machines along\n # with other jobs and services. Because you don't know in advance what host\n # your job will be provisioned on, Nomad will provide your tasks with\n # network configuration when they start up.\n #\n # For more information and examples on the \"template\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/network\n #\n network {\n port \"${service_name}\" {\n static = ${port}\n }\n }\n }\n }\n }\n}", + "vars": { + "cpu": "2000", + "datacenters": "yul1", + "group_count": "1", + "image": "grafana/grafana:7.3.7", + "job_name": "prod-grafana", + "mem": "2048", + "port": "3000", + "service_name": "grafana", + "use_canary": "true", + "use_vault_provider": "false" + } + }, + "sensitive_attributes": [] + } + ] + }, + { + "module": "module.grafana", + "mode": "managed", + "type": "nomad_job", + "name": "nomad_job_grafana", + "provider": "provider[\"registry.terraform.io/hashicorp/nomad\"].yul1", + "instances": [ + { + "schema_version": 0, + "attributes": { + "allocation_ids": [ + "1cf5f45a-3d10-b433-600e-f92696e49a25", + "d2ddca98-1bb8-680d-06f1-00fcf4887eca" + ], + "datacenters": [ + "yul1" + ], + "deployment_id": "fef8bdc5-f769-c504-f089-8886755e45ef", + "deployment_status": "successful", + "deregister_on_destroy": true, + "deregister_on_id_change": true, + "detach": false, + "id": "prod-grafana", + "jobspec": "job \"prod-grafana\" {\n # The \"region\" parameter specifies the region in which to execute the job.\n # If omitted, this inherits the default region name of \"global\".\n # region = \"global\"\n #\n # The \"datacenters\" parameter specifies the list of datacenters which should\n # be considered when placing this task. This must be provided.\n datacenters = \"yul1\"\n\n # The \"type\" parameter controls the type of job, which impacts the scheduler's\n # decision on placement. This configuration is optional and defaults to\n # \"service\". For a full list of job types and their differences, please see\n # the online documentation.\n #\n # For more information, please see the online documentation at:\n #\n # https://www.nomadproject.io/docs/jobspec/schedulers\n #\n type = \"service\"\n\n update {\n # The \"max_parallel\" parameter specifies the maximum number of updates to\n # perform in parallel. In this case, this specifies to update a single task\n # at a time.\n max_parallel = 1\n\n health_check = \"checks\"\n\n # The \"min_healthy_time\" parameter specifies the minimum time the allocation\n # must be in the healthy state before it is marked as healthy and unblocks\n # further allocations from being updated.\n min_healthy_time = \"10s\"\n\n # The \"healthy_deadline\" parameter specifies the deadline in which the\n # allocation must be marked as healthy after which the allocation is\n # automatically transitioned to unhealthy. Transitioning to unhealthy will\n # fail the deployment and potentially roll back the job if \"auto_revert\" is\n # set to true.\n healthy_deadline = \"3m\"\n\n # The \"progress_deadline\" parameter specifies the deadline in which an\n # allocation must be marked as healthy. The deadline begins when the first\n # allocation for the deployment is created and is reset whenever an allocation\n # as part of the deployment transitions to a healthy state. If no allocation\n # transitions to the healthy state before the progress deadline, the\n # deployment is marked as failed.\n progress_deadline = \"10m\"\n\n\n # The \"canary\" parameter specifies that changes to the job that would result\n # in destructive updates should create the specified number of canaries\n # without stopping any previous allocations. Once the operator determines the\n # canaries are healthy, they can be promoted which unblocks a rolling update\n # of the remaining allocations at a rate of \"max_parallel\".\n #\n # Further, setting \"canary\" equal to the count of the task group allows\n # blue/green deployments. When the job is updated, a full set of the new\n # version is deployed and upon promotion the old version is stopped.\n canary = 1\n\n # Specifies if the job should auto-promote to the canary version when all\n # canaries become healthy during a deployment. Defaults to false which means\n # canaries must be manually updated with the nomad deployment promote\n # command.\n auto_promote = true\n\n # The \"auto_revert\" parameter specifies if the job should auto-revert to the\n # last stable job on deployment failure. A job is marked as stable if all the\n # allocations as part of its deployment were marked healthy.\n auto_revert = true\n\n }\n\n # The \"group\" stanza defines a series of tasks that should be co-located on\n # the same Nomad client. Any task within a group will be placed on the same\n # client.\n #\n # For more information and examples on the \"group\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/group\n #\n group \"prod-group1-grafana\" {\n # The \"count\" parameter specifies the number of the task groups that should\n # be running under this group. This value must be non-negative and defaults\n # to 1.\n count = 1\n\n\n # The constraint allows restricting the set of eligible nodes. Constraints\n # may filter on attributes or client metadata.\n #\n # For more information and examples on the \"volume\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/constraint\n #\n constraint {\n attribute = \"${attr.cpu.arch}\"\n operator = \"!=\"\n value = \"arm64\"\n }\n\n # The \"task\" stanza creates an individual unit of work, such as a Docker\n # container, web application, or batch processing.\n #\n # For more information and examples on the \"task\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/task\n #\n task \"prod-task1-grafana\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"docker\"\n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n image = \"grafana/grafana:7.3.7\"\n dns_servers = [ \"${attr.unique.network.ip-address}\" ]\n volumes = [\n \"secrets/prometheus.yml:/etc/grafana/provisioning/datasources/prometheus.yml\",\n \"secrets/dashboards.yml:/etc/grafana/provisioning/dashboards/dashboards.yml\",\n \"secrets/grafana.ini:/etc/grafana/grafana.ini\",\n \"secrets/node_exporter.json:/etc/grafana/provisioning/dashboards/node_exporter.json\",\n \"secrets/docker_cadvisor.json:/etc/grafana/provisioning/dashboards/docker_cadvisor.json\",\n \"secrets/nomad.json:/etc/grafana/provisioning/dashboards/nomad.json\",\n \"secrets/consul.json:/etc/grafana/provisioning/dashboards/consul.json\",\n \"secrets/prometheus.json:/etc/grafana/provisioning/dashboards/prometheus.json\",\n \"secrets/blackbox_exporter_http.json:/etc/grafana/provisioning/dashboards/blackbox_exporter_http.json\",\n \"secrets/blackbox_exporter_icmp.json:/etc/grafana/provisioning/dashboards/blackbox_exporter_icmp.json\"\n ]\n }\n\n artifact {\n # Prometheus Node Exporter\n source = \"https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/node_exporter.json\"\n destination = \"secrets/\"\n }\n\n artifact {\n # Docker cAdvisor\n source = \"https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/docker_cadvisor.json\"\n destination = \"secrets/\"\n }\n\n artifact {\n # Nomad\n source = \"https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/nomad.json\"\n destination = \"secrets/\"\n }\n\n artifact {\n # Consul\n source = \"https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/consul.json\"\n destination = \"secrets/\"\n }\n\n artifact {\n # Prometheus\n source = \"https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/prometheus.json\"\n destination = \"secrets/\"\n }\n\n artifact {\n # Prometheus Blackbox Exporter ICMP\n source = \"https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/blackbox_exporter_icmp.json\"\n destination = \"secrets/\"\n }\n\n artifact {\n # Prometheus Blackbox Exporter HTTP\n source = \"https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/blackbox_exporter_http.json\"\n destination = \"secrets/\"\n }\n\n # The \"template\" stanza instructs Nomad to manage a template, such as\n # a configuration file or script. This template can optionally pull data\n # from Consul or Vault to populate runtime configuration data.\n #\n # For more information and examples on the \"template\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/template\n #\n template {\n change_mode = \"noop\"\n change_signal = \"SIGINT\"\n destination = \"secrets/prometheus.yml\"\n data = \u003c\u003cEOH\napiVersion: 1\ndatasources:\n- name: Prometheus\n type: prometheus\n access: direct\n orgId: 1\n url: http://prometheus.service.consul:9090\n basicAuth: false\n isDefault: true\n version: 1\n editable: false\nEOH\n }\n\n template {\n change_mode = \"noop\"\n change_signal = \"SIGINT\"\n destination = \"secrets/dashboards.yml\"\n data = \u003c\u003cEOH\napiVersion: 1\nproviders:\n- name: dashboards\n type: file\n disableDeletion: false\n updateIntervalSeconds: 10\n allowUiUpdates: false\n options:\n path: /etc/grafana/provisioning/dashboards\n foldersFromFilesStructure: true\nEOH\n }\n\n template {\n change_mode = \"noop\"\n change_signal = \"SIGINT\"\n destination = \"secrets/grafana.ini\"\n data = \u003c\u003cEOH\napp_mode = production\n\n[metrics]\nenabled = true\n\n[server]\nprotocol = http\nhttp_port = 3000\nroot_url = http://grafana.service.consul:3000\nenable_gzip = true\n;cert_file =\n;cert_key =\n\n[security]\nadmin_user = grafanauser\nadmin_password = Grafana1234\nsecret_key = SW2YcwTIb9zpOOhoPsMm\n\n[users]\nallow_sign_up = false\nallow_org_create = false\nauto_assign_org = true\nauto_assign_org_role = Viewer\ndefault_theme = dark\n\n[auth.basic]\nenabled = true\n\n[auth]\ndisable_login_form = false\ndisable_signout_menu = false\n\n[auth.anonymous]\nenabled = false\n\n[log]\nmode = console\nlevel = info\n\n[log.console]\nlevel = info\nformat = console\nEOH\n }\n\n # The service stanza instructs Nomad to register a service with Consul.\n #\n # For more information and examples on the \"task\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/service\n #\n service {\n name = \"grafana\"\n port = \"grafana\"\n tags = [ \"grafana${NOMAD_ALLOC_INDEX}\" ]\n check {\n name = \"Grafana Check Live\"\n type = \"http\"\n protocol = \"http\"\n tls_skip_verify = true\n path = \"/api/health\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # For more information and examples on the \"resources\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/resources\n #\n resources {\n cpu = 2000\n memory = 2048\n # The network stanza specifies the networking requirements for the task\n # group, including the network mode and port allocations. When scheduling\n # jobs in Nomad they are provisioned across your fleet of machines along\n # with other jobs and services. Because you don't know in advance what host\n # your job will be provisioned on, Nomad will provide your tasks with\n # network configuration when they start up.\n #\n # For more information and examples on the \"template\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/network\n #\n network {\n port \"grafana\" {\n static = 3000\n }\n }\n }\n }\n }\n}", + "json": null, + "modify_index": "7148410", + "name": "prod-grafana", + "namespace": "default", + "policy_override": null, + "purge_on_destroy": null, + "region": "global", + "task_groups": [ + { + "count": 1, + "meta": {}, + "name": "prod-group1-grafana", + "task": [ + { + "driver": "docker", + "meta": {}, + "name": "prod-task1-grafana", + "volume_mounts": [] + } + ], + "volumes": [] + } + ], + "type": "service" + }, + "sensitive_attributes": [], + "private": "bnVsbA==", + "dependencies": [ + "module.grafana.data.template_file.nomad_job_grafana" + ] + } + ] + }, + { "module": "module.minio", "mode": "data", "type": "template_file", @@ -48,12 +377,12 @@ "schema_version": 0, "attributes": { "filename": null, - "id": "e35f54f403b11159fde986f73d67cf4a4e4ab3cd53b4916f28fe0e8ec935823c", - "rendered": "job \"prod-minio\" {\n # The \"region\" parameter specifies the region in which to execute the job.\n # If omitted, this inherits the default region name of \"global\".\n # region = \"global\"\n #\n # The \"datacenters\" parameter specifies the list of datacenters which should\n # be considered when placing this task. This must be provided.\n datacenters = \"yul1\"\n\n # The \"type\" parameter controls the type of job, which impacts the scheduler's\n # decision on placement. This configuration is optional and defaults to\n # \"service\". For a full list of job types and their differences, please see\n # the online documentation.\n #\n # For more information, please see the online documentation at:\n #\n # https://www.nomadproject.io/docs/jobspec/schedulers.html\n #\n type = \"service\"\n\n update {\n # The \"max_parallel\" parameter specifies the maximum number of updates to\n # perform in parallel. In this case, this specifies to update a single task\n # at a time.\n max_parallel = 1\n\n health_check = \"checks\"\n\n # The \"min_healthy_time\" parameter specifies the minimum time the allocation\n # must be in the healthy state before it is marked as healthy and unblocks\n # further allocations from being updated.\n min_healthy_time = \"10s\"\n\n # The \"healthy_deadline\" parameter specifies the deadline in which the\n # allocation must be marked as healthy after which the allocation is\n # automatically transitioned to unhealthy. Transitioning to unhealthy will\n # fail the deployment and potentially roll back the job if \"auto_revert\" is\n # set to true.\n healthy_deadline = \"3m\"\n\n # The \"progress_deadline\" parameter specifies the deadline in which an\n # allocation must be marked as healthy. The deadline begins when the first\n # allocation for the deployment is created and is reset whenever an allocation\n # as part of the deployment transitions to a healthy state. If no allocation\n # transitions to the healthy state before the progress deadline, the\n # deployment is marked as failed.\n progress_deadline = \"10m\"\n\n\n # The \"canary\" parameter specifies that changes to the job that would result\n # in destructive updates should create the specified number of canaries\n # without stopping any previous allocations. Once the operator determines the\n # canaries are healthy, they can be promoted which unblocks a rolling update\n # of the remaining allocations at a rate of \"max_parallel\".\n #\n # Further, setting \"canary\" equal to the count of the task group allows\n # blue/green deployments. When the job is updated, a full set of the new\n # version is deployed and upon promotion the old version is stopped.\n canary = 1\n\n # Specifies if the job should auto-promote to the canary version when all\n # canaries become healthy during a deployment. Defaults to false which means\n # canaries must be manually updated with the nomad deployment promote\n # command.\n auto_promote = true\n\n # The \"auto_revert\" parameter specifies if the job should auto-revert to the\n # last stable job on deployment failure. A job is marked as stable if all the\n # allocations as part of its deployment were marked healthy.\n auto_revert = true\n\n }\n\n # All groups in this job should be scheduled on different hosts.\n constraint {\n operator = \"distinct_hosts\"\n value = \"true\"\n }\n\n # The \"group\" stanza defines a series of tasks that should be co-located on\n # the same Nomad client. Any task within a group will be placed on the same\n # client.\n #\n # For more information and examples on the \"group\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/group.html\n #\n group \"prod-group1-minio\" {\n # The \"count\" parameter specifies the number of the task groups that should\n # be running under this group. This value must be non-negative and defaults\n # to 1.\n count = 4\n\n # https://www.nomadproject.io/docs/job-specification/volume\n \n volume \"prod-volume1-minio\" {\n type = \"host\"\n read_only = false\n source = \"prod-volume-data1-1\"\n }\n \n\n # The \"task\" stanza creates an individual unit of work, such as a Docker\n # container, web application, or batch processing.\n #\n # For more information and examples on the \"task\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/task.html\n #\n task \"prod-task1-minio\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"docker\"\n\n \n volume_mount {\n volume = \"prod-volume1-minio\"\n destination = \"/data/\"\n read_only = false\n }\n \n\n \n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n image = \"minio/minio:RELEASE.2020-12-03T05-49-24Z\"\n dns_servers = [ \"${attr.unique.network.ip-address}\" ]\n network_mode = \"host\"\n command = \"server\"\n args = [ \"http://10.32.8.1{4...7}:9000/data/\" ]\n port_map {\n http = 9000\n }\n privileged = false\n }\n\n # The env stanza configures a list of environment variables to populate\n # the task's environment before starting.\n env {\n\n MINIO_ACCESS_KEY = \"minio\"\n MINIO_SECRET_KEY = \"minio123\"\n\n MINIO_BROWSER=\"off\"\n }\n\n # The service stanza instructs Nomad to register a service with Consul.\n #\n # For more information and examples on the \"task\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/service.html\n #\n service {\n name = \"storage\"\n port = \"http\"\n tags = [ \"storage${NOMAD_ALLOC_INDEX}\" ]\n check {\n name = \"Min.io Server HTTP Check Live\"\n type = \"http\"\n port = \"http\"\n protocol = \"http\"\n method = \"GET\"\n path = \"/minio/health/live\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n check {\n name = \"Min.io Server HTTP Check Ready\"\n type = \"http\"\n port = \"http\"\n protocol = \"http\"\n method = \"GET\"\n path = \"/minio/health/ready\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # For more information and examples on the \"resources\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/resources.html\n #\n resources {\n # The network stanza specifies the networking requirements for the task\n # group, including the network mode and port allocations. When scheduling\n # jobs in Nomad they are provisioned across your fleet of machines along\n # with other jobs and services. Because you don't know in advance what host\n # your job will be provisioned on, Nomad will provide your tasks with\n # network configuration when they start up.\n #\n # For more information and examples on the \"template\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/network.html\n #\n cpu = 40000\n memory = 40000\n network {\n port \"http\" {\n static = 9000\n }\n }\n }\n }\n }\n}\n", - "template": "job \"${job_name}\" {\n # The \"region\" parameter specifies the region in which to execute the job.\n # If omitted, this inherits the default region name of \"global\".\n # region = \"global\"\n #\n # The \"datacenters\" parameter specifies the list of datacenters which should\n # be considered when placing this task. This must be provided.\n datacenters = \"${datacenters}\"\n\n # The \"type\" parameter controls the type of job, which impacts the scheduler's\n # decision on placement. This configuration is optional and defaults to\n # \"service\". For a full list of job types and their differences, please see\n # the online documentation.\n #\n # For more information, please see the online documentation at:\n #\n # https://www.nomadproject.io/docs/jobspec/schedulers.html\n #\n type = \"service\"\n\n update {\n # The \"max_parallel\" parameter specifies the maximum number of updates to\n # perform in parallel. In this case, this specifies to update a single task\n # at a time.\n max_parallel = 1\n\n health_check = \"checks\"\n\n # The \"min_healthy_time\" parameter specifies the minimum time the allocation\n # must be in the healthy state before it is marked as healthy and unblocks\n # further allocations from being updated.\n min_healthy_time = \"10s\"\n\n # The \"healthy_deadline\" parameter specifies the deadline in which the\n # allocation must be marked as healthy after which the allocation is\n # automatically transitioned to unhealthy. Transitioning to unhealthy will\n # fail the deployment and potentially roll back the job if \"auto_revert\" is\n # set to true.\n healthy_deadline = \"3m\"\n\n # The \"progress_deadline\" parameter specifies the deadline in which an\n # allocation must be marked as healthy. The deadline begins when the first\n # allocation for the deployment is created and is reset whenever an allocation\n # as part of the deployment transitions to a healthy state. If no allocation\n # transitions to the healthy state before the progress deadline, the\n # deployment is marked as failed.\n progress_deadline = \"10m\"\n\n%{ if use_canary }\n # The \"canary\" parameter specifies that changes to the job that would result\n # in destructive updates should create the specified number of canaries\n # without stopping any previous allocations. Once the operator determines the\n # canaries are healthy, they can be promoted which unblocks a rolling update\n # of the remaining allocations at a rate of \"max_parallel\".\n #\n # Further, setting \"canary\" equal to the count of the task group allows\n # blue/green deployments. When the job is updated, a full set of the new\n # version is deployed and upon promotion the old version is stopped.\n canary = 1\n\n # Specifies if the job should auto-promote to the canary version when all\n # canaries become healthy during a deployment. Defaults to false which means\n # canaries must be manually updated with the nomad deployment promote\n # command.\n auto_promote = true\n\n # The \"auto_revert\" parameter specifies if the job should auto-revert to the\n # last stable job on deployment failure. A job is marked as stable if all the\n # allocations as part of its deployment were marked healthy.\n auto_revert = true\n%{ endif }\n }\n\n # All groups in this job should be scheduled on different hosts.\n constraint {\n operator = \"distinct_hosts\"\n value = \"true\"\n }\n\n # The \"group\" stanza defines a series of tasks that should be co-located on\n # the same Nomad client. Any task within a group will be placed on the same\n # client.\n #\n # For more information and examples on the \"group\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/group.html\n #\n group \"prod-group1-minio\" {\n # The \"count\" parameter specifies the number of the task groups that should\n # be running under this group. This value must be non-negative and defaults\n # to 1.\n count = ${group_count}\n\n # https://www.nomadproject.io/docs/job-specification/volume\n %{ if use_host_volume }\n volume \"prod-volume1-minio\" {\n type = \"host\"\n read_only = false\n source = \"${host_volume}\"\n }\n %{ endif }\n\n # The \"task\" stanza creates an individual unit of work, such as a Docker\n # container, web application, or batch processing.\n #\n # For more information and examples on the \"task\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/task.html\n #\n task \"prod-task1-minio\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"docker\"\n\n %{ if use_host_volume }\n volume_mount {\n volume = \"prod-volume1-minio\"\n destination = \"${data_dir}\"\n read_only = false\n }\n %{ endif }\n\n %{ if use_vault_provider }\n vault {\n policies = \"${vault_kv_policy_name}\"\n }\n %{ endif }\n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n image = \"${image}\"\n dns_servers = [ \"$${attr.unique.network.ip-address}\" ]\n network_mode = \"host\"\n command = \"server\"\n args = [ \"${host}:${port}${data_dir}\" ]\n port_map {\n http = ${port}\n }\n privileged = false\n }\n\n # The env stanza configures a list of environment variables to populate\n # the task's environment before starting.\n env {\n%{ if use_vault_provider }\n{{ with secret \"${vault_kv_path}\" }}\n MINIO_ACCESS_KEY = \"{{ .Data.data.${vault_kv_field_access_key} }}\"\n MINIO_SECRET_KEY = \"{{ .Data.data.${vault_kv_field_secret_key} }}\"\n{{ end }}\n%{ else }\n MINIO_ACCESS_KEY = \"${access_key}\"\n MINIO_SECRET_KEY = \"${secret_key}\"\n%{ endif }\n ${ envs }\n }\n\n # The service stanza instructs Nomad to register a service with Consul.\n #\n # For more information and examples on the \"task\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/service.html\n #\n service {\n name = \"${service_name}\"\n port = \"http\"\n tags = [ \"storage$${NOMAD_ALLOC_INDEX}\" ]\n check {\n name = \"Min.io Server HTTP Check Live\"\n type = \"http\"\n port = \"http\"\n protocol = \"http\"\n method = \"GET\"\n path = \"/minio/health/live\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n check {\n name = \"Min.io Server HTTP Check Ready\"\n type = \"http\"\n port = \"http\"\n protocol = \"http\"\n method = \"GET\"\n path = \"/minio/health/ready\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # For more information and examples on the \"resources\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/resources.html\n #\n resources {\n # The network stanza specifies the networking requirements for the task\n # group, including the network mode and port allocations. When scheduling\n # jobs in Nomad they are provisioned across your fleet of machines along\n # with other jobs and services. Because you don't know in advance what host\n # your job will be provisioned on, Nomad will provide your tasks with\n # network configuration when they start up.\n #\n # For more information and examples on the \"template\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/network.html\n #\n cpu = 40000\n memory = 40000\n network {\n port \"http\" {\n static = ${port}\n }\n }\n }\n }\n }\n}\n", + "id": "c38a0b7182d39c70ec07bdaa998f57a215d7193b264c1b1c1a299c84e7ca53de", + "rendered": "job \"prod-minio\" {\n # The \"region\" parameter specifies the region in which to execute the job.\n # If omitted, this inherits the default region name of \"global\".\n # region = \"global\"\n #\n # The \"datacenters\" parameter specifies the list of datacenters which should\n # be considered when placing this task. This must be provided.\n datacenters = \"yul1\"\n\n # The \"type\" parameter controls the type of job, which impacts the scheduler's\n # decision on placement. This configuration is optional and defaults to\n # \"service\". For a full list of job types and their differences, please see\n # the online documentation.\n #\n # For more information, please see the online documentation at:\n #\n # https://www.nomadproject.io/docs/jobspec/schedulers.html\n #\n type = \"service\"\n\n update {\n # The \"max_parallel\" parameter specifies the maximum number of updates to\n # perform in parallel. In this case, this specifies to update a single task\n # at a time.\n max_parallel = 1\n\n health_check = \"checks\"\n\n # The \"min_healthy_time\" parameter specifies the minimum time the allocation\n # must be in the healthy state before it is marked as healthy and unblocks\n # further allocations from being updated.\n min_healthy_time = \"10s\"\n\n # The \"healthy_deadline\" parameter specifies the deadline in which the\n # allocation must be marked as healthy after which the allocation is\n # automatically transitioned to unhealthy. Transitioning to unhealthy will\n # fail the deployment and potentially roll back the job if \"auto_revert\" is\n # set to true.\n healthy_deadline = \"3m\"\n\n # The \"progress_deadline\" parameter specifies the deadline in which an\n # allocation must be marked as healthy. The deadline begins when the first\n # allocation for the deployment is created and is reset whenever an allocation\n # as part of the deployment transitions to a healthy state. If no allocation\n # transitions to the healthy state before the progress deadline, the\n # deployment is marked as failed.\n progress_deadline = \"10m\"\n\n\n # The \"canary\" parameter specifies that changes to the job that would result\n # in destructive updates should create the specified number of canaries\n # without stopping any previous allocations. Once the operator determines the\n # canaries are healthy, they can be promoted which unblocks a rolling update\n # of the remaining allocations at a rate of \"max_parallel\".\n #\n # Further, setting \"canary\" equal to the count of the task group allows\n # blue/green deployments. When the job is updated, a full set of the new\n # version is deployed and upon promotion the old version is stopped.\n canary = 1\n\n # Specifies if the job should auto-promote to the canary version when all\n # canaries become healthy during a deployment. Defaults to false which means\n # canaries must be manually updated with the nomad deployment promote\n # command.\n auto_promote = true\n\n # The \"auto_revert\" parameter specifies if the job should auto-revert to the\n # last stable job on deployment failure. A job is marked as stable if all the\n # allocations as part of its deployment were marked healthy.\n auto_revert = true\n\n }\n\n # All groups in this job should be scheduled on different hosts.\n constraint {\n operator = \"distinct_hosts\"\n value = \"true\"\n }\n\n # The \"group\" stanza defines a series of tasks that should be co-located on\n # the same Nomad client. Any task within a group will be placed on the same\n # client.\n #\n # For more information and examples on the \"group\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/group.html\n #\n group \"prod-group1-minio\" {\n # The \"count\" parameter specifies the number of the task groups that should\n # be running under this group. This value must be non-negative and defaults\n # to 1.\n count = 4\n\n # https://www.nomadproject.io/docs/job-specification/volume\n \n volume \"prod-volume1-minio\" {\n type = \"host\"\n read_only = false\n source = \"prod-volume-data1-1\"\n }\n \n\n # The \"task\" stanza creates an individual unit of work, such as a Docker\n # container, web application, or batch processing.\n #\n # For more information and examples on the \"task\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/task.html\n #\n task \"prod-task1-minio\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"docker\"\n\n \n volume_mount {\n volume = \"prod-volume1-minio\"\n destination = \"/data/\"\n read_only = false\n }\n \n\n \n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n image = \"minio/minio:RELEASE.2020-12-03T05-49-24Z\"\n dns_servers = [ \"${attr.unique.network.ip-address}\" ]\n network_mode = \"host\"\n command = \"server\"\n args = [ \"http://10.32.8.1{4...7}:9000/data/\" ]\n port_map {\n http = 9000\n }\n privileged = false\n }\n\n # The env stanza configures a list of environment variables to populate\n # the task's environment before starting.\n env {\n\n MINIO_ACCESS_KEY = \"minio\"\n MINIO_SECRET_KEY = \"minio123\"\n\n MINIO_BROWSER=\"off\"\n }\n\n # The service stanza instructs Nomad to register a service with Consul.\n #\n # For more information and examples on the \"task\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/service.html\n #\n service {\n name = \"storage\"\n port = \"http\"\n tags = [ \"storage${NOMAD_ALLOC_INDEX}\" ]\n check {\n name = \"Min.io Server HTTP Check Live\"\n type = \"http\"\n port = \"http\"\n protocol = \"http\"\n method = \"GET\"\n path = \"/minio/health/live\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n check {\n name = \"Min.io Server HTTP Check Ready\"\n type = \"http\"\n port = \"http\"\n protocol = \"http\"\n method = \"GET\"\n path = \"/minio/health/ready\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # For more information and examples on the \"resources\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/resources.html\n #\n resources {\n cpu = 40000\n memory = 40000\n # The network stanza specifies the networking requirements for the task\n # group, including the network mode and port allocations. When scheduling\n # jobs in Nomad they are provisioned across your fleet of machines along\n # with other jobs and services. Because you don't know in advance what host\n # your job will be provisioned on, Nomad will provide your tasks with\n # network configuration when they start up.\n #\n # For more information and examples on the \"template\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/network.html\n #\n network {\n port \"http\" {\n static = 9000\n }\n }\n }\n }\n }\n}\n", + "template": "job \"${job_name}\" {\n # The \"region\" parameter specifies the region in which to execute the job.\n # If omitted, this inherits the default region name of \"global\".\n # region = \"global\"\n #\n # The \"datacenters\" parameter specifies the list of datacenters which should\n # be considered when placing this task. This must be provided.\n datacenters = \"${datacenters}\"\n\n # The \"type\" parameter controls the type of job, which impacts the scheduler's\n # decision on placement. This configuration is optional and defaults to\n # \"service\". For a full list of job types and their differences, please see\n # the online documentation.\n #\n # For more information, please see the online documentation at:\n #\n # https://www.nomadproject.io/docs/jobspec/schedulers.html\n #\n type = \"service\"\n\n update {\n # The \"max_parallel\" parameter specifies the maximum number of updates to\n # perform in parallel. In this case, this specifies to update a single task\n # at a time.\n max_parallel = 1\n\n health_check = \"checks\"\n\n # The \"min_healthy_time\" parameter specifies the minimum time the allocation\n # must be in the healthy state before it is marked as healthy and unblocks\n # further allocations from being updated.\n min_healthy_time = \"10s\"\n\n # The \"healthy_deadline\" parameter specifies the deadline in which the\n # allocation must be marked as healthy after which the allocation is\n # automatically transitioned to unhealthy. Transitioning to unhealthy will\n # fail the deployment and potentially roll back the job if \"auto_revert\" is\n # set to true.\n healthy_deadline = \"3m\"\n\n # The \"progress_deadline\" parameter specifies the deadline in which an\n # allocation must be marked as healthy. The deadline begins when the first\n # allocation for the deployment is created and is reset whenever an allocation\n # as part of the deployment transitions to a healthy state. If no allocation\n # transitions to the healthy state before the progress deadline, the\n # deployment is marked as failed.\n progress_deadline = \"10m\"\n\n%{ if use_canary }\n # The \"canary\" parameter specifies that changes to the job that would result\n # in destructive updates should create the specified number of canaries\n # without stopping any previous allocations. Once the operator determines the\n # canaries are healthy, they can be promoted which unblocks a rolling update\n # of the remaining allocations at a rate of \"max_parallel\".\n #\n # Further, setting \"canary\" equal to the count of the task group allows\n # blue/green deployments. When the job is updated, a full set of the new\n # version is deployed and upon promotion the old version is stopped.\n canary = 1\n\n # Specifies if the job should auto-promote to the canary version when all\n # canaries become healthy during a deployment. Defaults to false which means\n # canaries must be manually updated with the nomad deployment promote\n # command.\n auto_promote = true\n\n # The \"auto_revert\" parameter specifies if the job should auto-revert to the\n # last stable job on deployment failure. A job is marked as stable if all the\n # allocations as part of its deployment were marked healthy.\n auto_revert = true\n%{ endif }\n }\n\n # All groups in this job should be scheduled on different hosts.\n constraint {\n operator = \"distinct_hosts\"\n value = \"true\"\n }\n\n # The \"group\" stanza defines a series of tasks that should be co-located on\n # the same Nomad client. Any task within a group will be placed on the same\n # client.\n #\n # For more information and examples on the \"group\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/group.html\n #\n group \"prod-group1-minio\" {\n # The \"count\" parameter specifies the number of the task groups that should\n # be running under this group. This value must be non-negative and defaults\n # to 1.\n count = ${group_count}\n\n # https://www.nomadproject.io/docs/job-specification/volume\n %{ if use_host_volume }\n volume \"prod-volume1-minio\" {\n type = \"host\"\n read_only = false\n source = \"${host_volume}\"\n }\n %{ endif }\n\n # The \"task\" stanza creates an individual unit of work, such as a Docker\n # container, web application, or batch processing.\n #\n # For more information and examples on the \"task\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/task.html\n #\n task \"prod-task1-minio\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"docker\"\n\n %{ if use_host_volume }\n volume_mount {\n volume = \"prod-volume1-minio\"\n destination = \"${data_dir}\"\n read_only = false\n }\n %{ endif }\n\n %{ if use_vault_provider }\n vault {\n policies = \"${vault_kv_policy_name}\"\n }\n %{ endif }\n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n image = \"${image}\"\n dns_servers = [ \"$${attr.unique.network.ip-address}\" ]\n network_mode = \"host\"\n command = \"server\"\n args = [ \"${host}:${port}${data_dir}\" ]\n port_map {\n http = ${port}\n }\n privileged = false\n }\n\n # The env stanza configures a list of environment variables to populate\n # the task's environment before starting.\n env {\n%{ if use_vault_provider }\n{{ with secret \"${vault_kv_path}\" }}\n MINIO_ACCESS_KEY = \"{{ .Data.data.${vault_kv_field_access_key} }}\"\n MINIO_SECRET_KEY = \"{{ .Data.data.${vault_kv_field_secret_key} }}\"\n{{ end }}\n%{ else }\n MINIO_ACCESS_KEY = \"${access_key}\"\n MINIO_SECRET_KEY = \"${secret_key}\"\n%{ endif }\n ${ envs }\n }\n\n # The service stanza instructs Nomad to register a service with Consul.\n #\n # For more information and examples on the \"task\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/service.html\n #\n service {\n name = \"${service_name}\"\n port = \"http\"\n tags = [ \"storage$${NOMAD_ALLOC_INDEX}\" ]\n check {\n name = \"Min.io Server HTTP Check Live\"\n type = \"http\"\n port = \"http\"\n protocol = \"http\"\n method = \"GET\"\n path = \"/minio/health/live\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n check {\n name = \"Min.io Server HTTP Check Ready\"\n type = \"http\"\n port = \"http\"\n protocol = \"http\"\n method = \"GET\"\n path = \"/minio/health/ready\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # For more information and examples on the \"resources\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/resources.html\n #\n resources {\n cpu = ${cpu}\n memory = ${memory}\n # The network stanza specifies the networking requirements for the task\n # group, including the network mode and port allocations. When scheduling\n # jobs in Nomad they are provisioned across your fleet of machines along\n # with other jobs and services. Because you don't know in advance what host\n # your job will be provisioned on, Nomad will provide your tasks with\n # network configuration when they start up.\n #\n # For more information and examples on the \"template\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/network.html\n #\n network {\n port \"http\" {\n static = ${port}\n }\n }\n }\n }\n }\n}\n", "vars": { "access_key": "minio", - "cpu": "200", + "cpu": "40000", "cpu_proxy": "200", "data_dir": "/data/", "datacenters": "yul1", @@ -63,7 +392,7 @@ "host_volume": "prod-volume-data1-1", "image": "minio/minio:RELEASE.2020-12-03T05-49-24Z", "job_name": "prod-minio", - "memory": "1024", + "memory": "40000", "memory_proxy": "128", "port": "9000", "secret_key": "minio123", @@ -89,7 +418,7 @@ "schema_version": 0, "attributes": { "allocation_ids": [ - "df5ed2e3-2484-93bd-1bd2-f949d5a6ec8f" + "8ca5aa5b-2616-f167-f40e-a0becb50c87e" ], "datacenters": [ "yul1" @@ -102,7 +431,7 @@ "id": "prod-mc", "jobspec": "job \"prod-mc\" {\n # The \"region\" parameter specifies the region in which to execute the job.\n # If omitted, this inherits the default region name of \"global\".\n # region = \"global\"\n #\n # The \"datacenters\" parameter specifies the list of datacenters which should\n # be considered when placing this task. This must be provided.\n datacenters = \"yul1\"\n\n # The \"type\" parameter controls the type of job, which impacts the scheduler's\n # decision on placement. This configuration is optional and defaults to\n # \"service\". For a full list of job types and their differences, please see\n # the online documentation.\n #\n # For more information, please see the online documentation at:\n #\n # https://www.nomadproject.io/docs/jobspec/schedulers.html\n #\n type = \"batch\"\n\n # The \"group\" stanza defines a series of tasks that should be co-located on\n # the same Nomad client. Any task within a group will be placed on the same\n # client.\n #\n # For more information and examples on the \"group\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/group.html\n #\n group \"prod-group1-mc\" {\n task \"prod-task1-create-buckets\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"docker\"\n\n \n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n image = \"minio/mc:RELEASE.2020-12-10T01-26-17Z\"\n entrypoint = [\n \"/bin/sh\",\n \"-c\",\n \"mc config host add LOCALMINIO http://storage.service.consul:9000 $MINIO_ACCESS_KEY $MINIO_SECRET_KEY \u0026\u0026 mc mb -p LOCALMINIO/logs.fd.io LOCALMINIO/docs.fd.io ; mc policy set public LOCALMINIO/logs.fd.io mc policy set public LOCALMINIO/docs.fd.io mc ilm add --expiry-days '180' LOCALMINIO/logs.fd.io mc admin user add LOCALMINIO storage Storage1234 mc admin policy set LOCALMINIO writeonly user=storage\"\n ]\n dns_servers = [ \"${attr.unique.network.ip-address}\" ]\n privileged = false\n }\n\n # The env stanza configures a list of environment variables to populate\n # the task's environment before starting.\n env {\n \n MINIO_ACCESS_KEY = \"minio\"\n MINIO_SECRET_KEY = \"minio123\"\n \n \n }\n }\n }\n}\n", "json": null, - "modify_index": "5933670", + "modify_index": "7148419", "name": "prod-mc", "namespace": "default", "policy_override": null, @@ -150,8 +479,7 @@ "322e6ea5-acc7-2f37-3022-cd0a31c2f3db", "619833b9-dd70-46ae-f576-75c3cd058a13", "0510561a-c828-dd23-5910-b92d9f2c41ef", - "504924c8-387b-abe2-c4d5-d6a7424a4689", - "4f12caf3-8ca8-b697-13c0-8f35d21dcba1" + "504924c8-387b-abe2-c4d5-d6a7424a4689" ], "datacenters": [ "yul1" @@ -243,7 +571,7 @@ "schema_version": 0, "attributes": { "allocation_ids": [ - "de9af589-8f0b-6634-7199-c661f8f17df0" + "1dea6de0-d5cd-2a1b-fb42-0468e986e0d6" ], "datacenters": [ "yul1" @@ -287,6 +615,212 @@ ] } ] + }, + { + "module": "module.prometheus", + "mode": "data", + "type": "template_file", + "name": "nomad_job_prometheus", + "provider": "provider[\"registry.terraform.io/hashicorp/template\"]", + "instances": [ + { + "schema_version": 0, + "attributes": { + "filename": null, + "id": "cd26d062785357d96c95d6f8f40b2d8d7b430be3399de176e6b250822c4af86c", + "rendered": "job \"prod-prometheus\" {\n # The \"region\" parameter specifies the region in which to execute the job.\n # If omitted, this inherits the default region name of \"global\".\n # region = \"global\"\n #\n # The \"datacenters\" parameter specifies the list of datacenters which should\n # be considered when placing this task. This must be provided.\n datacenters = \"yul1\"\n\n # The \"type\" parameter controls the type of job, which impacts the scheduler's\n # decision on placement. This configuration is optional and defaults to\n # \"service\". For a full list of job types and their differences, please see\n # the online documentation.\n #\n # For more information, please see the online documentation at:\n #\n # https://www.nomadproject.io/docs/jobspec/schedulers\n #\n type = \"service\"\n\n update {\n # The \"max_parallel\" parameter specifies the maximum number of updates to\n # perform in parallel. In this case, this specifies to update a single task\n # at a time.\n max_parallel = 1\n\n health_check = \"checks\"\n\n # The \"min_healthy_time\" parameter specifies the minimum time the allocation\n # must be in the healthy state before it is marked as healthy and unblocks\n # further allocations from being updated.\n min_healthy_time = \"10s\"\n\n # The \"healthy_deadline\" parameter specifies the deadline in which the\n # allocation must be marked as healthy after which the allocation is\n # automatically transitioned to unhealthy. Transitioning to unhealthy will\n # fail the deployment and potentially roll back the job if \"auto_revert\" is\n # set to true.\n healthy_deadline = \"3m\"\n\n # The \"progress_deadline\" parameter specifies the deadline in which an\n # allocation must be marked as healthy. The deadline begins when the first\n # allocation for the deployment is created and is reset whenever an allocation\n # as part of the deployment transitions to a healthy state. If no allocation\n # transitions to the healthy state before the progress deadline, the\n # deployment is marked as failed.\n progress_deadline = \"10m\"\n\n\n # The \"canary\" parameter specifies that changes to the job that would result\n # in destructive updates should create the specified number of canaries\n # without stopping any previous allocations. Once the operator determines the\n # canaries are healthy, they can be promoted which unblocks a rolling update\n # of the remaining allocations at a rate of \"max_parallel\".\n #\n # Further, setting \"canary\" equal to the count of the task group allows\n # blue/green deployments. When the job is updated, a full set of the new\n # version is deployed and upon promotion the old version is stopped.\n canary = 1\n\n # Specifies if the job should auto-promote to the canary version when all\n # canaries become healthy during a deployment. Defaults to false which means\n # canaries must be manually updated with the nomad deployment promote\n # command.\n auto_promote = true\n\n # The \"auto_revert\" parameter specifies if the job should auto-revert to the\n # last stable job on deployment failure. A job is marked as stable if all the\n # allocations as part of its deployment were marked healthy.\n auto_revert = true\n\n }\n\n # The \"group\" stanza defines a series of tasks that should be co-located on\n # the same Nomad client. Any task within a group will be placed on the same\n # client.\n #\n # For more information and examples on the \"group\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/group\n #\n group \"prod-group1-prometheus\" {\n # The \"count\" parameter specifies the number of the task groups that should\n # be running under this group. This value must be non-negative and defaults\n # to 1.\n count = 4\n\n # The volume stanza allows the group to specify that it requires a given\n # volume from the cluster.\n #\n # For more information and examples on the \"volume\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/volume\n #\n \n volume \"prod-volume1-prometheus\" {\n type = \"host\"\n read_only = false\n source = \"prod-volume-data1-1\"\n }\n \n\n # The constraint allows restricting the set of eligible nodes. Constraints\n # may filter on attributes or client metadata.\n #\n # For more information and examples on the \"volume\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/constraint\n #\n constraint {\n attribute = \"${attr.cpu.arch}\"\n operator = \"!=\"\n value = \"arm64\"\n }\n\n # The \"task\" stanza creates an individual unit of work, such as a Docker\n # container, web application, or batch processing.\n #\n # For more information and examples on the \"task\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/task\n #\n task \"prod-task1-prometheus\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"exec\"\n\n \n volume_mount {\n volume = \"prod-volume1-prometheus\"\n destination = \"/data/\"\n read_only = false\n }\n \n\n \n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n command = \"local/prometheus-2.24.0.linux-amd64/prometheus\"\n args = [\n \"--config.file=secrets/prometheus.yml\",\n \"--storage.tsdb.path=/data/prometheus/\",\n \"--storage.tsdb.retention.time=15d\"\n ]\n }\n\n # The artifact stanza instructs Nomad to fetch and unpack a remote resource,\n # such as a file, tarball, or binary. Nomad downloads artifacts using the\n # popular go-getter library, which permits downloading artifacts from a\n # variety of locations using a URL as the input source.\n #\n # For more information and examples on the \"artifact\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/artifact\n #\n artifact {\n source = \"https://github.com/prometheus/prometheus/releases/download/v2.24.0/prometheus-2.24.0.linux-amd64.tar.gz\"\n }\n\n # The \"template\" stanza instructs Nomad to manage a template, such as\n # a configuration file or script. This template can optionally pull data\n # from Consul or Vault to populate runtime configuration data.\n #\n # For more information and examples on the \"template\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/template\n #\n template {\n change_mode = \"noop\"\n change_signal = \"SIGINT\"\n destination = \"secrets/alerts.yml\"\n left_delimiter = \"{{{\"\n right_delimiter = \"}}}\"\n data = \u003c\u003cEOH\n---\ngroups:\n- name: \"Consul\"\n rules:\n - alert: ConsulServiceHealthcheckFailed\n expr: consul_catalog_service_node_healthy == 0\n for: 0m\n labels:\n severity: critical\n annotations:\n summary: \"Consul service healthcheck failed (instance {{ $labels.instance }}).\"\n description: \"Service: `{{ $labels.service_name }}` Healthcheck: `{{ $labels.service_id }}`.\"\n - alert: ConsulMissingMasterNode\n expr: consul_raft_peers \u003c 3\n for: 0m\n labels:\n severity: critical\n annotations:\n summary: \"Consul missing master node (instance {{ $labels.instance }}).\"\n description: \"Numbers of consul raft peers should be 3, in order to preserve quorum.\"\n - alert: ConsulAgentUnhealthy\n expr: consul_health_node_status{status=\"critical\"} == 1\n for: 0m\n labels:\n severity: critical\n annotations:\n summary: \"Consul agent unhealthy (instance {{ $labels.instance }}).\"\n description: \"A Consul agent is down.\"\n- name: \"Hosts\"\n rules:\n - alert: NodeDown\n expr: up == 0\n for: 0m\n labels:\n severity: critical\n annotations:\n summary: \"Prometheus target missing (instance {{ $labels.instance }}).\"\n description: \"A Prometheus target has disappeared. An exporter might be crashed.\"\n - alert: HostHighCpuLoad\n expr: 100 - (avg by(instance) (rate(node_cpu_seconds_total{mode=\"idle\"}[2m])) * 100) \u003e 80\n for: 0m\n labels:\n severity: warning\n annotations:\n summary: \"Host high CPU load (instance {{ $labels.instance }}).\"\n description: \"CPU load is \u003e 80%.\"\n - alert: HostOutOfMemory\n expr: node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes * 100 \u003c 10\n for: 2m\n labels:\n severity: warning\n annotations:\n summary: \"Host out of memory (instance {{ $labels.instance }}).\"\n description: \"Node memory is filling up (\u003c 10% left).\"\n - alert: HostOomKillDetected\n expr: increase(node_vmstat_oom_kill[1m]) \u003e 0\n for: 0m\n labels:\n severity: warning\n annotations:\n summary: \"Host OOM kill detected (instance {{ $labels.instance }}).\"\n description: \"OOM kill detected.\"\n - alert: HostMemoryUnderMemoryPressure\n expr: rate(node_vmstat_pgmajfault[1m]) \u003e 1000\n for: 2m\n labels:\n severity: warning\n annotations:\n summary: \"Host memory under memory pressure (instance {{ $labels.instance }}).\"\n description: \"The node is under heavy memory pressure. High rate of major page faults.\"\n - alert: HostOutOfDiskSpace\n expr: (node_filesystem_avail_bytes * 100) / node_filesystem_size_bytes \u003c 10 and ON (instance, device, mountpoint) node_filesystem_readonly == 0\n for: 2m\n labels:\n severity: warning\n annotations:\n summary: \"Host out of disk space (instance {{ $labels.instance }}).\"\n description: \"Disk is almost full (\u003c 10% left).\"\n - alert: HostRaidDiskFailure\n expr: node_md_disks{state=\"failed\"} \u003e 0\n for: 2m\n labels:\n severity: warning\n annotations:\n summary: \"Host RAID disk failure (instance {{ $labels.instance }}).\"\n description: \"At least one device in RAID array on {{ $labels.instance }} failed. Array {{ $labels.md_device }} needs attention and possibly a disk swap.\"\n - alert: HostConntrackLimit\n expr: node_nf_conntrack_entries / node_nf_conntrack_entries_limit \u003e 0.8\n for: 5m\n labels:\n severity: warning\n annotations:\n summary: \"Host conntrack limit (instance {{ $labels.instance }}).\"\n description: \"The number of conntrack is approching limit.\"\n - alert: HostNetworkInterfaceSaturated\n expr: (rate(node_network_receive_bytes_total{device!~\"^tap.*\"}[1m]) + rate(node_network_transmit_bytes_total{device!~\"^tap.*\"}[1m])) / node_network_speed_bytes{device!~\"^tap.*\"} \u003e 0.8\n for: 1m\n labels:\n severity: warning\n annotations:\n summary: \"Host Network Interface Saturated (instance {{ $labels.instance }}).\"\n description: \"The network interface {{ $labels.interface }} on {{ $labels.instance }} is getting overloaded.\"\n - alert: HostSystemdServiceCrashed\n expr: node_systemd_unit_state{state=\"failed\"} == 1\n for: 0m\n labels:\n severity: warning\n annotations:\n summary: \"Host SystemD service crashed (instance {{ $labels.instance }}).\"\n description: \"SystemD service crashed.\"\n - alert: HostEdacCorrectableErrorsDetected\n expr: increase(node_edac_correctable_errors_total[1m]) \u003e 0\n for: 0m\n labels:\n severity: info\n annotations:\n summary: \"Host EDAC Correctable Errors detected (instance {{ $labels.instance }}).\"\n description: '{{ $labels.instance }} has had {{ printf \"%.0f\" $value }} correctable memory errors reported by EDAC in the last 5 minutes.'\n - alert: HostEdacUncorrectableErrorsDetected\n expr: node_edac_uncorrectable_errors_total \u003e 0\n for: 0m\n labels:\n severity: warning\n annotations:\n summary: \"Host EDAC Uncorrectable Errors detected (instance {{ $labels.instance }}).\"\n description: '{{ $labels.instance }} has had {{ printf \"%.0f\" $value }} uncorrectable memory errors reported by EDAC in the last 5 minutes.'\n- name: \"Min.io\"\n rules:\n - alert: MinioDiskOffline\n expr: minio_offline_disks \u003e 0\n for: 0m\n labels:\n severity: critical\n annotations:\n summary: \"Minio disk offline (instance {{ $labels.instance }})\"\n description: \"Minio disk is offline.\"\n - alert: MinioStorageSpaceExhausted\n expr: minio_disk_storage_free_bytes / 1024 / 1024 / 1024 \u003c 10\n for: 2m\n labels:\n severity: warning\n annotations:\n summary: \"Minio storage space exhausted (instance {{ $labels.instance }}).\"\n description: \"Minio storage space is low (\u003c 10 GB).\"\n- name: \"Prometheus\"\n rules:\n - alert: PrometheusConfigurationReloadFailure\n expr: prometheus_config_last_reload_successful != 1\n for: 0m\n labels:\n severity: warning\n annotations:\n summary: \"Prometheus configuration reload failure (instance {{ $labels.instance }}).\"\n description: \"Prometheus configuration reload error.\"\n - alert: PrometheusTooManyRestarts\n expr: changes(process_start_time_seconds{job=~\"prometheus|pushgateway|alertmanager\"}[15m]) \u003e 2\n for: 0m\n labels:\n severity: warning\n annotations:\n summary: \"Prometheus too many restarts (instance {{ $labels.instance }}).\"\n description: \"Prometheus has restarted more than twice in the last 15 minutes. It might be crashlooping.\"\n - alert: PrometheusAlertmanagerConfigurationReloadFailure\n expr: alertmanager_config_last_reload_successful != 1\n for: 0m\n labels:\n severity: warning\n annotations:\n summary: \"Prometheus AlertManager configuration reload failure (instance {{ $labels.instance }}).\"\n description: \"AlertManager configuration reload error.\"\n - alert: PrometheusRuleEvaluationFailures\n expr: increase(prometheus_rule_evaluation_failures_total[3m]) \u003e 0\n for: 0m\n labels:\n severity: critical\n annotations:\n summary: \"Prometheus rule evaluation failures (instance {{ $labels.instance }}).\"\n description: \"Prometheus encountered {{ $value }} rule evaluation failures, leading to potentially ignored alerts.\"\n - alert: PrometheusTargetScrapingSlow\n expr: prometheus_target_interval_length_seconds{quantile=\"0.9\"} \u003e 60\n for: 5m\n labels:\n severity: warning\n annotations:\n summary: \"Prometheus target scraping slow (instance {{ $labels.instance }}).\"\n description: \"Prometheus is scraping exporters slowly.\"\n - alert: PrometheusTsdbCompactionsFailed\n expr: increase(prometheus_tsdb_compactions_failed_total[1m]) \u003e 0\n for: 0m\n labels:\n severity: critical\n annotations:\n summary: \"Prometheus TSDB compactions failed (instance {{ $labels.instance }}).\"\n description: \"Prometheus encountered {{ $value }} TSDB compactions failures.\"\n - alert: PrometheusTsdbHeadTruncationsFailed\n expr: increase(prometheus_tsdb_head_truncations_failed_total[1m]) \u003e 0\n for: 0m\n labels:\n severity: critical\n annotations:\n summary: \"Prometheus TSDB head truncations failed (instance {{ $labels.instance }}).\"\n description: \"Prometheus encountered {{ $value }} TSDB head truncation failures.\"\n - alert: PrometheusTsdbWalCorruptions\n expr: increase(prometheus_tsdb_wal_corruptions_total[1m]) \u003e 0\n for: 0m\n labels:\n severity: critical\n annotations:\n summary: \"Prometheus TSDB WAL corruptions (instance {{ $labels.instance }}).\"\n description: \"Prometheus encountered {{ $value }} TSDB WAL corruptions.\"\n - alert: PrometheusTsdbWalTruncationsFailed\n expr: increase(prometheus_tsdb_wal_truncations_failed_total[1m]) \u003e 0\n for: 0m\n labels:\n severity: critical\n annotations:\n summary: \"Prometheus TSDB WAL truncations failed (instance {{ $labels.instance }}).\"\n description: \"Prometheus encountered {{ $value }} TSDB WAL truncation failures.\"\nEOH\n }\n\n template {\n change_mode = \"noop\"\n change_signal = \"SIGINT\"\n destination = \"secrets/prometheus.yml\"\n data = \u003c\u003cEOH\n---\nglobal:\n scrape_interval: 5s\n scrape_timeout: 5s\n evaluation_interval: 5s\n\nalerting:\n alertmanagers:\n - consul_sd_configs:\n - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n services: [ 'alertmanager' ]\n\nrule_files:\n - 'alerts.yml'\n\nscrape_configs:\n\n - job_name: 'Nomad Cluster'\n consul_sd_configs:\n - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n services: [ 'nomad-client', 'nomad' ]\n relabel_configs:\n - source_labels: [__meta_consul_tags]\n regex: '(.*)http(.*)'\n action: keep\n metrics_path: /v1/metrics\n params:\n format: [ 'prometheus' ]\n\n - job_name: 'Consul Cluster'\n static_configs:\n - targets: [ '10.30.51.30:8500', '10.30.51.32:8500', '10.30.51.33:8500' ]\n metrics_path: /v1/agent/metrics\n params:\n format: [ 'prometheus' ]\n\n - job_name: 'Alertmanager'\n consul_sd_configs:\n - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n services: [ 'alertmanager' ]\n\n - job_name: 'Blackbox Exporter (icmp)'\n static_configs:\n - targets: [ 'gerrit.fd.io' ]\n - targets: [ 'jenkins.fd.io' ]\n - targets: [ '10.30.51.32' ]\n params:\n module: [ 'icmp_v4' ]\n relabel_configs:\n - source_labels: [__address__]\n target_label: __param_target\n - source_labels: [__param_target]\n target_label: instance\n - target_label: __address__\n replacement: localhost:9115\n metrics_path: /probe\n\n - job_name: 'Blackbox Exporter (http)'\n static_configs:\n - targets: [ 'gerrit.fd.io' ]\n - targets: [ 'jenkins.fd.io' ]\n params:\n module: [ 'http_2xx' ]\n relabel_configs:\n - source_labels: [__address__]\n target_label: __param_target\n - source_labels: [__param_target]\n target_label: instance\n - target_label: __address__\n replacement: localhost:9115\n metrics_path: /probe\n\n - job_name: 'cAdvisor Exporter'\n consul_sd_configs:\n - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n services: [ 'cadvisorexporter' ]\n\n - job_name: 'Grafana'\n consul_sd_configs:\n - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n services: [ 'grafana' ]\n\n - job_name: 'Node Exporter'\n consul_sd_configs:\n - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n services: [ 'nodeexporter' ]\n\n - job_name: 'Prometheus'\n consul_sd_configs:\n - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n services: [ 'prometheus' ]\n\n - job_name: 'Minio'\n bearer_token: eyJhbGciOiJIUzUxMiIsInR5cCI6IkpXVCJ9.eyJleHAiOjQ3NjQ1ODEzMzcsImlzcyI6InByb21ldGhldXMiLCJzdWIiOiJtaW5pbyJ9.oeTw3EIaiFmlDikrHXWiWXMH2vxLfDLkfjEC7G2N3M_keH_xyA_l2ofLLNYtopa_3GCEZnxLQdPuFZrmgpkDWg\n consul_sd_configs:\n - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n services: [ 'storage' ]\n metrics_path: /minio/prometheus/metrics\nEOH\n }\n\n # The service stanza instructs Nomad to register a service with Consul.\n #\n # For more information and examples on the \"task\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/service\n #\n service {\n name = \"prometheus\"\n port = \"prometheus\"\n tags = [ \"prometheus${NOMAD_ALLOC_INDEX}\" ]\n check {\n name = \"Prometheus Check Live\"\n type = \"http\"\n path = \"/-/healthy\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # For more information and examples on the \"resources\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/resources\n #\n resources {\n cpu = 2000\n memory = 8192\n # The network stanza specifies the networking requirements for the task\n # group, including the network mode and port allocations. When scheduling\n # jobs in Nomad they are provisioned across your fleet of machines along\n # with other jobs and services. Because you don't know in advance what host\n # your job will be provisioned on, Nomad will provide your tasks with\n # network configuration when they start up.\n #\n # For more information and examples on the \"template\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/network\n #\n network {\n port \"prometheus\" {\n static = 9090\n }\n }\n }\n }\n }\n}", + "template": "job \"${job_name}\" {\n # The \"region\" parameter specifies the region in which to execute the job.\n # If omitted, this inherits the default region name of \"global\".\n # region = \"global\"\n #\n # The \"datacenters\" parameter specifies the list of datacenters which should\n # be considered when placing this task. This must be provided.\n datacenters = \"${datacenters}\"\n\n # The \"type\" parameter controls the type of job, which impacts the scheduler's\n # decision on placement. This configuration is optional and defaults to\n # \"service\". For a full list of job types and their differences, please see\n # the online documentation.\n #\n # For more information, please see the online documentation at:\n #\n # https://www.nomadproject.io/docs/jobspec/schedulers\n #\n type = \"service\"\n\n update {\n # The \"max_parallel\" parameter specifies the maximum number of updates to\n # perform in parallel. In this case, this specifies to update a single task\n # at a time.\n max_parallel = 1\n\n health_check = \"checks\"\n\n # The \"min_healthy_time\" parameter specifies the minimum time the allocation\n # must be in the healthy state before it is marked as healthy and unblocks\n # further allocations from being updated.\n min_healthy_time = \"10s\"\n\n # The \"healthy_deadline\" parameter specifies the deadline in which the\n # allocation must be marked as healthy after which the allocation is\n # automatically transitioned to unhealthy. Transitioning to unhealthy will\n # fail the deployment and potentially roll back the job if \"auto_revert\" is\n # set to true.\n healthy_deadline = \"3m\"\n\n # The \"progress_deadline\" parameter specifies the deadline in which an\n # allocation must be marked as healthy. The deadline begins when the first\n # allocation for the deployment is created and is reset whenever an allocation\n # as part of the deployment transitions to a healthy state. If no allocation\n # transitions to the healthy state before the progress deadline, the\n # deployment is marked as failed.\n progress_deadline = \"10m\"\n\n%{ if use_canary }\n # The \"canary\" parameter specifies that changes to the job that would result\n # in destructive updates should create the specified number of canaries\n # without stopping any previous allocations. Once the operator determines the\n # canaries are healthy, they can be promoted which unblocks a rolling update\n # of the remaining allocations at a rate of \"max_parallel\".\n #\n # Further, setting \"canary\" equal to the count of the task group allows\n # blue/green deployments. When the job is updated, a full set of the new\n # version is deployed and upon promotion the old version is stopped.\n canary = 1\n\n # Specifies if the job should auto-promote to the canary version when all\n # canaries become healthy during a deployment. Defaults to false which means\n # canaries must be manually updated with the nomad deployment promote\n # command.\n auto_promote = true\n\n # The \"auto_revert\" parameter specifies if the job should auto-revert to the\n # last stable job on deployment failure. A job is marked as stable if all the\n # allocations as part of its deployment were marked healthy.\n auto_revert = true\n%{ endif }\n }\n\n # The \"group\" stanza defines a series of tasks that should be co-located on\n # the same Nomad client. Any task within a group will be placed on the same\n # client.\n #\n # For more information and examples on the \"group\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/group\n #\n group \"prod-group1-${service_name}\" {\n # The \"count\" parameter specifies the number of the task groups that should\n # be running under this group. This value must be non-negative and defaults\n # to 1.\n count = ${group_count}\n\n # The volume stanza allows the group to specify that it requires a given\n # volume from the cluster.\n #\n # For more information and examples on the \"volume\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/volume\n #\n %{ if use_host_volume }\n volume \"prod-volume1-${service_name}\" {\n type = \"host\"\n read_only = false\n source = \"${host_volume}\"\n }\n %{ endif }\n\n # The constraint allows restricting the set of eligible nodes. Constraints\n # may filter on attributes or client metadata.\n #\n # For more information and examples on the \"volume\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/constraint\n #\n constraint {\n attribute = \"$${attr.cpu.arch}\"\n operator = \"!=\"\n value = \"arm64\"\n }\n\n # The \"task\" stanza creates an individual unit of work, such as a Docker\n # container, web application, or batch processing.\n #\n # For more information and examples on the \"task\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/task\n #\n task \"prod-task1-${service_name}\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"exec\"\n\n %{ if use_host_volume }\n volume_mount {\n volume = \"prod-volume1-${service_name}\"\n destination = \"${data_dir}\"\n read_only = false\n }\n %{ endif }\n\n %{ if use_vault_provider }\n vault {\n policies = \"${vault_kv_policy_name}\"\n }\n %{ endif }\n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n command = \"local/prometheus-${version}.linux-amd64/prometheus\"\n args = [\n \"--config.file=secrets/prometheus.yml\",\n \"--storage.tsdb.path=${data_dir}prometheus/\",\n \"--storage.tsdb.retention.time=15d\"\n ]\n }\n\n # The artifact stanza instructs Nomad to fetch and unpack a remote resource,\n # such as a file, tarball, or binary. Nomad downloads artifacts using the\n # popular go-getter library, which permits downloading artifacts from a\n # variety of locations using a URL as the input source.\n #\n # For more information and examples on the \"artifact\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/artifact\n #\n artifact {\n source = \"${url}\"\n }\n\n # The \"template\" stanza instructs Nomad to manage a template, such as\n # a configuration file or script. This template can optionally pull data\n # from Consul or Vault to populate runtime configuration data.\n #\n # For more information and examples on the \"template\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/template\n #\n template {\n change_mode = \"noop\"\n change_signal = \"SIGINT\"\n destination = \"secrets/alerts.yml\"\n left_delimiter = \"{{{\"\n right_delimiter = \"}}}\"\n data = \u003c\u003cEOH\n---\ngroups:\n- name: \"Consul\"\n rules:\n - alert: ConsulServiceHealthcheckFailed\n expr: consul_catalog_service_node_healthy == 0\n for: 0m\n labels:\n severity: critical\n annotations:\n summary: \"Consul service healthcheck failed (instance {{ $labels.instance }}).\"\n description: \"Service: `{{ $labels.service_name }}` Healthcheck: `{{ $labels.service_id }}`.\"\n - alert: ConsulMissingMasterNode\n expr: consul_raft_peers \u003c 3\n for: 0m\n labels:\n severity: critical\n annotations:\n summary: \"Consul missing master node (instance {{ $labels.instance }}).\"\n description: \"Numbers of consul raft peers should be 3, in order to preserve quorum.\"\n - alert: ConsulAgentUnhealthy\n expr: consul_health_node_status{status=\"critical\"} == 1\n for: 0m\n labels:\n severity: critical\n annotations:\n summary: \"Consul agent unhealthy (instance {{ $labels.instance }}).\"\n description: \"A Consul agent is down.\"\n- name: \"Hosts\"\n rules:\n - alert: NodeDown\n expr: up == 0\n for: 0m\n labels:\n severity: critical\n annotations:\n summary: \"Prometheus target missing (instance {{ $labels.instance }}).\"\n description: \"A Prometheus target has disappeared. An exporter might be crashed.\"\n - alert: HostHighCpuLoad\n expr: 100 - (avg by(instance) (rate(node_cpu_seconds_total{mode=\"idle\"}[2m])) * 100) \u003e 80\n for: 0m\n labels:\n severity: warning\n annotations:\n summary: \"Host high CPU load (instance {{ $labels.instance }}).\"\n description: \"CPU load is \u003e 80%.\"\n - alert: HostOutOfMemory\n expr: node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes * 100 \u003c 10\n for: 2m\n labels:\n severity: warning\n annotations:\n summary: \"Host out of memory (instance {{ $labels.instance }}).\"\n description: \"Node memory is filling up (\u003c 10% left).\"\n - alert: HostOomKillDetected\n expr: increase(node_vmstat_oom_kill[1m]) \u003e 0\n for: 0m\n labels:\n severity: warning\n annotations:\n summary: \"Host OOM kill detected (instance {{ $labels.instance }}).\"\n description: \"OOM kill detected.\"\n - alert: HostMemoryUnderMemoryPressure\n expr: rate(node_vmstat_pgmajfault[1m]) \u003e 1000\n for: 2m\n labels:\n severity: warning\n annotations:\n summary: \"Host memory under memory pressure (instance {{ $labels.instance }}).\"\n description: \"The node is under heavy memory pressure. High rate of major page faults.\"\n - alert: HostOutOfDiskSpace\n expr: (node_filesystem_avail_bytes * 100) / node_filesystem_size_bytes \u003c 10 and ON (instance, device, mountpoint) node_filesystem_readonly == 0\n for: 2m\n labels:\n severity: warning\n annotations:\n summary: \"Host out of disk space (instance {{ $labels.instance }}).\"\n description: \"Disk is almost full (\u003c 10% left).\"\n - alert: HostRaidDiskFailure\n expr: node_md_disks{state=\"failed\"} \u003e 0\n for: 2m\n labels:\n severity: warning\n annotations:\n summary: \"Host RAID disk failure (instance {{ $labels.instance }}).\"\n description: \"At least one device in RAID array on {{ $labels.instance }} failed. Array {{ $labels.md_device }} needs attention and possibly a disk swap.\"\n - alert: HostConntrackLimit\n expr: node_nf_conntrack_entries / node_nf_conntrack_entries_limit \u003e 0.8\n for: 5m\n labels:\n severity: warning\n annotations:\n summary: \"Host conntrack limit (instance {{ $labels.instance }}).\"\n description: \"The number of conntrack is approching limit.\"\n - alert: HostNetworkInterfaceSaturated\n expr: (rate(node_network_receive_bytes_total{device!~\"^tap.*\"}[1m]) + rate(node_network_transmit_bytes_total{device!~\"^tap.*\"}[1m])) / node_network_speed_bytes{device!~\"^tap.*\"} \u003e 0.8\n for: 1m\n labels:\n severity: warning\n annotations:\n summary: \"Host Network Interface Saturated (instance {{ $labels.instance }}).\"\n description: \"The network interface {{ $labels.interface }} on {{ $labels.instance }} is getting overloaded.\"\n - alert: HostSystemdServiceCrashed\n expr: node_systemd_unit_state{state=\"failed\"} == 1\n for: 0m\n labels:\n severity: warning\n annotations:\n summary: \"Host SystemD service crashed (instance {{ $labels.instance }}).\"\n description: \"SystemD service crashed.\"\n - alert: HostEdacCorrectableErrorsDetected\n expr: increase(node_edac_correctable_errors_total[1m]) \u003e 0\n for: 0m\n labels:\n severity: info\n annotations:\n summary: \"Host EDAC Correctable Errors detected (instance {{ $labels.instance }}).\"\n description: '{{ $labels.instance }} has had {{ printf \"%.0f\" $value }} correctable memory errors reported by EDAC in the last 5 minutes.'\n - alert: HostEdacUncorrectableErrorsDetected\n expr: node_edac_uncorrectable_errors_total \u003e 0\n for: 0m\n labels:\n severity: warning\n annotations:\n summary: \"Host EDAC Uncorrectable Errors detected (instance {{ $labels.instance }}).\"\n description: '{{ $labels.instance }} has had {{ printf \"%.0f\" $value }} uncorrectable memory errors reported by EDAC in the last 5 minutes.'\n- name: \"Min.io\"\n rules:\n - alert: MinioDiskOffline\n expr: minio_offline_disks \u003e 0\n for: 0m\n labels:\n severity: critical\n annotations:\n summary: \"Minio disk offline (instance {{ $labels.instance }})\"\n description: \"Minio disk is offline.\"\n - alert: MinioStorageSpaceExhausted\n expr: minio_disk_storage_free_bytes / 1024 / 1024 / 1024 \u003c 10\n for: 2m\n labels:\n severity: warning\n annotations:\n summary: \"Minio storage space exhausted (instance {{ $labels.instance }}).\"\n description: \"Minio storage space is low (\u003c 10 GB).\"\n- name: \"Prometheus\"\n rules:\n - alert: PrometheusConfigurationReloadFailure\n expr: prometheus_config_last_reload_successful != 1\n for: 0m\n labels:\n severity: warning\n annotations:\n summary: \"Prometheus configuration reload failure (instance {{ $labels.instance }}).\"\n description: \"Prometheus configuration reload error.\"\n - alert: PrometheusTooManyRestarts\n expr: changes(process_start_time_seconds{job=~\"prometheus|pushgateway|alertmanager\"}[15m]) \u003e 2\n for: 0m\n labels:\n severity: warning\n annotations:\n summary: \"Prometheus too many restarts (instance {{ $labels.instance }}).\"\n description: \"Prometheus has restarted more than twice in the last 15 minutes. It might be crashlooping.\"\n - alert: PrometheusAlertmanagerConfigurationReloadFailure\n expr: alertmanager_config_last_reload_successful != 1\n for: 0m\n labels:\n severity: warning\n annotations:\n summary: \"Prometheus AlertManager configuration reload failure (instance {{ $labels.instance }}).\"\n description: \"AlertManager configuration reload error.\"\n - alert: PrometheusRuleEvaluationFailures\n expr: increase(prometheus_rule_evaluation_failures_total[3m]) \u003e 0\n for: 0m\n labels:\n severity: critical\n annotations:\n summary: \"Prometheus rule evaluation failures (instance {{ $labels.instance }}).\"\n description: \"Prometheus encountered {{ $value }} rule evaluation failures, leading to potentially ignored alerts.\"\n - alert: PrometheusTargetScrapingSlow\n expr: prometheus_target_interval_length_seconds{quantile=\"0.9\"} \u003e 60\n for: 5m\n labels:\n severity: warning\n annotations:\n summary: \"Prometheus target scraping slow (instance {{ $labels.instance }}).\"\n description: \"Prometheus is scraping exporters slowly.\"\n - alert: PrometheusTsdbCompactionsFailed\n expr: increase(prometheus_tsdb_compactions_failed_total[1m]) \u003e 0\n for: 0m\n labels:\n severity: critical\n annotations:\n summary: \"Prometheus TSDB compactions failed (instance {{ $labels.instance }}).\"\n description: \"Prometheus encountered {{ $value }} TSDB compactions failures.\"\n - alert: PrometheusTsdbHeadTruncationsFailed\n expr: increase(prometheus_tsdb_head_truncations_failed_total[1m]) \u003e 0\n for: 0m\n labels:\n severity: critical\n annotations:\n summary: \"Prometheus TSDB head truncations failed (instance {{ $labels.instance }}).\"\n description: \"Prometheus encountered {{ $value }} TSDB head truncation failures.\"\n - alert: PrometheusTsdbWalCorruptions\n expr: increase(prometheus_tsdb_wal_corruptions_total[1m]) \u003e 0\n for: 0m\n labels:\n severity: critical\n annotations:\n summary: \"Prometheus TSDB WAL corruptions (instance {{ $labels.instance }}).\"\n description: \"Prometheus encountered {{ $value }} TSDB WAL corruptions.\"\n - alert: PrometheusTsdbWalTruncationsFailed\n expr: increase(prometheus_tsdb_wal_truncations_failed_total[1m]) \u003e 0\n for: 0m\n labels:\n severity: critical\n annotations:\n summary: \"Prometheus TSDB WAL truncations failed (instance {{ $labels.instance }}).\"\n description: \"Prometheus encountered {{ $value }} TSDB WAL truncation failures.\"\nEOH\n }\n\n template {\n change_mode = \"noop\"\n change_signal = \"SIGINT\"\n destination = \"secrets/prometheus.yml\"\n data = \u003c\u003cEOH\n---\nglobal:\n scrape_interval: 5s\n scrape_timeout: 5s\n evaluation_interval: 5s\n\nalerting:\n alertmanagers:\n - consul_sd_configs:\n - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n services: [ 'alertmanager' ]\n\nrule_files:\n - 'alerts.yml'\n\nscrape_configs:\n\n - job_name: 'Nomad Cluster'\n consul_sd_configs:\n - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n services: [ 'nomad-client', 'nomad' ]\n relabel_configs:\n - source_labels: [__meta_consul_tags]\n regex: '(.*)http(.*)'\n action: keep\n metrics_path: /v1/metrics\n params:\n format: [ 'prometheus' ]\n\n - job_name: 'Consul Cluster'\n static_configs:\n - targets: [ '10.30.51.30:8500', '10.30.51.32:8500', '10.30.51.33:8500' ]\n metrics_path: /v1/agent/metrics\n params:\n format: [ 'prometheus' ]\n\n - job_name: 'Alertmanager'\n consul_sd_configs:\n - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n services: [ 'alertmanager' ]\n\n - job_name: 'Blackbox Exporter (icmp)'\n static_configs:\n - targets: [ 'gerrit.fd.io' ]\n - targets: [ 'jenkins.fd.io' ]\n - targets: [ '10.30.51.32' ]\n params:\n module: [ 'icmp_v4' ]\n relabel_configs:\n - source_labels: [__address__]\n target_label: __param_target\n - source_labels: [__param_target]\n target_label: instance\n - target_label: __address__\n replacement: localhost:9115\n metrics_path: /probe\n\n - job_name: 'Blackbox Exporter (http)'\n static_configs:\n - targets: [ 'gerrit.fd.io' ]\n - targets: [ 'jenkins.fd.io' ]\n params:\n module: [ 'http_2xx' ]\n relabel_configs:\n - source_labels: [__address__]\n target_label: __param_target\n - source_labels: [__param_target]\n target_label: instance\n - target_label: __address__\n replacement: localhost:9115\n metrics_path: /probe\n\n - job_name: 'cAdvisor Exporter'\n consul_sd_configs:\n - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n services: [ 'cadvisorexporter' ]\n\n - job_name: 'Grafana'\n consul_sd_configs:\n - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n services: [ 'grafana' ]\n\n - job_name: 'Node Exporter'\n consul_sd_configs:\n - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n services: [ 'nodeexporter' ]\n\n - job_name: 'Prometheus'\n consul_sd_configs:\n - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n services: [ 'prometheus' ]\n\n - job_name: 'Minio'\n bearer_token: eyJhbGciOiJIUzUxMiIsInR5cCI6IkpXVCJ9.eyJleHAiOjQ3NjQ1ODEzMzcsImlzcyI6InByb21ldGhldXMiLCJzdWIiOiJtaW5pbyJ9.oeTw3EIaiFmlDikrHXWiWXMH2vxLfDLkfjEC7G2N3M_keH_xyA_l2ofLLNYtopa_3GCEZnxLQdPuFZrmgpkDWg\n consul_sd_configs:\n - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n services: [ 'storage' ]\n metrics_path: /minio/prometheus/metrics\nEOH\n }\n\n # The service stanza instructs Nomad to register a service with Consul.\n #\n # For more information and examples on the \"task\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/service\n #\n service {\n name = \"${service_name}\"\n port = \"${service_name}\"\n tags = [ \"${service_name}$${NOMAD_ALLOC_INDEX}\" ]\n check {\n name = \"Prometheus Check Live\"\n type = \"http\"\n path = \"/-/healthy\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # For more information and examples on the \"resources\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/resources\n #\n resources {\n cpu = ${cpu}\n memory = ${mem}\n # The network stanza specifies the networking requirements for the task\n # group, including the network mode and port allocations. When scheduling\n # jobs in Nomad they are provisioned across your fleet of machines along\n # with other jobs and services. Because you don't know in advance what host\n # your job will be provisioned on, Nomad will provide your tasks with\n # network configuration when they start up.\n #\n # For more information and examples on the \"template\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/network\n #\n network {\n port \"${service_name}\" {\n static = ${port}\n }\n }\n }\n }\n }\n}", + "vars": { + "cpu": "2000", + "data_dir": "/data/", + "datacenters": "yul1", + "group_count": "4", + "host_volume": "prod-volume-data1-1", + "job_name": "prod-prometheus", + "mem": "8192", + "port": "9090", + "service_name": "prometheus", + "url": "https://github.com/prometheus/prometheus/releases/download/v2.24.0/prometheus-2.24.0.linux-amd64.tar.gz", + "use_canary": "true", + "use_host_volume": "true", + "use_vault_provider": "false", + "version": "2.24.0" + } + }, + "sensitive_attributes": [] + } + ] + }, + { + "module": "module.prometheus", + "mode": "managed", + "type": "nomad_job", + "name": "nomad_job_prometheus", + "provider": "provider[\"registry.terraform.io/hashicorp/nomad\"].yul1", + "instances": [ + { + "schema_version": 0, + "attributes": { + "allocation_ids": [ + "79c4c6b7-e8e4-79e7-9dae-9a26142cd94c", + "2e11f44e-814e-db74-a9ee-8bcbebb1fa0b", + "83f9c9aa-f4f2-b832-a937-aaee4181493e", + "231f1338-a871-b44e-d545-e8af01d7eebe" + ], + "datacenters": [ + "yul1" + ], + "deployment_id": "4cbf8370-f2d7-16c2-d500-f6495d43537d", + "deployment_status": "successful", + "deregister_on_destroy": true, + "deregister_on_id_change": true, + "detach": false, + "id": "prod-prometheus", + "jobspec": "job \"prod-prometheus\" {\n # The \"region\" parameter specifies the region in which to execute the job.\n # If omitted, this inherits the default region name of \"global\".\n # region = \"global\"\n #\n # The \"datacenters\" parameter specifies the list of datacenters which should\n # be considered when placing this task. This must be provided.\n datacenters = \"yul1\"\n\n # The \"type\" parameter controls the type of job, which impacts the scheduler's\n # decision on placement. This configuration is optional and defaults to\n # \"service\". For a full list of job types and their differences, please see\n # the online documentation.\n #\n # For more information, please see the online documentation at:\n #\n # https://www.nomadproject.io/docs/jobspec/schedulers\n #\n type = \"service\"\n\n update {\n # The \"max_parallel\" parameter specifies the maximum number of updates to\n # perform in parallel. In this case, this specifies to update a single task\n # at a time.\n max_parallel = 1\n\n health_check = \"checks\"\n\n # The \"min_healthy_time\" parameter specifies the minimum time the allocation\n # must be in the healthy state before it is marked as healthy and unblocks\n # further allocations from being updated.\n min_healthy_time = \"10s\"\n\n # The \"healthy_deadline\" parameter specifies the deadline in which the\n # allocation must be marked as healthy after which the allocation is\n # automatically transitioned to unhealthy. Transitioning to unhealthy will\n # fail the deployment and potentially roll back the job if \"auto_revert\" is\n # set to true.\n healthy_deadline = \"3m\"\n\n # The \"progress_deadline\" parameter specifies the deadline in which an\n # allocation must be marked as healthy. The deadline begins when the first\n # allocation for the deployment is created and is reset whenever an allocation\n # as part of the deployment transitions to a healthy state. If no allocation\n # transitions to the healthy state before the progress deadline, the\n # deployment is marked as failed.\n progress_deadline = \"10m\"\n\n\n # The \"canary\" parameter specifies that changes to the job that would result\n # in destructive updates should create the specified number of canaries\n # without stopping any previous allocations. Once the operator determines the\n # canaries are healthy, they can be promoted which unblocks a rolling update\n # of the remaining allocations at a rate of \"max_parallel\".\n #\n # Further, setting \"canary\" equal to the count of the task group allows\n # blue/green deployments. When the job is updated, a full set of the new\n # version is deployed and upon promotion the old version is stopped.\n canary = 1\n\n # Specifies if the job should auto-promote to the canary version when all\n # canaries become healthy during a deployment. Defaults to false which means\n # canaries must be manually updated with the nomad deployment promote\n # command.\n auto_promote = true\n\n # The \"auto_revert\" parameter specifies if the job should auto-revert to the\n # last stable job on deployment failure. A job is marked as stable if all the\n # allocations as part of its deployment were marked healthy.\n auto_revert = true\n\n }\n\n # The \"group\" stanza defines a series of tasks that should be co-located on\n # the same Nomad client. Any task within a group will be placed on the same\n # client.\n #\n # For more information and examples on the \"group\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/group\n #\n group \"prod-group1-prometheus\" {\n # The \"count\" parameter specifies the number of the task groups that should\n # be running under this group. This value must be non-negative and defaults\n # to 1.\n count = 4\n\n # The volume stanza allows the group to specify that it requires a given\n # volume from the cluster.\n #\n # For more information and examples on the \"volume\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/volume\n #\n \n volume \"prod-volume1-prometheus\" {\n type = \"host\"\n read_only = false\n source = \"prod-volume-data1-1\"\n }\n \n\n # The constraint allows restricting the set of eligible nodes. Constraints\n # may filter on attributes or client metadata.\n #\n # For more information and examples on the \"volume\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/constraint\n #\n constraint {\n attribute = \"${attr.cpu.arch}\"\n operator = \"!=\"\n value = \"arm64\"\n }\n\n # The \"task\" stanza creates an individual unit of work, such as a Docker\n # container, web application, or batch processing.\n #\n # For more information and examples on the \"task\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/task\n #\n task \"prod-task1-prometheus\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"exec\"\n\n \n volume_mount {\n volume = \"prod-volume1-prometheus\"\n destination = \"/data/\"\n read_only = false\n }\n \n\n \n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n command = \"local/prometheus-2.24.0.linux-amd64/prometheus\"\n args = [\n \"--config.file=secrets/prometheus.yml\",\n \"--storage.tsdb.path=/data/prometheus/\",\n \"--storage.tsdb.retention.time=15d\"\n ]\n }\n\n # The artifact stanza instructs Nomad to fetch and unpack a remote resource,\n # such as a file, tarball, or binary. Nomad downloads artifacts using the\n # popular go-getter library, which permits downloading artifacts from a\n # variety of locations using a URL as the input source.\n #\n # For more information and examples on the \"artifact\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/artifact\n #\n artifact {\n source = \"https://github.com/prometheus/prometheus/releases/download/v2.24.0/prometheus-2.24.0.linux-amd64.tar.gz\"\n }\n\n # The \"template\" stanza instructs Nomad to manage a template, such as\n # a configuration file or script. This template can optionally pull data\n # from Consul or Vault to populate runtime configuration data.\n #\n # For more information and examples on the \"template\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/template\n #\n template {\n change_mode = \"noop\"\n change_signal = \"SIGINT\"\n destination = \"secrets/alerts.yml\"\n left_delimiter = \"{{{\"\n right_delimiter = \"}}}\"\n data = \u003c\u003cEOH\n---\ngroups:\n- name: \"Consul\"\n rules:\n - alert: ConsulServiceHealthcheckFailed\n expr: consul_catalog_service_node_healthy == 0\n for: 0m\n labels:\n severity: critical\n annotations:\n summary: \"Consul service healthcheck failed (instance {{ $labels.instance }}).\"\n description: \"Service: `{{ $labels.service_name }}` Healthcheck: `{{ $labels.service_id }}`.\"\n - alert: ConsulMissingMasterNode\n expr: consul_raft_peers \u003c 3\n for: 0m\n labels:\n severity: critical\n annotations:\n summary: \"Consul missing master node (instance {{ $labels.instance }}).\"\n description: \"Numbers of consul raft peers should be 3, in order to preserve quorum.\"\n - alert: ConsulAgentUnhealthy\n expr: consul_health_node_status{status=\"critical\"} == 1\n for: 0m\n labels:\n severity: critical\n annotations:\n summary: \"Consul agent unhealthy (instance {{ $labels.instance }}).\"\n description: \"A Consul agent is down.\"\n- name: \"Hosts\"\n rules:\n - alert: NodeDown\n expr: up == 0\n for: 0m\n labels:\n severity: critical\n annotations:\n summary: \"Prometheus target missing (instance {{ $labels.instance }}).\"\n description: \"A Prometheus target has disappeared. An exporter might be crashed.\"\n - alert: HostHighCpuLoad\n expr: 100 - (avg by(instance) (rate(node_cpu_seconds_total{mode=\"idle\"}[2m])) * 100) \u003e 80\n for: 0m\n labels:\n severity: warning\n annotations:\n summary: \"Host high CPU load (instance {{ $labels.instance }}).\"\n description: \"CPU load is \u003e 80%.\"\n - alert: HostOutOfMemory\n expr: node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes * 100 \u003c 10\n for: 2m\n labels:\n severity: warning\n annotations:\n summary: \"Host out of memory (instance {{ $labels.instance }}).\"\n description: \"Node memory is filling up (\u003c 10% left).\"\n - alert: HostOomKillDetected\n expr: increase(node_vmstat_oom_kill[1m]) \u003e 0\n for: 0m\n labels:\n severity: warning\n annotations:\n summary: \"Host OOM kill detected (instance {{ $labels.instance }}).\"\n description: \"OOM kill detected.\"\n - alert: HostMemoryUnderMemoryPressure\n expr: rate(node_vmstat_pgmajfault[1m]) \u003e 1000\n for: 2m\n labels:\n severity: warning\n annotations:\n summary: \"Host memory under memory pressure (instance {{ $labels.instance }}).\"\n description: \"The node is under heavy memory pressure. High rate of major page faults.\"\n - alert: HostOutOfDiskSpace\n expr: (node_filesystem_avail_bytes * 100) / node_filesystem_size_bytes \u003c 10 and ON (instance, device, mountpoint) node_filesystem_readonly == 0\n for: 2m\n labels:\n severity: warning\n annotations:\n summary: \"Host out of disk space (instance {{ $labels.instance }}).\"\n description: \"Disk is almost full (\u003c 10% left).\"\n - alert: HostRaidDiskFailure\n expr: node_md_disks{state=\"failed\"} \u003e 0\n for: 2m\n labels:\n severity: warning\n annotations:\n summary: \"Host RAID disk failure (instance {{ $labels.instance }}).\"\n description: \"At least one device in RAID array on {{ $labels.instance }} failed. Array {{ $labels.md_device }} needs attention and possibly a disk swap.\"\n - alert: HostConntrackLimit\n expr: node_nf_conntrack_entries / node_nf_conntrack_entries_limit \u003e 0.8\n for: 5m\n labels:\n severity: warning\n annotations:\n summary: \"Host conntrack limit (instance {{ $labels.instance }}).\"\n description: \"The number of conntrack is approching limit.\"\n - alert: HostNetworkInterfaceSaturated\n expr: (rate(node_network_receive_bytes_total{device!~\"^tap.*\"}[1m]) + rate(node_network_transmit_bytes_total{device!~\"^tap.*\"}[1m])) / node_network_speed_bytes{device!~\"^tap.*\"} \u003e 0.8\n for: 1m\n labels:\n severity: warning\n annotations:\n summary: \"Host Network Interface Saturated (instance {{ $labels.instance }}).\"\n description: \"The network interface {{ $labels.interface }} on {{ $labels.instance }} is getting overloaded.\"\n - alert: HostSystemdServiceCrashed\n expr: node_systemd_unit_state{state=\"failed\"} == 1\n for: 0m\n labels:\n severity: warning\n annotations:\n summary: \"Host SystemD service crashed (instance {{ $labels.instance }}).\"\n description: \"SystemD service crashed.\"\n - alert: HostEdacCorrectableErrorsDetected\n expr: increase(node_edac_correctable_errors_total[1m]) \u003e 0\n for: 0m\n labels:\n severity: info\n annotations:\n summary: \"Host EDAC Correctable Errors detected (instance {{ $labels.instance }}).\"\n description: '{{ $labels.instance }} has had {{ printf \"%.0f\" $value }} correctable memory errors reported by EDAC in the last 5 minutes.'\n - alert: HostEdacUncorrectableErrorsDetected\n expr: node_edac_uncorrectable_errors_total \u003e 0\n for: 0m\n labels:\n severity: warning\n annotations:\n summary: \"Host EDAC Uncorrectable Errors detected (instance {{ $labels.instance }}).\"\n description: '{{ $labels.instance }} has had {{ printf \"%.0f\" $value }} uncorrectable memory errors reported by EDAC in the last 5 minutes.'\n- name: \"Min.io\"\n rules:\n - alert: MinioDiskOffline\n expr: minio_offline_disks \u003e 0\n for: 0m\n labels:\n severity: critical\n annotations:\n summary: \"Minio disk offline (instance {{ $labels.instance }})\"\n description: \"Minio disk is offline.\"\n - alert: MinioStorageSpaceExhausted\n expr: minio_disk_storage_free_bytes / 1024 / 1024 / 1024 \u003c 10\n for: 2m\n labels:\n severity: warning\n annotations:\n summary: \"Minio storage space exhausted (instance {{ $labels.instance }}).\"\n description: \"Minio storage space is low (\u003c 10 GB).\"\n- name: \"Prometheus\"\n rules:\n - alert: PrometheusConfigurationReloadFailure\n expr: prometheus_config_last_reload_successful != 1\n for: 0m\n labels:\n severity: warning\n annotations:\n summary: \"Prometheus configuration reload failure (instance {{ $labels.instance }}).\"\n description: \"Prometheus configuration reload error.\"\n - alert: PrometheusTooManyRestarts\n expr: changes(process_start_time_seconds{job=~\"prometheus|pushgateway|alertmanager\"}[15m]) \u003e 2\n for: 0m\n labels:\n severity: warning\n annotations:\n summary: \"Prometheus too many restarts (instance {{ $labels.instance }}).\"\n description: \"Prometheus has restarted more than twice in the last 15 minutes. It might be crashlooping.\"\n - alert: PrometheusAlertmanagerConfigurationReloadFailure\n expr: alertmanager_config_last_reload_successful != 1\n for: 0m\n labels:\n severity: warning\n annotations:\n summary: \"Prometheus AlertManager configuration reload failure (instance {{ $labels.instance }}).\"\n description: \"AlertManager configuration reload error.\"\n - alert: PrometheusRuleEvaluationFailures\n expr: increase(prometheus_rule_evaluation_failures_total[3m]) \u003e 0\n for: 0m\n labels:\n severity: critical\n annotations:\n summary: \"Prometheus rule evaluation failures (instance {{ $labels.instance }}).\"\n description: \"Prometheus encountered {{ $value }} rule evaluation failures, leading to potentially ignored alerts.\"\n - alert: PrometheusTargetScrapingSlow\n expr: prometheus_target_interval_length_seconds{quantile=\"0.9\"} \u003e 60\n for: 5m\n labels:\n severity: warning\n annotations:\n summary: \"Prometheus target scraping slow (instance {{ $labels.instance }}).\"\n description: \"Prometheus is scraping exporters slowly.\"\n - alert: PrometheusTsdbCompactionsFailed\n expr: increase(prometheus_tsdb_compactions_failed_total[1m]) \u003e 0\n for: 0m\n labels:\n severity: critical\n annotations:\n summary: \"Prometheus TSDB compactions failed (instance {{ $labels.instance }}).\"\n description: \"Prometheus encountered {{ $value }} TSDB compactions failures.\"\n - alert: PrometheusTsdbHeadTruncationsFailed\n expr: increase(prometheus_tsdb_head_truncations_failed_total[1m]) \u003e 0\n for: 0m\n labels:\n severity: critical\n annotations:\n summary: \"Prometheus TSDB head truncations failed (instance {{ $labels.instance }}).\"\n description: \"Prometheus encountered {{ $value }} TSDB head truncation failures.\"\n - alert: PrometheusTsdbWalCorruptions\n expr: increase(prometheus_tsdb_wal_corruptions_total[1m]) \u003e 0\n for: 0m\n labels:\n severity: critical\n annotations:\n summary: \"Prometheus TSDB WAL corruptions (instance {{ $labels.instance }}).\"\n description: \"Prometheus encountered {{ $value }} TSDB WAL corruptions.\"\n - alert: PrometheusTsdbWalTruncationsFailed\n expr: increase(prometheus_tsdb_wal_truncations_failed_total[1m]) \u003e 0\n for: 0m\n labels:\n severity: critical\n annotations:\n summary: \"Prometheus TSDB WAL truncations failed (instance {{ $labels.instance }}).\"\n description: \"Prometheus encountered {{ $value }} TSDB WAL truncation failures.\"\nEOH\n }\n\n template {\n change_mode = \"noop\"\n change_signal = \"SIGINT\"\n destination = \"secrets/prometheus.yml\"\n data = \u003c\u003cEOH\n---\nglobal:\n scrape_interval: 5s\n scrape_timeout: 5s\n evaluation_interval: 5s\n\nalerting:\n alertmanagers:\n - consul_sd_configs:\n - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n services: [ 'alertmanager' ]\n\nrule_files:\n - 'alerts.yml'\n\nscrape_configs:\n\n - job_name: 'Nomad Cluster'\n consul_sd_configs:\n - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n services: [ 'nomad-client', 'nomad' ]\n relabel_configs:\n - source_labels: [__meta_consul_tags]\n regex: '(.*)http(.*)'\n action: keep\n metrics_path: /v1/metrics\n params:\n format: [ 'prometheus' ]\n\n - job_name: 'Consul Cluster'\n static_configs:\n - targets: [ '10.30.51.30:8500', '10.30.51.32:8500', '10.30.51.33:8500' ]\n metrics_path: /v1/agent/metrics\n params:\n format: [ 'prometheus' ]\n\n - job_name: 'Alertmanager'\n consul_sd_configs:\n - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n services: [ 'alertmanager' ]\n\n - job_name: 'Blackbox Exporter (icmp)'\n static_configs:\n - targets: [ 'gerrit.fd.io' ]\n - targets: [ 'jenkins.fd.io' ]\n - targets: [ '10.30.51.32' ]\n params:\n module: [ 'icmp_v4' ]\n relabel_configs:\n - source_labels: [__address__]\n target_label: __param_target\n - source_labels: [__param_target]\n target_label: instance\n - target_label: __address__\n replacement: localhost:9115\n metrics_path: /probe\n\n - job_name: 'Blackbox Exporter (http)'\n static_configs:\n - targets: [ 'gerrit.fd.io' ]\n - targets: [ 'jenkins.fd.io' ]\n params:\n module: [ 'http_2xx' ]\n relabel_configs:\n - source_labels: [__address__]\n target_label: __param_target\n - source_labels: [__param_target]\n target_label: instance\n - target_label: __address__\n replacement: localhost:9115\n metrics_path: /probe\n\n - job_name: 'cAdvisor Exporter'\n consul_sd_configs:\n - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n services: [ 'cadvisorexporter' ]\n\n - job_name: 'Grafana'\n consul_sd_configs:\n - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n services: [ 'grafana' ]\n\n - job_name: 'Node Exporter'\n consul_sd_configs:\n - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n services: [ 'nodeexporter' ]\n\n - job_name: 'Prometheus'\n consul_sd_configs:\n - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n services: [ 'prometheus' ]\n\n - job_name: 'Minio'\n bearer_token: eyJhbGciOiJIUzUxMiIsInR5cCI6IkpXVCJ9.eyJleHAiOjQ3NjQ1ODEzMzcsImlzcyI6InByb21ldGhldXMiLCJzdWIiOiJtaW5pbyJ9.oeTw3EIaiFmlDikrHXWiWXMH2vxLfDLkfjEC7G2N3M_keH_xyA_l2ofLLNYtopa_3GCEZnxLQdPuFZrmgpkDWg\n consul_sd_configs:\n - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n services: [ 'storage' ]\n metrics_path: /minio/prometheus/metrics\nEOH\n }\n\n # The service stanza instructs Nomad to register a service with Consul.\n #\n # For more information and examples on the \"task\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/service\n #\n service {\n name = \"prometheus\"\n port = \"prometheus\"\n tags = [ \"prometheus${NOMAD_ALLOC_INDEX}\" ]\n check {\n name = \"Prometheus Check Live\"\n type = \"http\"\n path = \"/-/healthy\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # For more information and examples on the \"resources\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/resources\n #\n resources {\n cpu = 2000\n memory = 8192\n # The network stanza specifies the networking requirements for the task\n # group, including the network mode and port allocations. When scheduling\n # jobs in Nomad they are provisioned across your fleet of machines along\n # with other jobs and services. Because you don't know in advance what host\n # your job will be provisioned on, Nomad will provide your tasks with\n # network configuration when they start up.\n #\n # For more information and examples on the \"template\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/network\n #\n network {\n port \"prometheus\" {\n static = 9090\n }\n }\n }\n }\n }\n}", + "json": null, + "modify_index": "7147932", + "name": "prod-prometheus", + "namespace": "default", + "policy_override": null, + "purge_on_destroy": null, + "region": "global", + "task_groups": [ + { + "count": 4, + "meta": {}, + "name": "prod-group1-prometheus", + "task": [ + { + "driver": "exec", + "meta": {}, + "name": "prod-task1-prometheus", + "volume_mounts": [ + { + "destination": "/data/", + "read_only": false, + "volume": "prod-volume1-prometheus" + } + ] + } + ], + "volumes": [ + { + "name": "prod-volume1-prometheus", + "read_only": false, + "source": "prod-volume-data1-1", + "type": "host" + } + ] + } + ], + "type": "service" + }, + "sensitive_attributes": [], + "private": "bnVsbA==", + "dependencies": [ + "module.prometheus.data.template_file.nomad_job_prometheus" + ] + } + ] + }, + { + "module": "module.vpp_device", + "mode": "data", + "type": "template_file", + "name": "nomad_job_csit_shim", + "provider": "provider[\"registry.terraform.io/hashicorp/template\"]", + "instances": [ + { + "schema_version": 0, + "attributes": { + "filename": null, + "id": "a285223159ce0af9e5427d857021e5651c09408af90decd3b93a90efd4fd7ce8", + "rendered": "job \"prod-device-csit-shim\" {\n # The \"region\" parameter specifies the region in which to execute the job.\n # If omitted, this inherits the default region name of \"global\".\n # region = \"global\"\n #\n # The \"datacenters\" parameter specifies the list of datacenters which should\n # be considered when placing this task. This must be provided.\n datacenters = \"yul1\"\n\n # The \"type\" parameter controls the type of job, which impacts the scheduler's\n # decision on placement. This configuration is optional and defaults to\n # \"service\". For a full list of job types and their differences, please see\n # the online documentation.\n #\n # For more information, please see the online documentation at:\n #\n # https://www.nomadproject.io/docs/jobspec/schedulers.html\n #\n type = \"system\"\n\n # The \"group\" stanza defines a series of tasks that should be co-located on\n # the same Nomad client. Any task within a group will be placed on the same\n # client.\n #\n # For more information and examples on the \"group\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/group.html\n #\n group \"prod-group1-csit-shim-amd\" {\n # The \"count\" parameter specifies the number of the task groups that should\n # be running under this group. This value must be non-negative and defaults\n # to 1.\n count = 1\n\n constraint {\n attribute = \"${node.class}\"\n value = \"csit\"\n }\n\n restart {\n interval = \"1m\"\n attempts = 3\n delay = \"15s\"\n mode = \"delay\"\n }\n\n # The \"task\" stanza creates an individual unit of work, such as a Docker\n # container, web application, or batch processing.\n #\n # For more information and examples on the \"task\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/task.html\n #\n task \"prod-task1-csit-shim-amd\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"docker\"\n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n image = \"csit_shim-ubuntu1804:local\"\n network_mode = \"host\"\n pid_mode = \"host\"\n volumes = [\n \"/var/run/docker.sock:/var/run/docker.sock\"\n ]\n privileged = true\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # For more information and examples on the \"resources\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/resources.html\n #\n resources {\n cpu = 1000\n memory = 5000\n network {\n port \"ssh\" {\n static = 6022\n }\n port \"ssh2\" {\n static = 6023\n }\n }\n }\n }\n }\n\n group \"prod-group1-csit-shim-arm\" {\n # The \"count\" parameter specifies the number of the task groups that should\n # be running under this group. This value must be non-negative and defaults\n # to 1.\n count = 1\n\n constraint {\n attribute = \"${node.class}\"\n value = \"csitarm\"\n }\n\n restart {\n interval = \"1m\"\n attempts = 3\n delay = \"15s\"\n mode = \"delay\"\n }\n\n # The \"task\" stanza creates an individual unit of work, such as a Docker\n # container, web application, or batch processing.\n #\n # For more information and examples on the \"task\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/task.html\n #\n task \"prod-task1-csit-shim-arm\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"docker\"\n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n image = \"csit_shim-ubuntu1804:local\"\n network_mode = \"host\"\n pid_mode = \"host\"\n volumes = [\n \"/var/run/docker.sock:/var/run/docker.sock\"\n ]\n privileged = true\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # For more information and examples on the \"resources\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/resources.html\n #\n resources {\n cpu = 1000\n memory = 5000\n network {\n port \"ssh\" {\n static = 6022\n }\n port \"ssh2\" {\n static = 6023\n }\n }\n }\n }\n }\n}", + "template": "job \"${job_name}\" {\n # The \"region\" parameter specifies the region in which to execute the job.\n # If omitted, this inherits the default region name of \"global\".\n # region = \"global\"\n #\n # The \"datacenters\" parameter specifies the list of datacenters which should\n # be considered when placing this task. This must be provided.\n datacenters = \"${datacenters}\"\n\n # The \"type\" parameter controls the type of job, which impacts the scheduler's\n # decision on placement. This configuration is optional and defaults to\n # \"service\". For a full list of job types and their differences, please see\n # the online documentation.\n #\n # For more information, please see the online documentation at:\n #\n # https://www.nomadproject.io/docs/jobspec/schedulers.html\n #\n type = \"system\"\n\n # The \"group\" stanza defines a series of tasks that should be co-located on\n # the same Nomad client. Any task within a group will be placed on the same\n # client.\n #\n # For more information and examples on the \"group\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/group.html\n #\n group \"prod-group1-csit-shim-amd\" {\n # The \"count\" parameter specifies the number of the task groups that should\n # be running under this group. This value must be non-negative and defaults\n # to 1.\n count = ${group_count}\n\n constraint {\n attribute = \"$${node.class}\"\n value = \"csit\"\n }\n\n restart {\n interval = \"1m\"\n attempts = 3\n delay = \"15s\"\n mode = \"delay\"\n }\n\n # The \"task\" stanza creates an individual unit of work, such as a Docker\n # container, web application, or batch processing.\n #\n # For more information and examples on the \"task\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/task.html\n #\n task \"prod-task1-csit-shim-amd\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"docker\"\n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n image = \"csit_shim-ubuntu1804:local\"\n network_mode = \"host\"\n pid_mode = \"host\"\n volumes = [\n \"/var/run/docker.sock:/var/run/docker.sock\"\n ]\n privileged = true\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # For more information and examples on the \"resources\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/resources.html\n #\n resources {\n cpu = ${cpu}\n memory = ${mem}\n network {\n port \"ssh\" {\n static = 6022\n }\n port \"ssh2\" {\n static = 6023\n }\n }\n }\n }\n }\n\n group \"prod-group1-csit-shim-arm\" {\n # The \"count\" parameter specifies the number of the task groups that should\n # be running under this group. This value must be non-negative and defaults\n # to 1.\n count = ${group_count}\n\n constraint {\n attribute = \"$${node.class}\"\n value = \"csitarm\"\n }\n\n restart {\n interval = \"1m\"\n attempts = 3\n delay = \"15s\"\n mode = \"delay\"\n }\n\n # The \"task\" stanza creates an individual unit of work, such as a Docker\n # container, web application, or batch processing.\n #\n # For more information and examples on the \"task\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/task.html\n #\n task \"prod-task1-csit-shim-arm\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"docker\"\n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n image = \"csit_shim-ubuntu1804:local\"\n network_mode = \"host\"\n pid_mode = \"host\"\n volumes = [\n \"/var/run/docker.sock:/var/run/docker.sock\"\n ]\n privileged = true\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # For more information and examples on the \"resources\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/resources.html\n #\n resources {\n cpu = ${cpu}\n memory = ${mem}\n network {\n port \"ssh\" {\n static = 6022\n }\n port \"ssh2\" {\n static = 6023\n }\n }\n }\n }\n }\n}", + "vars": { + "cpu": "1000", + "datacenters": "yul1", + "group_count": "1", + "job_name": "prod-device-csit-shim", + "mem": "5000" + } + }, + "sensitive_attributes": [] + } + ] + }, + { + "module": "module.vpp_device", + "mode": "managed", + "type": "nomad_job", + "name": "nomad_job_csit_shim", + "provider": "provider[\"registry.terraform.io/hashicorp/nomad\"].yul1", + "instances": [ + { + "schema_version": 0, + "attributes": { + "allocation_ids": [ + "ecfcd9ad-b959-0fa4-c1ec-8b82195830f1", + "190f5699-0d10-7f85-ac68-96927702070b", + "2fbbef45-f00a-1367-08c4-c2239de9e78d", + "dd57bc83-2229-d242-1caf-b743f186e7a2" + ], + "datacenters": [ + "yul1" + ], + "deployment_id": "", + "deployment_status": "", + "deregister_on_destroy": true, + "deregister_on_id_change": true, + "detach": false, + "id": "prod-device-csit-shim", + "jobspec": "job \"prod-device-csit-shim\" {\n # The \"region\" parameter specifies the region in which to execute the job.\n # If omitted, this inherits the default region name of \"global\".\n # region = \"global\"\n #\n # The \"datacenters\" parameter specifies the list of datacenters which should\n # be considered when placing this task. This must be provided.\n datacenters = \"yul1\"\n\n # The \"type\" parameter controls the type of job, which impacts the scheduler's\n # decision on placement. This configuration is optional and defaults to\n # \"service\". For a full list of job types and their differences, please see\n # the online documentation.\n #\n # For more information, please see the online documentation at:\n #\n # https://www.nomadproject.io/docs/jobspec/schedulers.html\n #\n type = \"system\"\n\n # The \"group\" stanza defines a series of tasks that should be co-located on\n # the same Nomad client. Any task within a group will be placed on the same\n # client.\n #\n # For more information and examples on the \"group\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/group.html\n #\n group \"prod-group1-csit-shim-amd\" {\n # The \"count\" parameter specifies the number of the task groups that should\n # be running under this group. This value must be non-negative and defaults\n # to 1.\n count = 1\n\n constraint {\n attribute = \"${node.class}\"\n value = \"csit\"\n }\n\n restart {\n interval = \"1m\"\n attempts = 3\n delay = \"15s\"\n mode = \"delay\"\n }\n\n # The \"task\" stanza creates an individual unit of work, such as a Docker\n # container, web application, or batch processing.\n #\n # For more information and examples on the \"task\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/task.html\n #\n task \"prod-task1-csit-shim-amd\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"docker\"\n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n image = \"csit_shim-ubuntu1804:local\"\n network_mode = \"host\"\n pid_mode = \"host\"\n volumes = [\n \"/var/run/docker.sock:/var/run/docker.sock\"\n ]\n privileged = true\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # For more information and examples on the \"resources\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/resources.html\n #\n resources {\n cpu = 1000\n memory = 5000\n network {\n port \"ssh\" {\n static = 6022\n }\n port \"ssh2\" {\n static = 6023\n }\n }\n }\n }\n }\n\n group \"prod-group1-csit-shim-arm\" {\n # The \"count\" parameter specifies the number of the task groups that should\n # be running under this group. This value must be non-negative and defaults\n # to 1.\n count = 1\n\n constraint {\n attribute = \"${node.class}\"\n value = \"csitarm\"\n }\n\n restart {\n interval = \"1m\"\n attempts = 3\n delay = \"15s\"\n mode = \"delay\"\n }\n\n # The \"task\" stanza creates an individual unit of work, such as a Docker\n # container, web application, or batch processing.\n #\n # For more information and examples on the \"task\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/task.html\n #\n task \"prod-task1-csit-shim-arm\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"docker\"\n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n image = \"csit_shim-ubuntu1804:local\"\n network_mode = \"host\"\n pid_mode = \"host\"\n volumes = [\n \"/var/run/docker.sock:/var/run/docker.sock\"\n ]\n privileged = true\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # For more information and examples on the \"resources\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/resources.html\n #\n resources {\n cpu = 1000\n memory = 5000\n network {\n port \"ssh\" {\n static = 6022\n }\n port \"ssh2\" {\n static = 6023\n }\n }\n }\n }\n }\n}", + "json": null, + "modify_index": "7077736", + "name": "prod-device-csit-shim", + "namespace": "default", + "policy_override": null, + "purge_on_destroy": null, + "region": "global", + "task_groups": [ + { + "count": 1, + "meta": {}, + "name": "prod-group1-csit-shim-amd", + "task": [ + { + "driver": "docker", + "meta": {}, + "name": "prod-task1-csit-shim-amd", + "volume_mounts": [] + } + ], + "volumes": [] + }, + { + "count": 1, + "meta": {}, + "name": "prod-group1-csit-shim-arm", + "task": [ + { + "driver": "docker", + "meta": {}, + "name": "prod-task1-csit-shim-arm", + "volume_mounts": [] + } + ], + "volumes": [] + } + ], + "type": "system" + }, + "sensitive_attributes": [], + "private": "bnVsbA==", + "dependencies": [ + "module.vpp_device.data.template_file.nomad_job_csit_shim" + ] + } + ] } ] } diff --git a/terraform-ci-infra/1n_nmd/terraform.tfstate.backup b/terraform-ci-infra/1n_nmd/terraform.tfstate.backup index 3290919ac6..de6ebe9598 100644 --- a/terraform-ci-infra/1n_nmd/terraform.tfstate.backup +++ b/terraform-ci-infra/1n_nmd/terraform.tfstate.backup @@ -1,11 +1,342 @@ { "version": 4, - "terraform_version": "0.14.2", - "serial": 220, + "terraform_version": "0.14.5", + "serial": 1026, "lineage": "e4e7f30a-652d-7a31-e31c-5e3a3388c9b9", "outputs": {}, "resources": [ { + "module": "module.alertmanager", + "mode": "data", + "type": "template_file", + "name": "nomad_job_alertmanager", + "provider": "provider[\"registry.terraform.io/hashicorp/template\"]", + "instances": [ + { + "schema_version": 0, + "attributes": { + "filename": null, + "id": "ae09d392c808970a05f2423cd8dbf158f6cb6d3ae50260cd7d16f1575ce43871", + "rendered": "job \"prod-alertmanager\" {\n # The \"region\" parameter specifies the region in which to execute the job.\n # If omitted, this inherits the default region name of \"global\".\n # region = \"global\"\n #\n # The \"datacenters\" parameter specifies the list of datacenters which should\n # be considered when placing this task. This must be provided.\n datacenters = \"yul1\"\n\n # The \"type\" parameter controls the type of job, which impacts the scheduler's\n # decision on placement. This configuration is optional and defaults to\n # \"service\". For a full list of job types and their differences, please see\n # the online documentation.\n #\n # For more information, please see the online documentation at:\n #\n # https://www.nomadproject.io/docs/jobspec/schedulers\n #\n type = \"service\"\n\n update {\n # The \"max_parallel\" parameter specifies the maximum number of updates to\n # perform in parallel. In this case, this specifies to update a single task\n # at a time.\n max_parallel = 1\n\n health_check = \"checks\"\n\n # The \"min_healthy_time\" parameter specifies the minimum time the allocation\n # must be in the healthy state before it is marked as healthy and unblocks\n # further allocations from being updated.\n min_healthy_time = \"10s\"\n\n # The \"healthy_deadline\" parameter specifies the deadline in which the\n # allocation must be marked as healthy after which the allocation is\n # automatically transitioned to unhealthy. Transitioning to unhealthy will\n # fail the deployment and potentially roll back the job if \"auto_revert\" is\n # set to true.\n healthy_deadline = \"3m\"\n\n # The \"progress_deadline\" parameter specifies the deadline in which an\n # allocation must be marked as healthy. The deadline begins when the first\n # allocation for the deployment is created and is reset whenever an allocation\n # as part of the deployment transitions to a healthy state. If no allocation\n # transitions to the healthy state before the progress deadline, the\n # deployment is marked as failed.\n progress_deadline = \"10m\"\n\n\n # The \"canary\" parameter specifies that changes to the job that would result\n # in destructive updates should create the specified number of canaries\n # without stopping any previous allocations. Once the operator determines the\n # canaries are healthy, they can be promoted which unblocks a rolling update\n # of the remaining allocations at a rate of \"max_parallel\".\n #\n # Further, setting \"canary\" equal to the count of the task group allows\n # blue/green deployments. When the job is updated, a full set of the new\n # version is deployed and upon promotion the old version is stopped.\n canary = 1\n\n # Specifies if the job should auto-promote to the canary version when all\n # canaries become healthy during a deployment. Defaults to false which means\n # canaries must be manually updated with the nomad deployment promote\n # command.\n auto_promote = true\n\n # The \"auto_revert\" parameter specifies if the job should auto-revert to the\n # last stable job on deployment failure. A job is marked as stable if all the\n # allocations as part of its deployment were marked healthy.\n auto_revert = true\n\n }\n\n # The \"group\" stanza defines a series of tasks that should be co-located on\n # the same Nomad client. Any task within a group will be placed on the same\n # client.\n #\n # For more information and examples on the \"group\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/group\n #\n group \"prod-group1-alertmanager\" {\n # The \"count\" parameter specifies the number of the task groups that should\n # be running under this group. This value must be non-negative and defaults\n # to 1.\n count = 1\n\n # The constraint allows restricting the set of eligible nodes. Constraints\n # may filter on attributes or client metadata.\n #\n # For more information and examples on the \"volume\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/constraint\n #\n constraint {\n attribute = \"${attr.cpu.arch}\"\n operator = \"!=\"\n value = \"arm64\"\n }\n\n # The \"task\" stanza creates an individual unit of work, such as a Docker\n # container, web application, or batch processing.\n #\n # For more information and examples on the \"task\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/task\n #\n task \"prod-task1-alertmanager\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"exec\"\n\n \n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n command = \"local/alertmanager-0.21.0.linux-amd64/alertmanager\"\n args = [\n \"--config.file=secrets/alertmanager.yml\"\n ]\n }\n\n # The artifact stanza instructs Nomad to fetch and unpack a remote resource,\n # such as a file, tarball, or binary. Nomad downloads artifacts using the\n # popular go-getter library, which permits downloading artifacts from a\n # variety of locations using a URL as the input source.\n #\n # For more information and examples on the \"artifact\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/artifact\n #\n artifact {\n source = \"https://github.com/prometheus/alertmanager/releases/download/v0.21.0/alertmanager-0.21.0.linux-amd64.tar.gz\"\n }\n\n # The \"template\" stanza instructs Nomad to manage a template, such as\n # a configuration file or script. This template can optionally pull data\n # from Consul or Vault to populate runtime configuration data.\n #\n # For more information and examples on the \"template\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/template\n #\n template {\n change_mode = \"noop\"\n change_signal = \"SIGINT\"\n destination = \"secrets/alertmanager.yml\"\n left_delimiter = \"{{{\"\n right_delimiter = \"}}}\"\n data = \u003c\u003cEOH\nglobal:\n # The API URL to use for Slack notifications.\n slack_api_url: 'https://hooks.slack.com/services/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'\n\n# The directory from which notification templates are read.\ntemplates:\n- '/etc/alertmanager/template/*.tmpl'\n\n#tls_config:\n# # CA certificate to validate the server certificate with.\n# ca_file: \u003cfilepath\u003e ]\n#\n# # Certificate and key files for client cert authentication to the server.\n# cert_file: \u003cfilepath\u003e\n# key_file: \u003cfilepath\u003e\n#\n# # ServerName extension to indicate the name of the server.\n# # http://tools.ietf.org/html/rfc4366#section-3.1\n# server_name: \u003cstring\u003e\n#\n# # Disable validation of the server certificate.\n# insecure_skip_verify: true\n\n# The root route on which each incoming alert enters.\nroute:\n receiver: 'default-receiver'\n\n # The labels by which incoming alerts are grouped together. For example,\n # multiple alerts coming in for cluster=A and alertname=LatencyHigh would\n # be batched into a single group.\n #\n # To aggregate by all possible labels use '...' as the sole label name.\n # This effectively disables aggregation entirely, passing through all\n # alerts as-is. This is unlikely to be what you want, unless you have\n # a very low alert volume or your upstream notification system performs\n # its own grouping. Example: group_by: [...]\n group_by: ['alertname', 'cluster', 'service']\n\n # When a new group of alerts is created by an incoming alert, wait at\n # least 'group_wait' to send the initial notification.\n # This way ensures that you get multiple alerts for the same group that start\n # firing shortly after another are batched together on the first\n # notification.\n group_wait: 30s\n\n # When the first notification was sent, wait 'group_interval' to send a batch\n # of new alerts that started firing for that group.\n group_interval: 5m\n\n # If an alert has successfully been sent, wait 'repeat_interval' to\n # resend them.\n repeat_interval: 3h\n\n # All the above attributes are inherited by all child routes and can\n # overwritten on each.\n # The child route trees.\n routes:\n # This routes performs a regular expression match on alert labels to\n # catch alerts that are related to a list of services.\n - match_re:\n service: .*\n receiver: default-receiver\n # The service has a sub-route for critical alerts, any alerts\n # that do not match, i.e. severity != critical, fall-back to the\n # parent node and are sent to 'team-X-mails'\n routes:\n - match:\n severity: critical\n receiver: 'default-receiver'\n\n# Inhibition rules allow to mute a set of alerts given that another alert is\n# firing.\n# We use this to mute any warning-level notifications if the same alert is\n# already critical.\ninhibit_rules:\n- source_match:\n severity: 'critical'\n target_match:\n severity: 'warning'\n # Apply inhibition if the alertname is the same.\n # CAUTION:\n # If all label names listed in `equal` are missing\n # from both the source and target alerts,\n # the inhibition rule will apply!\n equal: ['alertname', 'cluster', 'service']\n\nreceivers:\n- name: 'default-receiver'\n slack_configs:\n - channel: '#fdio-infra-monitoring'\n send_resolved: true\n icon_url: https://avatars3.githubusercontent.com/u/3380462\n title: |-\n [{{ .Status | toUpper }}{{ if eq .Status \"firing\" }}:{{ .Alerts.Firing | len }}{{ end }}] {{ .CommonLabels.alertname }} for {{ .CommonLabels.job }}\n {{- if gt (len .CommonLabels) (len .GroupLabels) -}}\n {{\" \"}}(\n {{- with .CommonLabels.Remove .GroupLabels.Names }}\n {{- range $index, $label := .SortedPairs -}}\n {{ if $index }}, {{ end }}\n {{- $label.Name }}=\"{{ $label.Value -}}\"\n {{- end }}\n {{- end -}}\n )\n {{- end }}\n text: \u003e-\n {{ range .Alerts -}}\n *Alert:* {{ .Annotations.summary }}{{ if .Labels.severity }} - `{{ .Labels.severity }}`{{ end }}\n\n *Description:* {{ .Annotations.description }}\n\n *Details:*\n {{ range .Labels.SortedPairs }} • *{{ .Name }}:* `{{ .Value }}`\n {{ end }}\n {{ end }}\nEOH\n }\n\n # The service stanza instructs Nomad to register a service with Consul.\n #\n # For more information and examples on the \"task\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/service\n #\n service {\n name = \"alertmanager\"\n port = \"alertmanager\"\n tags = [ \"alertmanager${NOMAD_ALLOC_INDEX}\" ]\n check {\n name = \"Alertmanager Check Live\"\n type = \"http\"\n path = \"/-/healthy\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # For more information and examples on the \"resources\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/resources\n #\n resources {\n cpu = 1000\n memory = 1024\n # The network stanza specifies the networking requirements for the task\n # group, including the network mode and port allocations. When scheduling\n # jobs in Nomad they are provisioned across your fleet of machines along\n # with other jobs and services. Because you don't know in advance what host\n # your job will be provisioned on, Nomad will provide your tasks with\n # network configuration when they start up.\n #\n # For more information and examples on the \"template\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/network\n #\n network {\n port \"alertmanager\" {\n static = 9093\n }\n }\n }\n }\n }\n}", + "template": "job \"${job_name}\" {\n # The \"region\" parameter specifies the region in which to execute the job.\n # If omitted, this inherits the default region name of \"global\".\n # region = \"global\"\n #\n # The \"datacenters\" parameter specifies the list of datacenters which should\n # be considered when placing this task. This must be provided.\n datacenters = \"${datacenters}\"\n\n # The \"type\" parameter controls the type of job, which impacts the scheduler's\n # decision on placement. This configuration is optional and defaults to\n # \"service\". For a full list of job types and their differences, please see\n # the online documentation.\n #\n # For more information, please see the online documentation at:\n #\n # https://www.nomadproject.io/docs/jobspec/schedulers\n #\n type = \"service\"\n\n update {\n # The \"max_parallel\" parameter specifies the maximum number of updates to\n # perform in parallel. In this case, this specifies to update a single task\n # at a time.\n max_parallel = 1\n\n health_check = \"checks\"\n\n # The \"min_healthy_time\" parameter specifies the minimum time the allocation\n # must be in the healthy state before it is marked as healthy and unblocks\n # further allocations from being updated.\n min_healthy_time = \"10s\"\n\n # The \"healthy_deadline\" parameter specifies the deadline in which the\n # allocation must be marked as healthy after which the allocation is\n # automatically transitioned to unhealthy. Transitioning to unhealthy will\n # fail the deployment and potentially roll back the job if \"auto_revert\" is\n # set to true.\n healthy_deadline = \"3m\"\n\n # The \"progress_deadline\" parameter specifies the deadline in which an\n # allocation must be marked as healthy. The deadline begins when the first\n # allocation for the deployment is created and is reset whenever an allocation\n # as part of the deployment transitions to a healthy state. If no allocation\n # transitions to the healthy state before the progress deadline, the\n # deployment is marked as failed.\n progress_deadline = \"10m\"\n\n%{ if use_canary }\n # The \"canary\" parameter specifies that changes to the job that would result\n # in destructive updates should create the specified number of canaries\n # without stopping any previous allocations. Once the operator determines the\n # canaries are healthy, they can be promoted which unblocks a rolling update\n # of the remaining allocations at a rate of \"max_parallel\".\n #\n # Further, setting \"canary\" equal to the count of the task group allows\n # blue/green deployments. When the job is updated, a full set of the new\n # version is deployed and upon promotion the old version is stopped.\n canary = 1\n\n # Specifies if the job should auto-promote to the canary version when all\n # canaries become healthy during a deployment. Defaults to false which means\n # canaries must be manually updated with the nomad deployment promote\n # command.\n auto_promote = true\n\n # The \"auto_revert\" parameter specifies if the job should auto-revert to the\n # last stable job on deployment failure. A job is marked as stable if all the\n # allocations as part of its deployment were marked healthy.\n auto_revert = true\n%{ endif }\n }\n\n # The \"group\" stanza defines a series of tasks that should be co-located on\n # the same Nomad client. Any task within a group will be placed on the same\n # client.\n #\n # For more information and examples on the \"group\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/group\n #\n group \"prod-group1-${service_name}\" {\n # The \"count\" parameter specifies the number of the task groups that should\n # be running under this group. This value must be non-negative and defaults\n # to 1.\n count = ${group_count}\n\n # The constraint allows restricting the set of eligible nodes. Constraints\n # may filter on attributes or client metadata.\n #\n # For more information and examples on the \"volume\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/constraint\n #\n constraint {\n attribute = \"$${attr.cpu.arch}\"\n operator = \"!=\"\n value = \"arm64\"\n }\n\n # The \"task\" stanza creates an individual unit of work, such as a Docker\n # container, web application, or batch processing.\n #\n # For more information and examples on the \"task\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/task\n #\n task \"prod-task1-${service_name}\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"exec\"\n\n %{ if use_vault_provider }\n vault {\n policies = \"${vault_kv_policy_name}\"\n }\n %{ endif }\n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n command = \"local/alertmanager-${version}.linux-amd64/alertmanager\"\n args = [\n \"--config.file=secrets/alertmanager.yml\"\n ]\n }\n\n # The artifact stanza instructs Nomad to fetch and unpack a remote resource,\n # such as a file, tarball, or binary. Nomad downloads artifacts using the\n # popular go-getter library, which permits downloading artifacts from a\n # variety of locations using a URL as the input source.\n #\n # For more information and examples on the \"artifact\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/artifact\n #\n artifact {\n source = \"${url}\"\n }\n\n # The \"template\" stanza instructs Nomad to manage a template, such as\n # a configuration file or script. This template can optionally pull data\n # from Consul or Vault to populate runtime configuration data.\n #\n # For more information and examples on the \"template\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/template\n #\n template {\n change_mode = \"noop\"\n change_signal = \"SIGINT\"\n destination = \"secrets/alertmanager.yml\"\n left_delimiter = \"{{{\"\n right_delimiter = \"}}}\"\n data = \u003c\u003cEOH\nglobal:\n # The API URL to use for Slack notifications.\n slack_api_url: '${slack_api_url}'\n\n# The directory from which notification templates are read.\ntemplates:\n- '/etc/alertmanager/template/*.tmpl'\n\n#tls_config:\n# # CA certificate to validate the server certificate with.\n# ca_file: \u003cfilepath\u003e ]\n#\n# # Certificate and key files for client cert authentication to the server.\n# cert_file: \u003cfilepath\u003e\n# key_file: \u003cfilepath\u003e\n#\n# # ServerName extension to indicate the name of the server.\n# # http://tools.ietf.org/html/rfc4366#section-3.1\n# server_name: \u003cstring\u003e\n#\n# # Disable validation of the server certificate.\n# insecure_skip_verify: true\n\n# The root route on which each incoming alert enters.\nroute:\n receiver: '${default_receiver}'\n\n # The labels by which incoming alerts are grouped together. For example,\n # multiple alerts coming in for cluster=A and alertname=LatencyHigh would\n # be batched into a single group.\n #\n # To aggregate by all possible labels use '...' as the sole label name.\n # This effectively disables aggregation entirely, passing through all\n # alerts as-is. This is unlikely to be what you want, unless you have\n # a very low alert volume or your upstream notification system performs\n # its own grouping. Example: group_by: [...]\n group_by: ['alertname', 'cluster', 'service']\n\n # When a new group of alerts is created by an incoming alert, wait at\n # least 'group_wait' to send the initial notification.\n # This way ensures that you get multiple alerts for the same group that start\n # firing shortly after another are batched together on the first\n # notification.\n group_wait: 30s\n\n # When the first notification was sent, wait 'group_interval' to send a batch\n # of new alerts that started firing for that group.\n group_interval: 5m\n\n # If an alert has successfully been sent, wait 'repeat_interval' to\n # resend them.\n repeat_interval: 3h\n\n # All the above attributes are inherited by all child routes and can\n # overwritten on each.\n # The child route trees.\n routes:\n # This routes performs a regular expression match on alert labels to\n # catch alerts that are related to a list of services.\n - match_re:\n service: .*\n receiver: ${default_receiver}\n # The service has a sub-route for critical alerts, any alerts\n # that do not match, i.e. severity != critical, fall-back to the\n # parent node and are sent to 'team-X-mails'\n routes:\n - match:\n severity: critical\n receiver: '${default_receiver}'\n\n# Inhibition rules allow to mute a set of alerts given that another alert is\n# firing.\n# We use this to mute any warning-level notifications if the same alert is\n# already critical.\ninhibit_rules:\n- source_match:\n severity: 'critical'\n target_match:\n severity: 'warning'\n # Apply inhibition if the alertname is the same.\n # CAUTION:\n # If all label names listed in `equal` are missing\n # from both the source and target alerts,\n # the inhibition rule will apply!\n equal: ['alertname', 'cluster', 'service']\n\nreceivers:\n- name: '${default_receiver}'\n slack_configs:\n - channel: '#${slack_channel}'\n send_resolved: true\n icon_url: https://avatars3.githubusercontent.com/u/3380462\n title: |-\n [{{ .Status | toUpper }}{{ if eq .Status \"firing\" }}:{{ .Alerts.Firing | len }}{{ end }}] {{ .CommonLabels.alertname }} for {{ .CommonLabels.job }}\n {{- if gt (len .CommonLabels) (len .GroupLabels) -}}\n {{\" \"}}(\n {{- with .CommonLabels.Remove .GroupLabels.Names }}\n {{- range $index, $label := .SortedPairs -}}\n {{ if $index }}, {{ end }}\n {{- $label.Name }}=\"{{ $label.Value -}}\"\n {{- end }}\n {{- end -}}\n )\n {{- end }}\n text: \u003e-\n {{ range .Alerts -}}\n *Alert:* {{ .Annotations.summary }}{{ if .Labels.severity }} - `{{ .Labels.severity }}`{{ end }}\n\n *Description:* {{ .Annotations.description }}\n\n *Details:*\n {{ range .Labels.SortedPairs }} • *{{ .Name }}:* `{{ .Value }}`\n {{ end }}\n {{ end }}\nEOH\n }\n\n # The service stanza instructs Nomad to register a service with Consul.\n #\n # For more information and examples on the \"task\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/service\n #\n service {\n name = \"${service_name}\"\n port = \"${service_name}\"\n tags = [ \"${service_name}$${NOMAD_ALLOC_INDEX}\" ]\n check {\n name = \"Alertmanager Check Live\"\n type = \"http\"\n path = \"/-/healthy\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # For more information and examples on the \"resources\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/resources\n #\n resources {\n cpu = ${cpu}\n memory = ${mem}\n # The network stanza specifies the networking requirements for the task\n # group, including the network mode and port allocations. When scheduling\n # jobs in Nomad they are provisioned across your fleet of machines along\n # with other jobs and services. Because you don't know in advance what host\n # your job will be provisioned on, Nomad will provide your tasks with\n # network configuration when they start up.\n #\n # For more information and examples on the \"template\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/network\n #\n network {\n port \"${service_name}\" {\n static = ${port}\n }\n }\n }\n }\n }\n}", + "vars": { + "cpu": "1000", + "datacenters": "yul1", + "default_receiver": "default-receiver", + "group_count": "1", + "job_name": "prod-alertmanager", + "mem": "1024", + "port": "9093", + "service_name": "alertmanager", + "slack_api_url": "https://hooks.slack.com/services/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", + "slack_channel": "fdio-infra-monitoring", + "url": "https://github.com/prometheus/alertmanager/releases/download/v0.21.0/alertmanager-0.21.0.linux-amd64.tar.gz", + "use_canary": "true", + "use_vault_provider": "false", + "version": "0.21.0" + } + }, + "sensitive_attributes": [] + } + ] + }, + { + "module": "module.alertmanager", + "mode": "managed", + "type": "nomad_job", + "name": "nomad_job_alertmanager", + "provider": "provider[\"registry.terraform.io/hashicorp/nomad\"].yul1", + "instances": [ + { + "schema_version": 0, + "attributes": { + "allocation_ids": [ + "464144d9-8c27-dc03-71bb-6f8d525bc486", + "d29e4d1a-be78-d7ec-0b53-c2b6ebcd2e00" + ], + "datacenters": [ + "yul1" + ], + "deployment_id": "d69d73a6-2a1b-ebf6-e421-30ce1f34f519", + "deployment_status": "successful", + "deregister_on_destroy": true, + "deregister_on_id_change": true, + "detach": false, + "id": "prod-alertmanager", + "jobspec": "job \"prod-alertmanager\" {\n # The \"region\" parameter specifies the region in which to execute the job.\n # If omitted, this inherits the default region name of \"global\".\n # region = \"global\"\n #\n # The \"datacenters\" parameter specifies the list of datacenters which should\n # be considered when placing this task. This must be provided.\n datacenters = \"yul1\"\n\n # The \"type\" parameter controls the type of job, which impacts the scheduler's\n # decision on placement. This configuration is optional and defaults to\n # \"service\". For a full list of job types and their differences, please see\n # the online documentation.\n #\n # For more information, please see the online documentation at:\n #\n # https://www.nomadproject.io/docs/jobspec/schedulers\n #\n type = \"service\"\n\n update {\n # The \"max_parallel\" parameter specifies the maximum number of updates to\n # perform in parallel. In this case, this specifies to update a single task\n # at a time.\n max_parallel = 1\n\n health_check = \"checks\"\n\n # The \"min_healthy_time\" parameter specifies the minimum time the allocation\n # must be in the healthy state before it is marked as healthy and unblocks\n # further allocations from being updated.\n min_healthy_time = \"10s\"\n\n # The \"healthy_deadline\" parameter specifies the deadline in which the\n # allocation must be marked as healthy after which the allocation is\n # automatically transitioned to unhealthy. Transitioning to unhealthy will\n # fail the deployment and potentially roll back the job if \"auto_revert\" is\n # set to true.\n healthy_deadline = \"3m\"\n\n # The \"progress_deadline\" parameter specifies the deadline in which an\n # allocation must be marked as healthy. The deadline begins when the first\n # allocation for the deployment is created and is reset whenever an allocation\n # as part of the deployment transitions to a healthy state. If no allocation\n # transitions to the healthy state before the progress deadline, the\n # deployment is marked as failed.\n progress_deadline = \"10m\"\n\n\n # The \"canary\" parameter specifies that changes to the job that would result\n # in destructive updates should create the specified number of canaries\n # without stopping any previous allocations. Once the operator determines the\n # canaries are healthy, they can be promoted which unblocks a rolling update\n # of the remaining allocations at a rate of \"max_parallel\".\n #\n # Further, setting \"canary\" equal to the count of the task group allows\n # blue/green deployments. When the job is updated, a full set of the new\n # version is deployed and upon promotion the old version is stopped.\n canary = 1\n\n # Specifies if the job should auto-promote to the canary version when all\n # canaries become healthy during a deployment. Defaults to false which means\n # canaries must be manually updated with the nomad deployment promote\n # command.\n auto_promote = true\n\n # The \"auto_revert\" parameter specifies if the job should auto-revert to the\n # last stable job on deployment failure. A job is marked as stable if all the\n # allocations as part of its deployment were marked healthy.\n auto_revert = true\n\n }\n\n # The \"group\" stanza defines a series of tasks that should be co-located on\n # the same Nomad client. Any task within a group will be placed on the same\n # client.\n #\n # For more information and examples on the \"group\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/group\n #\n group \"prod-group1-alertmanager\" {\n # The \"count\" parameter specifies the number of the task groups that should\n # be running under this group. This value must be non-negative and defaults\n # to 1.\n count = 1\n\n # The constraint allows restricting the set of eligible nodes. Constraints\n # may filter on attributes or client metadata.\n #\n # For more information and examples on the \"volume\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/constraint\n #\n constraint {\n attribute = \"${attr.cpu.arch}\"\n operator = \"!=\"\n value = \"arm64\"\n }\n\n # The \"task\" stanza creates an individual unit of work, such as a Docker\n # container, web application, or batch processing.\n #\n # For more information and examples on the \"task\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/task\n #\n task \"prod-task1-alertmanager\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"exec\"\n\n \n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n command = \"local/alertmanager-0.21.0.linux-amd64/alertmanager\"\n args = [\n \"--config.file=secrets/alertmanager.yml\"\n ]\n }\n\n # The artifact stanza instructs Nomad to fetch and unpack a remote resource,\n # such as a file, tarball, or binary. Nomad downloads artifacts using the\n # popular go-getter library, which permits downloading artifacts from a\n # variety of locations using a URL as the input source.\n #\n # For more information and examples on the \"artifact\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/artifact\n #\n artifact {\n source = \"https://github.com/prometheus/alertmanager/releases/download/v0.21.0/alertmanager-0.21.0.linux-amd64.tar.gz\"\n }\n\n # The \"template\" stanza instructs Nomad to manage a template, such as\n # a configuration file or script. This template can optionally pull data\n # from Consul or Vault to populate runtime configuration data.\n #\n # For more information and examples on the \"template\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/template\n #\n template {\n change_mode = \"noop\"\n change_signal = \"SIGINT\"\n destination = \"secrets/alertmanager.yml\"\n left_delimiter = \"{{{\"\n right_delimiter = \"}}}\"\n data = \u003c\u003cEOH\nglobal:\n # The API URL to use for Slack notifications.\n slack_api_url: 'https://hooks.slack.com/services/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'\n\n# The directory from which notification templates are read.\ntemplates:\n- '/etc/alertmanager/template/*.tmpl'\n\n#tls_config:\n# # CA certificate to validate the server certificate with.\n# ca_file: \u003cfilepath\u003e ]\n#\n# # Certificate and key files for client cert authentication to the server.\n# cert_file: \u003cfilepath\u003e\n# key_file: \u003cfilepath\u003e\n#\n# # ServerName extension to indicate the name of the server.\n# # http://tools.ietf.org/html/rfc4366#section-3.1\n# server_name: \u003cstring\u003e\n#\n# # Disable validation of the server certificate.\n# insecure_skip_verify: true\n\n# The root route on which each incoming alert enters.\nroute:\n receiver: 'default-receiver'\n\n # The labels by which incoming alerts are grouped together. For example,\n # multiple alerts coming in for cluster=A and alertname=LatencyHigh would\n # be batched into a single group.\n #\n # To aggregate by all possible labels use '...' as the sole label name.\n # This effectively disables aggregation entirely, passing through all\n # alerts as-is. This is unlikely to be what you want, unless you have\n # a very low alert volume or your upstream notification system performs\n # its own grouping. Example: group_by: [...]\n group_by: ['alertname', 'cluster', 'service']\n\n # When a new group of alerts is created by an incoming alert, wait at\n # least 'group_wait' to send the initial notification.\n # This way ensures that you get multiple alerts for the same group that start\n # firing shortly after another are batched together on the first\n # notification.\n group_wait: 30s\n\n # When the first notification was sent, wait 'group_interval' to send a batch\n # of new alerts that started firing for that group.\n group_interval: 5m\n\n # If an alert has successfully been sent, wait 'repeat_interval' to\n # resend them.\n repeat_interval: 3h\n\n # All the above attributes are inherited by all child routes and can\n # overwritten on each.\n # The child route trees.\n routes:\n # This routes performs a regular expression match on alert labels to\n # catch alerts that are related to a list of services.\n - match_re:\n service: .*\n receiver: default-receiver\n # The service has a sub-route for critical alerts, any alerts\n # that do not match, i.e. severity != critical, fall-back to the\n # parent node and are sent to 'team-X-mails'\n routes:\n - match:\n severity: critical\n receiver: 'default-receiver'\n\n# Inhibition rules allow to mute a set of alerts given that another alert is\n# firing.\n# We use this to mute any warning-level notifications if the same alert is\n# already critical.\ninhibit_rules:\n- source_match:\n severity: 'critical'\n target_match:\n severity: 'warning'\n # Apply inhibition if the alertname is the same.\n # CAUTION:\n # If all label names listed in `equal` are missing\n # from both the source and target alerts,\n # the inhibition rule will apply!\n equal: ['alertname', 'cluster', 'service']\n\nreceivers:\n- name: 'default-receiver'\n slack_configs:\n - channel: '#fdio-infra-monitoring'\n send_resolved: true\n icon_url: https://avatars3.githubusercontent.com/u/3380462\n title: |-\n [{{ .Status | toUpper }}{{ if eq .Status \"firing\" }}:{{ .Alerts.Firing | len }}{{ end }}] {{ .CommonLabels.alertname }} for {{ .CommonLabels.job }}\n {{- if gt (len .CommonLabels) (len .GroupLabels) -}}\n {{\" \"}}(\n {{- with .CommonLabels.Remove .GroupLabels.Names }}\n {{- range $index, $label := .SortedPairs -}}\n {{ if $index }}, {{ end }}\n {{- $label.Name }}=\"{{ $label.Value -}}\"\n {{- end }}\n {{- end -}}\n )\n {{- end }}\n text: \u003e-\n {{ range .Alerts -}}\n *Alert:* {{ .Annotations.summary }}{{ if .Labels.severity }} - `{{ .Labels.severity }}`{{ end }}\n\n *Description:* {{ .Annotations.description }}\n\n *Details:*\n {{ range .Labels.SortedPairs }} • *{{ .Name }}:* `{{ .Value }}`\n {{ end }}\n {{ end }}\nEOH\n }\n\n # The service stanza instructs Nomad to register a service with Consul.\n #\n # For more information and examples on the \"task\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/service\n #\n service {\n name = \"alertmanager\"\n port = \"alertmanager\"\n tags = [ \"alertmanager${NOMAD_ALLOC_INDEX}\" ]\n check {\n name = \"Alertmanager Check Live\"\n type = \"http\"\n path = \"/-/healthy\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # For more information and examples on the \"resources\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/resources\n #\n resources {\n cpu = 1000\n memory = 1024\n # The network stanza specifies the networking requirements for the task\n # group, including the network mode and port allocations. When scheduling\n # jobs in Nomad they are provisioned across your fleet of machines along\n # with other jobs and services. Because you don't know in advance what host\n # your job will be provisioned on, Nomad will provide your tasks with\n # network configuration when they start up.\n #\n # For more information and examples on the \"template\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/network\n #\n network {\n port \"alertmanager\" {\n static = 9093\n }\n }\n }\n }\n }\n}", + "json": null, + "modify_index": "7147924", + "name": "prod-alertmanager", + "namespace": "default", + "policy_override": null, + "purge_on_destroy": null, + "region": "global", + "task_groups": [ + { + "count": 1, + "meta": {}, + "name": "prod-group1-alertmanager", + "task": [ + { + "driver": "exec", + "meta": {}, + "name": "prod-task1-alertmanager", + "volume_mounts": [] + } + ], + "volumes": [] + } + ], + "type": "service" + }, + "sensitive_attributes": [], + "private": "bnVsbA==", + "dependencies": [ + "module.alertmanager.data.template_file.nomad_job_alertmanager" + ] + } + ] + }, + { + "module": "module.exporter", + "mode": "data", + "type": "template_file", + "name": "nomad_job_exporter", + "provider": "provider[\"registry.terraform.io/hashicorp/template\"]", + "instances": [ + { + "schema_version": 0, + "attributes": { + "filename": null, + "id": "28db119a83617686c94496ed114455041d4fc500d93c4de8f8b8cfbe7d4c1db2", + "rendered": "job \"prod-exporter\" {\n # The \"region\" parameter specifies the region in which to execute the job.\n # If omitted, this inherits the default region name of \"global\".\n # region = \"global\"\n #\n # The \"datacenters\" parameter specifies the list of datacenters which should\n # be considered when placing this task. This must be provided.\n datacenters = \"yul1\"\n\n # The \"type\" parameter controls the type of job, which impacts the scheduler's\n # decision on placement. This configuration is optional and defaults to\n # \"service\". For a full list of job types and their differences, please see\n # the online documentation.\n #\n # https://www.nomadproject.io/docs/jobspec/schedulers\n #\n type = \"system\"\n\n update {\n # The \"max_parallel\" parameter specifies the maximum number of updates to\n # perform in parallel. In this case, this specifies to update a single task\n # at a time.\n max_parallel = 1\n\n health_check = \"checks\"\n\n # The \"min_healthy_time\" parameter specifies the minimum time the allocation\n # must be in the healthy state before it is marked as healthy and unblocks\n # further allocations from being updated.\n min_healthy_time = \"10s\"\n\n # The \"healthy_deadline\" parameter specifies the deadline in which the\n # allocation must be marked as healthy after which the allocation is\n # automatically transitioned to unhealthy. Transitioning to unhealthy will\n # fail the deployment and potentially roll back the job if \"auto_revert\" is\n # set to true.\n healthy_deadline = \"3m\"\n\n # The \"progress_deadline\" parameter specifies the deadline in which an\n # allocation must be marked as healthy. The deadline begins when the first\n # allocation for the deployment is created and is reset whenever an allocation\n # as part of the deployment transitions to a healthy state. If no allocation\n # transitions to the healthy state before the progress deadline, the\n # deployment is marked as failed.\n progress_deadline = \"10m\"\n\n\n }\n\n # The \"group\" stanza defines a series of tasks that should be co-located on\n # the same Nomad client. Any task within a group will be placed on the same\n # client.\n #\n # https://www.nomadproject.io/docs/job-specification/group\n #\n group \"prod-group1-exporter-amd64\" {\n # The constraint allows restricting the set of eligible nodes. Constraints\n # may filter on attributes or client metadata.\n #\n # https://www.nomadproject.io/docs/job-specification/constraint\n #\n constraint {\n attribute = \"${attr.cpu.arch}\"\n operator = \"!=\"\n value = \"arm64\"\n }\n\n # The \"task\" stanza creates an individual unit of work, such as a Docker\n # container, web application, or batch processing.\n #\n # https://www.nomadproject.io/docs/job-specification/task\n #\n task \"prod-task1-nodeexporter-amd64\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"raw_exec\"\n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n command = \"local/node_exporter-1.0.1.linux-amd64/node_exporter\"\n }\n\n # The artifact stanza instructs Nomad to fetch and unpack a remote resource,\n # such as a file, tarball, or binary. Nomad downloads artifacts using the\n # popular go-getter library, which permits downloading artifacts from a\n # variety of locations using a URL as the input source.\n #\n # https://www.nomadproject.io/docs/job-specification/artifact\n #\n artifact {\n source = \"https://github.com/prometheus/node_exporter/releases/download/v1.0.1/node_exporter-1.0.1.linux-amd64.tar.gz\"\n }\n\n # The service stanza instructs Nomad to register a service with Consul.\n #\n # https://www.nomadproject.io/docs/job-specification/service\n #\n service {\n name = \"nodeexporter\"\n port = \"nodeexporter\"\n check {\n name = \"Node Exporter Check Live\"\n type = \"http\"\n path = \"/metrics\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # https://www.nomadproject.io/docs/job-specification/resources\n #\n resources {\n cpu = 500\n # The network stanza specifies the networking requirements for the task\n # group, including the network mode and port allocations. When scheduling\n # jobs in Nomad they are provisioned across your fleet of machines along\n # with other jobs and services. Because you don't know in advance what host\n # your job will be provisioned on, Nomad will provide your tasks with\n # network configuration when they start up.\n #\n # https://www.nomadproject.io/docs/job-specification/network\n #\n network {\n port \"nodeexporter\" {\n static = 9100\n }\n }\n }\n }\n task \"prod-task2-blackboxexporter-amd64\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"exec\"\n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n command = \"local/blackbox_exporter-0.18.0.linux-amd64/blackbox_exporter\"\n args = [\n \"--config.file=secrets/blackbox.yml\"\n ]\n }\n\n # The \"template\" stanza instructs Nomad to manage a template, such as\n # a configuration file or script. This template can optionally pull data\n # from Consul or Vault to populate runtime configuration data.\n #\n # https://www.nomadproject.io/docs/job-specification/template\n #\n template {\n change_mode = \"noop\"\n change_signal = \"SIGINT\"\n destination = \"secrets/blackbox.yml\"\n data = \u003c\u003cEOH\nmodules:\n http_2xx:\n prober: http\n timeout: 5s\n http:\n valid_http_versions: [\"HTTP/1.1\", \"HTTP/2.0\"]\n no_follow_redirects: false\n fail_if_ssl: false\n fail_if_not_ssl: true\n tls_config:\n insecure_skip_verify: false\n preferred_ip_protocol: \"ip4\"\n icmp_v4:\n prober: icmp\n timeout: 5s\n icmp:\n preferred_ip_protocol: \"ip4\"\n dns_udp:\n prober: dns\n timeout: 5s\n dns:\n query_name: \"jenkins.fd.io\"\n query_type: \"A\"\n valid_rcodes:\n - NOERROR\nEOH\n }\n\n # The artifact stanza instructs Nomad to fetch and unpack a remote resource,\n # such as a file, tarball, or binary. Nomad downloads artifacts using the\n # popular go-getter library, which permits downloading artifacts from a\n # variety of locations using a URL as the input source.\n #\n # https://www.nomadproject.io/docs/job-specification/artifact\n #\n artifact {\n source = \"https://github.com/prometheus/blackbox_exporter/releases/download/v0.18.0/blackbox_exporter-0.18.0.linux-amd64.tar.gz\"\n }\n\n # The service stanza instructs Nomad to register a service with Consul.\n #\n # https://www.nomadproject.io/docs/job-specification/service\n #\n service {\n name = \"blackboxexporter\"\n port = \"blackboxexporter\"\n tags = [ \"blackboxexporter${NOMAD_ALLOC_INDEX}\" ]\n check {\n name = \"Blackbox Exporter Check Live\"\n type = \"http\"\n path = \"/metrics\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # https://www.nomadproject.io/docs/job-specification/resources\n #\n resources {\n cpu = 500\n # The network stanza specifies the networking requirements for the task\n # group, including the network mode and port allocations. When scheduling\n # jobs in Nomad they are provisioned across your fleet of machines along\n # with other jobs and services. Because you don't know in advance what host\n # your job will be provisioned on, Nomad will provide your tasks with\n # network configuration when they start up.\n #\n # https://www.nomadproject.io/docs/job-specification/network\n #\n network {\n port \"blackboxexporter\" {\n static = 9115\n }\n }\n }\n }\n\n task \"prod-task3-cadvisorexporter-amd64\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"docker\"\n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n image = \"gcr.io/cadvisor/cadvisor:latest\"\n volumes = [\n \"/:/rootfs:ro\",\n \"/var/run:/var/run:rw\",\n \"/sys:/sys:ro\",\n \"/var/lib/docker/:/var/lib/docker:ro\",\n \"/cgroup:/cgroup:ro\"\n ]\n }\n\n # The service stanza instructs Nomad to register a service with Consul.\n #\n # https://www.nomadproject.io/docs/job-specification/service\n #\n service {\n name = \"cadvisorexporter\"\n port = \"cadvisorexporter\"\n check {\n name = \"cAdvisor Check Live\"\n type = \"http\"\n path = \"/metrics\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # https://www.nomadproject.io/docs/job-specification/resources\n #\n resources {\n cpu = 500\n # The network stanza specifies the networking requirements for the task\n # group, including the network mode and port allocations. When scheduling\n # jobs in Nomad they are provisioned across your fleet of machines along\n # with other jobs and services. Because you don't know in advance what host\n # your job will be provisioned on, Nomad will provide your tasks with\n # network configuration when they start up.\n #\n # https://www.nomadproject.io/docs/job-specification/network\n #\n network {\n port \"cadvisorexporter\" {\n static = 8080\n }\n }\n }\n }\n }\n\n group \"prod-group1-exporter-arm64\" {\n # The constraint allows restricting the set of eligible nodes. Constraints\n # may filter on attributes or client metadata.\n #\n # https://www.nomadproject.io/docs/job-specification/constraint\n #\n constraint {\n attribute = \"${attr.cpu.arch}\"\n operator = \"==\"\n value = \"arm64\"\n }\n\n # The \"task\" stanza creates an individual unit of work, such as a Docker\n # container, web application, or batch processing.\n #\n # https://www.nomadproject.io/docs/job-specification/task\n #\n task \"prod-task1-nodeexporter-arm64\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"raw_exec\"\n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n command = \"local/node_exporter-1.0.1.linux-arm64/node_exporter\"\n }\n\n # The artifact stanza instructs Nomad to fetch and unpack a remote resource,\n # such as a file, tarball, or binary. Nomad downloads artifacts using the\n # popular go-getter library, which permits downloading artifacts from a\n # variety of locations using a URL as the input source.\n #\n # https://www.nomadproject.io/docs/job-specification/artifact\n #\n artifact {\n source = \"https://github.com/prometheus/node_exporter/releases/download/v1.0.1/node_exporter-1.0.1.linux-arm64.tar.gz\"\n }\n\n # The service stanza instructs Nomad to register a service with Consul.\n #\n # https://www.nomadproject.io/docs/job-specification/service\n #\n service {\n name = \"nodeexporter\"\n port = \"nodeexporter\"\n check {\n name = \"Node Exporter Check Live\"\n type = \"http\"\n path = \"/metrics\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # https://www.nomadproject.io/docs/job-specification/resources\n #\n resources {\n cpu = 500\n # The network stanza specifies the networking requirements for the task\n # group, including the network mode and port allocations. When scheduling\n # jobs in Nomad they are provisioned across your fleet of machines along\n # with other jobs and services. Because you don't know in advance what host\n # your job will be provisioned on, Nomad will provide your tasks with\n # network configuration when they start up.\n #\n # https://www.nomadproject.io/docs/job-specification/network\n #\n network {\n port \"nodeexporter\" {\n static = 9100\n }\n }\n }\n }\n\n task \"prod-task2-blackboxexporter-arm64\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"exec\"\n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n command = \"local/blackbox_exporter-0.18.0.linux-arm64/blackbox_exporter\"\n args = [\n \"--config.file=secrets/blackbox.yml\"\n ]\n }\n\n # The \"template\" stanza instructs Nomad to manage a template, such as\n # a configuration file or script. This template can optionally pull data\n # from Consul or Vault to populate runtime configuration data.\n #\n # https://www.nomadproject.io/docs/job-specification/template\n #\n template {\n change_mode = \"noop\"\n change_signal = \"SIGINT\"\n destination = \"secrets/blackbox.yml\"\n data = \u003c\u003cEOH\nmodules:\n http_2xx:\n prober: http\n timeout: 5s\n http:\n valid_http_versions: [\"HTTP/1.1\", \"HTTP/2.0\"]\n no_follow_redirects: false\n fail_if_ssl: false\n fail_if_not_ssl: true\n tls_config:\n insecure_skip_verify: false\n preferred_ip_protocol: \"ip4\"\n icmp_v4:\n prober: icmp\n timeout: 5s\n icmp:\n preferred_ip_protocol: \"ip4\"\n dns_udp:\n prober: dns\n timeout: 5s\n dns:\n query_name: \"jenkins.fd.io\"\n query_type: \"A\"\n valid_rcodes:\n - NOERROR\nEOH\n }\n\n # The artifact stanza instructs Nomad to fetch and unpack a remote resource,\n # such as a file, tarball, or binary. Nomad downloads artifacts using the\n # popular go-getter library, which permits downloading artifacts from a\n # variety of locations using a URL as the input source.\n #\n # https://www.nomadproject.io/docs/job-specification/artifact\n #\n artifact {\n source = \"https://github.com/prometheus/blackbox_exporter/releases/download/v0.18.0/blackbox_exporter-0.18.0.linux-arm64.tar.gz\"\n }\n\n # The service stanza instructs Nomad to register a service with Consul.\n #\n # https://www.nomadproject.io/docs/job-specification/service\n #\n service {\n name = \"blackboxexporter\"\n port = \"blackboxexporter\"\n tags = [ \"blackboxexporter${NOMAD_ALLOC_INDEX}\" ]\n check {\n name = \"Blackbox Exporter Check Live\"\n type = \"http\"\n path = \"/metrics\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # https://www.nomadproject.io/docs/job-specification/resources\n #\n resources {\n cpu = 500\n # The network stanza specifies the networking requirements for the task\n # group, including the network mode and port allocations. When scheduling\n # jobs in Nomad they are provisioned across your fleet of machines along\n # with other jobs and services. Because you don't know in advance what host\n # your job will be provisioned on, Nomad will provide your tasks with\n # network configuration when they start up.\n #\n # https://www.nomadproject.io/docs/job-specification/network\n #\n network {\n port \"blackboxexporter\" {\n static = 9115\n }\n }\n }\n }\n\n task \"prod-task3-cadvisorexporter-arm64\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"docker\"\n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n # There is currently no official release for arm yet...using community.\n image = \"zcube/cadvisor:latest\"\n volumes = [\n \"/:/rootfs:ro\",\n \"/var/run:/var/run:rw\",\n \"/sys:/sys:ro\",\n \"/var/lib/docker/:/var/lib/docker:ro\",\n \"/cgroup:/cgroup:ro\"\n ]\n }\n\n # The service stanza instructs Nomad to register a service with Consul.\n #\n # https://www.nomadproject.io/docs/job-specification/service\n #\n service {\n name = \"cadvisorexporter\"\n port = \"cadvisorexporter\"\n check {\n name = \"cAdvisor Check Live\"\n type = \"http\"\n path = \"/metrics\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # https://www.nomadproject.io/docs/job-specification/resources\n #\n resources {\n cpu = 500\n # The network stanza specifies the networking requirements for the task\n # group, including the network mode and port allocations. When scheduling\n # jobs in Nomad they are provisioned across your fleet of machines along\n # with other jobs and services. Because you don't know in advance what host\n # your job will be provisioned on, Nomad will provide your tasks with\n # network configuration when they start up.\n #\n # https://www.nomadproject.io/docs/job-specification/network\n #\n network {\n port \"cadvisorexporter\" {\n static = 8080\n }\n }\n }\n }\n }\n}", + "template": "job \"${job_name}\" {\n # The \"region\" parameter specifies the region in which to execute the job.\n # If omitted, this inherits the default region name of \"global\".\n # region = \"global\"\n #\n # The \"datacenters\" parameter specifies the list of datacenters which should\n # be considered when placing this task. This must be provided.\n datacenters = \"${datacenters}\"\n\n # The \"type\" parameter controls the type of job, which impacts the scheduler's\n # decision on placement. This configuration is optional and defaults to\n # \"service\". For a full list of job types and their differences, please see\n # the online documentation.\n #\n # https://www.nomadproject.io/docs/jobspec/schedulers\n #\n type = \"system\"\n\n update {\n # The \"max_parallel\" parameter specifies the maximum number of updates to\n # perform in parallel. In this case, this specifies to update a single task\n # at a time.\n max_parallel = 1\n\n health_check = \"checks\"\n\n # The \"min_healthy_time\" parameter specifies the minimum time the allocation\n # must be in the healthy state before it is marked as healthy and unblocks\n # further allocations from being updated.\n min_healthy_time = \"10s\"\n\n # The \"healthy_deadline\" parameter specifies the deadline in which the\n # allocation must be marked as healthy after which the allocation is\n # automatically transitioned to unhealthy. Transitioning to unhealthy will\n # fail the deployment and potentially roll back the job if \"auto_revert\" is\n # set to true.\n healthy_deadline = \"3m\"\n\n # The \"progress_deadline\" parameter specifies the deadline in which an\n # allocation must be marked as healthy. The deadline begins when the first\n # allocation for the deployment is created and is reset whenever an allocation\n # as part of the deployment transitions to a healthy state. If no allocation\n # transitions to the healthy state before the progress deadline, the\n # deployment is marked as failed.\n progress_deadline = \"10m\"\n\n%{ if use_canary }\n # The \"canary\" parameter specifies that changes to the job that would result\n # in destructive updates should create the specified number of canaries\n # without stopping any previous allocations. Once the operator determines the\n # canaries are healthy, they can be promoted which unblocks a rolling update\n # of the remaining allocations at a rate of \"max_parallel\".\n #\n # Further, setting \"canary\" equal to the count of the task group allows\n # blue/green deployments. When the job is updated, a full set of the new\n # version is deployed and upon promotion the old version is stopped.\n canary = 1\n\n # Specifies if the job should auto-promote to the canary version when all\n # canaries become healthy during a deployment. Defaults to false which means\n # canaries must be manually updated with the nomad deployment promote\n # command.\n auto_promote = true\n\n # The \"auto_revert\" parameter specifies if the job should auto-revert to the\n # last stable job on deployment failure. A job is marked as stable if all the\n # allocations as part of its deployment were marked healthy.\n auto_revert = true\n%{ endif }\n }\n\n # The \"group\" stanza defines a series of tasks that should be co-located on\n # the same Nomad client. Any task within a group will be placed on the same\n # client.\n #\n # https://www.nomadproject.io/docs/job-specification/group\n #\n group \"prod-group1-exporter-amd64\" {\n # The constraint allows restricting the set of eligible nodes. Constraints\n # may filter on attributes or client metadata.\n #\n # https://www.nomadproject.io/docs/job-specification/constraint\n #\n constraint {\n attribute = \"$${attr.cpu.arch}\"\n operator = \"!=\"\n value = \"arm64\"\n }\n\n # The \"task\" stanza creates an individual unit of work, such as a Docker\n # container, web application, or batch processing.\n #\n # https://www.nomadproject.io/docs/job-specification/task\n #\n task \"prod-task1-${node_service_name}-amd64\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"raw_exec\"\n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n command = \"local/node_exporter-${node_version}.linux-amd64/node_exporter\"\n }\n\n # The artifact stanza instructs Nomad to fetch and unpack a remote resource,\n # such as a file, tarball, or binary. Nomad downloads artifacts using the\n # popular go-getter library, which permits downloading artifacts from a\n # variety of locations using a URL as the input source.\n #\n # https://www.nomadproject.io/docs/job-specification/artifact\n #\n artifact {\n source = \"${node_url_amd64}\"\n }\n\n # The service stanza instructs Nomad to register a service with Consul.\n #\n # https://www.nomadproject.io/docs/job-specification/service\n #\n service {\n name = \"${node_service_name}\"\n port = \"${node_service_name}\"\n check {\n name = \"Node Exporter Check Live\"\n type = \"http\"\n path = \"/metrics\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # https://www.nomadproject.io/docs/job-specification/resources\n #\n resources {\n cpu = 500\n # The network stanza specifies the networking requirements for the task\n # group, including the network mode and port allocations. When scheduling\n # jobs in Nomad they are provisioned across your fleet of machines along\n # with other jobs and services. Because you don't know in advance what host\n # your job will be provisioned on, Nomad will provide your tasks with\n # network configuration when they start up.\n #\n # https://www.nomadproject.io/docs/job-specification/network\n #\n network {\n port \"${node_service_name}\" {\n static = ${node_port}\n }\n }\n }\n }\n task \"prod-task2-${blackbox_service_name}-amd64\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"exec\"\n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n command = \"local/blackbox_exporter-${blackbox_version}.linux-amd64/blackbox_exporter\"\n args = [\n \"--config.file=secrets/blackbox.yml\"\n ]\n }\n\n # The \"template\" stanza instructs Nomad to manage a template, such as\n # a configuration file or script. This template can optionally pull data\n # from Consul or Vault to populate runtime configuration data.\n #\n # https://www.nomadproject.io/docs/job-specification/template\n #\n template {\n change_mode = \"noop\"\n change_signal = \"SIGINT\"\n destination = \"secrets/blackbox.yml\"\n data = \u003c\u003cEOH\nmodules:\n http_2xx:\n prober: http\n timeout: 5s\n http:\n valid_http_versions: [\"HTTP/1.1\", \"HTTP/2.0\"]\n no_follow_redirects: false\n fail_if_ssl: false\n fail_if_not_ssl: true\n tls_config:\n insecure_skip_verify: false\n preferred_ip_protocol: \"ip4\"\n icmp_v4:\n prober: icmp\n timeout: 5s\n icmp:\n preferred_ip_protocol: \"ip4\"\n dns_udp:\n prober: dns\n timeout: 5s\n dns:\n query_name: \"jenkins.fd.io\"\n query_type: \"A\"\n valid_rcodes:\n - NOERROR\nEOH\n }\n\n # The artifact stanza instructs Nomad to fetch and unpack a remote resource,\n # such as a file, tarball, or binary. Nomad downloads artifacts using the\n # popular go-getter library, which permits downloading artifacts from a\n # variety of locations using a URL as the input source.\n #\n # https://www.nomadproject.io/docs/job-specification/artifact\n #\n artifact {\n source = \"${blackbox_url_amd64}\"\n }\n\n # The service stanza instructs Nomad to register a service with Consul.\n #\n # https://www.nomadproject.io/docs/job-specification/service\n #\n service {\n name = \"${blackbox_service_name}\"\n port = \"${blackbox_service_name}\"\n tags = [ \"${blackbox_service_name}$${NOMAD_ALLOC_INDEX}\" ]\n check {\n name = \"Blackbox Exporter Check Live\"\n type = \"http\"\n path = \"/metrics\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # https://www.nomadproject.io/docs/job-specification/resources\n #\n resources {\n cpu = 500\n # The network stanza specifies the networking requirements for the task\n # group, including the network mode and port allocations. When scheduling\n # jobs in Nomad they are provisioned across your fleet of machines along\n # with other jobs and services. Because you don't know in advance what host\n # your job will be provisioned on, Nomad will provide your tasks with\n # network configuration when they start up.\n #\n # https://www.nomadproject.io/docs/job-specification/network\n #\n network {\n port \"${blackbox_service_name}\" {\n static = ${blackbox_port}\n }\n }\n }\n }\n\n task \"prod-task3-${cadvisor_service_name}-amd64\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"docker\"\n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n image = \"${cadvisor_image}\"\n volumes = [\n \"/:/rootfs:ro\",\n \"/var/run:/var/run:rw\",\n \"/sys:/sys:ro\",\n \"/var/lib/docker/:/var/lib/docker:ro\",\n \"/cgroup:/cgroup:ro\"\n ]\n }\n\n # The service stanza instructs Nomad to register a service with Consul.\n #\n # https://www.nomadproject.io/docs/job-specification/service\n #\n service {\n name = \"${cadvisor_service_name}\"\n port = \"${cadvisor_service_name}\"\n check {\n name = \"cAdvisor Check Live\"\n type = \"http\"\n path = \"/metrics\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # https://www.nomadproject.io/docs/job-specification/resources\n #\n resources {\n cpu = 500\n # The network stanza specifies the networking requirements for the task\n # group, including the network mode and port allocations. When scheduling\n # jobs in Nomad they are provisioned across your fleet of machines along\n # with other jobs and services. Because you don't know in advance what host\n # your job will be provisioned on, Nomad will provide your tasks with\n # network configuration when they start up.\n #\n # https://www.nomadproject.io/docs/job-specification/network\n #\n network {\n port \"${cadvisor_service_name}\" {\n static = ${cadvisor_port}\n }\n }\n }\n }\n }\n\n group \"prod-group1-exporter-arm64\" {\n # The constraint allows restricting the set of eligible nodes. Constraints\n # may filter on attributes or client metadata.\n #\n # https://www.nomadproject.io/docs/job-specification/constraint\n #\n constraint {\n attribute = \"$${attr.cpu.arch}\"\n operator = \"==\"\n value = \"arm64\"\n }\n\n # The \"task\" stanza creates an individual unit of work, such as a Docker\n # container, web application, or batch processing.\n #\n # https://www.nomadproject.io/docs/job-specification/task\n #\n task \"prod-task1-${node_service_name}-arm64\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"raw_exec\"\n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n command = \"local/node_exporter-${node_version}.linux-arm64/node_exporter\"\n }\n\n # The artifact stanza instructs Nomad to fetch and unpack a remote resource,\n # such as a file, tarball, or binary. Nomad downloads artifacts using the\n # popular go-getter library, which permits downloading artifacts from a\n # variety of locations using a URL as the input source.\n #\n # https://www.nomadproject.io/docs/job-specification/artifact\n #\n artifact {\n source = \"${node_url_arm64}\"\n }\n\n # The service stanza instructs Nomad to register a service with Consul.\n #\n # https://www.nomadproject.io/docs/job-specification/service\n #\n service {\n name = \"${node_service_name}\"\n port = \"${node_service_name}\"\n check {\n name = \"Node Exporter Check Live\"\n type = \"http\"\n path = \"/metrics\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # https://www.nomadproject.io/docs/job-specification/resources\n #\n resources {\n cpu = 500\n # The network stanza specifies the networking requirements for the task\n # group, including the network mode and port allocations. When scheduling\n # jobs in Nomad they are provisioned across your fleet of machines along\n # with other jobs and services. Because you don't know in advance what host\n # your job will be provisioned on, Nomad will provide your tasks with\n # network configuration when they start up.\n #\n # https://www.nomadproject.io/docs/job-specification/network\n #\n network {\n port \"${node_service_name}\" {\n static = ${node_port}\n }\n }\n }\n }\n\n task \"prod-task2-${blackbox_service_name}-arm64\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"exec\"\n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n command = \"local/blackbox_exporter-${blackbox_version}.linux-arm64/blackbox_exporter\"\n args = [\n \"--config.file=secrets/blackbox.yml\"\n ]\n }\n\n # The \"template\" stanza instructs Nomad to manage a template, such as\n # a configuration file or script. This template can optionally pull data\n # from Consul or Vault to populate runtime configuration data.\n #\n # https://www.nomadproject.io/docs/job-specification/template\n #\n template {\n change_mode = \"noop\"\n change_signal = \"SIGINT\"\n destination = \"secrets/blackbox.yml\"\n data = \u003c\u003cEOH\nmodules:\n http_2xx:\n prober: http\n timeout: 5s\n http:\n valid_http_versions: [\"HTTP/1.1\", \"HTTP/2.0\"]\n no_follow_redirects: false\n fail_if_ssl: false\n fail_if_not_ssl: true\n tls_config:\n insecure_skip_verify: false\n preferred_ip_protocol: \"ip4\"\n icmp_v4:\n prober: icmp\n timeout: 5s\n icmp:\n preferred_ip_protocol: \"ip4\"\n dns_udp:\n prober: dns\n timeout: 5s\n dns:\n query_name: \"jenkins.fd.io\"\n query_type: \"A\"\n valid_rcodes:\n - NOERROR\nEOH\n }\n\n # The artifact stanza instructs Nomad to fetch and unpack a remote resource,\n # such as a file, tarball, or binary. Nomad downloads artifacts using the\n # popular go-getter library, which permits downloading artifacts from a\n # variety of locations using a URL as the input source.\n #\n # https://www.nomadproject.io/docs/job-specification/artifact\n #\n artifact {\n source = \"${blackbox_url_arm64}\"\n }\n\n # The service stanza instructs Nomad to register a service with Consul.\n #\n # https://www.nomadproject.io/docs/job-specification/service\n #\n service {\n name = \"${blackbox_service_name}\"\n port = \"${blackbox_service_name}\"\n tags = [ \"${blackbox_service_name}$${NOMAD_ALLOC_INDEX}\" ]\n check {\n name = \"Blackbox Exporter Check Live\"\n type = \"http\"\n path = \"/metrics\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # https://www.nomadproject.io/docs/job-specification/resources\n #\n resources {\n cpu = 500\n # The network stanza specifies the networking requirements for the task\n # group, including the network mode and port allocations. When scheduling\n # jobs in Nomad they are provisioned across your fleet of machines along\n # with other jobs and services. Because you don't know in advance what host\n # your job will be provisioned on, Nomad will provide your tasks with\n # network configuration when they start up.\n #\n # https://www.nomadproject.io/docs/job-specification/network\n #\n network {\n port \"${blackbox_service_name}\" {\n static = ${blackbox_port}\n }\n }\n }\n }\n\n task \"prod-task3-${cadvisor_service_name}-arm64\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"docker\"\n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n # There is currently no official release for arm yet...using community.\n image = \"zcube/cadvisor:latest\"\n volumes = [\n \"/:/rootfs:ro\",\n \"/var/run:/var/run:rw\",\n \"/sys:/sys:ro\",\n \"/var/lib/docker/:/var/lib/docker:ro\",\n \"/cgroup:/cgroup:ro\"\n ]\n }\n\n # The service stanza instructs Nomad to register a service with Consul.\n #\n # https://www.nomadproject.io/docs/job-specification/service\n #\n service {\n name = \"${cadvisor_service_name}\"\n port = \"${cadvisor_service_name}\"\n check {\n name = \"cAdvisor Check Live\"\n type = \"http\"\n path = \"/metrics\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # https://www.nomadproject.io/docs/job-specification/resources\n #\n resources {\n cpu = 500\n # The network stanza specifies the networking requirements for the task\n # group, including the network mode and port allocations. When scheduling\n # jobs in Nomad they are provisioned across your fleet of machines along\n # with other jobs and services. Because you don't know in advance what host\n # your job will be provisioned on, Nomad will provide your tasks with\n # network configuration when they start up.\n #\n # https://www.nomadproject.io/docs/job-specification/network\n #\n network {\n port \"${cadvisor_service_name}\" {\n static = ${cadvisor_port}\n }\n }\n }\n }\n }\n}", + "vars": { + "blackbox_port": "9115", + "blackbox_service_name": "blackboxexporter", + "blackbox_url_amd64": "https://github.com/prometheus/blackbox_exporter/releases/download/v0.18.0/blackbox_exporter-0.18.0.linux-amd64.tar.gz", + "blackbox_url_arm64": "https://github.com/prometheus/blackbox_exporter/releases/download/v0.18.0/blackbox_exporter-0.18.0.linux-arm64.tar.gz", + "blackbox_version": "0.18.0", + "cadvisor_image": "gcr.io/cadvisor/cadvisor:latest", + "cadvisor_port": "8080", + "cadvisor_service_name": "cadvisorexporter", + "datacenters": "yul1", + "job_name": "prod-exporter", + "node_port": "9100", + "node_service_name": "nodeexporter", + "node_url_amd64": "https://github.com/prometheus/node_exporter/releases/download/v1.0.1/node_exporter-1.0.1.linux-amd64.tar.gz", + "node_url_arm64": "https://github.com/prometheus/node_exporter/releases/download/v1.0.1/node_exporter-1.0.1.linux-arm64.tar.gz", + "node_version": "1.0.1", + "use_canary": "false" + } + }, + "sensitive_attributes": [] + } + ] + }, + { + "module": "module.exporter", + "mode": "managed", + "type": "nomad_job", + "name": "nomad_job_exporter", + "provider": "provider[\"registry.terraform.io/hashicorp/nomad\"].yul1", + "instances": [ + { + "schema_version": 0, + "attributes": { + "allocation_ids": [ + "e11d14cf-0b12-7f11-f982-e75abb2fa245", + "be1d7792-8b38-0769-1899-4d78ac17d775", + "a382862b-e015-bb85-7fed-5a70ab5433e5", + "33190f8d-6b97-5a79-32c3-c2a48eb33cab", + "7b9a89f3-3094-73aa-de9e-b674cdf3962b", + "1b730294-e8c6-d330-72a6-7502ef6d8195", + "3b3932ce-d57e-d0c6-0d36-b32724d83a0f", + "d07855d6-29a8-dba5-92a8-bed5673c3b81", + "4ea7fa69-4819-5050-37ea-bbce995e994d", + "2c694f1a-fb0e-67b9-407a-dd5f1d72daa0", + "52e828d4-79a7-9e43-2cdb-1ba6088f3257", + "e23fc3eb-1699-e1e8-629b-82a21b72ecf4", + "6f83b8c0-4313-eb5a-9c22-e8db2226e832", + "15ee749c-07f0-2864-f907-919faa62cee2", + "12025e7c-4a27-9a9b-b0aa-a205179139eb", + "a6234b96-8c7b-1fd4-e85f-d361774d3005", + "fadf8b49-0e1c-98ea-42b5-119667fa092e", + "2cb8905c-3d36-878d-917e-493f8a982970", + "a1426c7b-a4a1-0f19-cc11-162b396e9ce9", + "f24eee7b-e480-3386-9a6e-357edb9ae137", + "7b7c32b2-9cc9-bb99-b203-2842e4495f5c", + "c90d6b3d-93ac-2fa6-e713-aa69b3a3be69" + ], + "datacenters": [ + "yul1" + ], + "deployment_id": "", + "deployment_status": "", + "deregister_on_destroy": true, + "deregister_on_id_change": true, + "detach": false, + "id": "prod-exporter", + "jobspec": "job \"prod-exporter\" {\n # The \"region\" parameter specifies the region in which to execute the job.\n # If omitted, this inherits the default region name of \"global\".\n # region = \"global\"\n #\n # The \"datacenters\" parameter specifies the list of datacenters which should\n # be considered when placing this task. This must be provided.\n datacenters = \"yul1\"\n\n # The \"type\" parameter controls the type of job, which impacts the scheduler's\n # decision on placement. This configuration is optional and defaults to\n # \"service\". For a full list of job types and their differences, please see\n # the online documentation.\n #\n # https://www.nomadproject.io/docs/jobspec/schedulers\n #\n type = \"system\"\n\n update {\n # The \"max_parallel\" parameter specifies the maximum number of updates to\n # perform in parallel. In this case, this specifies to update a single task\n # at a time.\n max_parallel = 1\n\n health_check = \"checks\"\n\n # The \"min_healthy_time\" parameter specifies the minimum time the allocation\n # must be in the healthy state before it is marked as healthy and unblocks\n # further allocations from being updated.\n min_healthy_time = \"10s\"\n\n # The \"healthy_deadline\" parameter specifies the deadline in which the\n # allocation must be marked as healthy after which the allocation is\n # automatically transitioned to unhealthy. Transitioning to unhealthy will\n # fail the deployment and potentially roll back the job if \"auto_revert\" is\n # set to true.\n healthy_deadline = \"3m\"\n\n # The \"progress_deadline\" parameter specifies the deadline in which an\n # allocation must be marked as healthy. The deadline begins when the first\n # allocation for the deployment is created and is reset whenever an allocation\n # as part of the deployment transitions to a healthy state. If no allocation\n # transitions to the healthy state before the progress deadline, the\n # deployment is marked as failed.\n progress_deadline = \"10m\"\n\n\n }\n\n # The \"group\" stanza defines a series of tasks that should be co-located on\n # the same Nomad client. Any task within a group will be placed on the same\n # client.\n #\n # https://www.nomadproject.io/docs/job-specification/group\n #\n group \"prod-group1-exporter-amd64\" {\n # The constraint allows restricting the set of eligible nodes. Constraints\n # may filter on attributes or client metadata.\n #\n # https://www.nomadproject.io/docs/job-specification/constraint\n #\n constraint {\n attribute = \"${attr.cpu.arch}\"\n operator = \"!=\"\n value = \"arm64\"\n }\n\n # The \"task\" stanza creates an individual unit of work, such as a Docker\n # container, web application, or batch processing.\n #\n # https://www.nomadproject.io/docs/job-specification/task\n #\n task \"prod-task1-nodeexporter-amd64\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"raw_exec\"\n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n command = \"local/node_exporter-1.0.1.linux-amd64/node_exporter\"\n }\n\n # The artifact stanza instructs Nomad to fetch and unpack a remote resource,\n # such as a file, tarball, or binary. Nomad downloads artifacts using the\n # popular go-getter library, which permits downloading artifacts from a\n # variety of locations using a URL as the input source.\n #\n # https://www.nomadproject.io/docs/job-specification/artifact\n #\n artifact {\n source = \"https://github.com/prometheus/node_exporter/releases/download/v1.0.1/node_exporter-1.0.1.linux-amd64.tar.gz\"\n }\n\n # The service stanza instructs Nomad to register a service with Consul.\n #\n # https://www.nomadproject.io/docs/job-specification/service\n #\n service {\n name = \"nodeexporter\"\n port = \"nodeexporter\"\n check {\n name = \"Node Exporter Check Live\"\n type = \"http\"\n path = \"/metrics\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # https://www.nomadproject.io/docs/job-specification/resources\n #\n resources {\n cpu = 500\n # The network stanza specifies the networking requirements for the task\n # group, including the network mode and port allocations. When scheduling\n # jobs in Nomad they are provisioned across your fleet of machines along\n # with other jobs and services. Because you don't know in advance what host\n # your job will be provisioned on, Nomad will provide your tasks with\n # network configuration when they start up.\n #\n # https://www.nomadproject.io/docs/job-specification/network\n #\n network {\n port \"nodeexporter\" {\n static = 9100\n }\n }\n }\n }\n task \"prod-task2-blackboxexporter-amd64\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"exec\"\n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n command = \"local/blackbox_exporter-0.18.0.linux-amd64/blackbox_exporter\"\n args = [\n \"--config.file=secrets/blackbox.yml\"\n ]\n }\n\n # The \"template\" stanza instructs Nomad to manage a template, such as\n # a configuration file or script. This template can optionally pull data\n # from Consul or Vault to populate runtime configuration data.\n #\n # https://www.nomadproject.io/docs/job-specification/template\n #\n template {\n change_mode = \"noop\"\n change_signal = \"SIGINT\"\n destination = \"secrets/blackbox.yml\"\n data = \u003c\u003cEOH\nmodules:\n http_2xx:\n prober: http\n timeout: 5s\n http:\n valid_http_versions: [\"HTTP/1.1\", \"HTTP/2.0\"]\n no_follow_redirects: false\n fail_if_ssl: false\n fail_if_not_ssl: true\n tls_config:\n insecure_skip_verify: false\n preferred_ip_protocol: \"ip4\"\n icmp_v4:\n prober: icmp\n timeout: 5s\n icmp:\n preferred_ip_protocol: \"ip4\"\n dns_udp:\n prober: dns\n timeout: 5s\n dns:\n query_name: \"jenkins.fd.io\"\n query_type: \"A\"\n valid_rcodes:\n - NOERROR\nEOH\n }\n\n # The artifact stanza instructs Nomad to fetch and unpack a remote resource,\n # such as a file, tarball, or binary. Nomad downloads artifacts using the\n # popular go-getter library, which permits downloading artifacts from a\n # variety of locations using a URL as the input source.\n #\n # https://www.nomadproject.io/docs/job-specification/artifact\n #\n artifact {\n source = \"https://github.com/prometheus/blackbox_exporter/releases/download/v0.18.0/blackbox_exporter-0.18.0.linux-amd64.tar.gz\"\n }\n\n # The service stanza instructs Nomad to register a service with Consul.\n #\n # https://www.nomadproject.io/docs/job-specification/service\n #\n service {\n name = \"blackboxexporter\"\n port = \"blackboxexporter\"\n tags = [ \"blackboxexporter${NOMAD_ALLOC_INDEX}\" ]\n check {\n name = \"Blackbox Exporter Check Live\"\n type = \"http\"\n path = \"/metrics\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # https://www.nomadproject.io/docs/job-specification/resources\n #\n resources {\n cpu = 500\n # The network stanza specifies the networking requirements for the task\n # group, including the network mode and port allocations. When scheduling\n # jobs in Nomad they are provisioned across your fleet of machines along\n # with other jobs and services. Because you don't know in advance what host\n # your job will be provisioned on, Nomad will provide your tasks with\n # network configuration when they start up.\n #\n # https://www.nomadproject.io/docs/job-specification/network\n #\n network {\n port \"blackboxexporter\" {\n static = 9115\n }\n }\n }\n }\n\n task \"prod-task3-cadvisorexporter-amd64\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"docker\"\n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n image = \"gcr.io/cadvisor/cadvisor:latest\"\n volumes = [\n \"/:/rootfs:ro\",\n \"/var/run:/var/run:rw\",\n \"/sys:/sys:ro\",\n \"/var/lib/docker/:/var/lib/docker:ro\",\n \"/cgroup:/cgroup:ro\"\n ]\n }\n\n # The service stanza instructs Nomad to register a service with Consul.\n #\n # https://www.nomadproject.io/docs/job-specification/service\n #\n service {\n name = \"cadvisorexporter\"\n port = \"cadvisorexporter\"\n check {\n name = \"cAdvisor Check Live\"\n type = \"http\"\n path = \"/metrics\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # https://www.nomadproject.io/docs/job-specification/resources\n #\n resources {\n cpu = 500\n # The network stanza specifies the networking requirements for the task\n # group, including the network mode and port allocations. When scheduling\n # jobs in Nomad they are provisioned across your fleet of machines along\n # with other jobs and services. Because you don't know in advance what host\n # your job will be provisioned on, Nomad will provide your tasks with\n # network configuration when they start up.\n #\n # https://www.nomadproject.io/docs/job-specification/network\n #\n network {\n port \"cadvisorexporter\" {\n static = 8080\n }\n }\n }\n }\n }\n\n group \"prod-group1-exporter-arm64\" {\n # The constraint allows restricting the set of eligible nodes. Constraints\n # may filter on attributes or client metadata.\n #\n # https://www.nomadproject.io/docs/job-specification/constraint\n #\n constraint {\n attribute = \"${attr.cpu.arch}\"\n operator = \"==\"\n value = \"arm64\"\n }\n\n # The \"task\" stanza creates an individual unit of work, such as a Docker\n # container, web application, or batch processing.\n #\n # https://www.nomadproject.io/docs/job-specification/task\n #\n task \"prod-task1-nodeexporter-arm64\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"raw_exec\"\n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n command = \"local/node_exporter-1.0.1.linux-arm64/node_exporter\"\n }\n\n # The artifact stanza instructs Nomad to fetch and unpack a remote resource,\n # such as a file, tarball, or binary. Nomad downloads artifacts using the\n # popular go-getter library, which permits downloading artifacts from a\n # variety of locations using a URL as the input source.\n #\n # https://www.nomadproject.io/docs/job-specification/artifact\n #\n artifact {\n source = \"https://github.com/prometheus/node_exporter/releases/download/v1.0.1/node_exporter-1.0.1.linux-arm64.tar.gz\"\n }\n\n # The service stanza instructs Nomad to register a service with Consul.\n #\n # https://www.nomadproject.io/docs/job-specification/service\n #\n service {\n name = \"nodeexporter\"\n port = \"nodeexporter\"\n check {\n name = \"Node Exporter Check Live\"\n type = \"http\"\n path = \"/metrics\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # https://www.nomadproject.io/docs/job-specification/resources\n #\n resources {\n cpu = 500\n # The network stanza specifies the networking requirements for the task\n # group, including the network mode and port allocations. When scheduling\n # jobs in Nomad they are provisioned across your fleet of machines along\n # with other jobs and services. Because you don't know in advance what host\n # your job will be provisioned on, Nomad will provide your tasks with\n # network configuration when they start up.\n #\n # https://www.nomadproject.io/docs/job-specification/network\n #\n network {\n port \"nodeexporter\" {\n static = 9100\n }\n }\n }\n }\n\n task \"prod-task2-blackboxexporter-arm64\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"exec\"\n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n command = \"local/blackbox_exporter-0.18.0.linux-arm64/blackbox_exporter\"\n args = [\n \"--config.file=secrets/blackbox.yml\"\n ]\n }\n\n # The \"template\" stanza instructs Nomad to manage a template, such as\n # a configuration file or script. This template can optionally pull data\n # from Consul or Vault to populate runtime configuration data.\n #\n # https://www.nomadproject.io/docs/job-specification/template\n #\n template {\n change_mode = \"noop\"\n change_signal = \"SIGINT\"\n destination = \"secrets/blackbox.yml\"\n data = \u003c\u003cEOH\nmodules:\n http_2xx:\n prober: http\n timeout: 5s\n http:\n valid_http_versions: [\"HTTP/1.1\", \"HTTP/2.0\"]\n no_follow_redirects: false\n fail_if_ssl: false\n fail_if_not_ssl: true\n tls_config:\n insecure_skip_verify: false\n preferred_ip_protocol: \"ip4\"\n icmp_v4:\n prober: icmp\n timeout: 5s\n icmp:\n preferred_ip_protocol: \"ip4\"\n dns_udp:\n prober: dns\n timeout: 5s\n dns:\n query_name: \"jenkins.fd.io\"\n query_type: \"A\"\n valid_rcodes:\n - NOERROR\nEOH\n }\n\n # The artifact stanza instructs Nomad to fetch and unpack a remote resource,\n # such as a file, tarball, or binary. Nomad downloads artifacts using the\n # popular go-getter library, which permits downloading artifacts from a\n # variety of locations using a URL as the input source.\n #\n # https://www.nomadproject.io/docs/job-specification/artifact\n #\n artifact {\n source = \"https://github.com/prometheus/blackbox_exporter/releases/download/v0.18.0/blackbox_exporter-0.18.0.linux-arm64.tar.gz\"\n }\n\n # The service stanza instructs Nomad to register a service with Consul.\n #\n # https://www.nomadproject.io/docs/job-specification/service\n #\n service {\n name = \"blackboxexporter\"\n port = \"blackboxexporter\"\n tags = [ \"blackboxexporter${NOMAD_ALLOC_INDEX}\" ]\n check {\n name = \"Blackbox Exporter Check Live\"\n type = \"http\"\n path = \"/metrics\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # https://www.nomadproject.io/docs/job-specification/resources\n #\n resources {\n cpu = 500\n # The network stanza specifies the networking requirements for the task\n # group, including the network mode and port allocations. When scheduling\n # jobs in Nomad they are provisioned across your fleet of machines along\n # with other jobs and services. Because you don't know in advance what host\n # your job will be provisioned on, Nomad will provide your tasks with\n # network configuration when they start up.\n #\n # https://www.nomadproject.io/docs/job-specification/network\n #\n network {\n port \"blackboxexporter\" {\n static = 9115\n }\n }\n }\n }\n\n task \"prod-task3-cadvisorexporter-arm64\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"docker\"\n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n # There is currently no official release for arm yet...using community.\n image = \"zcube/cadvisor:latest\"\n volumes = [\n \"/:/rootfs:ro\",\n \"/var/run:/var/run:rw\",\n \"/sys:/sys:ro\",\n \"/var/lib/docker/:/var/lib/docker:ro\",\n \"/cgroup:/cgroup:ro\"\n ]\n }\n\n # The service stanza instructs Nomad to register a service with Consul.\n #\n # https://www.nomadproject.io/docs/job-specification/service\n #\n service {\n name = \"cadvisorexporter\"\n port = \"cadvisorexporter\"\n check {\n name = \"cAdvisor Check Live\"\n type = \"http\"\n path = \"/metrics\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # https://www.nomadproject.io/docs/job-specification/resources\n #\n resources {\n cpu = 500\n # The network stanza specifies the networking requirements for the task\n # group, including the network mode and port allocations. When scheduling\n # jobs in Nomad they are provisioned across your fleet of machines along\n # with other jobs and services. Because you don't know in advance what host\n # your job will be provisioned on, Nomad will provide your tasks with\n # network configuration when they start up.\n #\n # https://www.nomadproject.io/docs/job-specification/network\n #\n network {\n port \"cadvisorexporter\" {\n static = 8080\n }\n }\n }\n }\n }\n}", + "json": null, + "modify_index": "7147927", + "name": "prod-exporter", + "namespace": "default", + "policy_override": null, + "purge_on_destroy": null, + "region": "global", + "task_groups": [ + { + "count": 1, + "meta": {}, + "name": "prod-group1-exporter-amd64", + "task": [ + { + "driver": "raw_exec", + "meta": {}, + "name": "prod-task1-nodeexporter-amd64", + "volume_mounts": [] + }, + { + "driver": "exec", + "meta": {}, + "name": "prod-task2-blackboxexporter-amd64", + "volume_mounts": [] + }, + { + "driver": "docker", + "meta": {}, + "name": "prod-task3-cadvisorexporter-amd64", + "volume_mounts": [] + } + ], + "volumes": [] + }, + { + "count": 1, + "meta": {}, + "name": "prod-group1-exporter-arm64", + "task": [ + { + "driver": "raw_exec", + "meta": {}, + "name": "prod-task1-nodeexporter-arm64", + "volume_mounts": [] + }, + { + "driver": "exec", + "meta": {}, + "name": "prod-task2-blackboxexporter-arm64", + "volume_mounts": [] + }, + { + "driver": "docker", + "meta": {}, + "name": "prod-task3-cadvisorexporter-arm64", + "volume_mounts": [] + } + ], + "volumes": [] + } + ], + "type": "system" + }, + "sensitive_attributes": [], + "private": "bnVsbA==", + "dependencies": [ + "module.exporter.data.template_file.nomad_job_exporter" + ] + } + ] + }, + { + "module": "module.grafana", + "mode": "data", + "type": "template_file", + "name": "nomad_job_grafana", + "provider": "provider[\"registry.terraform.io/hashicorp/template\"]", + "instances": [ + { + "schema_version": 0, + "attributes": { + "filename": null, + "id": "039453e436ebcc20c398c58e986fd3cbc8a797cf28b1006ce0407eba9bb0f9cf", + "rendered": "job \"prod-grafana\" {\n # The \"region\" parameter specifies the region in which to execute the job.\n # If omitted, this inherits the default region name of \"global\".\n # region = \"global\"\n #\n # The \"datacenters\" parameter specifies the list of datacenters which should\n # be considered when placing this task. This must be provided.\n datacenters = \"yul1\"\n\n # The \"type\" parameter controls the type of job, which impacts the scheduler's\n # decision on placement. This configuration is optional and defaults to\n # \"service\". For a full list of job types and their differences, please see\n # the online documentation.\n #\n # For more information, please see the online documentation at:\n #\n # https://www.nomadproject.io/docs/jobspec/schedulers\n #\n type = \"service\"\n\n update {\n # The \"max_parallel\" parameter specifies the maximum number of updates to\n # perform in parallel. In this case, this specifies to update a single task\n # at a time.\n max_parallel = 1\n\n health_check = \"checks\"\n\n # The \"min_healthy_time\" parameter specifies the minimum time the allocation\n # must be in the healthy state before it is marked as healthy and unblocks\n # further allocations from being updated.\n min_healthy_time = \"10s\"\n\n # The \"healthy_deadline\" parameter specifies the deadline in which the\n # allocation must be marked as healthy after which the allocation is\n # automatically transitioned to unhealthy. Transitioning to unhealthy will\n # fail the deployment and potentially roll back the job if \"auto_revert\" is\n # set to true.\n healthy_deadline = \"3m\"\n\n # The \"progress_deadline\" parameter specifies the deadline in which an\n # allocation must be marked as healthy. The deadline begins when the first\n # allocation for the deployment is created and is reset whenever an allocation\n # as part of the deployment transitions to a healthy state. If no allocation\n # transitions to the healthy state before the progress deadline, the\n # deployment is marked as failed.\n progress_deadline = \"10m\"\n\n\n # The \"canary\" parameter specifies that changes to the job that would result\n # in destructive updates should create the specified number of canaries\n # without stopping any previous allocations. Once the operator determines the\n # canaries are healthy, they can be promoted which unblocks a rolling update\n # of the remaining allocations at a rate of \"max_parallel\".\n #\n # Further, setting \"canary\" equal to the count of the task group allows\n # blue/green deployments. When the job is updated, a full set of the new\n # version is deployed and upon promotion the old version is stopped.\n canary = 1\n\n # Specifies if the job should auto-promote to the canary version when all\n # canaries become healthy during a deployment. Defaults to false which means\n # canaries must be manually updated with the nomad deployment promote\n # command.\n auto_promote = true\n\n # The \"auto_revert\" parameter specifies if the job should auto-revert to the\n # last stable job on deployment failure. A job is marked as stable if all the\n # allocations as part of its deployment were marked healthy.\n auto_revert = true\n\n }\n\n # The \"group\" stanza defines a series of tasks that should be co-located on\n # the same Nomad client. Any task within a group will be placed on the same\n # client.\n #\n # For more information and examples on the \"group\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/group\n #\n group \"prod-group1-grafana\" {\n # The \"count\" parameter specifies the number of the task groups that should\n # be running under this group. This value must be non-negative and defaults\n # to 1.\n count = 1\n\n\n # The constraint allows restricting the set of eligible nodes. Constraints\n # may filter on attributes or client metadata.\n #\n # For more information and examples on the \"volume\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/constraint\n #\n constraint {\n attribute = \"${attr.cpu.arch}\"\n operator = \"!=\"\n value = \"arm64\"\n }\n\n # The \"task\" stanza creates an individual unit of work, such as a Docker\n # container, web application, or batch processing.\n #\n # For more information and examples on the \"task\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/task\n #\n task \"prod-task1-grafana\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"docker\"\n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n image = \"grafana/grafana:7.3.7\"\n dns_servers = [ \"${attr.unique.network.ip-address}\" ]\n volumes = [\n \"secrets/prometheus.yml:/etc/grafana/provisioning/datasources/prometheus.yml\",\n \"secrets/dashboards.yml:/etc/grafana/provisioning/dashboards/dashboards.yml\",\n \"secrets/grafana.ini:/etc/grafana/grafana.ini\",\n \"secrets/node_exporter.json:/etc/grafana/provisioning/dashboards/node_exporter.json\",\n \"secrets/docker_cadvisor.json:/etc/grafana/provisioning/dashboards/docker_cadvisor.json\",\n \"secrets/nomad.json:/etc/grafana/provisioning/dashboards/nomad.json\",\n \"secrets/consul.json:/etc/grafana/provisioning/dashboards/consul.json\",\n \"secrets/prometheus.json:/etc/grafana/provisioning/dashboards/prometheus.json\"\n ]\n }\n\n artifact {\n # Node Exporter\n source = \"https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/node_exporter.json\"\n destination = \"secrets/\"\n }\n\n artifact {\n # Docker cAdvisor\n source = \"https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/docker_cadvisor.json\"\n destination = \"secrets/\"\n }\n\n artifact {\n # Nomad\n source = \"https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/nomad.json\"\n destination = \"secrets/\"\n }\n\n artifact {\n # Consul\n source = \"https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/consul.json\"\n destination = \"secrets/\"\n }\n\n artifact {\n # Prometheus\n source = \"https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/prometheus.json\"\n destination = \"secrets/\"\n }\n\n # The \"template\" stanza instructs Nomad to manage a template, such as\n # a configuration file or script. This template can optionally pull data\n # from Consul or Vault to populate runtime configuration data.\n #\n # For more information and examples on the \"template\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/template\n #\n template {\n change_mode = \"noop\"\n change_signal = \"SIGINT\"\n destination = \"secrets/prometheus.yml\"\n data = \u003c\u003cEOH\napiVersion: 1\ndatasources:\n- name: Prometheus\n type: prometheus\n access: direct\n orgId: 1\n url: http://prometheus.service.consul:9090\n basicAuth: false\n isDefault: true\n version: 1\n editable: false\nEOH\n }\n\n template {\n change_mode = \"noop\"\n change_signal = \"SIGINT\"\n destination = \"secrets/dashboards.yml\"\n data = \u003c\u003cEOH\napiVersion: 1\nproviders:\n- name: dashboards\n type: file\n disableDeletion: false\n updateIntervalSeconds: 10\n allowUiUpdates: false\n options:\n path: /etc/grafana/provisioning/dashboards\n foldersFromFilesStructure: true\nEOH\n }\n\n template {\n change_mode = \"noop\"\n change_signal = \"SIGINT\"\n destination = \"secrets/grafana.ini\"\n data = \u003c\u003cEOH\napp_mode = production\n\n[metrics]\nenabled = true\n\n[server]\nprotocol = http\nhttp_port = 3000\nroot_url = http://grafana.service.consul:3000\nenable_gzip = true\n;cert_file =\n;cert_key =\n\n[security]\nadmin_user = grafanauser\nadmin_password = Grafana1234\nsecret_key = SW2YcwTIb9zpOOhoPsMm\n\n[users]\nallow_sign_up = false\nallow_org_create = false\nauto_assign_org = true\nauto_assign_org_role = Viewer\ndefault_theme = dark\n\n[auth.basic]\nenabled = true\n\n[auth]\ndisable_login_form = false\ndisable_signout_menu = false\n\n[auth.anonymous]\nenabled = false\n\n[log]\nmode = console\nlevel = info\n\n[log.console]\nlevel = info\nformat = console\nEOH\n }\n\n # The service stanza instructs Nomad to register a service with Consul.\n #\n # For more information and examples on the \"task\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/service\n #\n service {\n name = \"grafana\"\n port = \"grafana\"\n tags = [ \"grafana${NOMAD_ALLOC_INDEX}\" ]\n check {\n name = \"Grafana Check Live\"\n type = \"http\"\n protocol = \"http\"\n tls_skip_verify = true\n path = \"/api/health\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # For more information and examples on the \"resources\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/resources\n #\n resources {\n cpu = 2000\n memory = 2048\n # The network stanza specifies the networking requirements for the task\n # group, including the network mode and port allocations. When scheduling\n # jobs in Nomad they are provisioned across your fleet of machines along\n # with other jobs and services. Because you don't know in advance what host\n # your job will be provisioned on, Nomad will provide your tasks with\n # network configuration when they start up.\n #\n # For more information and examples on the \"template\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/network\n #\n network {\n port \"grafana\" {\n static = 3000\n }\n }\n }\n }\n }\n}", + "template": "job \"${job_name}\" {\n # The \"region\" parameter specifies the region in which to execute the job.\n # If omitted, this inherits the default region name of \"global\".\n # region = \"global\"\n #\n # The \"datacenters\" parameter specifies the list of datacenters which should\n # be considered when placing this task. This must be provided.\n datacenters = \"${datacenters}\"\n\n # The \"type\" parameter controls the type of job, which impacts the scheduler's\n # decision on placement. This configuration is optional and defaults to\n # \"service\". For a full list of job types and their differences, please see\n # the online documentation.\n #\n # For more information, please see the online documentation at:\n #\n # https://www.nomadproject.io/docs/jobspec/schedulers\n #\n type = \"service\"\n\n update {\n # The \"max_parallel\" parameter specifies the maximum number of updates to\n # perform in parallel. In this case, this specifies to update a single task\n # at a time.\n max_parallel = 1\n\n health_check = \"checks\"\n\n # The \"min_healthy_time\" parameter specifies the minimum time the allocation\n # must be in the healthy state before it is marked as healthy and unblocks\n # further allocations from being updated.\n min_healthy_time = \"10s\"\n\n # The \"healthy_deadline\" parameter specifies the deadline in which the\n # allocation must be marked as healthy after which the allocation is\n # automatically transitioned to unhealthy. Transitioning to unhealthy will\n # fail the deployment and potentially roll back the job if \"auto_revert\" is\n # set to true.\n healthy_deadline = \"3m\"\n\n # The \"progress_deadline\" parameter specifies the deadline in which an\n # allocation must be marked as healthy. The deadline begins when the first\n # allocation for the deployment is created and is reset whenever an allocation\n # as part of the deployment transitions to a healthy state. If no allocation\n # transitions to the healthy state before the progress deadline, the\n # deployment is marked as failed.\n progress_deadline = \"10m\"\n\n%{ if use_canary }\n # The \"canary\" parameter specifies that changes to the job that would result\n # in destructive updates should create the specified number of canaries\n # without stopping any previous allocations. Once the operator determines the\n # canaries are healthy, they can be promoted which unblocks a rolling update\n # of the remaining allocations at a rate of \"max_parallel\".\n #\n # Further, setting \"canary\" equal to the count of the task group allows\n # blue/green deployments. When the job is updated, a full set of the new\n # version is deployed and upon promotion the old version is stopped.\n canary = 1\n\n # Specifies if the job should auto-promote to the canary version when all\n # canaries become healthy during a deployment. Defaults to false which means\n # canaries must be manually updated with the nomad deployment promote\n # command.\n auto_promote = true\n\n # The \"auto_revert\" parameter specifies if the job should auto-revert to the\n # last stable job on deployment failure. A job is marked as stable if all the\n # allocations as part of its deployment were marked healthy.\n auto_revert = true\n%{ endif }\n }\n\n # The \"group\" stanza defines a series of tasks that should be co-located on\n # the same Nomad client. Any task within a group will be placed on the same\n # client.\n #\n # For more information and examples on the \"group\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/group\n #\n group \"prod-group1-${service_name}\" {\n # The \"count\" parameter specifies the number of the task groups that should\n # be running under this group. This value must be non-negative and defaults\n # to 1.\n count = ${group_count}\n\n\n # The constraint allows restricting the set of eligible nodes. Constraints\n # may filter on attributes or client metadata.\n #\n # For more information and examples on the \"volume\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/constraint\n #\n constraint {\n attribute = \"$${attr.cpu.arch}\"\n operator = \"!=\"\n value = \"arm64\"\n }\n\n # The \"task\" stanza creates an individual unit of work, such as a Docker\n # container, web application, or batch processing.\n #\n # For more information and examples on the \"task\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/task\n #\n task \"prod-task1-${service_name}\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"docker\"\n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n image = \"${image}\"\n dns_servers = [ \"$${attr.unique.network.ip-address}\" ]\n volumes = [\n \"secrets/prometheus.yml:/etc/grafana/provisioning/datasources/prometheus.yml\",\n \"secrets/dashboards.yml:/etc/grafana/provisioning/dashboards/dashboards.yml\",\n \"secrets/grafana.ini:/etc/grafana/grafana.ini\",\n \"secrets/node_exporter.json:/etc/grafana/provisioning/dashboards/node_exporter.json\",\n \"secrets/docker_cadvisor.json:/etc/grafana/provisioning/dashboards/docker_cadvisor.json\",\n \"secrets/nomad.json:/etc/grafana/provisioning/dashboards/nomad.json\",\n \"secrets/consul.json:/etc/grafana/provisioning/dashboards/consul.json\",\n \"secrets/prometheus.json:/etc/grafana/provisioning/dashboards/prometheus.json\"\n ]\n }\n\n artifact {\n # Node Exporter\n source = \"https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/node_exporter.json\"\n destination = \"secrets/\"\n }\n\n artifact {\n # Docker cAdvisor\n source = \"https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/docker_cadvisor.json\"\n destination = \"secrets/\"\n }\n\n artifact {\n # Nomad\n source = \"https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/nomad.json\"\n destination = \"secrets/\"\n }\n\n artifact {\n # Consul\n source = \"https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/consul.json\"\n destination = \"secrets/\"\n }\n\n artifact {\n # Prometheus\n source = \"https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/prometheus.json\"\n destination = \"secrets/\"\n }\n\n # The \"template\" stanza instructs Nomad to manage a template, such as\n # a configuration file or script. This template can optionally pull data\n # from Consul or Vault to populate runtime configuration data.\n #\n # For more information and examples on the \"template\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/template\n #\n template {\n change_mode = \"noop\"\n change_signal = \"SIGINT\"\n destination = \"secrets/prometheus.yml\"\n data = \u003c\u003cEOH\napiVersion: 1\ndatasources:\n- name: Prometheus\n type: prometheus\n access: direct\n orgId: 1\n url: http://prometheus.service.consul:9090\n basicAuth: false\n isDefault: true\n version: 1\n editable: false\nEOH\n }\n\n template {\n change_mode = \"noop\"\n change_signal = \"SIGINT\"\n destination = \"secrets/dashboards.yml\"\n data = \u003c\u003cEOH\napiVersion: 1\nproviders:\n- name: dashboards\n type: file\n disableDeletion: false\n updateIntervalSeconds: 10\n allowUiUpdates: false\n options:\n path: /etc/grafana/provisioning/dashboards\n foldersFromFilesStructure: true\nEOH\n }\n\n template {\n change_mode = \"noop\"\n change_signal = \"SIGINT\"\n destination = \"secrets/grafana.ini\"\n data = \u003c\u003cEOH\napp_mode = production\n\n[metrics]\nenabled = true\n\n[server]\nprotocol = http\nhttp_port = ${port}\nroot_url = http://${service_name}.service.consul:${port}\nenable_gzip = true\n;cert_file =\n;cert_key =\n\n[security]\nadmin_user = grafanauser\nadmin_password = Grafana1234\nsecret_key = SW2YcwTIb9zpOOhoPsMm\n\n[users]\nallow_sign_up = false\nallow_org_create = false\nauto_assign_org = true\nauto_assign_org_role = Viewer\ndefault_theme = dark\n\n[auth.basic]\nenabled = true\n\n[auth]\ndisable_login_form = false\ndisable_signout_menu = false\n\n[auth.anonymous]\nenabled = false\n\n[log]\nmode = console\nlevel = info\n\n[log.console]\nlevel = info\nformat = console\nEOH\n }\n\n # The service stanza instructs Nomad to register a service with Consul.\n #\n # For more information and examples on the \"task\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/service\n #\n service {\n name = \"${service_name}\"\n port = \"${service_name}\"\n tags = [ \"${service_name}$${NOMAD_ALLOC_INDEX}\" ]\n check {\n name = \"Grafana Check Live\"\n type = \"http\"\n protocol = \"http\"\n tls_skip_verify = true\n path = \"/api/health\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # For more information and examples on the \"resources\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/resources\n #\n resources {\n cpu = ${cpu}\n memory = ${mem}\n # The network stanza specifies the networking requirements for the task\n # group, including the network mode and port allocations. When scheduling\n # jobs in Nomad they are provisioned across your fleet of machines along\n # with other jobs and services. Because you don't know in advance what host\n # your job will be provisioned on, Nomad will provide your tasks with\n # network configuration when they start up.\n #\n # For more information and examples on the \"template\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/network\n #\n network {\n port \"${service_name}\" {\n static = ${port}\n }\n }\n }\n }\n }\n}", + "vars": { + "cpu": "2000", + "datacenters": "yul1", + "group_count": "1", + "image": "grafana/grafana:7.3.7", + "job_name": "prod-grafana", + "mem": "2048", + "port": "3000", + "service_name": "grafana", + "use_canary": "true", + "use_vault_provider": "false" + } + }, + "sensitive_attributes": [] + } + ] + }, + { + "module": "module.grafana", + "mode": "managed", + "type": "nomad_job", + "name": "nomad_job_grafana", + "provider": "provider[\"registry.terraform.io/hashicorp/nomad\"].yul1", + "instances": [ + { + "schema_version": 0, + "attributes": { + "allocation_ids": [ + "d2ddca98-1bb8-680d-06f1-00fcf4887eca" + ], + "datacenters": [ + "yul1" + ], + "deployment_id": "4ef2df3e-696c-5382-5eec-991411a36a90", + "deployment_status": "successful", + "deregister_on_destroy": true, + "deregister_on_id_change": true, + "detach": false, + "id": "prod-grafana", + "jobspec": "job \"prod-grafana\" {\n # The \"region\" parameter specifies the region in which to execute the job.\n # If omitted, this inherits the default region name of \"global\".\n # region = \"global\"\n #\n # The \"datacenters\" parameter specifies the list of datacenters which should\n # be considered when placing this task. This must be provided.\n datacenters = \"yul1\"\n\n # The \"type\" parameter controls the type of job, which impacts the scheduler's\n # decision on placement. This configuration is optional and defaults to\n # \"service\". For a full list of job types and their differences, please see\n # the online documentation.\n #\n # For more information, please see the online documentation at:\n #\n # https://www.nomadproject.io/docs/jobspec/schedulers\n #\n type = \"service\"\n\n update {\n # The \"max_parallel\" parameter specifies the maximum number of updates to\n # perform in parallel. In this case, this specifies to update a single task\n # at a time.\n max_parallel = 1\n\n health_check = \"checks\"\n\n # The \"min_healthy_time\" parameter specifies the minimum time the allocation\n # must be in the healthy state before it is marked as healthy and unblocks\n # further allocations from being updated.\n min_healthy_time = \"10s\"\n\n # The \"healthy_deadline\" parameter specifies the deadline in which the\n # allocation must be marked as healthy after which the allocation is\n # automatically transitioned to unhealthy. Transitioning to unhealthy will\n # fail the deployment and potentially roll back the job if \"auto_revert\" is\n # set to true.\n healthy_deadline = \"3m\"\n\n # The \"progress_deadline\" parameter specifies the deadline in which an\n # allocation must be marked as healthy. The deadline begins when the first\n # allocation for the deployment is created and is reset whenever an allocation\n # as part of the deployment transitions to a healthy state. If no allocation\n # transitions to the healthy state before the progress deadline, the\n # deployment is marked as failed.\n progress_deadline = \"10m\"\n\n\n # The \"canary\" parameter specifies that changes to the job that would result\n # in destructive updates should create the specified number of canaries\n # without stopping any previous allocations. Once the operator determines the\n # canaries are healthy, they can be promoted which unblocks a rolling update\n # of the remaining allocations at a rate of \"max_parallel\".\n #\n # Further, setting \"canary\" equal to the count of the task group allows\n # blue/green deployments. When the job is updated, a full set of the new\n # version is deployed and upon promotion the old version is stopped.\n canary = 1\n\n # Specifies if the job should auto-promote to the canary version when all\n # canaries become healthy during a deployment. Defaults to false which means\n # canaries must be manually updated with the nomad deployment promote\n # command.\n auto_promote = true\n\n # The \"auto_revert\" parameter specifies if the job should auto-revert to the\n # last stable job on deployment failure. A job is marked as stable if all the\n # allocations as part of its deployment were marked healthy.\n auto_revert = true\n\n }\n\n # The \"group\" stanza defines a series of tasks that should be co-located on\n # the same Nomad client. Any task within a group will be placed on the same\n # client.\n #\n # For more information and examples on the \"group\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/group\n #\n group \"prod-group1-grafana\" {\n # The \"count\" parameter specifies the number of the task groups that should\n # be running under this group. This value must be non-negative and defaults\n # to 1.\n count = 1\n\n\n # The constraint allows restricting the set of eligible nodes. Constraints\n # may filter on attributes or client metadata.\n #\n # For more information and examples on the \"volume\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/constraint\n #\n constraint {\n attribute = \"${attr.cpu.arch}\"\n operator = \"!=\"\n value = \"arm64\"\n }\n\n # The \"task\" stanza creates an individual unit of work, such as a Docker\n # container, web application, or batch processing.\n #\n # For more information and examples on the \"task\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/task\n #\n task \"prod-task1-grafana\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"docker\"\n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n image = \"grafana/grafana:7.3.7\"\n dns_servers = [ \"${attr.unique.network.ip-address}\" ]\n volumes = [\n \"secrets/prometheus.yml:/etc/grafana/provisioning/datasources/prometheus.yml\",\n \"secrets/dashboards.yml:/etc/grafana/provisioning/dashboards/dashboards.yml\",\n \"secrets/grafana.ini:/etc/grafana/grafana.ini\",\n \"secrets/node_exporter.json:/etc/grafana/provisioning/dashboards/node_exporter.json\",\n \"secrets/docker_cadvisor.json:/etc/grafana/provisioning/dashboards/docker_cadvisor.json\",\n \"secrets/nomad.json:/etc/grafana/provisioning/dashboards/nomad.json\",\n \"secrets/consul.json:/etc/grafana/provisioning/dashboards/consul.json\",\n \"secrets/prometheus.json:/etc/grafana/provisioning/dashboards/prometheus.json\"\n ]\n }\n\n artifact {\n # Prometheus Node Exporter Full\n source = \"https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/node_exporter.json\"\n destination = \"secrets/\"\n }\n\n artifact {\n # Docker cAdvisor\n source = \"https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/docker_cadvisor.json\"\n destination = \"secrets/\"\n }\n\n artifact {\n # Nomad\n source = \"https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/nomad.json\"\n destination = \"secrets/\"\n }\n\n artifact {\n # Consul\n source = \"https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/consul.json\"\n destination = \"secrets/\"\n }\n\n artifact {\n # Prometheus\n source = \"https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/prometheus.json\"\n destination = \"secrets/\"\n }\n\n # The \"template\" stanza instructs Nomad to manage a template, such as\n # a configuration file or script. This template can optionally pull data\n # from Consul or Vault to populate runtime configuration data.\n #\n # For more information and examples on the \"template\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/template\n #\n template {\n change_mode = \"noop\"\n change_signal = \"SIGINT\"\n destination = \"secrets/prometheus.yml\"\n data = \u003c\u003cEOH\napiVersion: 1\ndatasources:\n- name: Prometheus\n type: prometheus\n access: direct\n orgId: 1\n url: http://prometheus.service.consul:9090\n basicAuth: false\n isDefault: true\n version: 1\n editable: false\nEOH\n }\n\n template {\n change_mode = \"noop\"\n change_signal = \"SIGINT\"\n destination = \"secrets/dashboards.yml\"\n data = \u003c\u003cEOH\napiVersion: 1\nproviders:\n- name: dashboards\n type: file\n disableDeletion: false\n updateIntervalSeconds: 10\n allowUiUpdates: false\n options:\n path: /etc/grafana/provisioning/dashboards\n foldersFromFilesStructure: true\nEOH\n }\n\n template {\n change_mode = \"noop\"\n change_signal = \"SIGINT\"\n destination = \"secrets/grafana.ini\"\n data = \u003c\u003cEOH\napp_mode = production\n\n[metrics]\nenabled = true\n\n[server]\nprotocol = http\nhttp_port = 3000\nroot_url = http://grafana.service.consul:3000\nenable_gzip = true\n;cert_file =\n;cert_key =\n\n[security]\nadmin_user = grafanauser\nadmin_password = Grafana1234\nsecret_key = SW2YcwTIb9zpOOhoPsMm\n\n[users]\nallow_sign_up = false\nallow_org_create = false\nauto_assign_org = true\nauto_assign_org_role = Viewer\ndefault_theme = dark\n\n[auth.basic]\nenabled = true\n\n[auth]\ndisable_login_form = false\ndisable_signout_menu = false\n\n[auth.anonymous]\nenabled = false\n\n[log]\nmode = console\nlevel = info\n\n[log.console]\nlevel = info\nformat = console\nEOH\n }\n\n # The service stanza instructs Nomad to register a service with Consul.\n #\n # For more information and examples on the \"task\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/service\n #\n service {\n name = \"grafana\"\n port = \"grafana\"\n tags = [ \"grafana${NOMAD_ALLOC_INDEX}\" ]\n check {\n name = \"Grafana Check Live\"\n type = \"http\"\n protocol = \"http\"\n tls_skip_verify = true\n path = \"/api/health\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # For more information and examples on the \"resources\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/resources\n #\n resources {\n cpu = 2000\n memory = 2048\n # The network stanza specifies the networking requirements for the task\n # group, including the network mode and port allocations. When scheduling\n # jobs in Nomad they are provisioned across your fleet of machines along\n # with other jobs and services. Because you don't know in advance what host\n # your job will be provisioned on, Nomad will provide your tasks with\n # network configuration when they start up.\n #\n # For more information and examples on the \"template\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/network\n #\n network {\n port \"grafana\" {\n static = 3000\n }\n }\n }\n }\n }\n}", + "json": null, + "modify_index": "7140252", + "name": "prod-grafana", + "namespace": "default", + "policy_override": null, + "purge_on_destroy": null, + "region": "global", + "task_groups": [ + { + "count": 1, + "meta": {}, + "name": "prod-group1-grafana", + "task": [ + { + "driver": "docker", + "meta": {}, + "name": "prod-task1-grafana", + "volume_mounts": [] + } + ], + "volumes": [] + } + ], + "type": "service" + }, + "sensitive_attributes": [], + "private": "bnVsbA==", + "dependencies": [ + "module.grafana.data.template_file.nomad_job_grafana" + ] + } + ] + }, + { "module": "module.minio", "mode": "data", "type": "template_file", @@ -48,12 +379,12 @@ "schema_version": 0, "attributes": { "filename": null, - "id": "7e4a32e6a9a032751c28bef6abffe54b7bee9b98b5bb80c9ba5fe18913a1afa7", - "rendered": "job \"prod-minio\" {\n # The \"region\" parameter specifies the region in which to execute the job.\n # If omitted, this inherits the default region name of \"global\".\n # region = \"global\"\n #\n # The \"datacenters\" parameter specifies the list of datacenters which should\n # be considered when placing this task. This must be provided.\n datacenters = \"yul1\"\n\n # The \"type\" parameter controls the type of job, which impacts the scheduler's\n # decision on placement. This configuration is optional and defaults to\n # \"service\". For a full list of job types and their differences, please see\n # the online documentation.\n #\n # For more information, please see the online documentation at:\n #\n # https://www.nomadproject.io/docs/jobspec/schedulers.html\n #\n type = \"service\"\n\n update {\n # The \"max_parallel\" parameter specifies the maximum number of updates to\n # perform in parallel. In this case, this specifies to update a single task\n # at a time.\n max_parallel = 1\n\n health_check = \"checks\"\n\n # The \"min_healthy_time\" parameter specifies the minimum time the allocation\n # must be in the healthy state before it is marked as healthy and unblocks\n # further allocations from being updated.\n min_healthy_time = \"10s\"\n\n # The \"healthy_deadline\" parameter specifies the deadline in which the\n # allocation must be marked as healthy after which the allocation is\n # automatically transitioned to unhealthy. Transitioning to unhealthy will\n # fail the deployment and potentially roll back the job if \"auto_revert\" is\n # set to true.\n healthy_deadline = \"3m\"\n\n # The \"progress_deadline\" parameter specifies the deadline in which an\n # allocation must be marked as healthy. The deadline begins when the first\n # allocation for the deployment is created and is reset whenever an allocation\n # as part of the deployment transitions to a healthy state. If no allocation\n # transitions to the healthy state before the progress deadline, the\n # deployment is marked as failed.\n progress_deadline = \"10m\"\n\n\n # The \"canary\" parameter specifies that changes to the job that would result\n # in destructive updates should create the specified number of canaries\n # without stopping any previous allocations. Once the operator determines the\n # canaries are healthy, they can be promoted which unblocks a rolling update\n # of the remaining allocations at a rate of \"max_parallel\".\n #\n # Further, setting \"canary\" equal to the count of the task group allows\n # blue/green deployments. When the job is updated, a full set of the new\n # version is deployed and upon promotion the old version is stopped.\n canary = 1\n\n # Specifies if the job should auto-promote to the canary version when all\n # canaries become healthy during a deployment. Defaults to false which means\n # canaries must be manually updated with the nomad deployment promote\n # command.\n auto_promote = true\n\n # The \"auto_revert\" parameter specifies if the job should auto-revert to the\n # last stable job on deployment failure. A job is marked as stable if all the\n # allocations as part of its deployment were marked healthy.\n auto_revert = true\n\n }\n\n # All groups in this job should be scheduled on different hosts.\n constraint {\n operator = \"distinct_hosts\"\n value = \"true\"\n }\n\n # The \"group\" stanza defines a series of tasks that should be co-located on\n # the same Nomad client. Any task within a group will be placed on the same\n # client.\n #\n # For more information and examples on the \"group\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/group.html\n #\n group \"prod-group1-minio\" {\n # The \"count\" parameter specifies the number of the task groups that should\n # be running under this group. This value must be non-negative and defaults\n # to 1.\n count = 4\n\n # https://www.nomadproject.io/docs/job-specification/volume\n \n volume \"prod-volume1-minio\" {\n type = \"host\"\n read_only = false\n source = \"prod-volume-data1-1\"\n }\n \n\n # The \"task\" stanza creates an individual unit of work, such as a Docker\n # container, web application, or batch processing.\n #\n # For more information and examples on the \"task\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/task.html\n #\n task \"prod-task1-minio\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"docker\"\n\n \n volume_mount {\n volume = \"prod-volume1-minio\"\n destination = \"/data/\"\n read_only = false\n }\n \n\n \n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n image = \"minio/minio:RELEASE.2020-12-03T05-49-24Z\"\n dns_servers = [ \"${attr.unique.network.ip-address}\" ]\n network_mode = \"host\"\n command = \"server\"\n args = [ \"http://10.32.8.1{4...7}:9000/data/\" ]\n port_map {\n http = 9000\n }\n privileged = false\n }\n\n # The env stanza configures a list of environment variables to populate\n # the task's environment before starting.\n env {\n\n MINIO_ACCESS_KEY = \"minio\"\n MINIO_SECRET_KEY = \"minio123\"\n\n MINIO_BROWSER=\"off\"\n }\n\n # The service stanza instructs Nomad to register a service with Consul.\n #\n # For more information and examples on the \"task\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/service.html\n #\n service {\n name = \"storage\"\n port = \"http\"\n tags = [ \"storage${NOMAD_ALLOC_INDEX}\" ]\n check {\n name = \"Min.io Server HTTP Check Live\"\n type = \"http\"\n port = \"http\"\n protocol = \"http\"\n method = \"GET\"\n path = \"/minio/health/live\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n check {\n name = \"Min.io Server HTTP Check Ready\"\n type = \"http\"\n port = \"http\"\n protocol = \"http\"\n method = \"GET\"\n path = \"/minio/health/ready\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # For more information and examples on the \"resources\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/resources.html\n #\n resources {\n # The network stanza specifies the networking requirements for the task\n # group, including the network mode and port allocations. When scheduling\n # jobs in Nomad they are provisioned across your fleet of machines along\n # with other jobs and services. Because you don't know in advance what host\n # your job will be provisioned on, Nomad will provide your tasks with\n # network configuration when they start up.\n #\n # For more information and examples on the \"template\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/network.html\n #\n network {\n port \"http\" {\n static = 9000\n }\n }\n }\n }\n }\n}\n", - "template": "job \"${job_name}\" {\n # The \"region\" parameter specifies the region in which to execute the job.\n # If omitted, this inherits the default region name of \"global\".\n # region = \"global\"\n #\n # The \"datacenters\" parameter specifies the list of datacenters which should\n # be considered when placing this task. This must be provided.\n datacenters = \"${datacenters}\"\n\n # The \"type\" parameter controls the type of job, which impacts the scheduler's\n # decision on placement. This configuration is optional and defaults to\n # \"service\". For a full list of job types and their differences, please see\n # the online documentation.\n #\n # For more information, please see the online documentation at:\n #\n # https://www.nomadproject.io/docs/jobspec/schedulers.html\n #\n type = \"service\"\n\n update {\n # The \"max_parallel\" parameter specifies the maximum number of updates to\n # perform in parallel. In this case, this specifies to update a single task\n # at a time.\n max_parallel = 1\n\n health_check = \"checks\"\n\n # The \"min_healthy_time\" parameter specifies the minimum time the allocation\n # must be in the healthy state before it is marked as healthy and unblocks\n # further allocations from being updated.\n min_healthy_time = \"10s\"\n\n # The \"healthy_deadline\" parameter specifies the deadline in which the\n # allocation must be marked as healthy after which the allocation is\n # automatically transitioned to unhealthy. Transitioning to unhealthy will\n # fail the deployment and potentially roll back the job if \"auto_revert\" is\n # set to true.\n healthy_deadline = \"3m\"\n\n # The \"progress_deadline\" parameter specifies the deadline in which an\n # allocation must be marked as healthy. The deadline begins when the first\n # allocation for the deployment is created and is reset whenever an allocation\n # as part of the deployment transitions to a healthy state. If no allocation\n # transitions to the healthy state before the progress deadline, the\n # deployment is marked as failed.\n progress_deadline = \"10m\"\n\n%{ if use_canary }\n # The \"canary\" parameter specifies that changes to the job that would result\n # in destructive updates should create the specified number of canaries\n # without stopping any previous allocations. Once the operator determines the\n # canaries are healthy, they can be promoted which unblocks a rolling update\n # of the remaining allocations at a rate of \"max_parallel\".\n #\n # Further, setting \"canary\" equal to the count of the task group allows\n # blue/green deployments. When the job is updated, a full set of the new\n # version is deployed and upon promotion the old version is stopped.\n canary = 1\n\n # Specifies if the job should auto-promote to the canary version when all\n # canaries become healthy during a deployment. Defaults to false which means\n # canaries must be manually updated with the nomad deployment promote\n # command.\n auto_promote = true\n\n # The \"auto_revert\" parameter specifies if the job should auto-revert to the\n # last stable job on deployment failure. A job is marked as stable if all the\n # allocations as part of its deployment were marked healthy.\n auto_revert = true\n%{ endif }\n }\n\n # All groups in this job should be scheduled on different hosts.\n constraint {\n operator = \"distinct_hosts\"\n value = \"true\"\n }\n\n # The \"group\" stanza defines a series of tasks that should be co-located on\n # the same Nomad client. Any task within a group will be placed on the same\n # client.\n #\n # For more information and examples on the \"group\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/group.html\n #\n group \"prod-group1-minio\" {\n # The \"count\" parameter specifies the number of the task groups that should\n # be running under this group. This value must be non-negative and defaults\n # to 1.\n count = ${group_count}\n\n # https://www.nomadproject.io/docs/job-specification/volume\n %{ if use_host_volume }\n volume \"prod-volume1-minio\" {\n type = \"host\"\n read_only = false\n source = \"${host_volume}\"\n }\n %{ endif }\n\n # The \"task\" stanza creates an individual unit of work, such as a Docker\n # container, web application, or batch processing.\n #\n # For more information and examples on the \"task\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/task.html\n #\n task \"prod-task1-minio\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"docker\"\n\n %{ if use_host_volume }\n volume_mount {\n volume = \"prod-volume1-minio\"\n destination = \"${data_dir}\"\n read_only = false\n }\n %{ endif }\n\n %{ if use_vault_provider }\n vault {\n policies = \"${vault_kv_policy_name}\"\n }\n %{ endif }\n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n image = \"${image}\"\n dns_servers = [ \"$${attr.unique.network.ip-address}\" ]\n network_mode = \"host\"\n command = \"server\"\n args = [ \"${host}:${port}${data_dir}\" ]\n port_map {\n http = ${port}\n }\n privileged = false\n }\n\n # The env stanza configures a list of environment variables to populate\n # the task's environment before starting.\n env {\n%{ if use_vault_provider }\n{{ with secret \"${vault_kv_path}\" }}\n MINIO_ACCESS_KEY = \"{{ .Data.data.${vault_kv_field_access_key} }}\"\n MINIO_SECRET_KEY = \"{{ .Data.data.${vault_kv_field_secret_key} }}\"\n{{ end }}\n%{ else }\n MINIO_ACCESS_KEY = \"${access_key}\"\n MINIO_SECRET_KEY = \"${secret_key}\"\n%{ endif }\n ${ envs }\n }\n\n # The service stanza instructs Nomad to register a service with Consul.\n #\n # For more information and examples on the \"task\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/service.html\n #\n service {\n name = \"${service_name}\"\n port = \"http\"\n tags = [ \"storage$${NOMAD_ALLOC_INDEX}\" ]\n check {\n name = \"Min.io Server HTTP Check Live\"\n type = \"http\"\n port = \"http\"\n protocol = \"http\"\n method = \"GET\"\n path = \"/minio/health/live\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n check {\n name = \"Min.io Server HTTP Check Ready\"\n type = \"http\"\n port = \"http\"\n protocol = \"http\"\n method = \"GET\"\n path = \"/minio/health/ready\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # For more information and examples on the \"resources\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/resources.html\n #\n resources {\n # The network stanza specifies the networking requirements for the task\n # group, including the network mode and port allocations. When scheduling\n # jobs in Nomad they are provisioned across your fleet of machines along\n # with other jobs and services. Because you don't know in advance what host\n # your job will be provisioned on, Nomad will provide your tasks with\n # network configuration when they start up.\n #\n # For more information and examples on the \"template\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/network.html\n #\n network {\n port \"http\" {\n static = ${port}\n }\n }\n }\n }\n }\n}\n", + "id": "c38a0b7182d39c70ec07bdaa998f57a215d7193b264c1b1c1a299c84e7ca53de", + "rendered": "job \"prod-minio\" {\n # The \"region\" parameter specifies the region in which to execute the job.\n # If omitted, this inherits the default region name of \"global\".\n # region = \"global\"\n #\n # The \"datacenters\" parameter specifies the list of datacenters which should\n # be considered when placing this task. This must be provided.\n datacenters = \"yul1\"\n\n # The \"type\" parameter controls the type of job, which impacts the scheduler's\n # decision on placement. This configuration is optional and defaults to\n # \"service\". For a full list of job types and their differences, please see\n # the online documentation.\n #\n # For more information, please see the online documentation at:\n #\n # https://www.nomadproject.io/docs/jobspec/schedulers.html\n #\n type = \"service\"\n\n update {\n # The \"max_parallel\" parameter specifies the maximum number of updates to\n # perform in parallel. In this case, this specifies to update a single task\n # at a time.\n max_parallel = 1\n\n health_check = \"checks\"\n\n # The \"min_healthy_time\" parameter specifies the minimum time the allocation\n # must be in the healthy state before it is marked as healthy and unblocks\n # further allocations from being updated.\n min_healthy_time = \"10s\"\n\n # The \"healthy_deadline\" parameter specifies the deadline in which the\n # allocation must be marked as healthy after which the allocation is\n # automatically transitioned to unhealthy. Transitioning to unhealthy will\n # fail the deployment and potentially roll back the job if \"auto_revert\" is\n # set to true.\n healthy_deadline = \"3m\"\n\n # The \"progress_deadline\" parameter specifies the deadline in which an\n # allocation must be marked as healthy. The deadline begins when the first\n # allocation for the deployment is created and is reset whenever an allocation\n # as part of the deployment transitions to a healthy state. If no allocation\n # transitions to the healthy state before the progress deadline, the\n # deployment is marked as failed.\n progress_deadline = \"10m\"\n\n\n # The \"canary\" parameter specifies that changes to the job that would result\n # in destructive updates should create the specified number of canaries\n # without stopping any previous allocations. Once the operator determines the\n # canaries are healthy, they can be promoted which unblocks a rolling update\n # of the remaining allocations at a rate of \"max_parallel\".\n #\n # Further, setting \"canary\" equal to the count of the task group allows\n # blue/green deployments. When the job is updated, a full set of the new\n # version is deployed and upon promotion the old version is stopped.\n canary = 1\n\n # Specifies if the job should auto-promote to the canary version when all\n # canaries become healthy during a deployment. Defaults to false which means\n # canaries must be manually updated with the nomad deployment promote\n # command.\n auto_promote = true\n\n # The \"auto_revert\" parameter specifies if the job should auto-revert to the\n # last stable job on deployment failure. A job is marked as stable if all the\n # allocations as part of its deployment were marked healthy.\n auto_revert = true\n\n }\n\n # All groups in this job should be scheduled on different hosts.\n constraint {\n operator = \"distinct_hosts\"\n value = \"true\"\n }\n\n # The \"group\" stanza defines a series of tasks that should be co-located on\n # the same Nomad client. Any task within a group will be placed on the same\n # client.\n #\n # For more information and examples on the \"group\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/group.html\n #\n group \"prod-group1-minio\" {\n # The \"count\" parameter specifies the number of the task groups that should\n # be running under this group. This value must be non-negative and defaults\n # to 1.\n count = 4\n\n # https://www.nomadproject.io/docs/job-specification/volume\n \n volume \"prod-volume1-minio\" {\n type = \"host\"\n read_only = false\n source = \"prod-volume-data1-1\"\n }\n \n\n # The \"task\" stanza creates an individual unit of work, such as a Docker\n # container, web application, or batch processing.\n #\n # For more information and examples on the \"task\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/task.html\n #\n task \"prod-task1-minio\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"docker\"\n\n \n volume_mount {\n volume = \"prod-volume1-minio\"\n destination = \"/data/\"\n read_only = false\n }\n \n\n \n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n image = \"minio/minio:RELEASE.2020-12-03T05-49-24Z\"\n dns_servers = [ \"${attr.unique.network.ip-address}\" ]\n network_mode = \"host\"\n command = \"server\"\n args = [ \"http://10.32.8.1{4...7}:9000/data/\" ]\n port_map {\n http = 9000\n }\n privileged = false\n }\n\n # The env stanza configures a list of environment variables to populate\n # the task's environment before starting.\n env {\n\n MINIO_ACCESS_KEY = \"minio\"\n MINIO_SECRET_KEY = \"minio123\"\n\n MINIO_BROWSER=\"off\"\n }\n\n # The service stanza instructs Nomad to register a service with Consul.\n #\n # For more information and examples on the \"task\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/service.html\n #\n service {\n name = \"storage\"\n port = \"http\"\n tags = [ \"storage${NOMAD_ALLOC_INDEX}\" ]\n check {\n name = \"Min.io Server HTTP Check Live\"\n type = \"http\"\n port = \"http\"\n protocol = \"http\"\n method = \"GET\"\n path = \"/minio/health/live\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n check {\n name = \"Min.io Server HTTP Check Ready\"\n type = \"http\"\n port = \"http\"\n protocol = \"http\"\n method = \"GET\"\n path = \"/minio/health/ready\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # For more information and examples on the \"resources\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/resources.html\n #\n resources {\n cpu = 40000\n memory = 40000\n # The network stanza specifies the networking requirements for the task\n # group, including the network mode and port allocations. When scheduling\n # jobs in Nomad they are provisioned across your fleet of machines along\n # with other jobs and services. Because you don't know in advance what host\n # your job will be provisioned on, Nomad will provide your tasks with\n # network configuration when they start up.\n #\n # For more information and examples on the \"template\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/network.html\n #\n network {\n port \"http\" {\n static = 9000\n }\n }\n }\n }\n }\n}\n", + "template": "job \"${job_name}\" {\n # The \"region\" parameter specifies the region in which to execute the job.\n # If omitted, this inherits the default region name of \"global\".\n # region = \"global\"\n #\n # The \"datacenters\" parameter specifies the list of datacenters which should\n # be considered when placing this task. This must be provided.\n datacenters = \"${datacenters}\"\n\n # The \"type\" parameter controls the type of job, which impacts the scheduler's\n # decision on placement. This configuration is optional and defaults to\n # \"service\". For a full list of job types and their differences, please see\n # the online documentation.\n #\n # For more information, please see the online documentation at:\n #\n # https://www.nomadproject.io/docs/jobspec/schedulers.html\n #\n type = \"service\"\n\n update {\n # The \"max_parallel\" parameter specifies the maximum number of updates to\n # perform in parallel. In this case, this specifies to update a single task\n # at a time.\n max_parallel = 1\n\n health_check = \"checks\"\n\n # The \"min_healthy_time\" parameter specifies the minimum time the allocation\n # must be in the healthy state before it is marked as healthy and unblocks\n # further allocations from being updated.\n min_healthy_time = \"10s\"\n\n # The \"healthy_deadline\" parameter specifies the deadline in which the\n # allocation must be marked as healthy after which the allocation is\n # automatically transitioned to unhealthy. Transitioning to unhealthy will\n # fail the deployment and potentially roll back the job if \"auto_revert\" is\n # set to true.\n healthy_deadline = \"3m\"\n\n # The \"progress_deadline\" parameter specifies the deadline in which an\n # allocation must be marked as healthy. The deadline begins when the first\n # allocation for the deployment is created and is reset whenever an allocation\n # as part of the deployment transitions to a healthy state. If no allocation\n # transitions to the healthy state before the progress deadline, the\n # deployment is marked as failed.\n progress_deadline = \"10m\"\n\n%{ if use_canary }\n # The \"canary\" parameter specifies that changes to the job that would result\n # in destructive updates should create the specified number of canaries\n # without stopping any previous allocations. Once the operator determines the\n # canaries are healthy, they can be promoted which unblocks a rolling update\n # of the remaining allocations at a rate of \"max_parallel\".\n #\n # Further, setting \"canary\" equal to the count of the task group allows\n # blue/green deployments. When the job is updated, a full set of the new\n # version is deployed and upon promotion the old version is stopped.\n canary = 1\n\n # Specifies if the job should auto-promote to the canary version when all\n # canaries become healthy during a deployment. Defaults to false which means\n # canaries must be manually updated with the nomad deployment promote\n # command.\n auto_promote = true\n\n # The \"auto_revert\" parameter specifies if the job should auto-revert to the\n # last stable job on deployment failure. A job is marked as stable if all the\n # allocations as part of its deployment were marked healthy.\n auto_revert = true\n%{ endif }\n }\n\n # All groups in this job should be scheduled on different hosts.\n constraint {\n operator = \"distinct_hosts\"\n value = \"true\"\n }\n\n # The \"group\" stanza defines a series of tasks that should be co-located on\n # the same Nomad client. Any task within a group will be placed on the same\n # client.\n #\n # For more information and examples on the \"group\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/group.html\n #\n group \"prod-group1-minio\" {\n # The \"count\" parameter specifies the number of the task groups that should\n # be running under this group. This value must be non-negative and defaults\n # to 1.\n count = ${group_count}\n\n # https://www.nomadproject.io/docs/job-specification/volume\n %{ if use_host_volume }\n volume \"prod-volume1-minio\" {\n type = \"host\"\n read_only = false\n source = \"${host_volume}\"\n }\n %{ endif }\n\n # The \"task\" stanza creates an individual unit of work, such as a Docker\n # container, web application, or batch processing.\n #\n # For more information and examples on the \"task\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/task.html\n #\n task \"prod-task1-minio\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"docker\"\n\n %{ if use_host_volume }\n volume_mount {\n volume = \"prod-volume1-minio\"\n destination = \"${data_dir}\"\n read_only = false\n }\n %{ endif }\n\n %{ if use_vault_provider }\n vault {\n policies = \"${vault_kv_policy_name}\"\n }\n %{ endif }\n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n image = \"${image}\"\n dns_servers = [ \"$${attr.unique.network.ip-address}\" ]\n network_mode = \"host\"\n command = \"server\"\n args = [ \"${host}:${port}${data_dir}\" ]\n port_map {\n http = ${port}\n }\n privileged = false\n }\n\n # The env stanza configures a list of environment variables to populate\n # the task's environment before starting.\n env {\n%{ if use_vault_provider }\n{{ with secret \"${vault_kv_path}\" }}\n MINIO_ACCESS_KEY = \"{{ .Data.data.${vault_kv_field_access_key} }}\"\n MINIO_SECRET_KEY = \"{{ .Data.data.${vault_kv_field_secret_key} }}\"\n{{ end }}\n%{ else }\n MINIO_ACCESS_KEY = \"${access_key}\"\n MINIO_SECRET_KEY = \"${secret_key}\"\n%{ endif }\n ${ envs }\n }\n\n # The service stanza instructs Nomad to register a service with Consul.\n #\n # For more information and examples on the \"task\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/service.html\n #\n service {\n name = \"${service_name}\"\n port = \"http\"\n tags = [ \"storage$${NOMAD_ALLOC_INDEX}\" ]\n check {\n name = \"Min.io Server HTTP Check Live\"\n type = \"http\"\n port = \"http\"\n protocol = \"http\"\n method = \"GET\"\n path = \"/minio/health/live\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n check {\n name = \"Min.io Server HTTP Check Ready\"\n type = \"http\"\n port = \"http\"\n protocol = \"http\"\n method = \"GET\"\n path = \"/minio/health/ready\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # For more information and examples on the \"resources\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/resources.html\n #\n resources {\n cpu = ${cpu}\n memory = ${memory}\n # The network stanza specifies the networking requirements for the task\n # group, including the network mode and port allocations. When scheduling\n # jobs in Nomad they are provisioned across your fleet of machines along\n # with other jobs and services. Because you don't know in advance what host\n # your job will be provisioned on, Nomad will provide your tasks with\n # network configuration when they start up.\n #\n # For more information and examples on the \"template\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/network.html\n #\n network {\n port \"http\" {\n static = ${port}\n }\n }\n }\n }\n }\n}\n", "vars": { "access_key": "minio", - "cpu": "200", + "cpu": "40000", "cpu_proxy": "200", "data_dir": "/data/", "datacenters": "yul1", @@ -63,7 +394,7 @@ "host_volume": "prod-volume-data1-1", "image": "minio/minio:RELEASE.2020-12-03T05-49-24Z", "job_name": "prod-minio", - "memory": "1024", + "memory": "40000", "memory_proxy": "128", "port": "9000", "secret_key": "minio123", @@ -82,6 +413,64 @@ "module": "module.minio", "mode": "managed", "type": "nomad_job", + "name": "nomad_job_mc", + "provider": "provider[\"registry.terraform.io/hashicorp/nomad\"].yul1", + "instances": [ + { + "schema_version": 0, + "attributes": { + "allocation_ids": [ + "5b129de9-a002-a1e5-7676-1f6623a6f4bd" + ], + "datacenters": [ + "yul1" + ], + "deployment_id": "", + "deployment_status": "", + "deregister_on_destroy": true, + "deregister_on_id_change": true, + "detach": false, + "id": "prod-mc", + "jobspec": "job \"prod-mc\" {\n # The \"region\" parameter specifies the region in which to execute the job.\n # If omitted, this inherits the default region name of \"global\".\n # region = \"global\"\n #\n # The \"datacenters\" parameter specifies the list of datacenters which should\n # be considered when placing this task. This must be provided.\n datacenters = \"yul1\"\n\n # The \"type\" parameter controls the type of job, which impacts the scheduler's\n # decision on placement. This configuration is optional and defaults to\n # \"service\". For a full list of job types and their differences, please see\n # the online documentation.\n #\n # For more information, please see the online documentation at:\n #\n # https://www.nomadproject.io/docs/jobspec/schedulers.html\n #\n type = \"batch\"\n\n # The \"group\" stanza defines a series of tasks that should be co-located on\n # the same Nomad client. Any task within a group will be placed on the same\n # client.\n #\n # For more information and examples on the \"group\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/group.html\n #\n group \"prod-group1-mc\" {\n task \"prod-task1-create-buckets\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"docker\"\n\n \n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n image = \"minio/mc:RELEASE.2020-12-10T01-26-17Z\"\n entrypoint = [\n \"/bin/sh\",\n \"-c\",\n \"mc config host add LOCALMINIO http://storage.service.consul:9000 $MINIO_ACCESS_KEY $MINIO_SECRET_KEY \u0026\u0026 mc mb -p LOCALMINIO/logs.fd.io LOCALMINIO/docs.fd.io ; mc policy set public LOCALMINIO/logs.fd.io mc policy set public LOCALMINIO/docs.fd.io mc ilm add --expiry-days '180' LOCALMINIO/logs.fd.io mc admin user add LOCALMINIO storage Storage1234 mc admin policy set LOCALMINIO writeonly user=storage\"\n ]\n dns_servers = [ \"${attr.unique.network.ip-address}\" ]\n privileged = false\n }\n\n # The env stanza configures a list of environment variables to populate\n # the task's environment before starting.\n env {\n \n MINIO_ACCESS_KEY = \"minio\"\n MINIO_SECRET_KEY = \"minio123\"\n \n \n }\n }\n }\n}\n", + "json": null, + "modify_index": "7147950", + "name": "prod-mc", + "namespace": "default", + "policy_override": null, + "purge_on_destroy": null, + "region": "global", + "task_groups": [ + { + "count": 1, + "meta": {}, + "name": "prod-group1-mc", + "task": [ + { + "driver": "docker", + "meta": {}, + "name": "prod-task1-create-buckets", + "volume_mounts": null + } + ], + "volumes": null + } + ], + "type": "batch" + }, + "sensitive_attributes": [], + "private": "bnVsbA==", + "dependencies": [ + "module.minio.data.template_file.nomad_job_mc", + "module.minio.data.template_file.nomad_job_minio", + "module.minio.nomad_job.nomad_job_minio" + ] + } + ] + }, + { + "module": "module.minio", + "mode": "managed", + "type": "nomad_job", "name": "nomad_job_minio", "provider": "provider[\"registry.terraform.io/hashicorp/nomad\"].yul1", "instances": [ @@ -89,23 +478,23 @@ "schema_version": 0, "attributes": { "allocation_ids": [ - "50aa74ba-c8fa-3523-aa88-ba7c7404b96b", - "fd433635-9fdf-61aa-6069-2fb2f80709d8", - "62d6aaf9-d9a7-395b-c8a3-c7998882b2d7", - "c9db0a63-c624-07a7-d9ed-1972a61d865d" + "322e6ea5-acc7-2f37-3022-cd0a31c2f3db", + "619833b9-dd70-46ae-f576-75c3cd058a13", + "0510561a-c828-dd23-5910-b92d9f2c41ef", + "504924c8-387b-abe2-c4d5-d6a7424a4689" ], "datacenters": [ "yul1" ], - "deployment_id": "d5b25946-c510-1017-3a50-f83c3616f718", + "deployment_id": "cd6d79cf-6e6f-289d-a0bb-6b2bb8da769a", "deployment_status": "successful", "deregister_on_destroy": true, "deregister_on_id_change": true, "detach": false, "id": "prod-minio", - "jobspec": "job \"prod-minio\" {\n # The \"region\" parameter specifies the region in which to execute the job.\n # If omitted, this inherits the default region name of \"global\".\n # region = \"global\"\n #\n # The \"datacenters\" parameter specifies the list of datacenters which should\n # be considered when placing this task. This must be provided.\n datacenters = \"yul1\"\n\n # The \"type\" parameter controls the type of job, which impacts the scheduler's\n # decision on placement. This configuration is optional and defaults to\n # \"service\". For a full list of job types and their differences, please see\n # the online documentation.\n #\n # For more information, please see the online documentation at:\n #\n # https://www.nomadproject.io/docs/jobspec/schedulers.html\n #\n type = \"service\"\n\n update {\n # The \"max_parallel\" parameter specifies the maximum number of updates to\n # perform in parallel. In this case, this specifies to update a single task\n # at a time.\n max_parallel = 1\n\n health_check = \"checks\"\n\n # The \"min_healthy_time\" parameter specifies the minimum time the allocation\n # must be in the healthy state before it is marked as healthy and unblocks\n # further allocations from being updated.\n min_healthy_time = \"10s\"\n\n # The \"healthy_deadline\" parameter specifies the deadline in which the\n # allocation must be marked as healthy after which the allocation is\n # automatically transitioned to unhealthy. Transitioning to unhealthy will\n # fail the deployment and potentially roll back the job if \"auto_revert\" is\n # set to true.\n healthy_deadline = \"3m\"\n\n # The \"progress_deadline\" parameter specifies the deadline in which an\n # allocation must be marked as healthy. The deadline begins when the first\n # allocation for the deployment is created and is reset whenever an allocation\n # as part of the deployment transitions to a healthy state. If no allocation\n # transitions to the healthy state before the progress deadline, the\n # deployment is marked as failed.\n progress_deadline = \"10m\"\n\n\n # The \"canary\" parameter specifies that changes to the job that would result\n # in destructive updates should create the specified number of canaries\n # without stopping any previous allocations. Once the operator determines the\n # canaries are healthy, they can be promoted which unblocks a rolling update\n # of the remaining allocations at a rate of \"max_parallel\".\n #\n # Further, setting \"canary\" equal to the count of the task group allows\n # blue/green deployments. When the job is updated, a full set of the new\n # version is deployed and upon promotion the old version is stopped.\n canary = 1\n\n # Specifies if the job should auto-promote to the canary version when all\n # canaries become healthy during a deployment. Defaults to false which means\n # canaries must be manually updated with the nomad deployment promote\n # command.\n auto_promote = true\n\n # The \"auto_revert\" parameter specifies if the job should auto-revert to the\n # last stable job on deployment failure. A job is marked as stable if all the\n # allocations as part of its deployment were marked healthy.\n auto_revert = true\n\n }\n\n # All groups in this job should be scheduled on different hosts.\n constraint {\n operator = \"distinct_hosts\"\n value = \"true\"\n }\n\n # The \"group\" stanza defines a series of tasks that should be co-located on\n # the same Nomad client. Any task within a group will be placed on the same\n # client.\n #\n # For more information and examples on the \"group\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/group.html\n #\n group \"prod-group1-minio\" {\n # The \"count\" parameter specifies the number of the task groups that should\n # be running under this group. This value must be non-negative and defaults\n # to 1.\n count = 4\n\n # https://www.nomadproject.io/docs/job-specification/volume\n \n volume \"prod-volume1-minio\" {\n type = \"host\"\n read_only = false\n source = \"prod-volume-data1-1\"\n }\n \n\n # The \"task\" stanza creates an individual unit of work, such as a Docker\n # container, web application, or batch processing.\n #\n # For more information and examples on the \"task\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/task.html\n #\n task \"prod-task1-minio\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"docker\"\n\n \n volume_mount {\n volume = \"prod-volume1-minio\"\n destination = \"/data/\"\n read_only = false\n }\n \n\n \n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n image = \"minio/minio:RELEASE.2020-12-03T05-49-24Z\"\n dns_servers = [ \"${attr.unique.network.ip-address}\" ]\n network_mode = \"host\"\n command = \"server\"\n args = [ \"http://10.32.8.1{4...7}:9000/data/\" ]\n port_map {\n http = 9000\n }\n privileged = false\n }\n\n # The env stanza configures a list of environment variables to populate\n # the task's environment before starting.\n env {\n\n MINIO_ACCESS_KEY = \"minio\"\n MINIO_SECRET_KEY = \"minio123\"\n\n MINIO_BROWSER=\"off\"\n }\n\n # The service stanza instructs Nomad to register a service with Consul.\n #\n # For more information and examples on the \"task\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/service.html\n #\n service {\n name = \"storage\"\n port = \"http\"\n tags = [ \"storage${NOMAD_ALLOC_INDEX}\" ]\n check {\n name = \"Min.io Server HTTP Check Live\"\n type = \"http\"\n port = \"http\"\n protocol = \"http\"\n method = \"GET\"\n path = \"/minio/health/live\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n check {\n name = \"Min.io Server HTTP Check Ready\"\n type = \"http\"\n port = \"http\"\n protocol = \"http\"\n method = \"GET\"\n path = \"/minio/health/ready\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # For more information and examples on the \"resources\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/resources.html\n #\n resources {\n # The network stanza specifies the networking requirements for the task\n # group, including the network mode and port allocations. When scheduling\n # jobs in Nomad they are provisioned across your fleet of machines along\n # with other jobs and services. Because you don't know in advance what host\n # your job will be provisioned on, Nomad will provide your tasks with\n # network configuration when they start up.\n #\n # For more information and examples on the \"template\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/network.html\n #\n network {\n port \"http\" {\n static = 9000\n }\n }\n }\n }\n }\n}\n", + "jobspec": "job \"prod-minio\" {\n # The \"region\" parameter specifies the region in which to execute the job.\n # If omitted, this inherits the default region name of \"global\".\n # region = \"global\"\n #\n # The \"datacenters\" parameter specifies the list of datacenters which should\n # be considered when placing this task. This must be provided.\n datacenters = \"yul1\"\n\n # The \"type\" parameter controls the type of job, which impacts the scheduler's\n # decision on placement. This configuration is optional and defaults to\n # \"service\". For a full list of job types and their differences, please see\n # the online documentation.\n #\n # For more information, please see the online documentation at:\n #\n # https://www.nomadproject.io/docs/jobspec/schedulers.html\n #\n type = \"service\"\n\n update {\n # The \"max_parallel\" parameter specifies the maximum number of updates to\n # perform in parallel. In this case, this specifies to update a single task\n # at a time.\n max_parallel = 1\n\n health_check = \"checks\"\n\n # The \"min_healthy_time\" parameter specifies the minimum time the allocation\n # must be in the healthy state before it is marked as healthy and unblocks\n # further allocations from being updated.\n min_healthy_time = \"10s\"\n\n # The \"healthy_deadline\" parameter specifies the deadline in which the\n # allocation must be marked as healthy after which the allocation is\n # automatically transitioned to unhealthy. Transitioning to unhealthy will\n # fail the deployment and potentially roll back the job if \"auto_revert\" is\n # set to true.\n healthy_deadline = \"3m\"\n\n # The \"progress_deadline\" parameter specifies the deadline in which an\n # allocation must be marked as healthy. The deadline begins when the first\n # allocation for the deployment is created and is reset whenever an allocation\n # as part of the deployment transitions to a healthy state. If no allocation\n # transitions to the healthy state before the progress deadline, the\n # deployment is marked as failed.\n progress_deadline = \"10m\"\n\n\n # The \"canary\" parameter specifies that changes to the job that would result\n # in destructive updates should create the specified number of canaries\n # without stopping any previous allocations. Once the operator determines the\n # canaries are healthy, they can be promoted which unblocks a rolling update\n # of the remaining allocations at a rate of \"max_parallel\".\n #\n # Further, setting \"canary\" equal to the count of the task group allows\n # blue/green deployments. When the job is updated, a full set of the new\n # version is deployed and upon promotion the old version is stopped.\n canary = 1\n\n # Specifies if the job should auto-promote to the canary version when all\n # canaries become healthy during a deployment. Defaults to false which means\n # canaries must be manually updated with the nomad deployment promote\n # command.\n auto_promote = true\n\n # The \"auto_revert\" parameter specifies if the job should auto-revert to the\n # last stable job on deployment failure. A job is marked as stable if all the\n # allocations as part of its deployment were marked healthy.\n auto_revert = true\n\n }\n\n # All groups in this job should be scheduled on different hosts.\n constraint {\n operator = \"distinct_hosts\"\n value = \"true\"\n }\n\n # The \"group\" stanza defines a series of tasks that should be co-located on\n # the same Nomad client. Any task within a group will be placed on the same\n # client.\n #\n # For more information and examples on the \"group\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/group.html\n #\n group \"prod-group1-minio\" {\n # The \"count\" parameter specifies the number of the task groups that should\n # be running under this group. This value must be non-negative and defaults\n # to 1.\n count = 4\n\n # https://www.nomadproject.io/docs/job-specification/volume\n \n volume \"prod-volume1-minio\" {\n type = \"host\"\n read_only = false\n source = \"prod-volume-data1-1\"\n }\n \n\n # The \"task\" stanza creates an individual unit of work, such as a Docker\n # container, web application, or batch processing.\n #\n # For more information and examples on the \"task\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/task.html\n #\n task \"prod-task1-minio\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"docker\"\n\n \n volume_mount {\n volume = \"prod-volume1-minio\"\n destination = \"/data/\"\n read_only = false\n }\n \n\n \n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n image = \"minio/minio:RELEASE.2020-12-03T05-49-24Z\"\n dns_servers = [ \"${attr.unique.network.ip-address}\" ]\n network_mode = \"host\"\n command = \"server\"\n args = [ \"http://10.32.8.1{4...7}:9000/data/\" ]\n port_map {\n http = 9000\n }\n privileged = false\n }\n\n # The env stanza configures a list of environment variables to populate\n # the task's environment before starting.\n env {\n\n MINIO_ACCESS_KEY = \"minio\"\n MINIO_SECRET_KEY = \"minio123\"\n\n MINIO_BROWSER=\"off\"\n }\n\n # The service stanza instructs Nomad to register a service with Consul.\n #\n # For more information and examples on the \"task\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/service.html\n #\n service {\n name = \"storage\"\n port = \"http\"\n tags = [ \"storage${NOMAD_ALLOC_INDEX}\" ]\n check {\n name = \"Min.io Server HTTP Check Live\"\n type = \"http\"\n port = \"http\"\n protocol = \"http\"\n method = \"GET\"\n path = \"/minio/health/live\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n check {\n name = \"Min.io Server HTTP Check Ready\"\n type = \"http\"\n port = \"http\"\n protocol = \"http\"\n method = \"GET\"\n path = \"/minio/health/ready\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # For more information and examples on the \"resources\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/resources.html\n #\n resources {\n # The network stanza specifies the networking requirements for the task\n # group, including the network mode and port allocations. When scheduling\n # jobs in Nomad they are provisioned across your fleet of machines along\n # with other jobs and services. Because you don't know in advance what host\n # your job will be provisioned on, Nomad will provide your tasks with\n # network configuration when they start up.\n #\n # For more information and examples on the \"template\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/network.html\n #\n cpu = 40000\n memory = 40000\n network {\n port \"http\" {\n static = 9000\n }\n }\n }\n }\n }\n}\n", "json": null, - "modify_index": "5922473", + "modify_index": "5933603", "name": "prod-minio", "namespace": "default", "policy_override": null, @@ -184,7 +573,7 @@ "schema_version": 0, "attributes": { "allocation_ids": [ - "de9af589-8f0b-6634-7199-c661f8f17df0" + "1dea6de0-d5cd-2a1b-fb42-0468e986e0d6" ], "datacenters": [ "yul1" @@ -228,6 +617,212 @@ ] } ] + }, + { + "module": "module.prometheus", + "mode": "data", + "type": "template_file", + "name": "nomad_job_prometheus", + "provider": "provider[\"registry.terraform.io/hashicorp/template\"]", + "instances": [ + { + "schema_version": 0, + "attributes": { + "filename": null, + "id": "cd26d062785357d96c95d6f8f40b2d8d7b430be3399de176e6b250822c4af86c", + "rendered": "job \"prod-prometheus\" {\n # The \"region\" parameter specifies the region in which to execute the job.\n # If omitted, this inherits the default region name of \"global\".\n # region = \"global\"\n #\n # The \"datacenters\" parameter specifies the list of datacenters which should\n # be considered when placing this task. This must be provided.\n datacenters = \"yul1\"\n\n # The \"type\" parameter controls the type of job, which impacts the scheduler's\n # decision on placement. This configuration is optional and defaults to\n # \"service\". For a full list of job types and their differences, please see\n # the online documentation.\n #\n # For more information, please see the online documentation at:\n #\n # https://www.nomadproject.io/docs/jobspec/schedulers\n #\n type = \"service\"\n\n update {\n # The \"max_parallel\" parameter specifies the maximum number of updates to\n # perform in parallel. In this case, this specifies to update a single task\n # at a time.\n max_parallel = 1\n\n health_check = \"checks\"\n\n # The \"min_healthy_time\" parameter specifies the minimum time the allocation\n # must be in the healthy state before it is marked as healthy and unblocks\n # further allocations from being updated.\n min_healthy_time = \"10s\"\n\n # The \"healthy_deadline\" parameter specifies the deadline in which the\n # allocation must be marked as healthy after which the allocation is\n # automatically transitioned to unhealthy. Transitioning to unhealthy will\n # fail the deployment and potentially roll back the job if \"auto_revert\" is\n # set to true.\n healthy_deadline = \"3m\"\n\n # The \"progress_deadline\" parameter specifies the deadline in which an\n # allocation must be marked as healthy. The deadline begins when the first\n # allocation for the deployment is created and is reset whenever an allocation\n # as part of the deployment transitions to a healthy state. If no allocation\n # transitions to the healthy state before the progress deadline, the\n # deployment is marked as failed.\n progress_deadline = \"10m\"\n\n\n # The \"canary\" parameter specifies that changes to the job that would result\n # in destructive updates should create the specified number of canaries\n # without stopping any previous allocations. Once the operator determines the\n # canaries are healthy, they can be promoted which unblocks a rolling update\n # of the remaining allocations at a rate of \"max_parallel\".\n #\n # Further, setting \"canary\" equal to the count of the task group allows\n # blue/green deployments. When the job is updated, a full set of the new\n # version is deployed and upon promotion the old version is stopped.\n canary = 1\n\n # Specifies if the job should auto-promote to the canary version when all\n # canaries become healthy during a deployment. Defaults to false which means\n # canaries must be manually updated with the nomad deployment promote\n # command.\n auto_promote = true\n\n # The \"auto_revert\" parameter specifies if the job should auto-revert to the\n # last stable job on deployment failure. A job is marked as stable if all the\n # allocations as part of its deployment were marked healthy.\n auto_revert = true\n\n }\n\n # The \"group\" stanza defines a series of tasks that should be co-located on\n # the same Nomad client. Any task within a group will be placed on the same\n # client.\n #\n # For more information and examples on the \"group\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/group\n #\n group \"prod-group1-prometheus\" {\n # The \"count\" parameter specifies the number of the task groups that should\n # be running under this group. This value must be non-negative and defaults\n # to 1.\n count = 4\n\n # The volume stanza allows the group to specify that it requires a given\n # volume from the cluster.\n #\n # For more information and examples on the \"volume\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/volume\n #\n \n volume \"prod-volume1-prometheus\" {\n type = \"host\"\n read_only = false\n source = \"prod-volume-data1-1\"\n }\n \n\n # The constraint allows restricting the set of eligible nodes. Constraints\n # may filter on attributes or client metadata.\n #\n # For more information and examples on the \"volume\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/constraint\n #\n constraint {\n attribute = \"${attr.cpu.arch}\"\n operator = \"!=\"\n value = \"arm64\"\n }\n\n # The \"task\" stanza creates an individual unit of work, such as a Docker\n # container, web application, or batch processing.\n #\n # For more information and examples on the \"task\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/task\n #\n task \"prod-task1-prometheus\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"exec\"\n\n \n volume_mount {\n volume = \"prod-volume1-prometheus\"\n destination = \"/data/\"\n read_only = false\n }\n \n\n \n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n command = \"local/prometheus-2.24.0.linux-amd64/prometheus\"\n args = [\n \"--config.file=secrets/prometheus.yml\",\n \"--storage.tsdb.path=/data/prometheus/\",\n \"--storage.tsdb.retention.time=15d\"\n ]\n }\n\n # The artifact stanza instructs Nomad to fetch and unpack a remote resource,\n # such as a file, tarball, or binary. Nomad downloads artifacts using the\n # popular go-getter library, which permits downloading artifacts from a\n # variety of locations using a URL as the input source.\n #\n # For more information and examples on the \"artifact\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/artifact\n #\n artifact {\n source = \"https://github.com/prometheus/prometheus/releases/download/v2.24.0/prometheus-2.24.0.linux-amd64.tar.gz\"\n }\n\n # The \"template\" stanza instructs Nomad to manage a template, such as\n # a configuration file or script. This template can optionally pull data\n # from Consul or Vault to populate runtime configuration data.\n #\n # For more information and examples on the \"template\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/template\n #\n template {\n change_mode = \"noop\"\n change_signal = \"SIGINT\"\n destination = \"secrets/alerts.yml\"\n left_delimiter = \"{{{\"\n right_delimiter = \"}}}\"\n data = \u003c\u003cEOH\n---\ngroups:\n- name: \"Consul\"\n rules:\n - alert: ConsulServiceHealthcheckFailed\n expr: consul_catalog_service_node_healthy == 0\n for: 0m\n labels:\n severity: critical\n annotations:\n summary: \"Consul service healthcheck failed (instance {{ $labels.instance }}).\"\n description: \"Service: `{{ $labels.service_name }}` Healthcheck: `{{ $labels.service_id }}`.\"\n - alert: ConsulMissingMasterNode\n expr: consul_raft_peers \u003c 3\n for: 0m\n labels:\n severity: critical\n annotations:\n summary: \"Consul missing master node (instance {{ $labels.instance }}).\"\n description: \"Numbers of consul raft peers should be 3, in order to preserve quorum.\"\n - alert: ConsulAgentUnhealthy\n expr: consul_health_node_status{status=\"critical\"} == 1\n for: 0m\n labels:\n severity: critical\n annotations:\n summary: \"Consul agent unhealthy (instance {{ $labels.instance }}).\"\n description: \"A Consul agent is down.\"\n- name: \"Hosts\"\n rules:\n - alert: NodeDown\n expr: up == 0\n for: 0m\n labels:\n severity: critical\n annotations:\n summary: \"Prometheus target missing (instance {{ $labels.instance }}).\"\n description: \"A Prometheus target has disappeared. An exporter might be crashed.\"\n - alert: HostHighCpuLoad\n expr: 100 - (avg by(instance) (rate(node_cpu_seconds_total{mode=\"idle\"}[2m])) * 100) \u003e 80\n for: 0m\n labels:\n severity: warning\n annotations:\n summary: \"Host high CPU load (instance {{ $labels.instance }}).\"\n description: \"CPU load is \u003e 80%.\"\n - alert: HostOutOfMemory\n expr: node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes * 100 \u003c 10\n for: 2m\n labels:\n severity: warning\n annotations:\n summary: \"Host out of memory (instance {{ $labels.instance }}).\"\n description: \"Node memory is filling up (\u003c 10% left).\"\n - alert: HostOomKillDetected\n expr: increase(node_vmstat_oom_kill[1m]) \u003e 0\n for: 0m\n labels:\n severity: warning\n annotations:\n summary: \"Host OOM kill detected (instance {{ $labels.instance }}).\"\n description: \"OOM kill detected.\"\n - alert: HostMemoryUnderMemoryPressure\n expr: rate(node_vmstat_pgmajfault[1m]) \u003e 1000\n for: 2m\n labels:\n severity: warning\n annotations:\n summary: \"Host memory under memory pressure (instance {{ $labels.instance }}).\"\n description: \"The node is under heavy memory pressure. High rate of major page faults.\"\n - alert: HostOutOfDiskSpace\n expr: (node_filesystem_avail_bytes * 100) / node_filesystem_size_bytes \u003c 10 and ON (instance, device, mountpoint) node_filesystem_readonly == 0\n for: 2m\n labels:\n severity: warning\n annotations:\n summary: \"Host out of disk space (instance {{ $labels.instance }}).\"\n description: \"Disk is almost full (\u003c 10% left).\"\n - alert: HostRaidDiskFailure\n expr: node_md_disks{state=\"failed\"} \u003e 0\n for: 2m\n labels:\n severity: warning\n annotations:\n summary: \"Host RAID disk failure (instance {{ $labels.instance }}).\"\n description: \"At least one device in RAID array on {{ $labels.instance }} failed. Array {{ $labels.md_device }} needs attention and possibly a disk swap.\"\n - alert: HostConntrackLimit\n expr: node_nf_conntrack_entries / node_nf_conntrack_entries_limit \u003e 0.8\n for: 5m\n labels:\n severity: warning\n annotations:\n summary: \"Host conntrack limit (instance {{ $labels.instance }}).\"\n description: \"The number of conntrack is approching limit.\"\n - alert: HostNetworkInterfaceSaturated\n expr: (rate(node_network_receive_bytes_total{device!~\"^tap.*\"}[1m]) + rate(node_network_transmit_bytes_total{device!~\"^tap.*\"}[1m])) / node_network_speed_bytes{device!~\"^tap.*\"} \u003e 0.8\n for: 1m\n labels:\n severity: warning\n annotations:\n summary: \"Host Network Interface Saturated (instance {{ $labels.instance }}).\"\n description: \"The network interface {{ $labels.interface }} on {{ $labels.instance }} is getting overloaded.\"\n - alert: HostSystemdServiceCrashed\n expr: node_systemd_unit_state{state=\"failed\"} == 1\n for: 0m\n labels:\n severity: warning\n annotations:\n summary: \"Host SystemD service crashed (instance {{ $labels.instance }}).\"\n description: \"SystemD service crashed.\"\n - alert: HostEdacCorrectableErrorsDetected\n expr: increase(node_edac_correctable_errors_total[1m]) \u003e 0\n for: 0m\n labels:\n severity: info\n annotations:\n summary: \"Host EDAC Correctable Errors detected (instance {{ $labels.instance }}).\"\n description: '{{ $labels.instance }} has had {{ printf \"%.0f\" $value }} correctable memory errors reported by EDAC in the last 5 minutes.'\n - alert: HostEdacUncorrectableErrorsDetected\n expr: node_edac_uncorrectable_errors_total \u003e 0\n for: 0m\n labels:\n severity: warning\n annotations:\n summary: \"Host EDAC Uncorrectable Errors detected (instance {{ $labels.instance }}).\"\n description: '{{ $labels.instance }} has had {{ printf \"%.0f\" $value }} uncorrectable memory errors reported by EDAC in the last 5 minutes.'\n- name: \"Min.io\"\n rules:\n - alert: MinioDiskOffline\n expr: minio_offline_disks \u003e 0\n for: 0m\n labels:\n severity: critical\n annotations:\n summary: \"Minio disk offline (instance {{ $labels.instance }})\"\n description: \"Minio disk is offline.\"\n - alert: MinioStorageSpaceExhausted\n expr: minio_disk_storage_free_bytes / 1024 / 1024 / 1024 \u003c 10\n for: 2m\n labels:\n severity: warning\n annotations:\n summary: \"Minio storage space exhausted (instance {{ $labels.instance }}).\"\n description: \"Minio storage space is low (\u003c 10 GB).\"\n- name: \"Prometheus\"\n rules:\n - alert: PrometheusConfigurationReloadFailure\n expr: prometheus_config_last_reload_successful != 1\n for: 0m\n labels:\n severity: warning\n annotations:\n summary: \"Prometheus configuration reload failure (instance {{ $labels.instance }}).\"\n description: \"Prometheus configuration reload error.\"\n - alert: PrometheusTooManyRestarts\n expr: changes(process_start_time_seconds{job=~\"prometheus|pushgateway|alertmanager\"}[15m]) \u003e 2\n for: 0m\n labels:\n severity: warning\n annotations:\n summary: \"Prometheus too many restarts (instance {{ $labels.instance }}).\"\n description: \"Prometheus has restarted more than twice in the last 15 minutes. It might be crashlooping.\"\n - alert: PrometheusAlertmanagerConfigurationReloadFailure\n expr: alertmanager_config_last_reload_successful != 1\n for: 0m\n labels:\n severity: warning\n annotations:\n summary: \"Prometheus AlertManager configuration reload failure (instance {{ $labels.instance }}).\"\n description: \"AlertManager configuration reload error.\"\n - alert: PrometheusRuleEvaluationFailures\n expr: increase(prometheus_rule_evaluation_failures_total[3m]) \u003e 0\n for: 0m\n labels:\n severity: critical\n annotations:\n summary: \"Prometheus rule evaluation failures (instance {{ $labels.instance }}).\"\n description: \"Prometheus encountered {{ $value }} rule evaluation failures, leading to potentially ignored alerts.\"\n - alert: PrometheusTargetScrapingSlow\n expr: prometheus_target_interval_length_seconds{quantile=\"0.9\"} \u003e 60\n for: 5m\n labels:\n severity: warning\n annotations:\n summary: \"Prometheus target scraping slow (instance {{ $labels.instance }}).\"\n description: \"Prometheus is scraping exporters slowly.\"\n - alert: PrometheusTsdbCompactionsFailed\n expr: increase(prometheus_tsdb_compactions_failed_total[1m]) \u003e 0\n for: 0m\n labels:\n severity: critical\n annotations:\n summary: \"Prometheus TSDB compactions failed (instance {{ $labels.instance }}).\"\n description: \"Prometheus encountered {{ $value }} TSDB compactions failures.\"\n - alert: PrometheusTsdbHeadTruncationsFailed\n expr: increase(prometheus_tsdb_head_truncations_failed_total[1m]) \u003e 0\n for: 0m\n labels:\n severity: critical\n annotations:\n summary: \"Prometheus TSDB head truncations failed (instance {{ $labels.instance }}).\"\n description: \"Prometheus encountered {{ $value }} TSDB head truncation failures.\"\n - alert: PrometheusTsdbWalCorruptions\n expr: increase(prometheus_tsdb_wal_corruptions_total[1m]) \u003e 0\n for: 0m\n labels:\n severity: critical\n annotations:\n summary: \"Prometheus TSDB WAL corruptions (instance {{ $labels.instance }}).\"\n description: \"Prometheus encountered {{ $value }} TSDB WAL corruptions.\"\n - alert: PrometheusTsdbWalTruncationsFailed\n expr: increase(prometheus_tsdb_wal_truncations_failed_total[1m]) \u003e 0\n for: 0m\n labels:\n severity: critical\n annotations:\n summary: \"Prometheus TSDB WAL truncations failed (instance {{ $labels.instance }}).\"\n description: \"Prometheus encountered {{ $value }} TSDB WAL truncation failures.\"\nEOH\n }\n\n template {\n change_mode = \"noop\"\n change_signal = \"SIGINT\"\n destination = \"secrets/prometheus.yml\"\n data = \u003c\u003cEOH\n---\nglobal:\n scrape_interval: 5s\n scrape_timeout: 5s\n evaluation_interval: 5s\n\nalerting:\n alertmanagers:\n - consul_sd_configs:\n - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n services: [ 'alertmanager' ]\n\nrule_files:\n - 'alerts.yml'\n\nscrape_configs:\n\n - job_name: 'Nomad Cluster'\n consul_sd_configs:\n - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n services: [ 'nomad-client', 'nomad' ]\n relabel_configs:\n - source_labels: [__meta_consul_tags]\n regex: '(.*)http(.*)'\n action: keep\n metrics_path: /v1/metrics\n params:\n format: [ 'prometheus' ]\n\n - job_name: 'Consul Cluster'\n static_configs:\n - targets: [ '10.30.51.30:8500', '10.30.51.32:8500', '10.30.51.33:8500' ]\n metrics_path: /v1/agent/metrics\n params:\n format: [ 'prometheus' ]\n\n - job_name: 'Alertmanager'\n consul_sd_configs:\n - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n services: [ 'alertmanager' ]\n\n - job_name: 'Blackbox Exporter (icmp)'\n static_configs:\n - targets: [ 'gerrit.fd.io' ]\n - targets: [ 'jenkins.fd.io' ]\n - targets: [ '10.30.51.32' ]\n params:\n module: [ 'icmp_v4' ]\n relabel_configs:\n - source_labels: [__address__]\n target_label: __param_target\n - source_labels: [__param_target]\n target_label: instance\n - target_label: __address__\n replacement: localhost:9115\n metrics_path: /probe\n\n - job_name: 'Blackbox Exporter (http)'\n static_configs:\n - targets: [ 'gerrit.fd.io' ]\n - targets: [ 'jenkins.fd.io' ]\n params:\n module: [ 'http_2xx' ]\n relabel_configs:\n - source_labels: [__address__]\n target_label: __param_target\n - source_labels: [__param_target]\n target_label: instance\n - target_label: __address__\n replacement: localhost:9115\n metrics_path: /probe\n\n - job_name: 'cAdvisor Exporter'\n consul_sd_configs:\n - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n services: [ 'cadvisorexporter' ]\n\n - job_name: 'Grafana'\n consul_sd_configs:\n - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n services: [ 'grafana' ]\n\n - job_name: 'Node Exporter'\n consul_sd_configs:\n - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n services: [ 'nodeexporter' ]\n\n - job_name: 'Prometheus'\n consul_sd_configs:\n - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n services: [ 'prometheus' ]\n\n - job_name: 'Minio'\n bearer_token: eyJhbGciOiJIUzUxMiIsInR5cCI6IkpXVCJ9.eyJleHAiOjQ3NjQ1ODEzMzcsImlzcyI6InByb21ldGhldXMiLCJzdWIiOiJtaW5pbyJ9.oeTw3EIaiFmlDikrHXWiWXMH2vxLfDLkfjEC7G2N3M_keH_xyA_l2ofLLNYtopa_3GCEZnxLQdPuFZrmgpkDWg\n consul_sd_configs:\n - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n services: [ 'storage' ]\n metrics_path: /minio/prometheus/metrics\nEOH\n }\n\n # The service stanza instructs Nomad to register a service with Consul.\n #\n # For more information and examples on the \"task\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/service\n #\n service {\n name = \"prometheus\"\n port = \"prometheus\"\n tags = [ \"prometheus${NOMAD_ALLOC_INDEX}\" ]\n check {\n name = \"Prometheus Check Live\"\n type = \"http\"\n path = \"/-/healthy\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # For more information and examples on the \"resources\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/resources\n #\n resources {\n cpu = 2000\n memory = 8192\n # The network stanza specifies the networking requirements for the task\n # group, including the network mode and port allocations. When scheduling\n # jobs in Nomad they are provisioned across your fleet of machines along\n # with other jobs and services. Because you don't know in advance what host\n # your job will be provisioned on, Nomad will provide your tasks with\n # network configuration when they start up.\n #\n # For more information and examples on the \"template\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/network\n #\n network {\n port \"prometheus\" {\n static = 9090\n }\n }\n }\n }\n }\n}", + "template": "job \"${job_name}\" {\n # The \"region\" parameter specifies the region in which to execute the job.\n # If omitted, this inherits the default region name of \"global\".\n # region = \"global\"\n #\n # The \"datacenters\" parameter specifies the list of datacenters which should\n # be considered when placing this task. This must be provided.\n datacenters = \"${datacenters}\"\n\n # The \"type\" parameter controls the type of job, which impacts the scheduler's\n # decision on placement. This configuration is optional and defaults to\n # \"service\". For a full list of job types and their differences, please see\n # the online documentation.\n #\n # For more information, please see the online documentation at:\n #\n # https://www.nomadproject.io/docs/jobspec/schedulers\n #\n type = \"service\"\n\n update {\n # The \"max_parallel\" parameter specifies the maximum number of updates to\n # perform in parallel. In this case, this specifies to update a single task\n # at a time.\n max_parallel = 1\n\n health_check = \"checks\"\n\n # The \"min_healthy_time\" parameter specifies the minimum time the allocation\n # must be in the healthy state before it is marked as healthy and unblocks\n # further allocations from being updated.\n min_healthy_time = \"10s\"\n\n # The \"healthy_deadline\" parameter specifies the deadline in which the\n # allocation must be marked as healthy after which the allocation is\n # automatically transitioned to unhealthy. Transitioning to unhealthy will\n # fail the deployment and potentially roll back the job if \"auto_revert\" is\n # set to true.\n healthy_deadline = \"3m\"\n\n # The \"progress_deadline\" parameter specifies the deadline in which an\n # allocation must be marked as healthy. The deadline begins when the first\n # allocation for the deployment is created and is reset whenever an allocation\n # as part of the deployment transitions to a healthy state. If no allocation\n # transitions to the healthy state before the progress deadline, the\n # deployment is marked as failed.\n progress_deadline = \"10m\"\n\n%{ if use_canary }\n # The \"canary\" parameter specifies that changes to the job that would result\n # in destructive updates should create the specified number of canaries\n # without stopping any previous allocations. Once the operator determines the\n # canaries are healthy, they can be promoted which unblocks a rolling update\n # of the remaining allocations at a rate of \"max_parallel\".\n #\n # Further, setting \"canary\" equal to the count of the task group allows\n # blue/green deployments. When the job is updated, a full set of the new\n # version is deployed and upon promotion the old version is stopped.\n canary = 1\n\n # Specifies if the job should auto-promote to the canary version when all\n # canaries become healthy during a deployment. Defaults to false which means\n # canaries must be manually updated with the nomad deployment promote\n # command.\n auto_promote = true\n\n # The \"auto_revert\" parameter specifies if the job should auto-revert to the\n # last stable job on deployment failure. A job is marked as stable if all the\n # allocations as part of its deployment were marked healthy.\n auto_revert = true\n%{ endif }\n }\n\n # The \"group\" stanza defines a series of tasks that should be co-located on\n # the same Nomad client. Any task within a group will be placed on the same\n # client.\n #\n # For more information and examples on the \"group\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/group\n #\n group \"prod-group1-${service_name}\" {\n # The \"count\" parameter specifies the number of the task groups that should\n # be running under this group. This value must be non-negative and defaults\n # to 1.\n count = ${group_count}\n\n # The volume stanza allows the group to specify that it requires a given\n # volume from the cluster.\n #\n # For more information and examples on the \"volume\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/volume\n #\n %{ if use_host_volume }\n volume \"prod-volume1-${service_name}\" {\n type = \"host\"\n read_only = false\n source = \"${host_volume}\"\n }\n %{ endif }\n\n # The constraint allows restricting the set of eligible nodes. Constraints\n # may filter on attributes or client metadata.\n #\n # For more information and examples on the \"volume\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/constraint\n #\n constraint {\n attribute = \"$${attr.cpu.arch}\"\n operator = \"!=\"\n value = \"arm64\"\n }\n\n # The \"task\" stanza creates an individual unit of work, such as a Docker\n # container, web application, or batch processing.\n #\n # For more information and examples on the \"task\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/task\n #\n task \"prod-task1-${service_name}\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"exec\"\n\n %{ if use_host_volume }\n volume_mount {\n volume = \"prod-volume1-${service_name}\"\n destination = \"${data_dir}\"\n read_only = false\n }\n %{ endif }\n\n %{ if use_vault_provider }\n vault {\n policies = \"${vault_kv_policy_name}\"\n }\n %{ endif }\n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n command = \"local/prometheus-${version}.linux-amd64/prometheus\"\n args = [\n \"--config.file=secrets/prometheus.yml\",\n \"--storage.tsdb.path=${data_dir}prometheus/\",\n \"--storage.tsdb.retention.time=15d\"\n ]\n }\n\n # The artifact stanza instructs Nomad to fetch and unpack a remote resource,\n # such as a file, tarball, or binary. Nomad downloads artifacts using the\n # popular go-getter library, which permits downloading artifacts from a\n # variety of locations using a URL as the input source.\n #\n # For more information and examples on the \"artifact\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/artifact\n #\n artifact {\n source = \"${url}\"\n }\n\n # The \"template\" stanza instructs Nomad to manage a template, such as\n # a configuration file or script. This template can optionally pull data\n # from Consul or Vault to populate runtime configuration data.\n #\n # For more information and examples on the \"template\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/template\n #\n template {\n change_mode = \"noop\"\n change_signal = \"SIGINT\"\n destination = \"secrets/alerts.yml\"\n left_delimiter = \"{{{\"\n right_delimiter = \"}}}\"\n data = \u003c\u003cEOH\n---\ngroups:\n- name: \"Consul\"\n rules:\n - alert: ConsulServiceHealthcheckFailed\n expr: consul_catalog_service_node_healthy == 0\n for: 0m\n labels:\n severity: critical\n annotations:\n summary: \"Consul service healthcheck failed (instance {{ $labels.instance }}).\"\n description: \"Service: `{{ $labels.service_name }}` Healthcheck: `{{ $labels.service_id }}`.\"\n - alert: ConsulMissingMasterNode\n expr: consul_raft_peers \u003c 3\n for: 0m\n labels:\n severity: critical\n annotations:\n summary: \"Consul missing master node (instance {{ $labels.instance }}).\"\n description: \"Numbers of consul raft peers should be 3, in order to preserve quorum.\"\n - alert: ConsulAgentUnhealthy\n expr: consul_health_node_status{status=\"critical\"} == 1\n for: 0m\n labels:\n severity: critical\n annotations:\n summary: \"Consul agent unhealthy (instance {{ $labels.instance }}).\"\n description: \"A Consul agent is down.\"\n- name: \"Hosts\"\n rules:\n - alert: NodeDown\n expr: up == 0\n for: 0m\n labels:\n severity: critical\n annotations:\n summary: \"Prometheus target missing (instance {{ $labels.instance }}).\"\n description: \"A Prometheus target has disappeared. An exporter might be crashed.\"\n - alert: HostHighCpuLoad\n expr: 100 - (avg by(instance) (rate(node_cpu_seconds_total{mode=\"idle\"}[2m])) * 100) \u003e 80\n for: 0m\n labels:\n severity: warning\n annotations:\n summary: \"Host high CPU load (instance {{ $labels.instance }}).\"\n description: \"CPU load is \u003e 80%.\"\n - alert: HostOutOfMemory\n expr: node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes * 100 \u003c 10\n for: 2m\n labels:\n severity: warning\n annotations:\n summary: \"Host out of memory (instance {{ $labels.instance }}).\"\n description: \"Node memory is filling up (\u003c 10% left).\"\n - alert: HostOomKillDetected\n expr: increase(node_vmstat_oom_kill[1m]) \u003e 0\n for: 0m\n labels:\n severity: warning\n annotations:\n summary: \"Host OOM kill detected (instance {{ $labels.instance }}).\"\n description: \"OOM kill detected.\"\n - alert: HostMemoryUnderMemoryPressure\n expr: rate(node_vmstat_pgmajfault[1m]) \u003e 1000\n for: 2m\n labels:\n severity: warning\n annotations:\n summary: \"Host memory under memory pressure (instance {{ $labels.instance }}).\"\n description: \"The node is under heavy memory pressure. High rate of major page faults.\"\n - alert: HostOutOfDiskSpace\n expr: (node_filesystem_avail_bytes * 100) / node_filesystem_size_bytes \u003c 10 and ON (instance, device, mountpoint) node_filesystem_readonly == 0\n for: 2m\n labels:\n severity: warning\n annotations:\n summary: \"Host out of disk space (instance {{ $labels.instance }}).\"\n description: \"Disk is almost full (\u003c 10% left).\"\n - alert: HostRaidDiskFailure\n expr: node_md_disks{state=\"failed\"} \u003e 0\n for: 2m\n labels:\n severity: warning\n annotations:\n summary: \"Host RAID disk failure (instance {{ $labels.instance }}).\"\n description: \"At least one device in RAID array on {{ $labels.instance }} failed. Array {{ $labels.md_device }} needs attention and possibly a disk swap.\"\n - alert: HostConntrackLimit\n expr: node_nf_conntrack_entries / node_nf_conntrack_entries_limit \u003e 0.8\n for: 5m\n labels:\n severity: warning\n annotations:\n summary: \"Host conntrack limit (instance {{ $labels.instance }}).\"\n description: \"The number of conntrack is approching limit.\"\n - alert: HostNetworkInterfaceSaturated\n expr: (rate(node_network_receive_bytes_total{device!~\"^tap.*\"}[1m]) + rate(node_network_transmit_bytes_total{device!~\"^tap.*\"}[1m])) / node_network_speed_bytes{device!~\"^tap.*\"} \u003e 0.8\n for: 1m\n labels:\n severity: warning\n annotations:\n summary: \"Host Network Interface Saturated (instance {{ $labels.instance }}).\"\n description: \"The network interface {{ $labels.interface }} on {{ $labels.instance }} is getting overloaded.\"\n - alert: HostSystemdServiceCrashed\n expr: node_systemd_unit_state{state=\"failed\"} == 1\n for: 0m\n labels:\n severity: warning\n annotations:\n summary: \"Host SystemD service crashed (instance {{ $labels.instance }}).\"\n description: \"SystemD service crashed.\"\n - alert: HostEdacCorrectableErrorsDetected\n expr: increase(node_edac_correctable_errors_total[1m]) \u003e 0\n for: 0m\n labels:\n severity: info\n annotations:\n summary: \"Host EDAC Correctable Errors detected (instance {{ $labels.instance }}).\"\n description: '{{ $labels.instance }} has had {{ printf \"%.0f\" $value }} correctable memory errors reported by EDAC in the last 5 minutes.'\n - alert: HostEdacUncorrectableErrorsDetected\n expr: node_edac_uncorrectable_errors_total \u003e 0\n for: 0m\n labels:\n severity: warning\n annotations:\n summary: \"Host EDAC Uncorrectable Errors detected (instance {{ $labels.instance }}).\"\n description: '{{ $labels.instance }} has had {{ printf \"%.0f\" $value }} uncorrectable memory errors reported by EDAC in the last 5 minutes.'\n- name: \"Min.io\"\n rules:\n - alert: MinioDiskOffline\n expr: minio_offline_disks \u003e 0\n for: 0m\n labels:\n severity: critical\n annotations:\n summary: \"Minio disk offline (instance {{ $labels.instance }})\"\n description: \"Minio disk is offline.\"\n - alert: MinioStorageSpaceExhausted\n expr: minio_disk_storage_free_bytes / 1024 / 1024 / 1024 \u003c 10\n for: 2m\n labels:\n severity: warning\n annotations:\n summary: \"Minio storage space exhausted (instance {{ $labels.instance }}).\"\n description: \"Minio storage space is low (\u003c 10 GB).\"\n- name: \"Prometheus\"\n rules:\n - alert: PrometheusConfigurationReloadFailure\n expr: prometheus_config_last_reload_successful != 1\n for: 0m\n labels:\n severity: warning\n annotations:\n summary: \"Prometheus configuration reload failure (instance {{ $labels.instance }}).\"\n description: \"Prometheus configuration reload error.\"\n - alert: PrometheusTooManyRestarts\n expr: changes(process_start_time_seconds{job=~\"prometheus|pushgateway|alertmanager\"}[15m]) \u003e 2\n for: 0m\n labels:\n severity: warning\n annotations:\n summary: \"Prometheus too many restarts (instance {{ $labels.instance }}).\"\n description: \"Prometheus has restarted more than twice in the last 15 minutes. It might be crashlooping.\"\n - alert: PrometheusAlertmanagerConfigurationReloadFailure\n expr: alertmanager_config_last_reload_successful != 1\n for: 0m\n labels:\n severity: warning\n annotations:\n summary: \"Prometheus AlertManager configuration reload failure (instance {{ $labels.instance }}).\"\n description: \"AlertManager configuration reload error.\"\n - alert: PrometheusRuleEvaluationFailures\n expr: increase(prometheus_rule_evaluation_failures_total[3m]) \u003e 0\n for: 0m\n labels:\n severity: critical\n annotations:\n summary: \"Prometheus rule evaluation failures (instance {{ $labels.instance }}).\"\n description: \"Prometheus encountered {{ $value }} rule evaluation failures, leading to potentially ignored alerts.\"\n - alert: PrometheusTargetScrapingSlow\n expr: prometheus_target_interval_length_seconds{quantile=\"0.9\"} \u003e 60\n for: 5m\n labels:\n severity: warning\n annotations:\n summary: \"Prometheus target scraping slow (instance {{ $labels.instance }}).\"\n description: \"Prometheus is scraping exporters slowly.\"\n - alert: PrometheusTsdbCompactionsFailed\n expr: increase(prometheus_tsdb_compactions_failed_total[1m]) \u003e 0\n for: 0m\n labels:\n severity: critical\n annotations:\n summary: \"Prometheus TSDB compactions failed (instance {{ $labels.instance }}).\"\n description: \"Prometheus encountered {{ $value }} TSDB compactions failures.\"\n - alert: PrometheusTsdbHeadTruncationsFailed\n expr: increase(prometheus_tsdb_head_truncations_failed_total[1m]) \u003e 0\n for: 0m\n labels:\n severity: critical\n annotations:\n summary: \"Prometheus TSDB head truncations failed (instance {{ $labels.instance }}).\"\n description: \"Prometheus encountered {{ $value }} TSDB head truncation failures.\"\n - alert: PrometheusTsdbWalCorruptions\n expr: increase(prometheus_tsdb_wal_corruptions_total[1m]) \u003e 0\n for: 0m\n labels:\n severity: critical\n annotations:\n summary: \"Prometheus TSDB WAL corruptions (instance {{ $labels.instance }}).\"\n description: \"Prometheus encountered {{ $value }} TSDB WAL corruptions.\"\n - alert: PrometheusTsdbWalTruncationsFailed\n expr: increase(prometheus_tsdb_wal_truncations_failed_total[1m]) \u003e 0\n for: 0m\n labels:\n severity: critical\n annotations:\n summary: \"Prometheus TSDB WAL truncations failed (instance {{ $labels.instance }}).\"\n description: \"Prometheus encountered {{ $value }} TSDB WAL truncation failures.\"\nEOH\n }\n\n template {\n change_mode = \"noop\"\n change_signal = \"SIGINT\"\n destination = \"secrets/prometheus.yml\"\n data = \u003c\u003cEOH\n---\nglobal:\n scrape_interval: 5s\n scrape_timeout: 5s\n evaluation_interval: 5s\n\nalerting:\n alertmanagers:\n - consul_sd_configs:\n - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n services: [ 'alertmanager' ]\n\nrule_files:\n - 'alerts.yml'\n\nscrape_configs:\n\n - job_name: 'Nomad Cluster'\n consul_sd_configs:\n - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n services: [ 'nomad-client', 'nomad' ]\n relabel_configs:\n - source_labels: [__meta_consul_tags]\n regex: '(.*)http(.*)'\n action: keep\n metrics_path: /v1/metrics\n params:\n format: [ 'prometheus' ]\n\n - job_name: 'Consul Cluster'\n static_configs:\n - targets: [ '10.30.51.30:8500', '10.30.51.32:8500', '10.30.51.33:8500' ]\n metrics_path: /v1/agent/metrics\n params:\n format: [ 'prometheus' ]\n\n - job_name: 'Alertmanager'\n consul_sd_configs:\n - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n services: [ 'alertmanager' ]\n\n - job_name: 'Blackbox Exporter (icmp)'\n static_configs:\n - targets: [ 'gerrit.fd.io' ]\n - targets: [ 'jenkins.fd.io' ]\n - targets: [ '10.30.51.32' ]\n params:\n module: [ 'icmp_v4' ]\n relabel_configs:\n - source_labels: [__address__]\n target_label: __param_target\n - source_labels: [__param_target]\n target_label: instance\n - target_label: __address__\n replacement: localhost:9115\n metrics_path: /probe\n\n - job_name: 'Blackbox Exporter (http)'\n static_configs:\n - targets: [ 'gerrit.fd.io' ]\n - targets: [ 'jenkins.fd.io' ]\n params:\n module: [ 'http_2xx' ]\n relabel_configs:\n - source_labels: [__address__]\n target_label: __param_target\n - source_labels: [__param_target]\n target_label: instance\n - target_label: __address__\n replacement: localhost:9115\n metrics_path: /probe\n\n - job_name: 'cAdvisor Exporter'\n consul_sd_configs:\n - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n services: [ 'cadvisorexporter' ]\n\n - job_name: 'Grafana'\n consul_sd_configs:\n - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n services: [ 'grafana' ]\n\n - job_name: 'Node Exporter'\n consul_sd_configs:\n - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n services: [ 'nodeexporter' ]\n\n - job_name: 'Prometheus'\n consul_sd_configs:\n - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n services: [ 'prometheus' ]\n\n - job_name: 'Minio'\n bearer_token: eyJhbGciOiJIUzUxMiIsInR5cCI6IkpXVCJ9.eyJleHAiOjQ3NjQ1ODEzMzcsImlzcyI6InByb21ldGhldXMiLCJzdWIiOiJtaW5pbyJ9.oeTw3EIaiFmlDikrHXWiWXMH2vxLfDLkfjEC7G2N3M_keH_xyA_l2ofLLNYtopa_3GCEZnxLQdPuFZrmgpkDWg\n consul_sd_configs:\n - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n services: [ 'storage' ]\n metrics_path: /minio/prometheus/metrics\nEOH\n }\n\n # The service stanza instructs Nomad to register a service with Consul.\n #\n # For more information and examples on the \"task\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/service\n #\n service {\n name = \"${service_name}\"\n port = \"${service_name}\"\n tags = [ \"${service_name}$${NOMAD_ALLOC_INDEX}\" ]\n check {\n name = \"Prometheus Check Live\"\n type = \"http\"\n path = \"/-/healthy\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # For more information and examples on the \"resources\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/resources\n #\n resources {\n cpu = ${cpu}\n memory = ${mem}\n # The network stanza specifies the networking requirements for the task\n # group, including the network mode and port allocations. When scheduling\n # jobs in Nomad they are provisioned across your fleet of machines along\n # with other jobs and services. Because you don't know in advance what host\n # your job will be provisioned on, Nomad will provide your tasks with\n # network configuration when they start up.\n #\n # For more information and examples on the \"template\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/network\n #\n network {\n port \"${service_name}\" {\n static = ${port}\n }\n }\n }\n }\n }\n}", + "vars": { + "cpu": "2000", + "data_dir": "/data/", + "datacenters": "yul1", + "group_count": "4", + "host_volume": "prod-volume-data1-1", + "job_name": "prod-prometheus", + "mem": "8192", + "port": "9090", + "service_name": "prometheus", + "url": "https://github.com/prometheus/prometheus/releases/download/v2.24.0/prometheus-2.24.0.linux-amd64.tar.gz", + "use_canary": "true", + "use_host_volume": "true", + "use_vault_provider": "false", + "version": "2.24.0" + } + }, + "sensitive_attributes": [] + } + ] + }, + { + "module": "module.prometheus", + "mode": "managed", + "type": "nomad_job", + "name": "nomad_job_prometheus", + "provider": "provider[\"registry.terraform.io/hashicorp/nomad\"].yul1", + "instances": [ + { + "schema_version": 0, + "attributes": { + "allocation_ids": [ + "79c4c6b7-e8e4-79e7-9dae-9a26142cd94c", + "2e11f44e-814e-db74-a9ee-8bcbebb1fa0b", + "83f9c9aa-f4f2-b832-a937-aaee4181493e", + "231f1338-a871-b44e-d545-e8af01d7eebe" + ], + "datacenters": [ + "yul1" + ], + "deployment_id": "4cbf8370-f2d7-16c2-d500-f6495d43537d", + "deployment_status": "successful", + "deregister_on_destroy": true, + "deregister_on_id_change": true, + "detach": false, + "id": "prod-prometheus", + "jobspec": "job \"prod-prometheus\" {\n # The \"region\" parameter specifies the region in which to execute the job.\n # If omitted, this inherits the default region name of \"global\".\n # region = \"global\"\n #\n # The \"datacenters\" parameter specifies the list of datacenters which should\n # be considered when placing this task. This must be provided.\n datacenters = \"yul1\"\n\n # The \"type\" parameter controls the type of job, which impacts the scheduler's\n # decision on placement. This configuration is optional and defaults to\n # \"service\". For a full list of job types and their differences, please see\n # the online documentation.\n #\n # For more information, please see the online documentation at:\n #\n # https://www.nomadproject.io/docs/jobspec/schedulers\n #\n type = \"service\"\n\n update {\n # The \"max_parallel\" parameter specifies the maximum number of updates to\n # perform in parallel. In this case, this specifies to update a single task\n # at a time.\n max_parallel = 1\n\n health_check = \"checks\"\n\n # The \"min_healthy_time\" parameter specifies the minimum time the allocation\n # must be in the healthy state before it is marked as healthy and unblocks\n # further allocations from being updated.\n min_healthy_time = \"10s\"\n\n # The \"healthy_deadline\" parameter specifies the deadline in which the\n # allocation must be marked as healthy after which the allocation is\n # automatically transitioned to unhealthy. Transitioning to unhealthy will\n # fail the deployment and potentially roll back the job if \"auto_revert\" is\n # set to true.\n healthy_deadline = \"3m\"\n\n # The \"progress_deadline\" parameter specifies the deadline in which an\n # allocation must be marked as healthy. The deadline begins when the first\n # allocation for the deployment is created and is reset whenever an allocation\n # as part of the deployment transitions to a healthy state. If no allocation\n # transitions to the healthy state before the progress deadline, the\n # deployment is marked as failed.\n progress_deadline = \"10m\"\n\n\n # The \"canary\" parameter specifies that changes to the job that would result\n # in destructive updates should create the specified number of canaries\n # without stopping any previous allocations. Once the operator determines the\n # canaries are healthy, they can be promoted which unblocks a rolling update\n # of the remaining allocations at a rate of \"max_parallel\".\n #\n # Further, setting \"canary\" equal to the count of the task group allows\n # blue/green deployments. When the job is updated, a full set of the new\n # version is deployed and upon promotion the old version is stopped.\n canary = 1\n\n # Specifies if the job should auto-promote to the canary version when all\n # canaries become healthy during a deployment. Defaults to false which means\n # canaries must be manually updated with the nomad deployment promote\n # command.\n auto_promote = true\n\n # The \"auto_revert\" parameter specifies if the job should auto-revert to the\n # last stable job on deployment failure. A job is marked as stable if all the\n # allocations as part of its deployment were marked healthy.\n auto_revert = true\n\n }\n\n # The \"group\" stanza defines a series of tasks that should be co-located on\n # the same Nomad client. Any task within a group will be placed on the same\n # client.\n #\n # For more information and examples on the \"group\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/group\n #\n group \"prod-group1-prometheus\" {\n # The \"count\" parameter specifies the number of the task groups that should\n # be running under this group. This value must be non-negative and defaults\n # to 1.\n count = 4\n\n # The volume stanza allows the group to specify that it requires a given\n # volume from the cluster.\n #\n # For more information and examples on the \"volume\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/volume\n #\n \n volume \"prod-volume1-prometheus\" {\n type = \"host\"\n read_only = false\n source = \"prod-volume-data1-1\"\n }\n \n\n # The constraint allows restricting the set of eligible nodes. Constraints\n # may filter on attributes or client metadata.\n #\n # For more information and examples on the \"volume\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/constraint\n #\n constraint {\n attribute = \"${attr.cpu.arch}\"\n operator = \"!=\"\n value = \"arm64\"\n }\n\n # The \"task\" stanza creates an individual unit of work, such as a Docker\n # container, web application, or batch processing.\n #\n # For more information and examples on the \"task\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/task\n #\n task \"prod-task1-prometheus\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"exec\"\n\n \n volume_mount {\n volume = \"prod-volume1-prometheus\"\n destination = \"/data/\"\n read_only = false\n }\n \n\n \n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n command = \"local/prometheus-2.24.0.linux-amd64/prometheus\"\n args = [\n \"--config.file=secrets/prometheus.yml\",\n \"--storage.tsdb.path=/data/prometheus/\",\n \"--storage.tsdb.retention.time=15d\"\n ]\n }\n\n # The artifact stanza instructs Nomad to fetch and unpack a remote resource,\n # such as a file, tarball, or binary. Nomad downloads artifacts using the\n # popular go-getter library, which permits downloading artifacts from a\n # variety of locations using a URL as the input source.\n #\n # For more information and examples on the \"artifact\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/artifact\n #\n artifact {\n source = \"https://github.com/prometheus/prometheus/releases/download/v2.24.0/prometheus-2.24.0.linux-amd64.tar.gz\"\n }\n\n # The \"template\" stanza instructs Nomad to manage a template, such as\n # a configuration file or script. This template can optionally pull data\n # from Consul or Vault to populate runtime configuration data.\n #\n # For more information and examples on the \"template\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/template\n #\n template {\n change_mode = \"noop\"\n change_signal = \"SIGINT\"\n destination = \"secrets/alerts.yml\"\n left_delimiter = \"{{{\"\n right_delimiter = \"}}}\"\n data = \u003c\u003cEOH\n---\ngroups:\n- name: \"Consul\"\n rules:\n - alert: ConsulServiceHealthcheckFailed\n expr: consul_catalog_service_node_healthy == 0\n for: 0m\n labels:\n severity: critical\n annotations:\n summary: \"Consul service healthcheck failed (instance {{ $labels.instance }}).\"\n description: \"Service: `{{ $labels.service_name }}` Healthcheck: `{{ $labels.service_id }}`.\"\n - alert: ConsulMissingMasterNode\n expr: consul_raft_peers \u003c 3\n for: 0m\n labels:\n severity: critical\n annotations:\n summary: \"Consul missing master node (instance {{ $labels.instance }}).\"\n description: \"Numbers of consul raft peers should be 3, in order to preserve quorum.\"\n - alert: ConsulAgentUnhealthy\n expr: consul_health_node_status{status=\"critical\"} == 1\n for: 0m\n labels:\n severity: critical\n annotations:\n summary: \"Consul agent unhealthy (instance {{ $labels.instance }}).\"\n description: \"A Consul agent is down.\"\n- name: \"Hosts\"\n rules:\n - alert: NodeDown\n expr: up == 0\n for: 0m\n labels:\n severity: critical\n annotations:\n summary: \"Prometheus target missing (instance {{ $labels.instance }}).\"\n description: \"A Prometheus target has disappeared. An exporter might be crashed.\"\n - alert: HostHighCpuLoad\n expr: 100 - (avg by(instance) (rate(node_cpu_seconds_total{mode=\"idle\"}[2m])) * 100) \u003e 80\n for: 0m\n labels:\n severity: warning\n annotations:\n summary: \"Host high CPU load (instance {{ $labels.instance }}).\"\n description: \"CPU load is \u003e 80%.\"\n - alert: HostOutOfMemory\n expr: node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes * 100 \u003c 10\n for: 2m\n labels:\n severity: warning\n annotations:\n summary: \"Host out of memory (instance {{ $labels.instance }}).\"\n description: \"Node memory is filling up (\u003c 10% left).\"\n - alert: HostOomKillDetected\n expr: increase(node_vmstat_oom_kill[1m]) \u003e 0\n for: 0m\n labels:\n severity: warning\n annotations:\n summary: \"Host OOM kill detected (instance {{ $labels.instance }}).\"\n description: \"OOM kill detected.\"\n - alert: HostMemoryUnderMemoryPressure\n expr: rate(node_vmstat_pgmajfault[1m]) \u003e 1000\n for: 2m\n labels:\n severity: warning\n annotations:\n summary: \"Host memory under memory pressure (instance {{ $labels.instance }}).\"\n description: \"The node is under heavy memory pressure. High rate of major page faults.\"\n - alert: HostOutOfDiskSpace\n expr: (node_filesystem_avail_bytes * 100) / node_filesystem_size_bytes \u003c 10 and ON (instance, device, mountpoint) node_filesystem_readonly == 0\n for: 2m\n labels:\n severity: warning\n annotations:\n summary: \"Host out of disk space (instance {{ $labels.instance }}).\"\n description: \"Disk is almost full (\u003c 10% left).\"\n - alert: HostRaidDiskFailure\n expr: node_md_disks{state=\"failed\"} \u003e 0\n for: 2m\n labels:\n severity: warning\n annotations:\n summary: \"Host RAID disk failure (instance {{ $labels.instance }}).\"\n description: \"At least one device in RAID array on {{ $labels.instance }} failed. Array {{ $labels.md_device }} needs attention and possibly a disk swap.\"\n - alert: HostConntrackLimit\n expr: node_nf_conntrack_entries / node_nf_conntrack_entries_limit \u003e 0.8\n for: 5m\n labels:\n severity: warning\n annotations:\n summary: \"Host conntrack limit (instance {{ $labels.instance }}).\"\n description: \"The number of conntrack is approching limit.\"\n - alert: HostNetworkInterfaceSaturated\n expr: (rate(node_network_receive_bytes_total{device!~\"^tap.*\"}[1m]) + rate(node_network_transmit_bytes_total{device!~\"^tap.*\"}[1m])) / node_network_speed_bytes{device!~\"^tap.*\"} \u003e 0.8\n for: 1m\n labels:\n severity: warning\n annotations:\n summary: \"Host Network Interface Saturated (instance {{ $labels.instance }}).\"\n description: \"The network interface {{ $labels.interface }} on {{ $labels.instance }} is getting overloaded.\"\n - alert: HostSystemdServiceCrashed\n expr: node_systemd_unit_state{state=\"failed\"} == 1\n for: 0m\n labels:\n severity: warning\n annotations:\n summary: \"Host SystemD service crashed (instance {{ $labels.instance }}).\"\n description: \"SystemD service crashed.\"\n - alert: HostEdacCorrectableErrorsDetected\n expr: increase(node_edac_correctable_errors_total[1m]) \u003e 0\n for: 0m\n labels:\n severity: info\n annotations:\n summary: \"Host EDAC Correctable Errors detected (instance {{ $labels.instance }}).\"\n description: '{{ $labels.instance }} has had {{ printf \"%.0f\" $value }} correctable memory errors reported by EDAC in the last 5 minutes.'\n - alert: HostEdacUncorrectableErrorsDetected\n expr: node_edac_uncorrectable_errors_total \u003e 0\n for: 0m\n labels:\n severity: warning\n annotations:\n summary: \"Host EDAC Uncorrectable Errors detected (instance {{ $labels.instance }}).\"\n description: '{{ $labels.instance }} has had {{ printf \"%.0f\" $value }} uncorrectable memory errors reported by EDAC in the last 5 minutes.'\n- name: \"Min.io\"\n rules:\n - alert: MinioDiskOffline\n expr: minio_offline_disks \u003e 0\n for: 0m\n labels:\n severity: critical\n annotations:\n summary: \"Minio disk offline (instance {{ $labels.instance }})\"\n description: \"Minio disk is offline.\"\n - alert: MinioStorageSpaceExhausted\n expr: minio_disk_storage_free_bytes / 1024 / 1024 / 1024 \u003c 10\n for: 2m\n labels:\n severity: warning\n annotations:\n summary: \"Minio storage space exhausted (instance {{ $labels.instance }}).\"\n description: \"Minio storage space is low (\u003c 10 GB).\"\n- name: \"Prometheus\"\n rules:\n - alert: PrometheusConfigurationReloadFailure\n expr: prometheus_config_last_reload_successful != 1\n for: 0m\n labels:\n severity: warning\n annotations:\n summary: \"Prometheus configuration reload failure (instance {{ $labels.instance }}).\"\n description: \"Prometheus configuration reload error.\"\n - alert: PrometheusTooManyRestarts\n expr: changes(process_start_time_seconds{job=~\"prometheus|pushgateway|alertmanager\"}[15m]) \u003e 2\n for: 0m\n labels:\n severity: warning\n annotations:\n summary: \"Prometheus too many restarts (instance {{ $labels.instance }}).\"\n description: \"Prometheus has restarted more than twice in the last 15 minutes. It might be crashlooping.\"\n - alert: PrometheusAlertmanagerConfigurationReloadFailure\n expr: alertmanager_config_last_reload_successful != 1\n for: 0m\n labels:\n severity: warning\n annotations:\n summary: \"Prometheus AlertManager configuration reload failure (instance {{ $labels.instance }}).\"\n description: \"AlertManager configuration reload error.\"\n - alert: PrometheusRuleEvaluationFailures\n expr: increase(prometheus_rule_evaluation_failures_total[3m]) \u003e 0\n for: 0m\n labels:\n severity: critical\n annotations:\n summary: \"Prometheus rule evaluation failures (instance {{ $labels.instance }}).\"\n description: \"Prometheus encountered {{ $value }} rule evaluation failures, leading to potentially ignored alerts.\"\n - alert: PrometheusTargetScrapingSlow\n expr: prometheus_target_interval_length_seconds{quantile=\"0.9\"} \u003e 60\n for: 5m\n labels:\n severity: warning\n annotations:\n summary: \"Prometheus target scraping slow (instance {{ $labels.instance }}).\"\n description: \"Prometheus is scraping exporters slowly.\"\n - alert: PrometheusTsdbCompactionsFailed\n expr: increase(prometheus_tsdb_compactions_failed_total[1m]) \u003e 0\n for: 0m\n labels:\n severity: critical\n annotations:\n summary: \"Prometheus TSDB compactions failed (instance {{ $labels.instance }}).\"\n description: \"Prometheus encountered {{ $value }} TSDB compactions failures.\"\n - alert: PrometheusTsdbHeadTruncationsFailed\n expr: increase(prometheus_tsdb_head_truncations_failed_total[1m]) \u003e 0\n for: 0m\n labels:\n severity: critical\n annotations:\n summary: \"Prometheus TSDB head truncations failed (instance {{ $labels.instance }}).\"\n description: \"Prometheus encountered {{ $value }} TSDB head truncation failures.\"\n - alert: PrometheusTsdbWalCorruptions\n expr: increase(prometheus_tsdb_wal_corruptions_total[1m]) \u003e 0\n for: 0m\n labels:\n severity: critical\n annotations:\n summary: \"Prometheus TSDB WAL corruptions (instance {{ $labels.instance }}).\"\n description: \"Prometheus encountered {{ $value }} TSDB WAL corruptions.\"\n - alert: PrometheusTsdbWalTruncationsFailed\n expr: increase(prometheus_tsdb_wal_truncations_failed_total[1m]) \u003e 0\n for: 0m\n labels:\n severity: critical\n annotations:\n summary: \"Prometheus TSDB WAL truncations failed (instance {{ $labels.instance }}).\"\n description: \"Prometheus encountered {{ $value }} TSDB WAL truncation failures.\"\nEOH\n }\n\n template {\n change_mode = \"noop\"\n change_signal = \"SIGINT\"\n destination = \"secrets/prometheus.yml\"\n data = \u003c\u003cEOH\n---\nglobal:\n scrape_interval: 5s\n scrape_timeout: 5s\n evaluation_interval: 5s\n\nalerting:\n alertmanagers:\n - consul_sd_configs:\n - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n services: [ 'alertmanager' ]\n\nrule_files:\n - 'alerts.yml'\n\nscrape_configs:\n\n - job_name: 'Nomad Cluster'\n consul_sd_configs:\n - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n services: [ 'nomad-client', 'nomad' ]\n relabel_configs:\n - source_labels: [__meta_consul_tags]\n regex: '(.*)http(.*)'\n action: keep\n metrics_path: /v1/metrics\n params:\n format: [ 'prometheus' ]\n\n - job_name: 'Consul Cluster'\n static_configs:\n - targets: [ '10.30.51.30:8500', '10.30.51.32:8500', '10.30.51.33:8500' ]\n metrics_path: /v1/agent/metrics\n params:\n format: [ 'prometheus' ]\n\n - job_name: 'Alertmanager'\n consul_sd_configs:\n - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n services: [ 'alertmanager' ]\n\n - job_name: 'Blackbox Exporter (icmp)'\n static_configs:\n - targets: [ 'gerrit.fd.io' ]\n - targets: [ 'jenkins.fd.io' ]\n - targets: [ '10.30.51.32' ]\n params:\n module: [ 'icmp_v4' ]\n relabel_configs:\n - source_labels: [__address__]\n target_label: __param_target\n - source_labels: [__param_target]\n target_label: instance\n - target_label: __address__\n replacement: localhost:9115\n metrics_path: /probe\n\n - job_name: 'Blackbox Exporter (http)'\n static_configs:\n - targets: [ 'gerrit.fd.io' ]\n - targets: [ 'jenkins.fd.io' ]\n params:\n module: [ 'http_2xx' ]\n relabel_configs:\n - source_labels: [__address__]\n target_label: __param_target\n - source_labels: [__param_target]\n target_label: instance\n - target_label: __address__\n replacement: localhost:9115\n metrics_path: /probe\n\n - job_name: 'cAdvisor Exporter'\n consul_sd_configs:\n - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n services: [ 'cadvisorexporter' ]\n\n - job_name: 'Grafana'\n consul_sd_configs:\n - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n services: [ 'grafana' ]\n\n - job_name: 'Node Exporter'\n consul_sd_configs:\n - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n services: [ 'nodeexporter' ]\n\n - job_name: 'Prometheus'\n consul_sd_configs:\n - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n services: [ 'prometheus' ]\n\n - job_name: 'Minio'\n bearer_token: eyJhbGciOiJIUzUxMiIsInR5cCI6IkpXVCJ9.eyJleHAiOjQ3NjQ1ODEzMzcsImlzcyI6InByb21ldGhldXMiLCJzdWIiOiJtaW5pbyJ9.oeTw3EIaiFmlDikrHXWiWXMH2vxLfDLkfjEC7G2N3M_keH_xyA_l2ofLLNYtopa_3GCEZnxLQdPuFZrmgpkDWg\n consul_sd_configs:\n - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n services: [ 'storage' ]\n metrics_path: /minio/prometheus/metrics\nEOH\n }\n\n # The service stanza instructs Nomad to register a service with Consul.\n #\n # For more information and examples on the \"task\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/service\n #\n service {\n name = \"prometheus\"\n port = \"prometheus\"\n tags = [ \"prometheus${NOMAD_ALLOC_INDEX}\" ]\n check {\n name = \"Prometheus Check Live\"\n type = \"http\"\n path = \"/-/healthy\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # For more information and examples on the \"resources\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/resources\n #\n resources {\n cpu = 2000\n memory = 8192\n # The network stanza specifies the networking requirements for the task\n # group, including the network mode and port allocations. When scheduling\n # jobs in Nomad they are provisioned across your fleet of machines along\n # with other jobs and services. Because you don't know in advance what host\n # your job will be provisioned on, Nomad will provide your tasks with\n # network configuration when they start up.\n #\n # For more information and examples on the \"template\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/network\n #\n network {\n port \"prometheus\" {\n static = 9090\n }\n }\n }\n }\n }\n}", + "json": null, + "modify_index": "7147932", + "name": "prod-prometheus", + "namespace": "default", + "policy_override": null, + "purge_on_destroy": null, + "region": "global", + "task_groups": [ + { + "count": 4, + "meta": {}, + "name": "prod-group1-prometheus", + "task": [ + { + "driver": "exec", + "meta": {}, + "name": "prod-task1-prometheus", + "volume_mounts": [ + { + "destination": "/data/", + "read_only": false, + "volume": "prod-volume1-prometheus" + } + ] + } + ], + "volumes": [ + { + "name": "prod-volume1-prometheus", + "read_only": false, + "source": "prod-volume-data1-1", + "type": "host" + } + ] + } + ], + "type": "service" + }, + "sensitive_attributes": [], + "private": "bnVsbA==", + "dependencies": [ + "module.prometheus.data.template_file.nomad_job_prometheus" + ] + } + ] + }, + { + "module": "module.vpp_device", + "mode": "data", + "type": "template_file", + "name": "nomad_job_csit_shim", + "provider": "provider[\"registry.terraform.io/hashicorp/template\"]", + "instances": [ + { + "schema_version": 0, + "attributes": { + "filename": null, + "id": "a285223159ce0af9e5427d857021e5651c09408af90decd3b93a90efd4fd7ce8", + "rendered": "job \"prod-device-csit-shim\" {\n # The \"region\" parameter specifies the region in which to execute the job.\n # If omitted, this inherits the default region name of \"global\".\n # region = \"global\"\n #\n # The \"datacenters\" parameter specifies the list of datacenters which should\n # be considered when placing this task. This must be provided.\n datacenters = \"yul1\"\n\n # The \"type\" parameter controls the type of job, which impacts the scheduler's\n # decision on placement. This configuration is optional and defaults to\n # \"service\". For a full list of job types and their differences, please see\n # the online documentation.\n #\n # For more information, please see the online documentation at:\n #\n # https://www.nomadproject.io/docs/jobspec/schedulers.html\n #\n type = \"system\"\n\n # The \"group\" stanza defines a series of tasks that should be co-located on\n # the same Nomad client. Any task within a group will be placed on the same\n # client.\n #\n # For more information and examples on the \"group\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/group.html\n #\n group \"prod-group1-csit-shim-amd\" {\n # The \"count\" parameter specifies the number of the task groups that should\n # be running under this group. This value must be non-negative and defaults\n # to 1.\n count = 1\n\n constraint {\n attribute = \"${node.class}\"\n value = \"csit\"\n }\n\n restart {\n interval = \"1m\"\n attempts = 3\n delay = \"15s\"\n mode = \"delay\"\n }\n\n # The \"task\" stanza creates an individual unit of work, such as a Docker\n # container, web application, or batch processing.\n #\n # For more information and examples on the \"task\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/task.html\n #\n task \"prod-task1-csit-shim-amd\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"docker\"\n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n image = \"csit_shim-ubuntu1804:local\"\n network_mode = \"host\"\n pid_mode = \"host\"\n volumes = [\n \"/var/run/docker.sock:/var/run/docker.sock\"\n ]\n privileged = true\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # For more information and examples on the \"resources\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/resources.html\n #\n resources {\n cpu = 1000\n memory = 5000\n network {\n port \"ssh\" {\n static = 6022\n }\n port \"ssh2\" {\n static = 6023\n }\n }\n }\n }\n }\n\n group \"prod-group1-csit-shim-arm\" {\n # The \"count\" parameter specifies the number of the task groups that should\n # be running under this group. This value must be non-negative and defaults\n # to 1.\n count = 1\n\n constraint {\n attribute = \"${node.class}\"\n value = \"csitarm\"\n }\n\n restart {\n interval = \"1m\"\n attempts = 3\n delay = \"15s\"\n mode = \"delay\"\n }\n\n # The \"task\" stanza creates an individual unit of work, such as a Docker\n # container, web application, or batch processing.\n #\n # For more information and examples on the \"task\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/task.html\n #\n task \"prod-task1-csit-shim-arm\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"docker\"\n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n image = \"csit_shim-ubuntu1804:local\"\n network_mode = \"host\"\n pid_mode = \"host\"\n volumes = [\n \"/var/run/docker.sock:/var/run/docker.sock\"\n ]\n privileged = true\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # For more information and examples on the \"resources\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/resources.html\n #\n resources {\n cpu = 1000\n memory = 5000\n network {\n port \"ssh\" {\n static = 6022\n }\n port \"ssh2\" {\n static = 6023\n }\n }\n }\n }\n }\n}", + "template": "job \"${job_name}\" {\n # The \"region\" parameter specifies the region in which to execute the job.\n # If omitted, this inherits the default region name of \"global\".\n # region = \"global\"\n #\n # The \"datacenters\" parameter specifies the list of datacenters which should\n # be considered when placing this task. This must be provided.\n datacenters = \"${datacenters}\"\n\n # The \"type\" parameter controls the type of job, which impacts the scheduler's\n # decision on placement. This configuration is optional and defaults to\n # \"service\". For a full list of job types and their differences, please see\n # the online documentation.\n #\n # For more information, please see the online documentation at:\n #\n # https://www.nomadproject.io/docs/jobspec/schedulers.html\n #\n type = \"system\"\n\n # The \"group\" stanza defines a series of tasks that should be co-located on\n # the same Nomad client. Any task within a group will be placed on the same\n # client.\n #\n # For more information and examples on the \"group\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/group.html\n #\n group \"prod-group1-csit-shim-amd\" {\n # The \"count\" parameter specifies the number of the task groups that should\n # be running under this group. This value must be non-negative and defaults\n # to 1.\n count = ${group_count}\n\n constraint {\n attribute = \"$${node.class}\"\n value = \"csit\"\n }\n\n restart {\n interval = \"1m\"\n attempts = 3\n delay = \"15s\"\n mode = \"delay\"\n }\n\n # The \"task\" stanza creates an individual unit of work, such as a Docker\n # container, web application, or batch processing.\n #\n # For more information and examples on the \"task\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/task.html\n #\n task \"prod-task1-csit-shim-amd\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"docker\"\n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n image = \"csit_shim-ubuntu1804:local\"\n network_mode = \"host\"\n pid_mode = \"host\"\n volumes = [\n \"/var/run/docker.sock:/var/run/docker.sock\"\n ]\n privileged = true\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # For more information and examples on the \"resources\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/resources.html\n #\n resources {\n cpu = ${cpu}\n memory = ${mem}\n network {\n port \"ssh\" {\n static = 6022\n }\n port \"ssh2\" {\n static = 6023\n }\n }\n }\n }\n }\n\n group \"prod-group1-csit-shim-arm\" {\n # The \"count\" parameter specifies the number of the task groups that should\n # be running under this group. This value must be non-negative and defaults\n # to 1.\n count = ${group_count}\n\n constraint {\n attribute = \"$${node.class}\"\n value = \"csitarm\"\n }\n\n restart {\n interval = \"1m\"\n attempts = 3\n delay = \"15s\"\n mode = \"delay\"\n }\n\n # The \"task\" stanza creates an individual unit of work, such as a Docker\n # container, web application, or batch processing.\n #\n # For more information and examples on the \"task\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/task.html\n #\n task \"prod-task1-csit-shim-arm\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"docker\"\n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n image = \"csit_shim-ubuntu1804:local\"\n network_mode = \"host\"\n pid_mode = \"host\"\n volumes = [\n \"/var/run/docker.sock:/var/run/docker.sock\"\n ]\n privileged = true\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # For more information and examples on the \"resources\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/resources.html\n #\n resources {\n cpu = ${cpu}\n memory = ${mem}\n network {\n port \"ssh\" {\n static = 6022\n }\n port \"ssh2\" {\n static = 6023\n }\n }\n }\n }\n }\n}", + "vars": { + "cpu": "1000", + "datacenters": "yul1", + "group_count": "1", + "job_name": "prod-device-csit-shim", + "mem": "5000" + } + }, + "sensitive_attributes": [] + } + ] + }, + { + "module": "module.vpp_device", + "mode": "managed", + "type": "nomad_job", + "name": "nomad_job_csit_shim", + "provider": "provider[\"registry.terraform.io/hashicorp/nomad\"].yul1", + "instances": [ + { + "schema_version": 0, + "attributes": { + "allocation_ids": [ + "ecfcd9ad-b959-0fa4-c1ec-8b82195830f1", + "190f5699-0d10-7f85-ac68-96927702070b", + "2fbbef45-f00a-1367-08c4-c2239de9e78d", + "dd57bc83-2229-d242-1caf-b743f186e7a2" + ], + "datacenters": [ + "yul1" + ], + "deployment_id": "", + "deployment_status": "", + "deregister_on_destroy": true, + "deregister_on_id_change": true, + "detach": false, + "id": "prod-device-csit-shim", + "jobspec": "job \"prod-device-csit-shim\" {\n # The \"region\" parameter specifies the region in which to execute the job.\n # If omitted, this inherits the default region name of \"global\".\n # region = \"global\"\n #\n # The \"datacenters\" parameter specifies the list of datacenters which should\n # be considered when placing this task. This must be provided.\n datacenters = \"yul1\"\n\n # The \"type\" parameter controls the type of job, which impacts the scheduler's\n # decision on placement. This configuration is optional and defaults to\n # \"service\". For a full list of job types and their differences, please see\n # the online documentation.\n #\n # For more information, please see the online documentation at:\n #\n # https://www.nomadproject.io/docs/jobspec/schedulers.html\n #\n type = \"system\"\n\n # The \"group\" stanza defines a series of tasks that should be co-located on\n # the same Nomad client. Any task within a group will be placed on the same\n # client.\n #\n # For more information and examples on the \"group\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/group.html\n #\n group \"prod-group1-csit-shim-amd\" {\n # The \"count\" parameter specifies the number of the task groups that should\n # be running under this group. This value must be non-negative and defaults\n # to 1.\n count = 1\n\n constraint {\n attribute = \"${node.class}\"\n value = \"csit\"\n }\n\n restart {\n interval = \"1m\"\n attempts = 3\n delay = \"15s\"\n mode = \"delay\"\n }\n\n # The \"task\" stanza creates an individual unit of work, such as a Docker\n # container, web application, or batch processing.\n #\n # For more information and examples on the \"task\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/task.html\n #\n task \"prod-task1-csit-shim-amd\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"docker\"\n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n image = \"csit_shim-ubuntu1804:local\"\n network_mode = \"host\"\n pid_mode = \"host\"\n volumes = [\n \"/var/run/docker.sock:/var/run/docker.sock\"\n ]\n privileged = true\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # For more information and examples on the \"resources\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/resources.html\n #\n resources {\n cpu = 1000\n memory = 5000\n network {\n port \"ssh\" {\n static = 6022\n }\n port \"ssh2\" {\n static = 6023\n }\n }\n }\n }\n }\n\n group \"prod-group1-csit-shim-arm\" {\n # The \"count\" parameter specifies the number of the task groups that should\n # be running under this group. This value must be non-negative and defaults\n # to 1.\n count = 1\n\n constraint {\n attribute = \"${node.class}\"\n value = \"csitarm\"\n }\n\n restart {\n interval = \"1m\"\n attempts = 3\n delay = \"15s\"\n mode = \"delay\"\n }\n\n # The \"task\" stanza creates an individual unit of work, such as a Docker\n # container, web application, or batch processing.\n #\n # For more information and examples on the \"task\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/task.html\n #\n task \"prod-task1-csit-shim-arm\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"docker\"\n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n image = \"csit_shim-ubuntu1804:local\"\n network_mode = \"host\"\n pid_mode = \"host\"\n volumes = [\n \"/var/run/docker.sock:/var/run/docker.sock\"\n ]\n privileged = true\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # For more information and examples on the \"resources\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/resources.html\n #\n resources {\n cpu = 1000\n memory = 5000\n network {\n port \"ssh\" {\n static = 6022\n }\n port \"ssh2\" {\n static = 6023\n }\n }\n }\n }\n }\n}", + "json": null, + "modify_index": "7077736", + "name": "prod-device-csit-shim", + "namespace": "default", + "policy_override": null, + "purge_on_destroy": null, + "region": "global", + "task_groups": [ + { + "count": 1, + "meta": {}, + "name": "prod-group1-csit-shim-amd", + "task": [ + { + "driver": "docker", + "meta": {}, + "name": "prod-task1-csit-shim-amd", + "volume_mounts": [] + } + ], + "volumes": [] + }, + { + "count": 1, + "meta": {}, + "name": "prod-group1-csit-shim-arm", + "task": [ + { + "driver": "docker", + "meta": {}, + "name": "prod-task1-csit-shim-arm", + "volume_mounts": [] + } + ], + "volumes": [] + } + ], + "type": "system" + }, + "sensitive_attributes": [], + "private": "bnVsbA==", + "dependencies": [ + "module.vpp_device.data.template_file.nomad_job_csit_shim" + ] + } + ] } ] } |