From 0bbb81c4fd1afdee6eb23ba4d49171d8dced6b19 Mon Sep 17 00:00:00 2001 From: Peter Mikus Date: Wed, 9 Feb 2022 09:58:09 +0100 Subject: feat(terraform): Refactor Alertmanager - prepare for ETL Signed-off-by: Peter Mikus Change-Id: I8931f76f78b5acee39716398b92e4b107d399773 --- .../alertmanager/conf/nomad/alertmanager.hcl | 385 --------------------- .../alertmanager/conf/nomad/alertmanager.hcl.tftpl | 380 ++++++++++++++++++++ .../1n_nmd/alertmanager/fdio/main.tf | 14 + .../1n_nmd/alertmanager/fdio/providers.tf | 13 + .../1n_nmd/alertmanager/fdio/variables.tf | 47 +++ .../1n_nmd/alertmanager/fdio/versions.tf | 17 + fdio.infra.terraform/1n_nmd/alertmanager/main.tf | 70 ++-- .../1n_nmd/alertmanager/variables.tf | 131 +++++-- .../1n_nmd/alertmanager/versions.tf | 10 +- fdio.infra.terraform/1n_nmd/main.tf | 30 -- 10 files changed, 606 insertions(+), 491 deletions(-) delete mode 100644 fdio.infra.terraform/1n_nmd/alertmanager/conf/nomad/alertmanager.hcl create mode 100644 fdio.infra.terraform/1n_nmd/alertmanager/conf/nomad/alertmanager.hcl.tftpl create mode 100644 fdio.infra.terraform/1n_nmd/alertmanager/fdio/main.tf create mode 100644 fdio.infra.terraform/1n_nmd/alertmanager/fdio/providers.tf create mode 100644 fdio.infra.terraform/1n_nmd/alertmanager/fdio/variables.tf create mode 100644 fdio.infra.terraform/1n_nmd/alertmanager/fdio/versions.tf (limited to 'fdio.infra.terraform/1n_nmd') diff --git a/fdio.infra.terraform/1n_nmd/alertmanager/conf/nomad/alertmanager.hcl b/fdio.infra.terraform/1n_nmd/alertmanager/conf/nomad/alertmanager.hcl deleted file mode 100644 index ab92761ac2..0000000000 --- a/fdio.infra.terraform/1n_nmd/alertmanager/conf/nomad/alertmanager.hcl +++ /dev/null @@ -1,385 +0,0 @@ -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 reschedule stanza specifies the group's rescheduling strategy. If - # specified at the job level, the configuration will apply to all groups - # within the job. If the reschedule stanza is present on both the job and the - # group, they are merged with the group stanza taking the highest precedence - # and then the job. - reschedule { - delay = "30s" - delay_function = "constant" - unlimited = true - } - - # 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 restart stanza configures a tasks's behavior on task failure. Restarts - # happen on the client that is running the task. - # - # https://www.nomadproject.io/docs/job-specification/restart - # - restart { - interval = "30m" - attempts = 40 - delay = "15s" - mode = "delay" - } - - # 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 = "$${attr.cpu.arch}" - operator = "!=" - value = "arm64" - } - - constraint { - attribute = "$${node.class}" - value = "builder" - } - - # 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 = < ] -# -# # Certificate and key files for client cert authentication to the server. -# cert_file: -# key_file: -# -# # ServerName extension to indicate the name of the server. -# # http://tools.ietf.org/html/rfc4366#section-3.1 -# server_name: -# -# # Disable validation of the server certificate. -# insecure_skip_verify: true - -# The root route on which each incoming alert enters. -route: - receiver: '${slack_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'] - - # 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: - - match_re: - alertname: JenkinsJob.* - receiver: ${slack_jenkins_receiver} - routes: - - match: - severity: critical - receiver: '${slack_jenkins_receiver}' - - - match_re: - service: .* - receiver: ${slack_default_receiver} - routes: - - match: - severity: critical - receiver: '${slack_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' - equal: ['alertname', 'instance'] - -receivers: -- name: '${slack_jenkins_receiver}' - slack_configs: - - api_url: 'https://hooks.slack.com/services/${slack_jenkins_api_key}' - channel: '#${slack_jenkins_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 }}="{{ $label.Value -}}" - {{- end }} - {{- end -}} - ) - {{- end }} - text: >- - {{ range .Alerts -}} - *Alert:* {{ .Annotations.summary }}{{ if .Labels.severity }} - `{{ .Labels.severity }}`{{ end }} - - *Description:* {{ .Annotations.description }} - - *Details:* - {{ range .Labels.SortedPairs }} • *{{ .Name }}:* `{{ .Value }}` - {{ end }} - {{ end }} - -- name: '${slack_default_receiver}' - slack_configs: - - api_url: 'https://hooks.slack.com/services/${slack_default_api_key}' - channel: '#${slack_default_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/fdio.infra.terraform/1n_nmd/alertmanager/conf/nomad/alertmanager.hcl.tftpl b/fdio.infra.terraform/1n_nmd/alertmanager/conf/nomad/alertmanager.hcl.tftpl new file mode 100644 index 0000000000..d1bb8e85cd --- /dev/null +++ b/fdio.infra.terraform/1n_nmd/alertmanager/conf/nomad/alertmanager.hcl.tftpl @@ -0,0 +1,380 @@ +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 = "${region}" + + # 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 = "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 = ${max_parallel} + + 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 = ${canary} + + # 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 = ${auto_promote} + + # 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 = ${auto_revert} +%{ endif } + } + + # All groups in this job should be scheduled on different hosts. + constraint { + operator = "distinct_hosts" + value = "true" + } + + # 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 "${job_name}-group-1" { + # 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. The key of the stanza is the name of the volume + # as it will be exposed to task configuration. + # + # https://www.nomadproject.io/docs/job-specification/volume + %{ if use_host_volume } + volume "${job_name}-volume-1" { + type = "host" + read_only = false + source = "${volume_source}" + } + %{ endif } + + # The restart stanza configures a tasks's behavior on task failure. Restarts + # happen on the client that is running the task. + # + # https://www.nomadproject.io/docs/job-specification/restart + # + restart { + interval = "30m" + attempts = 40 + delay = "15s" + mode = "delay" + } + + # 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" + } + + constraint { + attribute = "$${node.class}" + value = "builder" + } + + # 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 "${service_name}" { + static = ${port} + to = ${port} + } + } + + # 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 "${job_name}-task-1" { + # The "driver" parameter specifies the task driver that should be used to + # run the task. + driver = "exec" + + %{ if use_host_volume } + volume_mount { + volume = "${job_name}-volume-1" + destination = "${volume_destination}" + 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/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. + # + # 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. + # + # https://www.nomadproject.io/docs/job-specification/template + # + template { + change_mode = "noop" + change_signal = "SIGINT" + destination = "secrets/alertmanager.yml" + left_delimiter = "{{{" + right_delimiter = "}}}" + data = < ] +# +# # Certificate and key files for client cert authentication to the server. +# cert_file: +# key_file: +# +# # ServerName extension to indicate the name of the server. +# # http://tools.ietf.org/html/rfc4366#section-3.1 +# server_name: +# +# # Disable validation of the server certificate. +# insecure_skip_verify: true + +# The root route on which each incoming alert enters. +route: + receiver: '${slack_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'] + + # 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: + - match_re: + alertname: JenkinsJob.* + receiver: ${slack_jenkins_receiver} + routes: + - match: + severity: critical + receiver: '${slack_jenkins_receiver}' + + - match_re: + service: .* + receiver: ${slack_default_receiver} + routes: + - match: + severity: critical + receiver: '${slack_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' + equal: ['alertname', 'instance'] + +receivers: +- name: '${slack_jenkins_receiver}' + slack_configs: + - api_url: 'https://hooks.slack.com/services/${slack_jenkins_api_key}' + channel: '#${slack_jenkins_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 }} + +- name: '${slack_default_receiver}' + slack_configs: + - api_url: 'https://hooks.slack.com/services/${slack_default_api_key}' + channel: '#${slack_default_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. + # + # https://www.nomadproject.io/docs/job-specification/resources + # + resources { + cpu = ${cpu} + memory = ${memory} + } + } + } +} diff --git a/fdio.infra.terraform/1n_nmd/alertmanager/fdio/main.tf b/fdio.infra.terraform/1n_nmd/alertmanager/fdio/main.tf new file mode 100644 index 0000000000..745e450a8c --- /dev/null +++ b/fdio.infra.terraform/1n_nmd/alertmanager/fdio/main.tf @@ -0,0 +1,14 @@ +module "alertmanager" { + providers = { + nomad = nomad.yul1 + } + source = "../" + + # alertmanager + datacenters = ["yul1"] + slack_jenkins_api_key = "TE07RD1V1/B01U1NV9HV3/hKZXJJ74g2JcISq4K3QC1eG9" + slack_jenkins_channel = "fdio-jobs-monitoring" + slack_default_api_key = "TE07RD1V1/B01UUK23B6C/hZTcCu42FUv8d6rtirHtcYIi" + slack_default_channel = "fdio-infra-monitoring" + am_version = "0.23.0" +} \ No newline at end of file diff --git a/fdio.infra.terraform/1n_nmd/alertmanager/fdio/providers.tf b/fdio.infra.terraform/1n_nmd/alertmanager/fdio/providers.tf new file mode 100644 index 0000000000..42a6a45ce0 --- /dev/null +++ b/fdio.infra.terraform/1n_nmd/alertmanager/fdio/providers.tf @@ -0,0 +1,13 @@ +provider "nomad" { + address = var.nomad_provider_address + alias = "yul1" + # ca_file = var.nomad_provider_ca_file + # cert_file = var.nomad_provider_cert_file + # key_file = var.nomad_provider_key_file +} + +provider "vault" { + address = var.vault_provider_address + skip_tls_verify = var.vault_provider_skip_tls_verify + token = var.vault_provider_token +} \ No newline at end of file diff --git a/fdio.infra.terraform/1n_nmd/alertmanager/fdio/variables.tf b/fdio.infra.terraform/1n_nmd/alertmanager/fdio/variables.tf new file mode 100644 index 0000000000..7d5be09d21 --- /dev/null +++ b/fdio.infra.terraform/1n_nmd/alertmanager/fdio/variables.tf @@ -0,0 +1,47 @@ +variable "nomad_acl" { + description = "Nomad ACLs enabled/disabled." + type = bool + default = false +} + +variable "nomad_provider_address" { + description = "FD.io Nomad cluster address." + type = string + default = "http://10.32.8.14:4646" +} + +variable "nomad_provider_ca_file" { + description = "A local file path to a PEM-encoded certificate authority." + type = string + default = "/etc/nomad.d/ssl/nomad-ca.pem" +} + +variable "nomad_provider_cert_file" { + description = "A local file path to a PEM-encoded certificate." + type = string + default = "/etc/nomad.d/ssl/nomad-cli.pem" +} + +variable "nomad_provider_key_file" { + description = "A local file path to a PEM-encoded private key." + type = string + default = "/etc/nomad.d/ssl/nomad-cli-key.pem" +} + +variable "vault_provider_address" { + description = "Vault cluster address." + type = string + default = "http://10.30.51.28:8200" +} + +variable "vault_provider_skip_tls_verify" { + description = "Verification of the Vault server's TLS certificate." + type = bool + default = false +} + +variable "vault_provider_token" { + description = "Vault root token." + type = string + sensitive = true +} \ No newline at end of file diff --git a/fdio.infra.terraform/1n_nmd/alertmanager/fdio/versions.tf b/fdio.infra.terraform/1n_nmd/alertmanager/fdio/versions.tf new file mode 100644 index 0000000000..385c5c3f18 --- /dev/null +++ b/fdio.infra.terraform/1n_nmd/alertmanager/fdio/versions.tf @@ -0,0 +1,17 @@ +terraform { + backend "consul" { + address = "10.32.8.14:8500" + scheme = "http" + path = "terraform/alertmanager" + } + required_providers { + nomad = { + source = "hashicorp/nomad" + version = ">= 1.4.16" + } + vault = { + version = ">= 3.2.1" + } + } + required_version = ">= 1.1.4" +} \ No newline at end of file diff --git a/fdio.infra.terraform/1n_nmd/alertmanager/main.tf b/fdio.infra.terraform/1n_nmd/alertmanager/main.tf index b7ab5dce92..e8a1389150 100644 --- a/fdio.infra.terraform/1n_nmd/alertmanager/main.tf +++ b/fdio.infra.terraform/1n_nmd/alertmanager/main.tf @@ -1,40 +1,48 @@ locals { - datacenters = join(",", var.nomad_datacenters) - - alertmanager_url = join("", + datacenters = join(",", var.datacenters) + url = join("", [ "https://github.com", "/prometheus/alertmanager/releases/download/", - "v${var.alertmanager_version}/", - "alertmanager-${var.alertmanager_version}.linux-amd64.tar.gz" + "v${var.am_version}/", + "alertmanager-${var.am_version}.linux-amd64.tar.gz" ] ) } -data "template_file" "nomad_job_alertmanager" { - template = file("${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_jenkins_api_key = var.alertmanager_slack_jenkins_api_key - slack_jenkins_channel = var.alertmanager_slack_jenkins_channel - slack_jenkins_receiver = var.alertmanager_slack_jenkins_receiver - slack_default_api_key = var.alertmanager_slack_default_api_key - slack_default_channel = var.alertmanager_slack_default_channel - slack_default_receiver = var.alertmanager_slack_default_receiver - } -} - resource "nomad_job" "nomad_job_alertmanager" { - jobspec = data.template_file.nomad_job_alertmanager.rendered - detach = false -} \ No newline at end of file + jobspec = templatefile( + "${path.module}/conf/nomad/alertmanager.hcl.tftpl", + { + auto_promote = var.auto_promote, + auto_revert = var.auto_revert, + canary = var.canary, + cpu = var.cpu, + datacenters = local.datacenters, + group_count = var.group_count, + job_name = var.job_name, + max_parallel = var.max_parallel, + memory = var.memory + port = var.port, + region = var.region, + service_name = var.service_name, + slack_jenkins_api_key = var.slack_jenkins_api_key, + slack_jenkins_channel = var.slack_jenkins_channel, + slack_jenkins_receiver = var.slack_jenkins_receiver, + slack_default_api_key = var.slack_default_api_key, + slack_default_channel = var.slack_default_channel, + slack_default_receiver = var.slack_default_receiver, + url = local.url, + use_canary = var.use_canary, + use_host_volume = var.use_host_volume, + use_vault_provider = var.vault_secret.use_vault_provider, + vault_kv_policy_name = var.vault_secret.vault_kv_policy_name, + vault_kv_path = var.vault_secret.vault_kv_path, + vault_kv_field_access_key = var.vault_secret.vault_kv_field_access_key, + vault_kv_field_secret_key = var.vault_secret.vault_kv_field_secret_key, + version = var.am_version, + volume_destination = var.volume_destination, + volume_source = var.volume_source + }) + detach = false +} diff --git a/fdio.infra.terraform/1n_nmd/alertmanager/variables.tf b/fdio.infra.terraform/1n_nmd/alertmanager/variables.tf index e24ceb64c6..e452598fa6 100644 --- a/fdio.infra.terraform/1n_nmd/alertmanager/variables.tf +++ b/fdio.infra.terraform/1n_nmd/alertmanager/variables.tf @@ -1,43 +1,102 @@ # Nomad -variable "nomad_datacenters" { - description = "Nomad data centers" +variable "datacenters" { + description = "Specifies the list of DCs to be considered placing this task" type = list(string) default = ["dc1"] } -# Alermanager -variable "alertmanager_job_name" { - description = "Job name" +variable "region" { + description = "Specifies the list of DCs to be considered placing this task" type = string - default = "alertmanager" + default = "global" +} + +variable "volume_source" { + description = "The name of the volume to request" + type = string + default = "persistence" +} + +# Alertmanager +variable "am_version" { + description = "Alertmanager version" + type = string + default = "0.21.0" +} + +variable "auto_promote" { + description = "Specifies if the job should auto-promote to the canary version" + type = bool + default = true +} + +variable "auto_revert" { + description = "Specifies if the job should auto-revert to the last stable job" + type = bool + default = true } -variable "alertmanager_group_count" { - description = "Number of group instances" +variable "canary" { + description = "Equal to the count of the task group allows blue/green depl." type = number default = 1 } -variable "alertmanager_service_name" { - description = "Service name" +variable "cpu" { + description = "CPU allocation" + type = number + default = 1000 +} + +variable "group_count" { + description = "Specifies the number of the task groups running under this one" + type = number + default = 1 +} + +variable "job_name" { + description = "Specifies a name for the job" type = string default = "alertmanager" } -variable "alertmanager_version" { - description = "Version" +variable "max_parallel" { + description = "Specifies the maximum number of updates to perform in parallel" + type = number + default = 1 +} + +variable "memory" { + description = "Specifies the memory required in MB" + type = number + default = 1024 +} + +variable "port" { + description = "Specifies the static TCP/UDP port to allocate" + type = number + default = 9093 +} + +variable "service_name" { + description = "Specifies the name this service will be advertised in Consul" type = string - default = "0.21.0" + default = "alertmanager" } -variable "alertmanager_use_canary" { +variable "use_canary" { description = "Uses canary deployment" type = bool + default = true +} + +variable "use_host_volume" { + description = "Use Nomad host volume feature" + type = bool default = false } -variable "alertmanager_vault_secret" { - description = "Set of properties to be able to fetch secret from vault" +variable "vault_secret" { type = object({ use_vault_provider = bool, vault_kv_policy_name = string, @@ -45,57 +104,53 @@ variable "alertmanager_vault_secret" { vault_kv_field_access_key = string, vault_kv_field_secret_key = string }) + description = "Set of properties to be able to fetch secret from vault." + default = { + use_vault_provider = false + vault_kv_policy_name = "kv" + vault_kv_path = "secret/data/alertmanager" + vault_kv_field_access_key = "access_key" + vault_kv_field_secret_key = "secret_key" + } } -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 "volume_destination" { + description = "Specifies where the volume should be mounted inside the task" + type = string + default = "/data/" } -variable "alertmanager_slack_jenkins_api_key" { +variable "slack_jenkins_api_key" { description = "Alertmanager jenkins slack API key" type = string default = "XXXXXXXXX/XXXXXXXXXXX/XXXXXXXXXXXXXXXXXXXXXXXX" } -variable "alertmanager_slack_jenkins_receiver" { +variable "slack_jenkins_receiver" { description = "Alertmanager jenkins slack receiver" type = string default = "jenkins-slack-receiver" } -variable "alertmanager_slack_jenkins_channel" { +variable "slack_jenkins_channel" { description = "Alertmanager jenkins slack channel" type = string default = "jenkins-channel" } -variable "alertmanager_slack_default_api_key" { +variable "slack_default_api_key" { description = "Alertmanager default slack API key" type = string default = "XXXXXXXXX/XXXXXXXXXXX/XXXXXXXXXXXXXXXXXXXXXXXX" } -variable "alertmanager_slack_default_receiver" { +variable "slack_default_receiver" { description = "Alertmanager default slack receiver" type = string default = "default-slack-receiver" } -variable "alertmanager_slack_default_channel" { +variable "slack_default_channel" { description = "Alertmanager default slack channel" type = string default = "default-channel" diff --git a/fdio.infra.terraform/1n_nmd/alertmanager/versions.tf b/fdio.infra.terraform/1n_nmd/alertmanager/versions.tf index b80610a525..5f283ed4ea 100644 --- a/fdio.infra.terraform/1n_nmd/alertmanager/versions.tf +++ b/fdio.infra.terraform/1n_nmd/alertmanager/versions.tf @@ -2,12 +2,8 @@ terraform { required_providers { nomad = { source = "hashicorp/nomad" - version = "~> 1.4.15" - } - template = { - source = "hashicorp/template" - version = "~> 2.2.0" + version = ">= 1.4.16" } } - required_version = ">= 1.0.3" -} + required_version = ">= 1.1.4" +} \ No newline at end of file diff --git a/fdio.infra.terraform/1n_nmd/main.tf b/fdio.infra.terraform/1n_nmd/main.tf index ed4f2b5ac3..7cdd245b7a 100644 --- a/fdio.infra.terraform/1n_nmd/main.tf +++ b/fdio.infra.terraform/1n_nmd/main.tf @@ -4,36 +4,6 @@ # 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_jenkins_api_key = "TE07RD1V1/B01U1NV9HV3/hKZXJJ74g2JcISq4K3QC1eG9" - alertmanager_slack_jenkins_channel = "fdio-jobs-monitoring" - alertmanager_slack_default_api_key = "TE07RD1V1/B01UUK23B6C/hZTcCu42FUv8d6rtirHtcYIi" - alertmanager_slack_default_channel = "fdio-infra-monitoring" -} - module "grafana" { source = "./grafana" providers = { -- cgit 1.2.3-korg