diff options
author | pmikus <pmikus@cisco.com> | 2021-11-08 12:50:51 +0100 |
---|---|---|
committer | Peter Mikus <pmikus@cisco.com> | 2021-11-11 07:25:59 +0000 |
commit | db7290d702450430e0d58e23f91e34407e08b41c (patch) | |
tree | 0350486f05197be82d57755df0dc17b4a71acc97 | |
parent | 5390d5cedf42ecc0d589d79a0a9d1b346ebb5c11 (diff) |
feat(Terraform): Minio S3 gateway proxy
Signed-off-by: pmikus <pmikus@cisco.com>
Change-Id: I9543a856a2e5791b61accd7a183bc5a2bf2e6187
16 files changed, 661 insertions, 1345 deletions
diff --git a/fdio.infra.terraform/1n_nmd/alertmanager/providers.tf b/fdio.infra.terraform/1n_nmd/alertmanager/versions.tf index 1399201d21..b80610a525 100644 --- a/fdio.infra.terraform/1n_nmd/alertmanager/providers.tf +++ b/fdio.infra.terraform/1n_nmd/alertmanager/versions.tf @@ -2,11 +2,11 @@ terraform { required_providers { nomad = { source = "hashicorp/nomad" - version = "~> 1.4.9" + version = "~> 1.4.15" } template = { source = "hashicorp/template" - version = "~> 2.1.2" + version = "~> 2.2.0" } } required_version = ">= 1.0.3" diff --git a/fdio.infra.terraform/1n_nmd/grafana/providers.tf b/fdio.infra.terraform/1n_nmd/grafana/versions.tf index 1399201d21..b80610a525 100644 --- a/fdio.infra.terraform/1n_nmd/grafana/providers.tf +++ b/fdio.infra.terraform/1n_nmd/grafana/versions.tf @@ -2,11 +2,11 @@ terraform { required_providers { nomad = { source = "hashicorp/nomad" - version = "~> 1.4.9" + version = "~> 1.4.15" } template = { source = "hashicorp/template" - version = "~> 2.1.2" + version = "~> 2.2.0" } } required_version = ">= 1.0.3" diff --git a/fdio.infra.terraform/1n_nmd/main.tf b/fdio.infra.terraform/1n_nmd/main.tf index a8a1bb9315..ed4f2b5ac3 100644 --- a/fdio.infra.terraform/1n_nmd/main.tf +++ b/fdio.infra.terraform/1n_nmd/main.tf @@ -60,62 +60,91 @@ module "grafana" { grafana_port = 3000 } -module "minio" { - source = "./minio" +#module "minio" { +# source = "./minio" +# providers = { +# nomad = nomad.yul1 +# } +# +# # nomad +# 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.2021-07-27T02-40-15Z" +# 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_buckets = ["logs.fd.io"] +#} + +data "vault_generic_secret" "minio_creds" { + path = "kv/secret/data/minio" +} + +module "minio_s3_gateway" { + source = "./minio_s3_gateway" providers = { nomad = nomad.yul1 } # nomad - nomad_datacenters = ["yul1"] - nomad_host_volume = "prod-volume-data1-1" + datacenters = ["yul1"] + volume_source = "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.2021-07-27T02-40-15Z" - 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 client - mc_job_name = "prod-mc" - mc_container_image = "minio/mc:RELEASE.2021-07-27T02-40-15Z" - 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" + job_name = "minio-s3-gateway" + group_count = 4 + service_name = "minio" + mode = "gateway" + port_base = 9001 + port_console = 9002 + image = "minio/minio:latest" + access_key = data.vault_generic_secret.minio_creds.data["access_key"] + secret_key = data.vault_generic_secret.minio_creds.data["secret_key"] + volume_destination = "/data/" + use_host_volume = true + use_canary = true + envs = [ + "MINIO_BROWSER=\"off\"", + "MINIO_CACHE=\"on\"", + "MINIO_CACHE_DRIVES=\"/data/s3_cache1\"", + "MINIO_CACHE_EXCLUDE=\"\"", + "MINIO_CACHE_QUOTA=80", + "MINIO_CACHE_AFTER=1", + "MINIO_CACHE_WATERMARK_LOW=70", + "MINIO_CACHE_WATERMARK_HIGH=90" ] - minio_buckets = ["logs.fd.io", "docs.fd.io"] } -module "nginx" { - source = "./nginx" - providers = { - nomad = nomad.yul1 - } - - # nomad - nomad_datacenters = ["yul1"] - nomad_host_volume = "prod-volume-data1-1" - - # nginx - nginx_job_name = "prod-nginx" - nginx_use_host_volume = true -} +#module "nginx" { +# source = "./nginx" +# providers = { +# nomad = nomad.yul1 +# } +# +# # nomad +# nomad_datacenters = ["yul1"] +# nomad_host_volume = "prod-volume-data1-1" +# +# # nginx +# nginx_job_name = "prod-nginx" +# nginx_use_host_volume = true +#} module "prometheus" { source = "./prometheus" diff --git a/fdio.infra.terraform/1n_nmd/minio_s3_gateway/conf/nomad/minio.hcl b/fdio.infra.terraform/1n_nmd/minio_s3_gateway/conf/nomad/minio.hcl new file mode 100644 index 0000000000..6210040b0c --- /dev/null +++ b/fdio.infra.terraform/1n_nmd/minio_s3_gateway/conf/nomad/minio.hcl @@ -0,0 +1,246 @@ +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 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 "base" { + static = ${port_base} + to = ${port_base} + } + port "console" { + static = ${port_console} + to = ${port_console} + } + } + + # The "task" stanza creates an individual unit of work, such as a Docker + # container, web application, or batch processing. + # + # https://www.nomadproject.io/docs/job-specification/task.html + # + task "${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 = "${vault_kv_policy_name}" + } + %{ endif } + + # The "config" stanza specifies the driver configuration, which is passed + # directly to the driver to start the task. The details of configurations + # are specific to each driver, so please see specific driver + # documentation for more information. + config { + args = [ + "${mode}", "s3", + "-address", ":${port_base}", + "-console-address", ":${port_console}" + ] + command = "local/minio" + } + + # 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 = "https://dl.min.io/server/minio/release/linux-amd64/minio" + } + + # The env stanza configures a list of environment variables to populate + # the task's environment before starting. + env { +%{ if use_vault_provider } +{{ with secret "${vault_kv_path}" }} + MINIO_ROOT_USER = "{{ .Data.data.${vault_kv_field_access_key} }}" + MINIO_ROOT_PASSWORD = "{{ .Data.data.${vault_kv_field_secret_key} }}" +{{ end }} +%{ else } + MINIO_ROOT_USER = "${access_key}" + MINIO_ROOT_PASSWORD = "${secret_key}" + AWS_ACCESS_KEY_ID = "${access_key}" + AWS_SECRET_ACCESS_KEY = "${secret_key}" +%{ endif } + ${ envs } + } + + # The service stanza instructs Nomad to register a service with Consul. + # + # https://www.nomadproject.io/docs/job-specification/service + # + service { + name = "${service_name}" + port = "base" + tags = [ "${service_name}$${NOMAD_ALLOC_INDEX}" ] + check { + name = "Min.io Server HTTP Check Live" + type = "http" + port = "base" + protocol = "http" + method = "GET" + path = "/minio/health/live" + interval = "10s" + timeout = "2s" + } + check { + name = "Min.io Server HTTP Check Ready" + type = "http" + port = "base" + protocol = "http" + method = "GET" + path = "/minio/health/ready" + 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/minio_s3_gateway/main.tf b/fdio.infra.terraform/1n_nmd/minio_s3_gateway/main.tf new file mode 100644 index 0000000000..2ae3cac9c2 --- /dev/null +++ b/fdio.infra.terraform/1n_nmd/minio_s3_gateway/main.tf @@ -0,0 +1,51 @@ +locals { + datacenters = join(",", var.datacenters) + envs = join("\n", concat([], var.envs)) + upstreams = jsonencode(var.upstreams) +} + +data "template_file" "nomad_job_minio" { + template = file("${path.module}/conf/nomad/minio.hcl") + vars = { + access_key = var.access_key + auto_promote = var.auto_promote + auto_revert = var.auto_revert + canary = var.canary + cpu = var.cpu + cpu_proxy = var.resource_proxy.cpu + datacenters = local.datacenters + envs = local.envs + group_count = var.group_count + host = var.host + image = var.image + job_name = var.job_name + max_parallel = var.max_parallel + memory = var.memory + memory_proxy = var.resource_proxy.memory + mode = var.mode + port_base = var.port_base + port_console = var.port_console + region = var.region + secret_key = var.secret_key + service_name = var.service_name + use_canary = var.use_canary + use_host_volume = var.use_host_volume + upstreams = local.upstreams + use_vault_kms = var.kms_variables.use_vault_kms + use_vault_provider = var.vault_secret.use_vault_provider + vault_address = var.kms_variables.vault_address + vault_kms_approle_kv = var.kms_variables.vault_kms_approle_kv + vault_kms_key_name = var.kms_variables.vault_kms_key_name + 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 + volume_destination = var.volume_destination + volume_source = var.volume_source + } +} + +resource "nomad_job" "nomad_job_minio" { + jobspec = data.template_file.nomad_job_minio.rendered + detach = false +} diff --git a/fdio.infra.terraform/1n_nmd/minio_s3_gateway/variables.tf b/fdio.infra.terraform/1n_nmd/minio_s3_gateway/variables.tf new file mode 100644 index 0000000000..b9f790b01f --- /dev/null +++ b/fdio.infra.terraform/1n_nmd/minio_s3_gateway/variables.tf @@ -0,0 +1,199 @@ +# Nomad + +variable "datacenters" { + description = "Specifies the list of DCs to be considered placing this task" + type = list(string) + default = ["dc1"] +} + +variable "region" { + description = "Specifies the list of DCs to be considered placing this task" + type = string + default = "global" +} + +variable "volume_source" { + description = "The name of the volume to request" + type = string + default = "persistence" +} + +# Minio +variable "access_key" { + description = "Minio access key" + type = string + default = "minio" +} + +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 "canary" { + description = "Equal to the count of the task group allows blue/green depl." + type = number + default = 1 +} + +variable "cpu" { + description = "Specifies the CPU required to run this task in MHz" + type = number + default = 1000 +} + +variable "envs" { + description = "Minio environment variables" + type = list(string) + default = [] +} + +variable "group_count" { + description = "Specifies the number of the task groups running under this one" + type = number + default = 1 +} + +variable "host" { + description = "Minio host" + type = string + default = "127.0.0.1" +} + +variable "image" { + description = "The Docker image to run" + type = string + default = "minio/minio:latest" +} + +variable "job_name" { + description = "Specifies a name for the job" + type = string + default = "minio" +} + +variable "kms_variables" { + type = object({ + use_vault_kms = string + vault_address = string, + vault_kms_approle_kv = string, + vault_kms_key_name = string + }) + description = "Set of properties to be able to transit secrets in vault" + default = { + use_vault_kms = false + vault_address = "", + vault_kms_approle_kv = "", + vault_kms_key_name = "" + } +} + +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 "mode" { + description = "Specifies the Minio mode" + type = string + default = "server" +} + +variable "port_base" { + description = "Specifies the static TCP/UDP port to allocate" + type = number + default = 9000 +} + +variable "port_console" { + description = "Specifies the static TCP/UDP port to allocate" + type = number + default = 9001 +} + +variable "resource_proxy" { + description = "Minio proxy resources" + type = object({ + cpu = number, + memory = number + }) + default = { + cpu = 2000, + memory = 1024 + } + validation { + condition = var.resource_proxy.cpu >= 200 && var.resource_proxy.memory >= 128 + error_message = "Proxy resource must be at least: cpu=200, memory=128." + } +} + +variable "service_name" { + description = "Specifies the name this service will be advertised in Consul" + type = string + default = "AKIAVWHHCAXZJUHH7QFN" +} + +variable "secret_key" { + description = "Minio secret key" + type = string + default = "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" +} + +variable "upstreams" { + type = list(object({ + service_name = string, + port = number, + })) + description = "List of upstream services" + default = [] +} + +variable "use_canary" { + description = "Uses canary deployment for Minio" + type = bool + default = false +} + +variable "use_host_volume" { + description = "Use Nomad host volume feature" + type = bool + default = false +} + +variable "vault_secret" { + 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 + }) + 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/minio" + vault_kv_field_access_key = "access_key" + vault_kv_field_secret_key = "secret_key" + } +} + +variable "volume_destination" { + description = "Specifies where the volume should be mounted inside the task" + type = string + default = "/data/" +} diff --git a/fdio.infra.terraform/1n_nmd/prometheus/providers.tf b/fdio.infra.terraform/1n_nmd/minio_s3_gateway/versions.tf index 1399201d21..b80610a525 100644 --- a/fdio.infra.terraform/1n_nmd/prometheus/providers.tf +++ b/fdio.infra.terraform/1n_nmd/minio_s3_gateway/versions.tf @@ -2,11 +2,11 @@ terraform { required_providers { nomad = { source = "hashicorp/nomad" - version = "~> 1.4.9" + version = "~> 1.4.15" } template = { source = "hashicorp/template" - version = "~> 2.1.2" + version = "~> 2.2.0" } } required_version = ">= 1.0.3" diff --git a/fdio.infra.terraform/1n_nmd/prometheus/conf/nomad/prometheus.hcl b/fdio.infra.terraform/1n_nmd/prometheus/conf/nomad/prometheus.hcl index 368a361184..2019aeba96 100644 --- a/fdio.infra.terraform/1n_nmd/prometheus/conf/nomad/prometheus.hcl +++ b/fdio.infra.terraform/1n_nmd/prometheus/conf/nomad/prometheus.hcl @@ -596,6 +596,13 @@ scrape_configs: - server: '{{ env "NOMAD_IP_prometheus" }}:8500' services: [ 'storage' ] metrics_path: /minio/prometheus/metrics + + - job_name: 'Minio Proxy' + bearer_token: eyJhbGciOiJIUzUxMiIsInR5cCI6IkpXVCJ9.eyJleHAiOjQ3OTAwNjE1NDIsImlzcyI6InByb21ldGhldXMiLCJzdWIiOiJBS0lBUTJBSDdZUFBXVDZDV1hYSSJ9.CU9x9j-yO0_Uta5iep6yqNiGQPolrr2608E3lpU6Yg21rIv_eOwS5zqzXaSvrhzkJP9H5kO1Pj6kqjYhbqjN_w + consul_sd_configs: + - server: '{{ env "NOMAD_IP_prometheus" }}:8500' + services: [ 'minio' ] + metrics_path: /minio/v2/metrics/cluster EOH } diff --git a/fdio.infra.terraform/1n_nmd/vpp_device/providers.tf b/fdio.infra.terraform/1n_nmd/prometheus/versions.tf index 1399201d21..b80610a525 100644 --- a/fdio.infra.terraform/1n_nmd/vpp_device/providers.tf +++ b/fdio.infra.terraform/1n_nmd/prometheus/versions.tf @@ -2,11 +2,11 @@ terraform { required_providers { nomad = { source = "hashicorp/nomad" - version = "~> 1.4.9" + version = "~> 1.4.15" } template = { source = "hashicorp/template" - version = "~> 2.1.2" + version = "~> 2.2.0" } } required_version = ">= 1.0.3" diff --git a/fdio.infra.terraform/1n_nmd/providers.tf b/fdio.infra.terraform/1n_nmd/providers.tf index c3b9ec275d..92ddb553e7 100644 --- a/fdio.infra.terraform/1n_nmd/providers.tf +++ b/fdio.infra.terraform/1n_nmd/providers.tf @@ -1,21 +1,13 @@ -terraform { - required_providers { - nomad = { - source = "hashicorp/nomad" - version = "~> 1.4.9" - } - template = { - source = "hashicorp/template" - version = "~> 2.1.2" - } - vault = { - version = ">=2.14.0" - } - } - required_version = ">= 0.13" -} - 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 = "http://10.30.51.28:8200" + skip_tls_verify = true + token = var.token }
\ No newline at end of file diff --git a/fdio.infra.terraform/1n_nmd/terraform.tfstate b/fdio.infra.terraform/1n_nmd/terraform.tfstate deleted file mode 100644 index 701b8a34ae..0000000000 --- a/fdio.infra.terraform/1n_nmd/terraform.tfstate +++ /dev/null @@ -1,631 +0,0 @@ -{ - "version": 4, - "terraform_version": "1.0.4", - "serial": 1192, - "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": "2cd0a107978c5fd503445b71a5ad611daf96b7b57ad1bc15e3cb5c7dee391806", - "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 reschedule stanza specifies the group's rescheduling strategy. If\n # specified at the job level, the configuration will apply to all groups\n # within the job. If the reschedule stanza is present on both the job and the\n # group, they are merged with the group stanza taking the highest precedence\n # and then the job.\n reschedule {\n delay = \"30s\"\n delay_function = \"constant\"\n unlimited = 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\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 restart stanza configures a tasks's behavior on task failure. Restarts\n # happen on the client that is running the task.\n #\n # https://www.nomadproject.io/docs/job-specification/restart\n #\n restart {\n interval = \"30m\"\n attempts = 40\n delay = \"15s\"\n mode = \"delay\"\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 constraint {\n attribute = \"${node.class}\"\n value = \"builder\"\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\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-slack-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']\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 - match_re:\n alertname: JenkinsJob.*\n receiver: jenkins-slack-receiver\n routes:\n - match:\n severity: critical\n receiver: 'jenkins-slack-receiver'\n\n - match_re:\n service: .*\n receiver: default-slack-receiver\n routes:\n - match:\n severity: critical\n receiver: 'default-slack-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 equal: ['alertname', 'instance']\n\nreceivers:\n- name: 'jenkins-slack-receiver'\n slack_configs:\n - api_url: 'TE07RD1V1/B01U1NV9HV3/hKZXJJ74g2JcISq4K3QC1eG9'\n channel: '#fdio-jobs-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 }}\n\n- name: 'default-slack-receiver'\n slack_configs:\n - api_url: 'TE07RD1V1/B01UUK23B6C/hZTcCu42FUv8d6rtirHtcYIi'\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 reschedule stanza specifies the group's rescheduling strategy. If\n # specified at the job level, the configuration will apply to all groups\n # within the job. If the reschedule stanza is present on both the job and the\n # group, they are merged with the group stanza taking the highest precedence\n # and then the job.\n reschedule {\n delay = \"30s\"\n delay_function = \"constant\"\n unlimited = 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\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 restart stanza configures a tasks's behavior on task failure. Restarts\n # happen on the client that is running the task.\n #\n # https://www.nomadproject.io/docs/job-specification/restart\n #\n restart {\n interval = \"30m\"\n attempts = 40\n delay = \"15s\"\n mode = \"delay\"\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 constraint {\n attribute = \"$${node.class}\"\n value = \"builder\"\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\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: '${slack_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']\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 - match_re:\n alertname: JenkinsJob.*\n receiver: ${slack_jenkins_receiver}\n routes:\n - match:\n severity: critical\n receiver: '${slack_jenkins_receiver}'\n\n - match_re:\n service: .*\n receiver: ${slack_default_receiver}\n routes:\n - match:\n severity: critical\n receiver: '${slack_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 equal: ['alertname', 'instance']\n\nreceivers:\n- name: '${slack_jenkins_receiver}'\n slack_configs:\n - api_url: '${slack_jenkins_api_key}'\n channel: '#${slack_jenkins_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 }}\n\n- name: '${slack_default_receiver}'\n slack_configs:\n - api_url: '${slack_default_api_key}'\n channel: '#${slack_default_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", - "group_count": "1", - "job_name": "prod-alertmanager", - "mem": "1024", - "port": "9093", - "service_name": "alertmanager", - "slack_default_api_key": "TE07RD1V1/B01UUK23B6C/hZTcCu42FUv8d6rtirHtcYIi", - "slack_default_channel": "fdio-infra-monitoring", - "slack_default_receiver": "default-slack-receiver", - "slack_jenkins_api_key": "TE07RD1V1/B01U1NV9HV3/hKZXJJ74g2JcISq4K3QC1eG9", - "slack_jenkins_channel": "fdio-jobs-monitoring", - "slack_jenkins_receiver": "jenkins-slack-receiver", - "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": [ - "74fdbd88-0e34-f990-3181-0413a373dcb2", - "412155f9-a6d4-f17c-3898-1e1c7cc1912b" - ], - "datacenters": [ - "yul1" - ], - "deployment_id": "9b9e24ac-9932-f3eb-cc6e-cd64d41f8327", - "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 reschedule stanza specifies the group's rescheduling strategy. If\n # specified at the job level, the configuration will apply to all groups\n # within the job. If the reschedule stanza is present on both the job and the\n # group, they are merged with the group stanza taking the highest precedence\n # and then the job.\n reschedule {\n delay = \"30s\"\n delay_function = \"constant\"\n unlimited = 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\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 restart stanza configures a tasks's behavior on task failure. Restarts\n # happen on the client that is running the task.\n #\n # https://www.nomadproject.io/docs/job-specification/restart\n #\n restart {\n interval = \"30m\"\n attempts = 40\n delay = \"15s\"\n mode = \"delay\"\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 constraint {\n attribute = \"${node.class}\"\n value = \"builder\"\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\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-slack-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']\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 - match_re:\n alertname: JenkinsJob.*\n receiver: jenkins-slack-receiver\n routes:\n - match:\n severity: critical\n receiver: 'jenkins-slack-receiver'\n\n - match_re:\n service: .*\n receiver: default-slack-receiver\n routes:\n - match:\n severity: critical\n receiver: 'default-slack-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 equal: ['alertname', 'instance']\n\nreceivers:\n- name: 'jenkins-slack-receiver'\n slack_configs:\n - api_url: 'TE07RD1V1/B01U1NV9HV3/hKZXJJ74g2JcISq4K3QC1eG9'\n channel: '#fdio-jobs-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 }}\n\n- name: 'default-slack-receiver'\n slack_configs:\n - api_url: 'TE07RD1V1/B01UUK23B6C/hZTcCu42FUv8d6rtirHtcYIi'\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": "9138748", - "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.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": "ce0ab0b08359da392c19c0f354b0f082630aa887ad51701986b5ce80b8aa39ea", - "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 reschedule stanza specifies the group's rescheduling strategy. If\n # specified at the job level, the configuration will apply to all groups\n # within the job. If the reschedule stanza is present on both the job and the\n # group, they are merged with the group stanza taking the highest precedence\n # and then the job.\n reschedule {\n delay = \"30s\"\n delay_function = \"constant\"\n unlimited = 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\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 # The restart stanza configures a tasks's behavior on task failure. Restarts\n # happen on the client that is running the task.\n #\n # https://www.nomadproject.io/docs/job-specification/restart\n #\n restart {\n interval = \"30m\"\n attempts = 40\n delay = \"15s\"\n mode = \"delay\"\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 = \"${attr.cpu.arch}\"\n operator = \"!=\"\n value = \"arm64\"\n }\n\n constraint {\n attribute = \"${node.class}\"\n value = \"builder\"\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 = [ \"172.17.0.1\" ]\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/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 # 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 HTTP\n source = \"https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/blackbox_exporter_http.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 # 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${NOMAD_ALLOC_INDEX}\" ]\n check {\n name = \"Grafana Check Live\"\n type = \"http\"\n protocol = \"http\"\n tls_skip_verify = true\n path = \"/api/health\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # For more information and examples on the \"resources\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/resources\n #\n resources {\n cpu = 1000\n memory = 2048\n # The network stanza specifies the networking requirements for the task\n # group, including the network mode and port allocations. When scheduling\n # jobs in Nomad they are provisioned across your fleet of machines along\n # with other jobs and services. Because you don't know in advance what host\n # your job will be provisioned on, Nomad will provide your tasks with\n # network configuration when they start up.\n #\n # For more information and examples on the \"template\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/network\n #\n network {\n port \"grafana\" {\n static = 3000\n }\n }\n }\n }\n }\n}", - "template": "job \"${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 reschedule stanza specifies the group's rescheduling strategy. If\n # specified at the job level, the configuration will apply to all groups\n # within the job. If the reschedule stanza is present on both the job and the\n # group, they are merged with the group stanza taking the highest precedence\n # and then the job.\n reschedule {\n delay = \"30s\"\n delay_function = \"constant\"\n unlimited = 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\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 restart stanza configures a tasks's behavior on task failure. Restarts\n # happen on the client that is running the task.\n #\n # https://www.nomadproject.io/docs/job-specification/restart\n #\n restart {\n interval = \"30m\"\n attempts = 40\n delay = \"15s\"\n mode = \"delay\"\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 = \"$${attr.cpu.arch}\"\n operator = \"!=\"\n value = \"arm64\"\n }\n\n constraint {\n attribute = \"$${node.class}\"\n value = \"builder\"\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 = [ \"172.17.0.1\" ]\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/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 # 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 HTTP\n source = \"https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/blackbox_exporter_http.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 # 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": "1000", - "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": [ - "218d0f2c-ecf3-30bd-edc0-eaa3a4d8b384", - "18869dde-8c4e-3aa0-1baa-ddcb5c6dc5bc" - ], - "datacenters": [ - "yul1" - ], - "deployment_id": "9bd732cd-ec36-7f96-1b82-24e60b51c048", - "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 reschedule stanza specifies the group's rescheduling strategy. If\n # specified at the job level, the configuration will apply to all groups\n # within the job. If the reschedule stanza is present on both the job and the\n # group, they are merged with the group stanza taking the highest precedence\n # and then the job.\n reschedule {\n delay = \"30s\"\n delay_function = \"constant\"\n unlimited = 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\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 # The restart stanza configures a tasks's behavior on task failure. Restarts\n # happen on the client that is running the task.\n #\n # https://www.nomadproject.io/docs/job-specification/restart\n #\n restart {\n interval = \"30m\"\n attempts = 40\n delay = \"15s\"\n mode = \"delay\"\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 constraint {\n attribute = \"${node.class}\"\n value = \"builder\"\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 = [ \"172.17.0.1\" ]\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/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 # 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 HTTP\n source = \"https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/blackbox_exporter_http.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 # 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 = 1000\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": "9138744", - "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", - "name": "nomad_job_mc", - "provider": "provider[\"registry.terraform.io/hashicorp/template\"]", - "instances": [ - { - "schema_version": 0, - "attributes": { - "filename": null, - "id": "e9e956124e6fed4268bec199b9d7fd7aaff506e906b53621c6dc0e3116c40f52", - "rendered": "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.2021-07-27T02-40-15Z\"\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", - "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 = \"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 %{ 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 entrypoint = [\n \"/bin/sh\",\n \"-c\",\n \"${command}\"\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 %{ 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 }\n}\n", - "vars": { - "access_key": "minio", - "command": "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", - "datacenters": "yul1", - "envs": "", - "image": "minio/mc:RELEASE.2021-07-27T02-40-15Z", - "job_name": "prod-mc", - "minio_port": "9000", - "minio_service_name": "storage", - "secret_key": "minio123", - "service_name": "mc", - "use_vault_provider": "false" - } - }, - "sensitive_attributes": [] - } - ] - }, - { - "module": "module.minio", - "mode": "data", - "type": "template_file", - "name": "nomad_job_minio", - "provider": "provider[\"registry.terraform.io/hashicorp/template\"]", - "instances": [ - { - "schema_version": 0, - "attributes": { - "filename": null, - "id": "68243169c0df15ef6b56803101ed0c744a84545c34df366ee4036052c6292ef3", - "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 # 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 # 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 # https://www.nomadproject.io/docs/job-specification/group\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 restart stanza configures a tasks's behavior on task failure. Restarts\n # happen on the client that is running the task.\n #\n # https://www.nomadproject.io/docs/job-specification/restart\n #\n restart {\n interval = \"30m\"\n attempts = 40\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 # 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.2021-07-27T02-40-15Z\"\n dns_servers = [ \"172.17.0.1\" ]\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 # https://www.nomadproject.io/docs/job-specification/service\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 # https://www.nomadproject.io/docs/job-specification/resources\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 # https://www.nomadproject.io/docs/job-specification/network\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 # 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 # 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 # https://www.nomadproject.io/docs/job-specification/group\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 restart stanza configures a tasks's behavior on task failure. Restarts\n # happen on the client that is running the task.\n #\n # https://www.nomadproject.io/docs/job-specification/restart\n #\n restart {\n interval = \"30m\"\n attempts = 40\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 # 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 = \"${image}\"\n dns_servers = [ \"172.17.0.1\" ]\n network_mode = \"host\"\n command = \"server\"\n args = [ \"${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 ${ envs }\n }\n\n # The service stanza instructs Nomad to register a service with Consul.\n #\n # https://www.nomadproject.io/docs/job-specification/service\n #\n service {\n name = \"${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 # https://www.nomadproject.io/docs/job-specification/resources\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 # https://www.nomadproject.io/docs/job-specification/network\n #\n network {\n port \"http\" {\n static = ${port}\n }\n }\n }\n }\n }\n}\n", - "vars": { - "access_key": "minio", - "cpu": "40000", - "cpu_proxy": "200", - "data_dir": "/data/", - "datacenters": "yul1", - "envs": "MINIO_BROWSER=\"off\"", - "group_count": "4", - "host": "http://10.32.8.1{4...7}", - "host_volume": "prod-volume-data1-1", - "image": "minio/minio:RELEASE.2021-07-27T02-40-15Z", - "job_name": "prod-minio", - "memory": "40000", - "memory_proxy": "128", - "port": "9000", - "secret_key": "minio123", - "service_name": "storage", - "upstreams": "[]", - "use_canary": "true", - "use_host_volume": "true", - "use_vault_provider": "false" - } - }, - "sensitive_attributes": [] - } - ] - }, - { - "module": "module.minio", - "mode": "managed", - "type": "nomad_job", - "name": "nomad_job_minio", - "provider": "provider[\"registry.terraform.io/hashicorp/nomad\"].yul1", - "instances": [ - { - "schema_version": 0, - "attributes": { - "allocation_ids": [ - "924ac00a-b010-4af9-712d-1958c43c5363", - "1f464e9b-5892-45d8-9f6c-538ff61ac976", - "8b00df36-88c8-9cad-ce94-a2827b815be4", - "d257257b-4ed7-1a72-8ad5-7dc078e371b3" - ], - "datacenters": [ - "yul1" - ], - "deployment_id": "33d8013c-7c7c-6828-a204-58d9286b61ef", - "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 # 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 # 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 # https://www.nomadproject.io/docs/job-specification/group\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 restart stanza configures a tasks's behavior on task failure. Restarts\n # happen on the client that is running the task.\n #\n # https://www.nomadproject.io/docs/job-specification/restart\n #\n restart {\n interval = \"30m\"\n attempts = 40\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 # 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.2021-07-27T02-40-15Z\"\n dns_servers = [ \"172.17.0.1\" ]\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 # https://www.nomadproject.io/docs/job-specification/service\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 # https://www.nomadproject.io/docs/job-specification/resources\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 # https://www.nomadproject.io/docs/job-specification/network\n #\n network {\n port \"http\" {\n static = 9000\n }\n }\n }\n }\n }\n}\n", - "json": null, - "modify_index": "8949013", - "name": "prod-minio", - "namespace": "default", - "policy_override": null, - "purge_on_destroy": null, - "region": "global", - "task_groups": [ - { - "count": 4, - "meta": {}, - "name": "prod-group1-minio", - "task": [ - { - "driver": "docker", - "meta": {}, - "name": "prod-task1-minio", - "volume_mounts": [ - { - "destination": "/data/", - "read_only": false, - "volume": "prod-volume1-minio" - } - ] - } - ], - "volumes": [ - { - "name": "prod-volume1-minio", - "read_only": false, - "source": "prod-volume-data1-1", - "type": "host" - } - ] - } - ], - "type": "service" - }, - "sensitive_attributes": [], - "private": "bnVsbA==", - "dependencies": [ - "module.minio.data.template_file.nomad_job_minio" - ] - } - ] - }, - { - "module": "module.nginx", - "mode": "data", - "type": "template_file", - "name": "nomad_job_nginx", - "provider": "provider[\"registry.terraform.io/hashicorp/template\"]", - "instances": [ - { - "schema_version": 0, - "attributes": { - "filename": null, - "id": "6406c7bfb6f177869e124475f94fada7f69c2e6631c6943a6a00a167fd19a925", - "rendered": "job \"prod-nginx\" {\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 = 0\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 # 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 = false\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 = 0\n }\n\n # The reschedule stanza specifies the group's rescheduling strategy. If\n # specified at the job level, the configuration will apply to all groups\n # within the job. If the reschedule stanza is present on both the job and the\n # group, they are merged with the group stanza taking the highest precedence\n # and then the job.\n reschedule {\n delay = \"30s\"\n delay_function = \"constant\"\n unlimited = 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-nginx\" {\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 # https://www.nomadproject.io/docs/job-specification/volume\n \n volume \"prod-volume1-nginx\" {\n type = \"host\"\n read_only = false\n source = \"prod-volume-data1-1\"\n }\n \n\n # The restart stanza configures a tasks's behavior on task failure. Restarts\n # happen on the client that is running the task.\n #\n # https://www.nomadproject.io/docs/job-specification/restart\n #\n restart {\n interval = \"30m\"\n attempts = 40\n delay = \"15s\"\n mode = \"delay\"\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 constraint {\n attribute = \"${node.class}\"\n value = \"builder\"\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-nginx\" {\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 = \"nginx:stable\"\n port_map {\n https = 443\n }\n privileged = false\n volumes = [\n \"/etc/ssl/certs/logs.nginx.service.consul.crt:/etc/ssl/certs/logs.nginx.service.consul.crt\",\n \"/etc/ssl/private/logs.nginx.service.consul.key:/etc/ssl/private/logs.nginx.service.consul.key\",\n \"custom/upstream.conf:/etc/nginx/conf.d/upstream.conf\",\n \"custom/server_logs.conf:/etc/nginx/conf.d/server_logs.conf\"\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 # 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.html\n #\n template {\n data = \u003c\u003cEOH\n upstream storage {\n {{ range service \"storage\" }}\n server {{ .Address }}:{{ .Port }};\n {{ end }}\n }\n EOH\n destination = \"custom/upstream.conf\"\n }\n template {\n data = \u003c\u003cEOH\n server {\n listen 443 ssl default_server;\n server_name logs.nginx.service.consul;\n\n ssl_certificate /etc/ssl/certs/logs.nginx.service.consul.crt;\n ssl_certificate_key /etc/ssl/private/logs.nginx.service.consul.key;\n ssl_protocols TLSv1.2;\n ssl_prefer_server_ciphers on;\n ssl_ciphers \"ECDHE-ECDSA-AES256-GCM-SHA384:ECDHE-RSA-AES256-GCM-SHA384:ECDHE-ECDSA-CHACHA20-POLY1305:ECDHE-RSA-CHACHA20-POLY1305:ECDHE-ECDSA-AES256-SHA384:ECDHE-RSA-AES256-SHA384\";\n ssl_session_timeout 10m;\n ssl_session_cache shared:SSL:10m;\n ssl_session_tickets off;\n ssl_stapling on;\n ssl_stapling_verify on;\n\n fastcgi_hide_header X-Powered-By;\n\n client_max_body_size 0;\n client_header_timeout 60;\n client_body_timeout 86400;\n fastcgi_read_timeout 86400;\n proxy_connect_timeout 60;\n proxy_read_timeout 86400;\n proxy_send_timeout 86400;\n send_timeout 86400;\n\n keepalive_timeout 70;\n location / {\n chunked_transfer_encoding off;\n proxy_connect_timeout 300;\n proxy_http_version 1.1;\n proxy_set_header Host $host:$server_port;\n proxy_set_header Connection \"\";\n proxy_pass http://storage/logs.fd.io/;\n server_name_in_redirect off;\n }\n location ~ (.*html.gz)$ {\n add_header Content-Encoding gzip;\n add_header Content-Type text/html;\n chunked_transfer_encoding off;\n proxy_connect_timeout 300;\n proxy_http_version 1.1;\n proxy_set_header Host $host:$server_port;\n proxy_set_header Connection \"\";\n proxy_pass http://storage/logs.fd.io/$1;\n server_name_in_redirect off;\n }\n location ~ (.*txt.gz|.*log.gz)$ {\n add_header Content-Encoding gzip;\n add_header Content-Type text/plain;\n chunked_transfer_encoding off;\n proxy_connect_timeout 300;\n proxy_http_version 1.1;\n proxy_set_header Host $host:$server_port;\n proxy_set_header Connection \"\";\n proxy_pass http://storage/logs.fd.io/$1;\n server_name_in_redirect off;\n }\n location ~ (.*xml.gz)$ {\n add_header Content-Encoding gzip;\n add_header Content-Type application/xml;\n chunked_transfer_encoding off;\n proxy_connect_timeout 300;\n proxy_http_version 1.1;\n proxy_set_header Host $host:$server_port;\n proxy_set_header Connection \"\";\n proxy_pass http://storage/logs.fd.io/$1;\n server_name_in_redirect off;\n }\n }\n EOH\n destination = \"custom/logs.conf\"\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 = \"nginx\"\n port = \"https\"\n tags = [ \"logs\" ]\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 = 2000\n memory = 4096\n network {\n mode = \"bridge\"\n port \"https\" {\n static = 443\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 = 0\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 # 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 = false\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 = 0\n }\n\n # The reschedule stanza specifies the group's rescheduling strategy. If\n # specified at the job level, the configuration will apply to all groups\n # within the job. If the reschedule stanza is present on both the job and the\n # group, they are merged with the group stanza taking the highest precedence\n # and then the job.\n reschedule {\n delay = \"30s\"\n delay_function = \"constant\"\n unlimited = 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-nginx\" {\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 # https://www.nomadproject.io/docs/job-specification/volume\n %{ if use_host_volume }\n volume \"prod-volume1-nginx\" {\n type = \"host\"\n read_only = false\n source = \"${host_volume}\"\n }\n %{ endif }\n\n # The restart stanza configures a tasks's behavior on task failure. Restarts\n # happen on the client that is running the task.\n #\n # https://www.nomadproject.io/docs/job-specification/restart\n #\n restart {\n interval = \"30m\"\n attempts = 40\n delay = \"15s\"\n mode = \"delay\"\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 constraint {\n attribute = \"$${node.class}\"\n value = \"builder\"\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-nginx\" {\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 = \"nginx:stable\"\n port_map {\n https = 443\n }\n privileged = false\n volumes = [\n \"/etc/ssl/certs/logs.nginx.service.consul.crt:/etc/ssl/certs/logs.nginx.service.consul.crt\",\n \"/etc/ssl/private/logs.nginx.service.consul.key:/etc/ssl/private/logs.nginx.service.consul.key\",\n \"custom/upstream.conf:/etc/nginx/conf.d/upstream.conf\",\n \"custom/server_logs.conf:/etc/nginx/conf.d/server_logs.conf\"\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 # 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.html\n #\n template {\n data = \u003c\u003cEOH\n upstream storage {\n {{ range service \"storage\" }}\n server {{ .Address }}:{{ .Port }};\n {{ end }}\n }\n EOH\n destination = \"custom/upstream.conf\"\n }\n template {\n data = \u003c\u003cEOH\n server {\n listen 443 ssl default_server;\n server_name logs.nginx.service.consul;\n\n ssl_certificate /etc/ssl/certs/logs.nginx.service.consul.crt;\n ssl_certificate_key /etc/ssl/private/logs.nginx.service.consul.key;\n ssl_protocols TLSv1.2;\n ssl_prefer_server_ciphers on;\n ssl_ciphers \"ECDHE-ECDSA-AES256-GCM-SHA384:ECDHE-RSA-AES256-GCM-SHA384:ECDHE-ECDSA-CHACHA20-POLY1305:ECDHE-RSA-CHACHA20-POLY1305:ECDHE-ECDSA-AES256-SHA384:ECDHE-RSA-AES256-SHA384\";\n ssl_session_timeout 10m;\n ssl_session_cache shared:SSL:10m;\n ssl_session_tickets off;\n ssl_stapling on;\n ssl_stapling_verify on;\n\n fastcgi_hide_header X-Powered-By;\n\n client_max_body_size 0;\n client_header_timeout 60;\n client_body_timeout 86400;\n fastcgi_read_timeout 86400;\n proxy_connect_timeout 60;\n proxy_read_timeout 86400;\n proxy_send_timeout 86400;\n send_timeout 86400;\n\n keepalive_timeout 70;\n location / {\n chunked_transfer_encoding off;\n proxy_connect_timeout 300;\n proxy_http_version 1.1;\n proxy_set_header Host $host:$server_port;\n proxy_set_header Connection \"\";\n proxy_pass http://storage/logs.fd.io/;\n server_name_in_redirect off;\n }\n location ~ (.*html.gz)$ {\n add_header Content-Encoding gzip;\n add_header Content-Type text/html;\n chunked_transfer_encoding off;\n proxy_connect_timeout 300;\n proxy_http_version 1.1;\n proxy_set_header Host $host:$server_port;\n proxy_set_header Connection \"\";\n proxy_pass http://storage/logs.fd.io/$1;\n server_name_in_redirect off;\n }\n location ~ (.*txt.gz|.*log.gz)$ {\n add_header Content-Encoding gzip;\n add_header Content-Type text/plain;\n chunked_transfer_encoding off;\n proxy_connect_timeout 300;\n proxy_http_version 1.1;\n proxy_set_header Host $host:$server_port;\n proxy_set_header Connection \"\";\n proxy_pass http://storage/logs.fd.io/$1;\n server_name_in_redirect off;\n }\n location ~ (.*xml.gz)$ {\n add_header Content-Encoding gzip;\n add_header Content-Type application/xml;\n chunked_transfer_encoding off;\n proxy_connect_timeout 300;\n proxy_http_version 1.1;\n proxy_set_header Host $host:$server_port;\n proxy_set_header Connection \"\";\n proxy_pass http://storage/logs.fd.io/$1;\n server_name_in_redirect off;\n }\n }\n EOH\n destination = \"custom/logs.conf\"\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 = \"nginx\"\n port = \"https\"\n tags = [ \"logs\" ]\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 = 2000\n memory = 4096\n network {\n mode = \"bridge\"\n port \"https\" {\n static = 443\n }\n }\n }\n }\n }\n}", - "vars": { - "datacenters": "yul1", - "host_volume": "prod-volume-data1-1", - "job_name": "prod-nginx", - "use_host_volume": "true" - } - }, - "sensitive_attributes": [] - } - ] - }, - { - "module": "module.nginx", - "mode": "managed", - "type": "nomad_job", - "name": "nomad_job_nginx", - "provider": "provider[\"registry.terraform.io/hashicorp/nomad\"].yul1", - "instances": [ - { - "schema_version": 0, - "attributes": { - "allocation_ids": [ - "5f0b5208-cb84-507d-18d0-d294925c13e0", - "9a5e3312-8802-e842-1eb0-0cc01a4d4575" - ], - "datacenters": [ - "yul1" - ], - "deployment_id": "", - "deployment_status": "", - "deregister_on_destroy": true, - "deregister_on_id_change": true, - "detach": false, - "id": "prod-nginx", - "jobspec": "job \"prod-nginx\" {\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 = 0\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 # 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 = false\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 = 0\n }\n\n # The reschedule stanza specifies the group's rescheduling strategy. If\n # specified at the job level, the configuration will apply to all groups\n # within the job. If the reschedule stanza is present on both the job and the\n # group, they are merged with the group stanza taking the highest precedence\n # and then the job.\n reschedule {\n delay = \"30s\"\n delay_function = \"constant\"\n unlimited = 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-nginx\" {\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 # https://www.nomadproject.io/docs/job-specification/volume\n \n volume \"prod-volume1-nginx\" {\n type = \"host\"\n read_only = false\n source = \"prod-volume-data1-1\"\n }\n \n\n # The restart stanza configures a tasks's behavior on task failure. Restarts\n # happen on the client that is running the task.\n #\n # https://www.nomadproject.io/docs/job-specification/restart\n #\n restart {\n interval = \"30m\"\n attempts = 40\n delay = \"15s\"\n mode = \"delay\"\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 constraint {\n attribute = \"${node.class}\"\n value = \"builder\"\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-nginx\" {\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 = \"nginx:stable\"\n port_map {\n https = 443\n }\n privileged = false\n volumes = [\n \"/etc/ssl/certs/logs.nginx.service.consul.crt:/etc/ssl/certs/logs.nginx.service.consul.crt\",\n \"/etc/ssl/private/logs.nginx.service.consul.key:/etc/ssl/private/logs.nginx.service.consul.key\",\n \"custom/upstream.conf:/etc/nginx/conf.d/upstream.conf\",\n \"custom/server_logs.conf:/etc/nginx/conf.d/server_logs.conf\"\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 # 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.html\n #\n template {\n data = \u003c\u003cEOH\n upstream storage {\n {{ range service \"storage\" }}\n server {{ .Address }}:{{ .Port }};\n {{ end }}\n }\n EOH\n destination = \"custom/upstream.conf\"\n }\n template {\n data = \u003c\u003cEOH\n server {\n listen 443 ssl default_server;\n server_name logs.nginx.service.consul;\n\n ssl_certificate /etc/ssl/certs/logs.nginx.service.consul.crt;\n ssl_certificate_key /etc/ssl/private/logs.nginx.service.consul.key;\n ssl_protocols TLSv1.2;\n ssl_prefer_server_ciphers on;\n ssl_ciphers \"ECDHE-ECDSA-AES256-GCM-SHA384:ECDHE-RSA-AES256-GCM-SHA384:ECDHE-ECDSA-CHACHA20-POLY1305:ECDHE-RSA-CHACHA20-POLY1305:ECDHE-ECDSA-AES256-SHA384:ECDHE-RSA-AES256-SHA384\";\n ssl_session_timeout 10m;\n ssl_session_cache shared:SSL:10m;\n ssl_session_tickets off;\n ssl_stapling on;\n ssl_stapling_verify on;\n\n fastcgi_hide_header X-Powered-By;\n\n client_max_body_size 0;\n client_header_timeout 60;\n client_body_timeout 86400;\n fastcgi_read_timeout 86400;\n proxy_connect_timeout 60;\n proxy_read_timeout 86400;\n proxy_send_timeout 86400;\n send_timeout 86400;\n\n keepalive_timeout 70;\n location / {\n chunked_transfer_encoding off;\n proxy_connect_timeout 300;\n proxy_http_version 1.1;\n proxy_set_header Host $host:$server_port;\n proxy_set_header Connection \"\";\n proxy_pass http://storage/logs.fd.io/;\n server_name_in_redirect off;\n }\n location ~ (.*html.gz)$ {\n add_header Content-Encoding gzip;\n add_header Content-Type text/html;\n chunked_transfer_encoding off;\n proxy_connect_timeout 300;\n proxy_http_version 1.1;\n proxy_set_header Host $host:$server_port;\n proxy_set_header Connection \"\";\n proxy_pass http://storage/logs.fd.io/$1;\n server_name_in_redirect off;\n }\n location ~ (.*txt.gz|.*log.gz)$ {\n add_header Content-Encoding gzip;\n add_header Content-Type text/plain;\n chunked_transfer_encoding off;\n proxy_connect_timeout 300;\n proxy_http_version 1.1;\n proxy_set_header Host $host:$server_port;\n proxy_set_header Connection \"\";\n proxy_pass http://storage/logs.fd.io/$1;\n server_name_in_redirect off;\n }\n location ~ (.*xml.gz)$ {\n add_header Content-Encoding gzip;\n add_header Content-Type application/xml;\n chunked_transfer_encoding off;\n proxy_connect_timeout 300;\n proxy_http_version 1.1;\n proxy_set_header Host $host:$server_port;\n proxy_set_header Connection \"\";\n proxy_pass http://storage/logs.fd.io/$1;\n server_name_in_redirect off;\n }\n }\n EOH\n destination = \"custom/logs.conf\"\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 = \"nginx\"\n port = \"https\"\n tags = [ \"logs\" ]\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 = 2000\n memory = 4096\n network {\n mode = \"bridge\"\n port \"https\" {\n static = 443\n }\n }\n }\n }\n }\n}", - "json": null, - "modify_index": "9138746", - "name": "prod-nginx", - "namespace": "default", - "policy_override": null, - "purge_on_destroy": null, - "region": "global", - "task_groups": [ - { - "count": 1, - "meta": {}, - "name": "prod-group1-nginx", - "task": [ - { - "driver": "docker", - "meta": {}, - "name": "prod-task1-nginx", - "volume_mounts": [] - } - ], - "volumes": [ - { - "name": "prod-volume1-nginx", - "read_only": false, - "source": "prod-volume-data1-1", - "type": "host" - } - ] - } - ], - "type": "service" - }, - "sensitive_attributes": [], - "private": "bnVsbA==", - "dependencies": [ - "module.nginx.data.template_file.nomad_job_nginx" - ] - } - ] - }, - { - "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": "2cfc207e58bdcd266ac342e51f9e5a442c595ddad94d04462ca1ad78ea24cf61", - "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 reschedule stanza specifies the group's rescheduling strategy. If\n # specified at the job level, the configuration will apply to all groups\n # within the job. If the reschedule stanza is present on both the job and the\n # group, they are merged with the group stanza taking the highest precedence\n # and then the job.\n reschedule {\n delay = \"30s\"\n delay_function = \"constant\"\n unlimited = 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\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 restart stanza configures a tasks's behavior on task failure. Restarts\n # happen on the client that is running the task.\n #\n # https://www.nomadproject.io/docs/job-specification/restart\n #\n restart {\n interval = \"30m\"\n attempts = 40\n delay = \"15s\"\n mode = \"delay\"\n }\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 constraint {\n attribute = \"${node.class}\"\n value = \"builder\"\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-2.28.1.linux-amd64/prometheus\"\n args = [\n \"--config.file=secrets/prometheus.yml\",\n \"--storage.tsdb.path=/data/prometheus/\",\n \"--storage.tsdb.retention.time=7d\"\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/v2.28.1/prometheus-2.28.1.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: \"Jenkins Job Health Exporter\"\n rules:\n - alert: JenkinsJobHealthExporterFailures\n expr: jenkins_job_failure{id=~\".*\"} \u003e jenkins_job_success{id=~\".*\"}\n for: 0m\n labels:\n severity: critical\n annotations:\n summary: \"Jenkins Job Health detected high failure rate on jenkins jobs.\"\n description: \"Job: {{ $labels.id }}\"\n - alert: JenkinsJobHealthExporterUnstable\n expr: jenkins_job_unstable{id=~\".*\"} \u003e jenkins_job_success{id=~\".*\"}\n for: 0m\n labels:\n severity: warning\n annotations:\n summary: \"Jenkins Job Health detected high unstable rate on jenkins jobs.\"\n description: \"Job: {{ $labels.id }}\"\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: 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: [ '10.30.51.22:8500' ]\n - targets: [ '10.30.51.24:8500' ]\n - targets: [ '10.30.51.25:8500' ]\n - targets: [ '10.30.51.26:8500' ]\n - targets: [ '10.30.51.28:8500' ]\n - targets: [ '10.30.51.29:8500' ]\n - targets: [ '10.30.51.30:8500' ]\n - targets: [ '10.30.51.39:8500' ]\n - targets: [ '10.30.51.40:8500' ]\n - targets: [ '10.30.51.50:8500' ]\n - targets: [ '10.30.51.51:8500' ]\n - targets: [ '10.30.51.65:8500' ]\n - targets: [ '10.30.51.66:8500' ]\n - targets: [ '10.30.51.67:8500' ]\n - targets: [ '10.30.51.68:8500' ]\n - targets: [ '10.30.51.70:8500' ]\n - targets: [ '10.30.51.71:8500' ]\n - targets: [ '10.32.8.14:8500' ]\n - targets: [ '10.32.8.15:8500' ]\n - targets: [ '10.32.8.16:8500' ]\n - targets: [ '10.32.8.17:8500' ]\n metrics_path: /v1/agent/metrics\n params:\n format: [ 'prometheus' ]\n\n - job_name: 'Blackbox Exporter (icmp)'\n static_configs:\n - targets: [ 'gerrit.fd.io' ]\n - targets: [ 'jenkins.fd.io' ]\n - targets: [ '10.32.8.17' ]\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: 'Jenkins Job Health Exporter'\n static_configs:\n - targets: [ '10.30.51.22:9186' ]\n metric_relabel_configs:\n - source_labels: [ __name__ ]\n regex: '^(vpp.*|csit.*)_(success|failure|total|unstable|reqtime_ms)$'\n action: replace\n replacement: '$1'\n target_label: id\n - source_labels: [ __name__ ]\n regex: '^(vpp.*|csit.*)_(success|failure|total|unstable|reqtime_ms)$'\n replacement: 'jenkins_job_$2'\n target_label: __name__\n\n - job_name: 'Node Exporter'\n static_configs:\n - targets: [ '10.30.51.22:9100' ]\n - targets: [ '10.30.51.24:9100' ]\n - targets: [ '10.30.51.25:9100' ]\n - targets: [ '10.30.51.26:9100' ]\n - targets: [ '10.30.51.28:9100' ]\n - targets: [ '10.30.51.29:9100' ]\n - targets: [ '10.30.51.30:9100' ]\n - targets: [ '10.30.51.39:9100' ]\n - targets: [ '10.30.51.40:9100' ]\n - targets: [ '10.30.51.50:9100' ]\n - targets: [ '10.30.51.51:9100' ]\n - targets: [ '10.30.51.65:9100' ]\n - targets: [ '10.30.51.66:9100' ]\n - targets: [ '10.30.51.67:9100' ]\n - targets: [ '10.30.51.68:9100' ]\n - targets: [ '10.30.51.70:9100' ]\n - targets: [ '10.30.51.71:9100' ]\n - targets: [ '10.32.8.14:9100' ]\n - targets: [ '10.32.8.15:9100' ]\n - targets: [ '10.32.8.16:9100' ]\n - targets: [ '10.32.8.17:9100' ]\n\n - job_name: 'Alertmanager'\n consul_sd_configs:\n - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n services: [ 'alertmanager' ]\n\n - job_name: 'Grafana'\n consul_sd_configs:\n - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n services: [ 'grafana' ]\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 reschedule stanza specifies the group's rescheduling strategy. If\n # specified at the job level, the configuration will apply to all groups\n # within the job. If the reschedule stanza is present on both the job and the\n # group, they are merged with the group stanza taking the highest precedence\n # and then the job.\n reschedule {\n delay = \"30s\"\n delay_function = \"constant\"\n unlimited = 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\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 restart stanza configures a tasks's behavior on task failure. Restarts\n # happen on the client that is running the task.\n #\n # https://www.nomadproject.io/docs/job-specification/restart\n #\n restart {\n interval = \"30m\"\n attempts = 40\n delay = \"15s\"\n mode = \"delay\"\n }\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 constraint {\n attribute = \"$${node.class}\"\n value = \"builder\"\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=7d\"\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: \"Jenkins Job Health Exporter\"\n rules:\n - alert: JenkinsJobHealthExporterFailures\n expr: jenkins_job_failure{id=~\".*\"} \u003e jenkins_job_success{id=~\".*\"}\n for: 0m\n labels:\n severity: critical\n annotations:\n summary: \"Jenkins Job Health detected high failure rate on jenkins jobs.\"\n description: \"Job: {{ $labels.id }}\"\n - alert: JenkinsJobHealthExporterUnstable\n expr: jenkins_job_unstable{id=~\".*\"} \u003e jenkins_job_success{id=~\".*\"}\n for: 0m\n labels:\n severity: warning\n annotations:\n summary: \"Jenkins Job Health detected high unstable rate on jenkins jobs.\"\n description: \"Job: {{ $labels.id }}\"\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: 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: [ '10.30.51.22:8500' ]\n - targets: [ '10.30.51.24:8500' ]\n - targets: [ '10.30.51.25:8500' ]\n - targets: [ '10.30.51.26:8500' ]\n - targets: [ '10.30.51.28:8500' ]\n - targets: [ '10.30.51.29:8500' ]\n - targets: [ '10.30.51.30:8500' ]\n - targets: [ '10.30.51.39:8500' ]\n - targets: [ '10.30.51.40:8500' ]\n - targets: [ '10.30.51.50:8500' ]\n - targets: [ '10.30.51.51:8500' ]\n - targets: [ '10.30.51.65:8500' ]\n - targets: [ '10.30.51.66:8500' ]\n - targets: [ '10.30.51.67:8500' ]\n - targets: [ '10.30.51.68:8500' ]\n - targets: [ '10.30.51.70:8500' ]\n - targets: [ '10.30.51.71:8500' ]\n - targets: [ '10.32.8.14:8500' ]\n - targets: [ '10.32.8.15:8500' ]\n - targets: [ '10.32.8.16:8500' ]\n - targets: [ '10.32.8.17:8500' ]\n metrics_path: /v1/agent/metrics\n params:\n format: [ 'prometheus' ]\n\n - job_name: 'Blackbox Exporter (icmp)'\n static_configs:\n - targets: [ 'gerrit.fd.io' ]\n - targets: [ 'jenkins.fd.io' ]\n - targets: [ '10.32.8.17' ]\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: 'Jenkins Job Health Exporter'\n static_configs:\n - targets: [ '10.30.51.22:9186' ]\n metric_relabel_configs:\n - source_labels: [ __name__ ]\n regex: '^(vpp.*|csit.*)_(success|failure|total|unstable|reqtime_ms)$'\n action: replace\n replacement: '$1'\n target_label: id\n - source_labels: [ __name__ ]\n regex: '^(vpp.*|csit.*)_(success|failure|total|unstable|reqtime_ms)$'\n replacement: 'jenkins_job_$2'\n target_label: __name__\n\n - job_name: 'Node Exporter'\n static_configs:\n - targets: [ '10.30.51.22:9100' ]\n - targets: [ '10.30.51.24:9100' ]\n - targets: [ '10.30.51.25:9100' ]\n - targets: [ '10.30.51.26:9100' ]\n - targets: [ '10.30.51.28:9100' ]\n - targets: [ '10.30.51.29:9100' ]\n - targets: [ '10.30.51.30:9100' ]\n - targets: [ '10.30.51.39:9100' ]\n - targets: [ '10.30.51.40:9100' ]\n - targets: [ '10.30.51.50:9100' ]\n - targets: [ '10.30.51.51:9100' ]\n - targets: [ '10.30.51.65:9100' ]\n - targets: [ '10.30.51.66:9100' ]\n - targets: [ '10.30.51.67:9100' ]\n - targets: [ '10.30.51.68:9100' ]\n - targets: [ '10.30.51.70:9100' ]\n - targets: [ '10.30.51.71:9100' ]\n - targets: [ '10.32.8.14:9100' ]\n - targets: [ '10.32.8.15:9100' ]\n - targets: [ '10.32.8.16:9100' ]\n - targets: [ '10.32.8.17:9100' ]\n\n - job_name: 'Alertmanager'\n consul_sd_configs:\n - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n services: [ 'alertmanager' ]\n\n - job_name: 'Grafana'\n consul_sd_configs:\n - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n services: [ 'grafana' ]\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/v2.28.1/prometheus-2.28.1.linux-amd64.tar.gz", - "use_canary": "true", - "use_host_volume": "true", - "use_vault_provider": "false", - "version": "2.28.1" - } - }, - "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": [ - "655f7aa1-199f-4241-9ff0-37620b2f3f10", - "f80ed1f8-7783-6b17-0ed0-db3ab7786dbf", - "0df91982-632b-a2dd-5149-d81cd93235f6", - "277d7a3b-c31a-e4eb-a8fe-d97377fb4d9c", - "6d8dc89f-788d-1229-5558-0e56398eb6f0", - "b9f0d581-0093-d4e0-a502-9f15475b7b93" - ], - "datacenters": [ - "yul1" - ], - "deployment_id": "c5203cd1-b38b-44ca-21d0-4b1638ad382a", - "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 reschedule stanza specifies the group's rescheduling strategy. If\n # specified at the job level, the configuration will apply to all groups\n # within the job. If the reschedule stanza is present on both the job and the\n # group, they are merged with the group stanza taking the highest precedence\n # and then the job.\n reschedule {\n delay = \"30s\"\n delay_function = \"constant\"\n unlimited = 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\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 restart stanza configures a tasks's behavior on task failure. Restarts\n # happen on the client that is running the task.\n #\n # https://www.nomadproject.io/docs/job-specification/restart\n #\n restart {\n interval = \"30m\"\n attempts = 40\n delay = \"15s\"\n mode = \"delay\"\n }\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 constraint {\n attribute = \"${node.class}\"\n value = \"builder\"\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-2.28.1.linux-amd64/prometheus\"\n args = [\n \"--config.file=secrets/prometheus.yml\",\n \"--storage.tsdb.path=/data/prometheus/\",\n \"--storage.tsdb.retention.time=7d\"\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/v2.28.1/prometheus-2.28.1.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: \"Jenkins Job Health Exporter\"\n rules:\n - alert: JenkinsJobHealthExporterFailures\n expr: jenkins_job_failure{id=~\".*\"} \u003e jenkins_job_success{id=~\".*\"}\n for: 0m\n labels:\n severity: critical\n annotations:\n summary: \"Jenkins Job Health detected high failure rate on jenkins jobs.\"\n description: \"Job: {{ $labels.id }}\"\n - alert: JenkinsJobHealthExporterUnstable\n expr: jenkins_job_unstable{id=~\".*\"} \u003e jenkins_job_success{id=~\".*\"}\n for: 0m\n labels:\n severity: warning\n annotations:\n summary: \"Jenkins Job Health detected high unstable rate on jenkins jobs.\"\n description: \"Job: {{ $labels.id }}\"\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: 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: [ '10.30.51.22:8500' ]\n - targets: [ '10.30.51.24:8500' ]\n - targets: [ '10.30.51.25:8500' ]\n - targets: [ '10.30.51.26:8500' ]\n - targets: [ '10.30.51.28:8500' ]\n - targets: [ '10.30.51.29:8500' ]\n - targets: [ '10.30.51.30:8500' ]\n - targets: [ '10.30.51.39:8500' ]\n - targets: [ '10.30.51.40:8500' ]\n - targets: [ '10.30.51.50:8500' ]\n - targets: [ '10.30.51.51:8500' ]\n - targets: [ '10.30.51.65:8500' ]\n - targets: [ '10.30.51.66:8500' ]\n - targets: [ '10.30.51.67:8500' ]\n - targets: [ '10.30.51.68:8500' ]\n - targets: [ '10.30.51.70:8500' ]\n - targets: [ '10.30.51.71:8500' ]\n - targets: [ '10.32.8.14:8500' ]\n - targets: [ '10.32.8.15:8500' ]\n - targets: [ '10.32.8.16:8500' ]\n - targets: [ '10.32.8.17:8500' ]\n metrics_path: /v1/agent/metrics\n params:\n format: [ 'prometheus' ]\n\n - job_name: 'Blackbox Exporter (icmp)'\n static_configs:\n - targets: [ 'gerrit.fd.io' ]\n - targets: [ 'jenkins.fd.io' ]\n - targets: [ '10.32.8.17' ]\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: 'Jenkins Job Health Exporter'\n static_configs:\n - targets: [ '10.30.51.22:9186' ]\n metric_relabel_configs:\n - source_labels: [ __name__ ]\n regex: '^(vpp.*|csit.*)_(success|failure|total|unstable|reqtime_ms)$'\n action: replace\n replacement: '$1'\n target_label: id\n - source_labels: [ __name__ ]\n regex: '^(vpp.*|csit.*)_(success|failure|total|unstable|reqtime_ms)$'\n replacement: 'jenkins_job_$2'\n target_label: __name__\n\n - job_name: 'Node Exporter'\n static_configs:\n - targets: [ '10.30.51.22:9100' ]\n - targets: [ '10.30.51.24:9100' ]\n - targets: [ '10.30.51.25:9100' ]\n - targets: [ '10.30.51.26:9100' ]\n - targets: [ '10.30.51.28:9100' ]\n - targets: [ '10.30.51.29:9100' ]\n - targets: [ '10.30.51.30:9100' ]\n - targets: [ '10.30.51.39:9100' ]\n - targets: [ '10.30.51.40:9100' ]\n - targets: [ '10.30.51.50:9100' ]\n - targets: [ '10.30.51.51:9100' ]\n - targets: [ '10.30.51.65:9100' ]\n - targets: [ '10.30.51.66:9100' ]\n - targets: [ '10.30.51.67:9100' ]\n - targets: [ '10.30.51.68:9100' ]\n - targets: [ '10.30.51.70:9100' ]\n - targets: [ '10.30.51.71:9100' ]\n - targets: [ '10.32.8.14:9100' ]\n - targets: [ '10.32.8.15:9100' ]\n - targets: [ '10.32.8.16:9100' ]\n - targets: [ '10.32.8.17:9100' ]\n\n - job_name: 'Alertmanager'\n consul_sd_configs:\n - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n services: [ 'alertmanager' ]\n\n - job_name: 'Grafana'\n consul_sd_configs:\n - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n services: [ 'grafana' ]\n\n - job_name: 'Prometheus'\n consul_sd_configs:\n - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n services: [ 'prometheus' ]\n\n - job_name: 'Minio'\n bearer_token: eyJhbGciOiJIUzUxMiIsInR5cCI6IkpXVCJ9.eyJleHAiOjQ3NjQ1ODEzMzcsImlzcyI6InByb21ldGhldXMiLCJzdWIiOiJtaW5pbyJ9.oeTw3EIaiFmlDikrHXWiWXMH2vxLfDLkfjEC7G2N3M_keH_xyA_l2ofLLNYtopa_3GCEZnxLQdPuFZrmgpkDWg\n consul_sd_configs:\n - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n services: [ 'storage' ]\n metrics_path: /minio/prometheus/metrics\nEOH\n }\n\n # The service stanza instructs Nomad to register a service with Consul.\n #\n # For more information and examples on the \"task\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/service\n #\n service {\n name = \"prometheus\"\n port = \"prometheus\"\n tags = [ \"prometheus${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": "9138750", - "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": "bebf27b2f8eb532adad3cabb86953deed4d0e9970ab0524d7857b3ebeebb917d", - "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 = \"${node.class}\"\n value = \"csit\"\n }\n\n restart {\n interval = \"1m\"\n attempts = 3\n delay = \"15s\"\n mode = \"delay\"\n }\n\n # The \"task\" stanza creates an individual unit of work, such as a Docker\n # container, web application, or batch processing.\n #\n # For more information and examples on the \"task\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/task.html\n #\n task \"prod-task1-csit-shim-amd\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"docker\"\n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n image = \"fdiotools/csit_shim-ubuntu2004:2021_03_04_142103_UTC-x86_64\"\n network_mode = \"host\"\n pid_mode = \"host\"\n volumes = [\n \"/var/run/docker.sock:/var/run/docker.sock\"\n ]\n privileged = true\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # For more information and examples on the \"resources\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/resources.html\n #\n resources {\n cpu = 1500\n memory = 4096\n network {\n port \"ssh\" {\n static = 6022\n }\n port \"ssh2\" {\n static = 6023\n }\n }\n }\n }\n }\n\n group \"prod-group1-csit-shim-arm\" {\n # The \"count\" parameter specifies the number of the task groups that should\n # be running under this group. This value must be non-negative and defaults\n # to 1.\n count = 1\n\n constraint {\n attribute = \"${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 = \"fdiotools/csit_shim-ubuntu2004:2021_03_02_143938_UTC-aarch64\"\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 = 1500\n memory = 4096\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 = \"$${node.class}\"\n value = \"csit\"\n }\n\n restart {\n interval = \"1m\"\n attempts = 3\n delay = \"15s\"\n mode = \"delay\"\n }\n\n # The \"task\" stanza creates an individual unit of work, such as a Docker\n # container, web application, or batch processing.\n #\n # For more information and examples on the \"task\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/task.html\n #\n task \"prod-task1-csit-shim-amd\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"docker\"\n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n image = \"${image_x86_64}\"\n network_mode = \"host\"\n pid_mode = \"host\"\n volumes = [\n \"/var/run/docker.sock:/var/run/docker.sock\"\n ]\n privileged = true\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # For more information and examples on the \"resources\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/resources.html\n #\n resources {\n cpu = ${cpu}\n memory = ${mem}\n network {\n port \"ssh\" {\n static = 6022\n }\n port \"ssh2\" {\n static = 6023\n }\n }\n }\n }\n }\n\n group \"prod-group1-csit-shim-arm\" {\n # The \"count\" parameter specifies the number of the task groups that should\n # be running under this group. This value must be non-negative and defaults\n # to 1.\n count = ${group_count}\n\n constraint {\n attribute = \"$${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 = \"${image_aarch64}\"\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": "1500", - "datacenters": "yul1", - "group_count": "1", - "image_aarch64": "fdiotools/csit_shim-ubuntu2004:2021_03_02_143938_UTC-aarch64", - "image_x86_64": "fdiotools/csit_shim-ubuntu2004:2021_03_04_142103_UTC-x86_64", - "job_name": "prod-device-csit-shim", - "mem": "4096" - } - }, - "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": [], - "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 = \"fdiotools/csit_shim-ubuntu2004:2021_03_04_142103_UTC-x86_64\"\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 = 1500\n memory = 4096\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 = \"fdiotools/csit_shim-ubuntu2004:2021_03_02_143938_UTC-aarch64\"\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 = 1500\n memory = 4096\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": "7575030", - "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/fdio.infra.terraform/1n_nmd/terraform.tfstate.backup b/fdio.infra.terraform/1n_nmd/terraform.tfstate.backup deleted file mode 100644 index 5397697870..0000000000 --- a/fdio.infra.terraform/1n_nmd/terraform.tfstate.backup +++ /dev/null @@ -1,635 +0,0 @@ -{ - "version": 4, - "terraform_version": "1.0.4", - "serial": 1187, - "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": "7e96dc4e316a25b07430e5ffc2ecdb94ae41f06770ba8667ae4d5f77ef25c6f7", - "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 reschedule stanza specifies the group's rescheduling strategy. If\n # specified at the job level, the configuration will apply to all groups\n # within the job. If the reschedule stanza is present on both the job and the\n # group, they are merged with the group stanza taking the highest precedence\n # and then the job.\n reschedule {\n delay = \"30s\"\n delay_function = \"constant\"\n unlimited = 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\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 restart stanza configures a tasks's behavior on task failure. Restarts\n # happen on the client that is running the task.\n #\n # https://www.nomadproject.io/docs/job-specification/restart\n #\n restart {\n interval = \"30m\"\n attempts = 40\n delay = \"15s\"\n mode = \"delay\"\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-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\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-slack-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']\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 - match_re:\n alertname: JenkinsJob.*\n receiver: jenkins-slack-receiver\n routes:\n - match:\n severity: critical\n receiver: 'jenkins-slack-receiver'\n\n - match_re:\n service: .*\n receiver: default-slack-receiver\n routes:\n - match:\n severity: critical\n receiver: 'default-slack-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 equal: ['alertname', 'instance']\n\nreceivers:\n- name: 'jenkins-slack-receiver'\n slack_configs:\n - api_url: 'TE07RD1V1/B01U1NV9HV3/hKZXJJ74g2JcISq4K3QC1eG9'\n channel: '#fdio-jobs-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 }}\n\n- name: 'default-slack-receiver'\n slack_configs:\n - api_url: 'TE07RD1V1/B01UUK23B6C/hZTcCu42FUv8d6rtirHtcYIi'\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 reschedule stanza specifies the group's rescheduling strategy. If\n # specified at the job level, the configuration will apply to all groups\n # within the job. If the reschedule stanza is present on both the job and the\n # group, they are merged with the group stanza taking the highest precedence\n # and then the job.\n reschedule {\n delay = \"30s\"\n delay_function = \"constant\"\n unlimited = 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\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 restart stanza configures a tasks's behavior on task failure. Restarts\n # happen on the client that is running the task.\n #\n # https://www.nomadproject.io/docs/job-specification/restart\n #\n restart {\n interval = \"30m\"\n attempts = 40\n delay = \"15s\"\n mode = \"delay\"\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 = \"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\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: '${slack_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']\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 - match_re:\n alertname: JenkinsJob.*\n receiver: ${slack_jenkins_receiver}\n routes:\n - match:\n severity: critical\n receiver: '${slack_jenkins_receiver}'\n\n - match_re:\n service: .*\n receiver: ${slack_default_receiver}\n routes:\n - match:\n severity: critical\n receiver: '${slack_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 equal: ['alertname', 'instance']\n\nreceivers:\n- name: '${slack_jenkins_receiver}'\n slack_configs:\n - api_url: '${slack_jenkins_api_key}'\n channel: '#${slack_jenkins_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 }}\n\n- name: '${slack_default_receiver}'\n slack_configs:\n - api_url: '${slack_default_api_key}'\n channel: '#${slack_default_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", - "group_count": "1", - "job_name": "prod-alertmanager", - "mem": "1024", - "port": "9093", - "service_name": "alertmanager", - "slack_default_api_key": "TE07RD1V1/B01UUK23B6C/hZTcCu42FUv8d6rtirHtcYIi", - "slack_default_channel": "fdio-infra-monitoring", - "slack_default_receiver": "default-slack-receiver", - "slack_jenkins_api_key": "TE07RD1V1/B01U1NV9HV3/hKZXJJ74g2JcISq4K3QC1eG9", - "slack_jenkins_channel": "fdio-jobs-monitoring", - "slack_jenkins_receiver": "jenkins-slack-receiver", - "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": [ - "778f4f9d-dea8-e5bd-c9cf-f7a7e2d3a24e" - ], - "datacenters": [ - "yul1" - ], - "deployment_id": "4dc972fd-cb2c-51d8-f730-08b5f7554ceb", - "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 reschedule stanza specifies the group's rescheduling strategy. If\n # specified at the job level, the configuration will apply to all groups\n # within the job. If the reschedule stanza is present on both the job and the\n # group, they are merged with the group stanza taking the highest precedence\n # and then the job.\n reschedule {\n delay = \"30s\"\n delay_function = \"constant\"\n unlimited = 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\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 restart stanza configures a tasks's behavior on task failure. Restarts\n # happen on the client that is running the task.\n #\n # https://www.nomadproject.io/docs/job-specification/restart\n #\n restart {\n interval = \"30m\"\n attempts = 40\n delay = \"15s\"\n mode = \"delay\"\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-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\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-slack-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']\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 - match_re:\n alertname: JenkinsJob.*\n receiver: jenkins-slack-receiver\n routes:\n - match:\n severity: critical\n receiver: 'jenkins-slack-receiver'\n\n - match_re:\n service: .*\n receiver: default-slack-receiver\n routes:\n - match:\n severity: critical\n receiver: 'default-slack-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 equal: ['alertname', 'instance']\n\nreceivers:\n- name: 'jenkins-slack-receiver'\n slack_configs:\n - api_url: 'TE07RD1V1/B01U1NV9HV3/hKZXJJ74g2JcISq4K3QC1eG9'\n channel: '#fdio-jobs-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 }}\n\n- name: 'default-slack-receiver'\n slack_configs:\n - api_url: 'TE07RD1V1/B01UUK23B6C/hZTcCu42FUv8d6rtirHtcYIi'\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": "8259282", - "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.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": "cf7f3cd265a99a6f72f774f25564f1ec0e9e2c268a8f76112aed6cffe73bc4d4", - "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 reschedule stanza specifies the group's rescheduling strategy. If\n # specified at the job level, the configuration will apply to all groups\n # within the job. If the reschedule stanza is present on both the job and the\n # group, they are merged with the group stanza taking the highest precedence\n # and then the job.\n reschedule {\n delay = \"30s\"\n delay_function = \"constant\"\n unlimited = 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\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 # The restart stanza configures a tasks's behavior on task failure. Restarts\n # happen on the client that is running the task.\n #\n # https://www.nomadproject.io/docs/job-specification/restart\n #\n restart {\n interval = \"30m\"\n attempts = 40\n delay = \"15s\"\n mode = \"delay\"\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 = [ \"172.17.0.1\" ]\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 HTTP\n source = \"https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/blackbox_exporter_http.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 # 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 = 1000\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 reschedule stanza specifies the group's rescheduling strategy. If\n # specified at the job level, the configuration will apply to all groups\n # within the job. If the reschedule stanza is present on both the job and the\n # group, they are merged with the group stanza taking the highest precedence\n # and then the job.\n reschedule {\n delay = \"30s\"\n delay_function = \"constant\"\n unlimited = 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\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 restart stanza configures a tasks's behavior on task failure. Restarts\n # happen on the client that is running the task.\n #\n # https://www.nomadproject.io/docs/job-specification/restart\n #\n restart {\n interval = \"30m\"\n attempts = 40\n delay = \"15s\"\n mode = \"delay\"\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 = [ \"172.17.0.1\" ]\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 HTTP\n source = \"https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/blackbox_exporter_http.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 # 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": "1000", - "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": [ - "01d60c86-d59b-83ac-78c8-a903ac63816e" - ], - "datacenters": [ - "yul1" - ], - "deployment_id": "6d9fa6f6-7f84-4765-9488-7d92f32ec4df", - "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 reschedule stanza specifies the group's rescheduling strategy. If\n # specified at the job level, the configuration will apply to all groups\n # within the job. If the reschedule stanza is present on both the job and the\n # group, they are merged with the group stanza taking the highest precedence\n # and then the job.\n reschedule {\n delay = \"30s\"\n delay_function = \"constant\"\n unlimited = 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\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 # The restart stanza configures a tasks's behavior on task failure. Restarts\n # happen on the client that is running the task.\n #\n # https://www.nomadproject.io/docs/job-specification/restart\n #\n restart {\n interval = \"30m\"\n attempts = 40\n delay = \"15s\"\n mode = \"delay\"\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 = [ \"172.17.0.1\" ]\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 HTTP\n source = \"https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/blackbox_exporter_http.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 # 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 = 1000\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": "7575032", - "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", - "name": "nomad_job_mc", - "provider": "provider[\"registry.terraform.io/hashicorp/template\"]", - "instances": [ - { - "schema_version": 0, - "attributes": { - "filename": null, - "id": "e9e956124e6fed4268bec199b9d7fd7aaff506e906b53621c6dc0e3116c40f52", - "rendered": "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.2021-07-27T02-40-15Z\"\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", - "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 = \"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 %{ 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 entrypoint = [\n \"/bin/sh\",\n \"-c\",\n \"${command}\"\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 %{ 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 }\n}\n", - "vars": { - "access_key": "minio", - "command": "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", - "datacenters": "yul1", - "envs": "", - "image": "minio/mc:RELEASE.2021-07-27T02-40-15Z", - "job_name": "prod-mc", - "minio_port": "9000", - "minio_service_name": "storage", - "secret_key": "minio123", - "service_name": "mc", - "use_vault_provider": "false" - } - }, - "sensitive_attributes": [] - } - ] - }, - { - "module": "module.minio", - "mode": "data", - "type": "template_file", - "name": "nomad_job_minio", - "provider": "provider[\"registry.terraform.io/hashicorp/template\"]", - "instances": [ - { - "schema_version": 0, - "attributes": { - "filename": null, - "id": "68243169c0df15ef6b56803101ed0c744a84545c34df366ee4036052c6292ef3", - "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 # 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 # 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 # https://www.nomadproject.io/docs/job-specification/group\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 restart stanza configures a tasks's behavior on task failure. Restarts\n # happen on the client that is running the task.\n #\n # https://www.nomadproject.io/docs/job-specification/restart\n #\n restart {\n interval = \"30m\"\n attempts = 40\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 # 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.2021-07-27T02-40-15Z\"\n dns_servers = [ \"172.17.0.1\" ]\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 # https://www.nomadproject.io/docs/job-specification/service\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 # https://www.nomadproject.io/docs/job-specification/resources\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 # https://www.nomadproject.io/docs/job-specification/network\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 # 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 # 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 # https://www.nomadproject.io/docs/job-specification/group\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 restart stanza configures a tasks's behavior on task failure. Restarts\n # happen on the client that is running the task.\n #\n # https://www.nomadproject.io/docs/job-specification/restart\n #\n restart {\n interval = \"30m\"\n attempts = 40\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 # 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 = [ \"172.17.0.1\" ]\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 # https://www.nomadproject.io/docs/job-specification/service\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 # https://www.nomadproject.io/docs/job-specification/resources\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 # https://www.nomadproject.io/docs/job-specification/network\n #\n network {\n port \"http\" {\n static = ${port}\n }\n }\n }\n }\n }\n}\n", - "vars": { - "access_key": "minio", - "cpu": "40000", - "cpu_proxy": "200", - "data_dir": "/data/", - "datacenters": "yul1", - "envs": "MINIO_BROWSER=\"off\"", - "group_count": "4", - "host": "http://10.32.8.1{4...7}", - "host_volume": "prod-volume-data1-1", - "image": "minio/minio:RELEASE.2021-07-27T02-40-15Z", - "job_name": "prod-minio", - "memory": "40000", - "memory_proxy": "128", - "port": "9000", - "secret_key": "minio123", - "service_name": "storage", - "upstreams": "[]", - "use_canary": "true", - "use_host_volume": "true", - "use_vault_provider": "false" - } - }, - "sensitive_attributes": [] - } - ] - }, - { - "module": "module.minio", - "mode": "managed", - "type": "nomad_job", - "name": "nomad_job_minio", - "provider": "provider[\"registry.terraform.io/hashicorp/nomad\"].yul1", - "instances": [ - { - "schema_version": 0, - "attributes": { - "allocation_ids": [ - "844e34c1-13e6-3ddb-9402-e876230e5cdb", - "44e1a0f0-5328-eafb-3beb-bfd53af2b618", - "a6695ea0-2563-72ae-1791-a08ef933ff72", - "51126acb-945c-2629-5787-76b85677ddd0" - ], - "datacenters": [ - "yul1" - ], - "deployment_id": "33d8013c-7c7c-6828-a204-58d9286b61ef", - "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 # 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 # 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 # https://www.nomadproject.io/docs/job-specification/group\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 restart stanza configures a tasks's behavior on task failure. Restarts\n # happen on the client that is running the task.\n #\n # https://www.nomadproject.io/docs/job-specification/restart\n #\n restart {\n interval = \"30m\"\n attempts = 40\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 # 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.2021-07-27T02-40-15Z\"\n dns_servers = [ \"172.17.0.1\" ]\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 # https://www.nomadproject.io/docs/job-specification/service\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 # https://www.nomadproject.io/docs/job-specification/resources\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 # https://www.nomadproject.io/docs/job-specification/network\n #\n network {\n port \"http\" {\n static = 9000\n }\n }\n }\n }\n }\n}\n", - "json": null, - "modify_index": "8949013", - "name": "prod-minio", - "namespace": "default", - "policy_override": null, - "purge_on_destroy": null, - "region": "global", - "task_groups": [ - { - "count": 4, - "meta": {}, - "name": "prod-group1-minio", - "task": [ - { - "driver": "docker", - "meta": {}, - "name": "prod-task1-minio", - "volume_mounts": [ - { - "destination": "/data/", - "read_only": false, - "volume": "prod-volume1-minio" - } - ] - } - ], - "volumes": [ - { - "name": "prod-volume1-minio", - "read_only": false, - "source": "prod-volume-data1-1", - "type": "host" - } - ] - } - ], - "type": "service" - }, - "sensitive_attributes": [], - "private": "bnVsbA==", - "dependencies": [ - "module.minio.data.template_file.nomad_job_minio" - ] - } - ] - }, - { - "module": "module.nginx", - "mode": "data", - "type": "template_file", - "name": "nomad_job_nginx", - "provider": "provider[\"registry.terraform.io/hashicorp/template\"]", - "instances": [ - { - "schema_version": 0, - "attributes": { - "filename": null, - "id": "f6d48eb498752cd7c1c73a26a146961048a1b7f7d53602df55b413f27226e519", - "rendered": "job \"prod-nginx\" {\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 = 0\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 # 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 = false\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 = 0\n }\n\n # The reschedule stanza specifies the group's rescheduling strategy. If\n # specified at the job level, the configuration will apply to all groups\n # within the job. If the reschedule stanza is present on both the job and the\n # group, they are merged with the group stanza taking the highest precedence\n # and then the job.\n reschedule {\n delay = \"30s\"\n delay_function = \"constant\"\n unlimited = 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-nginx\" {\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 # https://www.nomadproject.io/docs/job-specification/volume\n \n volume \"prod-volume1-nginx\" {\n type = \"host\"\n read_only = false\n source = \"prod-volume-data1-1\"\n }\n \n\n # The restart stanza configures a tasks's behavior on task failure. Restarts\n # happen on the client that is running the task.\n #\n # https://www.nomadproject.io/docs/job-specification/restart\n #\n restart {\n interval = \"30m\"\n attempts = 40\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-nginx\" {\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 = \"nginx:stable\"\n port_map {\n https = 443\n }\n privileged = false\n volumes = [\n \"/etc/ssl/certs/docs.nginx.service.consul.crt:/etc/ssl/certs/docs.nginx.service.consul.crt\",\n \"/etc/ssl/private/docs.nginx.service.consul.key:/etc/ssl/private/docs.nginx.service.consul.key\",\n \"/etc/ssl/certs/logs.nginx.service.consul.crt:/etc/ssl/certs/logs.nginx.service.consul.crt\",\n \"/etc/ssl/private/logs.nginx.service.consul.key:/etc/ssl/private/logs.nginx.service.consul.key\",\n \"custom/upstream.conf:/etc/nginx/conf.d/upstream.conf\",\n \"custom/logs.conf:/etc/nginx/conf.d/logs.conf\",\n \"custom/docs.conf:/etc/nginx/conf.d/docs.conf\"\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 # 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.html\n #\n template {\n data = \u003c\u003cEOH\n upstream storage {\n {{ range service \"storage\" }}\n server {{ .Address }}:{{ .Port }};\n {{ end }}\n }\n EOH\n destination = \"custom/upstream.conf\"\n }\n template {\n data = \u003c\u003cEOH\n server {\n listen 443 ssl default_server;\n server_name logs.nginx.service.consul;\n keepalive_timeout 70;\n ssl_session_cache shared:SSL:10m;\n ssl_session_timeout 10m;\n ssl_protocols TLSv1.2;\n ssl_prefer_server_ciphers on;\n ssl_ciphers \"ECDHE-ECDSA-AES256-GCM-SHA384:ECDHE-RSA-AES256-GCM-SHA384:ECDHE-ECDSA-CHACHA20-POLY1305:ECDHE-RSA-CHACHA20-POLY1305:ECDHE-ECDSA-AES256-SHA384:ECDHE-RSA-AES256-SHA384\";\n ssl_certificate /etc/ssl/certs/logs.nginx.service.consul.crt;\n ssl_certificate_key /etc/ssl/private/logs.nginx.service.consul.key;\n location / {\n chunked_transfer_encoding off;\n proxy_connect_timeout 300;\n proxy_http_version 1.1;\n proxy_set_header Host $host:$server_port;\n proxy_set_header Connection \"\";\n proxy_pass http://storage/logs.fd.io/;\n server_name_in_redirect off;\n }\n location ~ (.*html.gz)$ {\n add_header Content-Encoding gzip;\n add_header Content-Type text/html;\n chunked_transfer_encoding off;\n proxy_connect_timeout 300;\n proxy_http_version 1.1;\n proxy_set_header Host $host:$server_port;\n proxy_set_header Connection \"\";\n proxy_pass http://storage/logs.fd.io/$1;\n server_name_in_redirect off;\n }\n location ~ (.*txt.gz|.*log.gz)$ {\n add_header Content-Encoding gzip;\n add_header Content-Type text/plain;\n chunked_transfer_encoding off;\n proxy_connect_timeout 300;\n proxy_http_version 1.1;\n proxy_set_header Host $host:$server_port;\n proxy_set_header Connection \"\";\n proxy_pass http://storage/logs.fd.io/$1;\n server_name_in_redirect off;\n }\n location ~ (.*xml.gz)$ {\n add_header Content-Encoding gzip;\n add_header Content-Type application/xml;\n chunked_transfer_encoding off;\n proxy_connect_timeout 300;\n proxy_http_version 1.1;\n proxy_set_header Host $host:$server_port;\n proxy_set_header Connection \"\";\n proxy_pass http://storage/logs.fd.io/$1;\n server_name_in_redirect off;\n }\n }\n EOH\n destination = \"custom/logs.conf\"\n }\n template {\n data = \u003c\u003cEOH\n server {\n listen 443 ssl;\n server_name docs.nginx.service.consul;\n keepalive_timeout 70;\n ssl_session_cache shared:SSL:10m;\n ssl_session_timeout 10m;\n ssl_protocols TLSv1.2;\n ssl_prefer_server_ciphers on;\n ssl_ciphers \"ECDHE-ECDSA-AES256-GCM-SHA384:ECDHE-RSA-AES256-GCM-SHA384:ECDHE-ECDSA-CHACHA20-POLY1305:ECDHE-RSA-CHACHA20-POLY1305:ECDHE-ECDSA-AES256-SHA384:ECDHE-RSA-AES256-SHA384\";\n ssl_certificate /etc/ssl/certs/docs.nginx.service.consul.crt;\n ssl_certificate_key /etc/ssl/private/docs.nginx.service.consul.key;\n location / {\n chunked_transfer_encoding off;\n proxy_connect_timeout 300;\n proxy_http_version 1.1;\n proxy_set_header Host $host:$server_port;\n proxy_set_header Connection \"\";\n proxy_pass http://storage/docs.fd.io/;\n server_name_in_redirect off;\n }\n }\n EOH\n destination = \"custom/docs.conf\"\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 = \"nginx\"\n port = \"https\"\n tags = [ \"docs\", \"logs\" ]\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 = 2000\n memory = 4096\n network {\n mode = \"bridge\"\n port \"https\" {\n static = 443\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 = 0\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 # 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 = false\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 = 0\n }\n\n # The reschedule stanza specifies the group's rescheduling strategy. If\n # specified at the job level, the configuration will apply to all groups\n # within the job. If the reschedule stanza is present on both the job and the\n # group, they are merged with the group stanza taking the highest precedence\n # and then the job.\n reschedule {\n delay = \"30s\"\n delay_function = \"constant\"\n unlimited = 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-nginx\" {\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 # https://www.nomadproject.io/docs/job-specification/volume\n %{ if use_host_volume }\n volume \"prod-volume1-nginx\" {\n type = \"host\"\n read_only = false\n source = \"${host_volume}\"\n }\n %{ endif }\n\n # The restart stanza configures a tasks's behavior on task failure. Restarts\n # happen on the client that is running the task.\n #\n # https://www.nomadproject.io/docs/job-specification/restart\n #\n restart {\n interval = \"30m\"\n attempts = 40\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-nginx\" {\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 = \"nginx:stable\"\n port_map {\n https = 443\n }\n privileged = false\n volumes = [\n \"/etc/ssl/certs/docs.nginx.service.consul.crt:/etc/ssl/certs/docs.nginx.service.consul.crt\",\n \"/etc/ssl/private/docs.nginx.service.consul.key:/etc/ssl/private/docs.nginx.service.consul.key\",\n \"/etc/ssl/certs/logs.nginx.service.consul.crt:/etc/ssl/certs/logs.nginx.service.consul.crt\",\n \"/etc/ssl/private/logs.nginx.service.consul.key:/etc/ssl/private/logs.nginx.service.consul.key\",\n \"custom/upstream.conf:/etc/nginx/conf.d/upstream.conf\",\n \"custom/logs.conf:/etc/nginx/conf.d/logs.conf\",\n \"custom/docs.conf:/etc/nginx/conf.d/docs.conf\"\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 # 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.html\n #\n template {\n data = \u003c\u003cEOH\n upstream storage {\n {{ range service \"storage\" }}\n server {{ .Address }}:{{ .Port }};\n {{ end }}\n }\n EOH\n destination = \"custom/upstream.conf\"\n }\n template {\n data = \u003c\u003cEOH\n server {\n listen 443 ssl default_server;\n server_name logs.nginx.service.consul;\n keepalive_timeout 70;\n ssl_session_cache shared:SSL:10m;\n ssl_session_timeout 10m;\n ssl_protocols TLSv1.2;\n ssl_prefer_server_ciphers on;\n ssl_ciphers \"ECDHE-ECDSA-AES256-GCM-SHA384:ECDHE-RSA-AES256-GCM-SHA384:ECDHE-ECDSA-CHACHA20-POLY1305:ECDHE-RSA-CHACHA20-POLY1305:ECDHE-ECDSA-AES256-SHA384:ECDHE-RSA-AES256-SHA384\";\n ssl_certificate /etc/ssl/certs/logs.nginx.service.consul.crt;\n ssl_certificate_key /etc/ssl/private/logs.nginx.service.consul.key;\n location / {\n chunked_transfer_encoding off;\n proxy_connect_timeout 300;\n proxy_http_version 1.1;\n proxy_set_header Host $host:$server_port;\n proxy_set_header Connection \"\";\n proxy_pass http://storage/logs.fd.io/;\n server_name_in_redirect off;\n }\n location ~ (.*html.gz)$ {\n add_header Content-Encoding gzip;\n add_header Content-Type text/html;\n chunked_transfer_encoding off;\n proxy_connect_timeout 300;\n proxy_http_version 1.1;\n proxy_set_header Host $host:$server_port;\n proxy_set_header Connection \"\";\n proxy_pass http://storage/logs.fd.io/$1;\n server_name_in_redirect off;\n }\n location ~ (.*txt.gz|.*log.gz)$ {\n add_header Content-Encoding gzip;\n add_header Content-Type text/plain;\n chunked_transfer_encoding off;\n proxy_connect_timeout 300;\n proxy_http_version 1.1;\n proxy_set_header Host $host:$server_port;\n proxy_set_header Connection \"\";\n proxy_pass http://storage/logs.fd.io/$1;\n server_name_in_redirect off;\n }\n location ~ (.*xml.gz)$ {\n add_header Content-Encoding gzip;\n add_header Content-Type application/xml;\n chunked_transfer_encoding off;\n proxy_connect_timeout 300;\n proxy_http_version 1.1;\n proxy_set_header Host $host:$server_port;\n proxy_set_header Connection \"\";\n proxy_pass http://storage/logs.fd.io/$1;\n server_name_in_redirect off;\n }\n }\n EOH\n destination = \"custom/logs.conf\"\n }\n template {\n data = \u003c\u003cEOH\n server {\n listen 443 ssl;\n server_name docs.nginx.service.consul;\n keepalive_timeout 70;\n ssl_session_cache shared:SSL:10m;\n ssl_session_timeout 10m;\n ssl_protocols TLSv1.2;\n ssl_prefer_server_ciphers on;\n ssl_ciphers \"ECDHE-ECDSA-AES256-GCM-SHA384:ECDHE-RSA-AES256-GCM-SHA384:ECDHE-ECDSA-CHACHA20-POLY1305:ECDHE-RSA-CHACHA20-POLY1305:ECDHE-ECDSA-AES256-SHA384:ECDHE-RSA-AES256-SHA384\";\n ssl_certificate /etc/ssl/certs/docs.nginx.service.consul.crt;\n ssl_certificate_key /etc/ssl/private/docs.nginx.service.consul.key;\n location / {\n chunked_transfer_encoding off;\n proxy_connect_timeout 300;\n proxy_http_version 1.1;\n proxy_set_header Host $host:$server_port;\n proxy_set_header Connection \"\";\n proxy_pass http://storage/docs.fd.io/;\n server_name_in_redirect off;\n }\n }\n EOH\n destination = \"custom/docs.conf\"\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 = \"nginx\"\n port = \"https\"\n tags = [ \"docs\", \"logs\" ]\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 = 2000\n memory = 4096\n network {\n mode = \"bridge\"\n port \"https\" {\n static = 443\n }\n }\n }\n }\n }\n}", - "vars": { - "datacenters": "yul1", - "host_volume": "prod-volume-data1-1", - "job_name": "prod-nginx", - "use_host_volume": "true" - } - }, - "sensitive_attributes": [] - } - ] - }, - { - "module": "module.nginx", - "mode": "managed", - "type": "nomad_job", - "name": "nomad_job_nginx", - "provider": "provider[\"registry.terraform.io/hashicorp/nomad\"].yul1", - "instances": [ - { - "schema_version": 0, - "attributes": { - "allocation_ids": [ - "8a81e41d-911d-e083-9bcd-b5b3c70b33fa" - ], - "datacenters": [ - "yul1" - ], - "deployment_id": "", - "deployment_status": "", - "deregister_on_destroy": true, - "deregister_on_id_change": true, - "detach": false, - "id": "prod-nginx", - "jobspec": "job \"prod-nginx\" {\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 = 0\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 # 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 = false\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 = 0\n }\n\n # The reschedule stanza specifies the group's rescheduling strategy. If\n # specified at the job level, the configuration will apply to all groups\n # within the job. If the reschedule stanza is present on both the job and the\n # group, they are merged with the group stanza taking the highest precedence\n # and then the job.\n reschedule {\n delay = \"30s\"\n delay_function = \"constant\"\n unlimited = 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-nginx\" {\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 # https://www.nomadproject.io/docs/job-specification/volume\n \n volume \"prod-volume1-nginx\" {\n type = \"host\"\n read_only = false\n source = \"prod-volume-data1-1\"\n }\n \n\n # The restart stanza configures a tasks's behavior on task failure. Restarts\n # happen on the client that is running the task.\n #\n # https://www.nomadproject.io/docs/job-specification/restart\n #\n restart {\n interval = \"30m\"\n attempts = 40\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-nginx\" {\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 = \"nginx:stable\"\n port_map {\n https = 443\n }\n privileged = false\n volumes = [\n \"/etc/ssl/certs/docs.nginx.service.consul.crt:/etc/ssl/certs/docs.nginx.service.consul.crt\",\n \"/etc/ssl/private/docs.nginx.service.consul.key:/etc/ssl/private/docs.nginx.service.consul.key\",\n \"/etc/ssl/certs/logs.nginx.service.consul.crt:/etc/ssl/certs/logs.nginx.service.consul.crt\",\n \"/etc/ssl/private/logs.nginx.service.consul.key:/etc/ssl/private/logs.nginx.service.consul.key\",\n \"custom/upstream.conf:/etc/nginx/conf.d/upstream.conf\",\n \"custom/logs.conf:/etc/nginx/conf.d/logs.conf\",\n \"custom/docs.conf:/etc/nginx/conf.d/docs.conf\"\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 # 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.html\n #\n template {\n data = \u003c\u003cEOH\n upstream storage {\n {{ range service \"storage\" }}\n server {{ .Address }}:{{ .Port }};\n {{ end }}\n }\n EOH\n destination = \"custom/upstream.conf\"\n }\n template {\n data = \u003c\u003cEOH\n server {\n listen 443 ssl default_server;\n server_name logs.nginx.service.consul;\n keepalive_timeout 70;\n ssl_session_cache shared:SSL:10m;\n ssl_session_timeout 10m;\n ssl_protocols TLSv1.2;\n ssl_prefer_server_ciphers on;\n ssl_ciphers \"ECDHE-ECDSA-AES256-GCM-SHA384:ECDHE-RSA-AES256-GCM-SHA384:ECDHE-ECDSA-CHACHA20-POLY1305:ECDHE-RSA-CHACHA20-POLY1305:ECDHE-ECDSA-AES256-SHA384:ECDHE-RSA-AES256-SHA384\";\n ssl_certificate /etc/ssl/certs/logs.nginx.service.consul.crt;\n ssl_certificate_key /etc/ssl/private/logs.nginx.service.consul.key;\n location / {\n chunked_transfer_encoding off;\n proxy_connect_timeout 300;\n proxy_http_version 1.1;\n proxy_set_header Host $host:$server_port;\n proxy_set_header Connection \"\";\n proxy_pass http://storage/logs.fd.io/;\n server_name_in_redirect off;\n }\n location ~ (.*html.gz)$ {\n add_header Content-Encoding gzip;\n add_header Content-Type text/html;\n chunked_transfer_encoding off;\n proxy_connect_timeout 300;\n proxy_http_version 1.1;\n proxy_set_header Host $host:$server_port;\n proxy_set_header Connection \"\";\n proxy_pass http://storage/logs.fd.io/$1;\n server_name_in_redirect off;\n }\n location ~ (.*txt.gz|.*log.gz)$ {\n add_header Content-Encoding gzip;\n add_header Content-Type text/plain;\n chunked_transfer_encoding off;\n proxy_connect_timeout 300;\n proxy_http_version 1.1;\n proxy_set_header Host $host:$server_port;\n proxy_set_header Connection \"\";\n proxy_pass http://storage/logs.fd.io/$1;\n server_name_in_redirect off;\n }\n location ~ (.*xml.gz)$ {\n add_header Content-Encoding gzip;\n add_header Content-Type application/xml;\n chunked_transfer_encoding off;\n proxy_connect_timeout 300;\n proxy_http_version 1.1;\n proxy_set_header Host $host:$server_port;\n proxy_set_header Connection \"\";\n proxy_pass http://storage/logs.fd.io/$1;\n server_name_in_redirect off;\n }\n }\n EOH\n destination = \"custom/logs.conf\"\n }\n template {\n data = \u003c\u003cEOH\n server {\n listen 443 ssl;\n server_name docs.nginx.service.consul;\n keepalive_timeout 70;\n ssl_session_cache shared:SSL:10m;\n ssl_session_timeout 10m;\n ssl_protocols TLSv1.2;\n ssl_prefer_server_ciphers on;\n ssl_ciphers \"ECDHE-ECDSA-AES256-GCM-SHA384:ECDHE-RSA-AES256-GCM-SHA384:ECDHE-ECDSA-CHACHA20-POLY1305:ECDHE-RSA-CHACHA20-POLY1305:ECDHE-ECDSA-AES256-SHA384:ECDHE-RSA-AES256-SHA384\";\n ssl_certificate /etc/ssl/certs/docs.nginx.service.consul.crt;\n ssl_certificate_key /etc/ssl/private/docs.nginx.service.consul.key;\n location / {\n chunked_transfer_encoding off;\n proxy_connect_timeout 300;\n proxy_http_version 1.1;\n proxy_set_header Host $host:$server_port;\n proxy_set_header Connection \"\";\n proxy_pass http://storage/docs.fd.io/;\n server_name_in_redirect off;\n }\n }\n EOH\n destination = \"custom/docs.conf\"\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 = \"nginx\"\n port = \"https\"\n tags = [ \"docs\", \"logs\" ]\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 = 2000\n memory = 4096\n network {\n mode = \"bridge\"\n port \"https\" {\n static = 443\n }\n }\n }\n }\n }\n}", - "json": null, - "modify_index": "8993958", - "name": "prod-nginx", - "namespace": "default", - "policy_override": null, - "purge_on_destroy": null, - "region": "global", - "task_groups": [ - { - "count": 1, - "meta": {}, - "name": "prod-group1-nginx", - "task": [ - { - "driver": "docker", - "meta": {}, - "name": "prod-task1-nginx", - "volume_mounts": [] - } - ], - "volumes": [ - { - "name": "prod-volume1-nginx", - "read_only": false, - "source": "prod-volume-data1-1", - "type": "host" - } - ] - } - ], - "type": "service" - }, - "sensitive_attributes": [], - "private": "bnVsbA==", - "dependencies": [ - "module.nginx.data.template_file.nomad_job_nginx" - ] - } - ] - }, - { - "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": "170256de3b14e7562d5d4b196864b5c0ad562cf124c5866d85bd81a3f35bcc27", - "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 reschedule stanza specifies the group's rescheduling strategy. If\n # specified at the job level, the configuration will apply to all groups\n # within the job. If the reschedule stanza is present on both the job and the\n # group, they are merged with the group stanza taking the highest precedence\n # and then the job.\n reschedule {\n delay = \"30s\"\n delay_function = \"constant\"\n unlimited = 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\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 restart stanza configures a tasks's behavior on task failure. Restarts\n # happen on the client that is running the task.\n #\n # https://www.nomadproject.io/docs/job-specification/restart\n #\n restart {\n interval = \"30m\"\n attempts = 40\n delay = \"15s\"\n mode = \"delay\"\n }\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-2.28.1.linux-amd64/prometheus\"\n args = [\n \"--config.file=secrets/prometheus.yml\",\n \"--storage.tsdb.path=/data/prometheus/\",\n \"--storage.tsdb.retention.time=7d\"\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/v2.28.1/prometheus-2.28.1.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: \"Jenkins Job Health Exporter\"\n rules:\n - alert: JenkinsJobHealthExporterFailures\n expr: jenkins_job_failure{id=~\".*\"} \u003e jenkins_job_success{id=~\".*\"}\n for: 0m\n labels:\n severity: critical\n annotations:\n summary: \"Jenkins Job Health detected high failure rate on jenkins jobs.\"\n description: \"Job: {{ $labels.id }}\"\n - alert: JenkinsJobHealthExporterUnstable\n expr: jenkins_job_unstable{id=~\".*\"} \u003e jenkins_job_success{id=~\".*\"}\n for: 0m\n labels:\n severity: warning\n annotations:\n summary: \"Jenkins Job Health detected high unstable rate on jenkins jobs.\"\n description: \"Job: {{ $labels.id }}\"\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: 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: [ '10.30.51.22:8500' ]\n - targets: [ '10.30.51.24:8500' ]\n - targets: [ '10.30.51.25:8500' ]\n - targets: [ '10.30.51.26:8500' ]\n - targets: [ '10.30.51.28:8500' ]\n - targets: [ '10.30.51.29:8500' ]\n - targets: [ '10.30.51.30:8500' ]\n - targets: [ '10.30.51.39:8500' ]\n - targets: [ '10.30.51.40:8500' ]\n - targets: [ '10.30.51.50:8500' ]\n - targets: [ '10.30.51.51:8500' ]\n - targets: [ '10.30.51.65:8500' ]\n - targets: [ '10.30.51.66:8500' ]\n - targets: [ '10.30.51.67:8500' ]\n - targets: [ '10.30.51.68:8500' ]\n - targets: [ '10.30.51.70:8500' ]\n - targets: [ '10.30.51.71:8500' ]\n - targets: [ '10.32.8.14:8500' ]\n - targets: [ '10.32.8.15:8500' ]\n - targets: [ '10.32.8.16:8500' ]\n - targets: [ '10.32.8.17:8500' ]\n metrics_path: /v1/agent/metrics\n params:\n format: [ 'prometheus' ]\n\n - job_name: 'Blackbox Exporter (icmp)'\n static_configs:\n - targets: [ 'gerrit.fd.io' ]\n - targets: [ 'jenkins.fd.io' ]\n - targets: [ '10.32.8.17' ]\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: 'Jenkins Job Health Exporter'\n static_configs:\n - targets: [ '10.30.51.22:9186' ]\n metric_relabel_configs:\n - source_labels: [ __name__ ]\n regex: '^(vpp.*|csit.*)_(success|failure|total|unstable|reqtime_ms)$'\n action: replace\n replacement: '$1'\n target_label: id\n - source_labels: [ __name__ ]\n regex: '^(vpp.*|csit.*)_(success|failure|total|unstable|reqtime_ms)$'\n replacement: 'jenkins_job_$2'\n target_label: __name__\n\n - job_name: 'Node Exporter'\n static_configs:\n - targets: [ '10.30.51.22:9100' ]\n - targets: [ '10.30.51.24:9100' ]\n - targets: [ '10.30.51.25:9100' ]\n - targets: [ '10.30.51.26:9100' ]\n - targets: [ '10.30.51.28:9100' ]\n - targets: [ '10.30.51.29:9100' ]\n - targets: [ '10.30.51.30:9100' ]\n - targets: [ '10.30.51.39:9100' ]\n - targets: [ '10.30.51.40:9100' ]\n - targets: [ '10.30.51.50:9100' ]\n - targets: [ '10.30.51.51:9100' ]\n - targets: [ '10.30.51.65:9100' ]\n - targets: [ '10.30.51.66:9100' ]\n - targets: [ '10.30.51.67:9100' ]\n - targets: [ '10.30.51.68:9100' ]\n - targets: [ '10.30.51.70:9100' ]\n - targets: [ '10.30.51.71:9100' ]\n - targets: [ '10.32.8.14:9100' ]\n - targets: [ '10.32.8.15:9100' ]\n - targets: [ '10.32.8.16:9100' ]\n - targets: [ '10.32.8.17:9100' ]\n\n - job_name: 'Alertmanager'\n consul_sd_configs:\n - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n services: [ 'alertmanager' ]\n\n - job_name: 'Grafana'\n consul_sd_configs:\n - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n services: [ 'grafana' ]\n\n - job_name: 'Prometheus'\n consul_sd_configs:\n - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n services: [ 'prometheus' ]\n\n - job_name: 'Minio'\n bearer_token: eyJhbGciOiJIUzUxMiIsInR5cCI6IkpXVCJ9.eyJleHAiOjQ3NjQ1ODEzMzcsImlzcyI6InByb21ldGhldXMiLCJzdWIiOiJtaW5pbyJ9.oeTw3EIaiFmlDikrHXWiWXMH2vxLfDLkfjEC7G2N3M_keH_xyA_l2ofLLNYtopa_3GCEZnxLQdPuFZrmgpkDWg\n consul_sd_configs:\n - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n services: [ 'storage' ]\n metrics_path: /minio/prometheus/metrics\nEOH\n }\n\n # The service stanza instructs Nomad to register a service with Consul.\n #\n # For more information and examples on the \"task\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/service\n #\n service {\n name = \"prometheus\"\n port = \"prometheus\"\n tags = [ \"prometheus${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 reschedule stanza specifies the group's rescheduling strategy. If\n # specified at the job level, the configuration will apply to all groups\n # within the job. If the reschedule stanza is present on both the job and the\n # group, they are merged with the group stanza taking the highest precedence\n # and then the job.\n reschedule {\n delay = \"30s\"\n delay_function = \"constant\"\n unlimited = 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\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 = ${group_count}\n\n # The restart stanza configures a tasks's behavior on task failure. Restarts\n # happen on the client that is running the task.\n #\n # https://www.nomadproject.io/docs/job-specification/restart\n #\n restart {\n interval = \"30m\"\n attempts = 40\n delay = \"15s\"\n mode = \"delay\"\n }\n\n # The volume stanza allows the group to specify that it requires a given\n # volume from the cluster.\n #\n # For more information and examples on the \"volume\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/volume\n #\n %{ if use_host_volume }\n volume \"prod-volume1-${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=7d\"\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: \"Jenkins Job Health Exporter\"\n rules:\n - alert: JenkinsJobHealthExporterFailures\n expr: jenkins_job_failure{id=~\".*\"} \u003e jenkins_job_success{id=~\".*\"}\n for: 0m\n labels:\n severity: critical\n annotations:\n summary: \"Jenkins Job Health detected high failure rate on jenkins jobs.\"\n description: \"Job: {{ $labels.id }}\"\n - alert: JenkinsJobHealthExporterUnstable\n expr: jenkins_job_unstable{id=~\".*\"} \u003e jenkins_job_success{id=~\".*\"}\n for: 0m\n labels:\n severity: warning\n annotations:\n summary: \"Jenkins Job Health detected high unstable rate on jenkins jobs.\"\n description: \"Job: {{ $labels.id }}\"\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: 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: [ '10.30.51.22:8500' ]\n - targets: [ '10.30.51.24:8500' ]\n - targets: [ '10.30.51.25:8500' ]\n - targets: [ '10.30.51.26:8500' ]\n - targets: [ '10.30.51.28:8500' ]\n - targets: [ '10.30.51.29:8500' ]\n - targets: [ '10.30.51.30:8500' ]\n - targets: [ '10.30.51.39:8500' ]\n - targets: [ '10.30.51.40:8500' ]\n - targets: [ '10.30.51.50:8500' ]\n - targets: [ '10.30.51.51:8500' ]\n - targets: [ '10.30.51.65:8500' ]\n - targets: [ '10.30.51.66:8500' ]\n - targets: [ '10.30.51.67:8500' ]\n - targets: [ '10.30.51.68:8500' ]\n - targets: [ '10.30.51.70:8500' ]\n - targets: [ '10.30.51.71:8500' ]\n - targets: [ '10.32.8.14:8500' ]\n - targets: [ '10.32.8.15:8500' ]\n - targets: [ '10.32.8.16:8500' ]\n - targets: [ '10.32.8.17:8500' ]\n metrics_path: /v1/agent/metrics\n params:\n format: [ 'prometheus' ]\n\n - job_name: 'Blackbox Exporter (icmp)'\n static_configs:\n - targets: [ 'gerrit.fd.io' ]\n - targets: [ 'jenkins.fd.io' ]\n - targets: [ '10.32.8.17' ]\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: 'Jenkins Job Health Exporter'\n static_configs:\n - targets: [ '10.30.51.22:9186' ]\n metric_relabel_configs:\n - source_labels: [ __name__ ]\n regex: '^(vpp.*|csit.*)_(success|failure|total|unstable|reqtime_ms)$'\n action: replace\n replacement: '$1'\n target_label: id\n - source_labels: [ __name__ ]\n regex: '^(vpp.*|csit.*)_(success|failure|total|unstable|reqtime_ms)$'\n replacement: 'jenkins_job_$2'\n target_label: __name__\n\n - job_name: 'Node Exporter'\n static_configs:\n - targets: [ '10.30.51.22:9100' ]\n - targets: [ '10.30.51.24:9100' ]\n - targets: [ '10.30.51.25:9100' ]\n - targets: [ '10.30.51.26:9100' ]\n - targets: [ '10.30.51.28:9100' ]\n - targets: [ '10.30.51.29:9100' ]\n - targets: [ '10.30.51.30:9100' ]\n - targets: [ '10.30.51.39:9100' ]\n - targets: [ '10.30.51.40:9100' ]\n - targets: [ '10.30.51.50:9100' ]\n - targets: [ '10.30.51.51:9100' ]\n - targets: [ '10.30.51.65:9100' ]\n - targets: [ '10.30.51.66:9100' ]\n - targets: [ '10.30.51.67:9100' ]\n - targets: [ '10.30.51.68:9100' ]\n - targets: [ '10.30.51.70:9100' ]\n - targets: [ '10.30.51.71:9100' ]\n - targets: [ '10.32.8.14:9100' ]\n - targets: [ '10.32.8.15:9100' ]\n - targets: [ '10.32.8.16:9100' ]\n - targets: [ '10.32.8.17:9100' ]\n\n - job_name: 'Alertmanager'\n consul_sd_configs:\n - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n services: [ 'alertmanager' ]\n\n - job_name: 'Grafana'\n consul_sd_configs:\n - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n services: [ 'grafana' ]\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/v2.28.1/prometheus-2.28.1.linux-amd64.tar.gz", - "use_canary": "true", - "use_host_volume": "true", - "use_vault_provider": "false", - "version": "2.28.1" - } - }, - "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": [ - "9b7311cc-95ba-fead-8c92-91148f48d218", - "5564fb46-6a89-1e92-7bcd-7f5fa55c42e8", - "519e4ea1-f088-069c-3bc2-eb6de1b36b9e", - "6f144324-2ee0-c1fd-0f71-c07cc1fda099", - "6776d9ca-70ba-129f-05a9-ca6fccdb6289", - "0fb06047-62e0-48e4-e352-63b4602407f2", - "ddb72c78-1f3f-2d1e-0157-7b7bb05aaa4a", - "67dfb1da-36a3-e442-5c66-8d6340f579c3" - ], - "datacenters": [ - "yul1" - ], - "deployment_id": "88fd2d42-3b5a-8e1e-3047-7a4f93417fd3", - "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 reschedule stanza specifies the group's rescheduling strategy. If\n # specified at the job level, the configuration will apply to all groups\n # within the job. If the reschedule stanza is present on both the job and the\n # group, they are merged with the group stanza taking the highest precedence\n # and then the job.\n reschedule {\n delay = \"30s\"\n delay_function = \"constant\"\n unlimited = 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\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 restart stanza configures a tasks's behavior on task failure. Restarts\n # happen on the client that is running the task.\n #\n # https://www.nomadproject.io/docs/job-specification/restart\n #\n restart {\n interval = \"30m\"\n attempts = 40\n delay = \"15s\"\n mode = \"delay\"\n }\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-2.28.1.linux-amd64/prometheus\"\n args = [\n \"--config.file=secrets/prometheus.yml\",\n \"--storage.tsdb.path=/data/prometheus/\",\n \"--storage.tsdb.retention.time=7d\"\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/v2.28.1/prometheus-2.28.1.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: \"Jenkins Job Health Exporter\"\n rules:\n - alert: JenkinsJobHealthExporterFailures\n expr: jenkins_job_failure{id=~\".*\"} \u003e jenkins_job_success{id=~\".*\"}\n for: 0m\n labels:\n severity: critical\n annotations:\n summary: \"Jenkins Job Health detected high failure rate on jenkins jobs.\"\n description: \"Job: {{ $labels.id }}\"\n - alert: JenkinsJobHealthExporterUnstable\n expr: jenkins_job_unstable{id=~\".*\"} \u003e jenkins_job_success{id=~\".*\"}\n for: 0m\n labels:\n severity: warning\n annotations:\n summary: \"Jenkins Job Health detected high unstable rate on jenkins jobs.\"\n description: \"Job: {{ $labels.id }}\"\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: 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: [ '10.30.51.22:8500' ]\n - targets: [ '10.30.51.24:8500' ]\n - targets: [ '10.30.51.25:8500' ]\n - targets: [ '10.30.51.26:8500' ]\n - targets: [ '10.30.51.28:8500' ]\n - targets: [ '10.30.51.29:8500' ]\n - targets: [ '10.30.51.30:8500' ]\n - targets: [ '10.30.51.39:8500' ]\n - targets: [ '10.30.51.40:8500' ]\n - targets: [ '10.30.51.50:8500' ]\n - targets: [ '10.30.51.51:8500' ]\n - targets: [ '10.30.51.65:8500' ]\n - targets: [ '10.30.51.66:8500' ]\n - targets: [ '10.30.51.67:8500' ]\n - targets: [ '10.30.51.68:8500' ]\n - targets: [ '10.30.51.70:8500' ]\n - targets: [ '10.30.51.71:8500' ]\n - targets: [ '10.32.8.14:8500' ]\n - targets: [ '10.32.8.15:8500' ]\n - targets: [ '10.32.8.16:8500' ]\n - targets: [ '10.32.8.17:8500' ]\n metrics_path: /v1/agent/metrics\n params:\n format: [ 'prometheus' ]\n\n - job_name: 'Blackbox Exporter (icmp)'\n static_configs:\n - targets: [ 'gerrit.fd.io' ]\n - targets: [ 'jenkins.fd.io' ]\n - targets: [ '10.32.8.17' ]\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: 'Jenkins Job Health Exporter'\n static_configs:\n - targets: [ '10.30.51.22:9186' ]\n metric_relabel_configs:\n - source_labels: [ __name__ ]\n regex: '^(vpp.*|csit.*)_(success|failure|total|unstable|reqtime_ms)$'\n action: replace\n replacement: '$1'\n target_label: id\n - source_labels: [ __name__ ]\n regex: '^(vpp.*|csit.*)_(success|failure|total|unstable|reqtime_ms)$'\n replacement: 'jenkins_job_$2'\n target_label: __name__\n\n - job_name: 'Node Exporter'\n static_configs:\n - targets: [ '10.30.51.22:9100' ]\n - targets: [ '10.30.51.24:9100' ]\n - targets: [ '10.30.51.25:9100' ]\n - targets: [ '10.30.51.26:9100' ]\n - targets: [ '10.30.51.28:9100' ]\n - targets: [ '10.30.51.29:9100' ]\n - targets: [ '10.30.51.30:9100' ]\n - targets: [ '10.30.51.39:9100' ]\n - targets: [ '10.30.51.40:9100' ]\n - targets: [ '10.30.51.50:9100' ]\n - targets: [ '10.30.51.51:9100' ]\n - targets: [ '10.30.51.65:9100' ]\n - targets: [ '10.30.51.66:9100' ]\n - targets: [ '10.30.51.67:9100' ]\n - targets: [ '10.30.51.68:9100' ]\n - targets: [ '10.30.51.70:9100' ]\n - targets: [ '10.30.51.71:9100' ]\n - targets: [ '10.32.8.14:9100' ]\n - targets: [ '10.32.8.15:9100' ]\n - targets: [ '10.32.8.16:9100' ]\n - targets: [ '10.32.8.17:9100' ]\n\n - job_name: 'Alertmanager'\n consul_sd_configs:\n - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n services: [ 'alertmanager' ]\n\n - job_name: 'Grafana'\n consul_sd_configs:\n - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n services: [ 'grafana' ]\n\n - job_name: 'Prometheus'\n consul_sd_configs:\n - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n services: [ 'prometheus' ]\n\n - job_name: 'Minio'\n bearer_token: eyJhbGciOiJIUzUxMiIsInR5cCI6IkpXVCJ9.eyJleHAiOjQ3NjQ1ODEzMzcsImlzcyI6InByb21ldGhldXMiLCJzdWIiOiJtaW5pbyJ9.oeTw3EIaiFmlDikrHXWiWXMH2vxLfDLkfjEC7G2N3M_keH_xyA_l2ofLLNYtopa_3GCEZnxLQdPuFZrmgpkDWg\n consul_sd_configs:\n - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n services: [ 'storage' ]\n metrics_path: /minio/prometheus/metrics\nEOH\n }\n\n # The service stanza instructs Nomad to register a service with Consul.\n #\n # For more information and examples on the \"task\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/service\n #\n service {\n name = \"prometheus\"\n port = \"prometheus\"\n tags = [ \"prometheus${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": "8995654", - "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": "bebf27b2f8eb532adad3cabb86953deed4d0e9970ab0524d7857b3ebeebb917d", - "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 = \"${node.class}\"\n value = \"csit\"\n }\n\n restart {\n interval = \"1m\"\n attempts = 3\n delay = \"15s\"\n mode = \"delay\"\n }\n\n # The \"task\" stanza creates an individual unit of work, such as a Docker\n # container, web application, or batch processing.\n #\n # For more information and examples on the \"task\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/task.html\n #\n task \"prod-task1-csit-shim-amd\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"docker\"\n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n image = \"fdiotools/csit_shim-ubuntu2004:2021_03_04_142103_UTC-x86_64\"\n network_mode = \"host\"\n pid_mode = \"host\"\n volumes = [\n \"/var/run/docker.sock:/var/run/docker.sock\"\n ]\n privileged = true\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # For more information and examples on the \"resources\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/resources.html\n #\n resources {\n cpu = 1500\n memory = 4096\n network {\n port \"ssh\" {\n static = 6022\n }\n port \"ssh2\" {\n static = 6023\n }\n }\n }\n }\n }\n\n group \"prod-group1-csit-shim-arm\" {\n # The \"count\" parameter specifies the number of the task groups that should\n # be running under this group. This value must be non-negative and defaults\n # to 1.\n count = 1\n\n constraint {\n attribute = \"${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 = \"fdiotools/csit_shim-ubuntu2004:2021_03_02_143938_UTC-aarch64\"\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 = 1500\n memory = 4096\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 = \"$${node.class}\"\n value = \"csit\"\n }\n\n restart {\n interval = \"1m\"\n attempts = 3\n delay = \"15s\"\n mode = \"delay\"\n }\n\n # The \"task\" stanza creates an individual unit of work, such as a Docker\n # container, web application, or batch processing.\n #\n # For more information and examples on the \"task\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/task.html\n #\n task \"prod-task1-csit-shim-amd\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"docker\"\n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n image = \"${image_x86_64}\"\n network_mode = \"host\"\n pid_mode = \"host\"\n volumes = [\n \"/var/run/docker.sock:/var/run/docker.sock\"\n ]\n privileged = true\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # For more information and examples on the \"resources\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/resources.html\n #\n resources {\n cpu = ${cpu}\n memory = ${mem}\n network {\n port \"ssh\" {\n static = 6022\n }\n port \"ssh2\" {\n static = 6023\n }\n }\n }\n }\n }\n\n group \"prod-group1-csit-shim-arm\" {\n # The \"count\" parameter specifies the number of the task groups that should\n # be running under this group. This value must be non-negative and defaults\n # to 1.\n count = ${group_count}\n\n constraint {\n attribute = \"$${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 = \"${image_aarch64}\"\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": "1500", - "datacenters": "yul1", - "group_count": "1", - "image_aarch64": "fdiotools/csit_shim-ubuntu2004:2021_03_02_143938_UTC-aarch64", - "image_x86_64": "fdiotools/csit_shim-ubuntu2004:2021_03_04_142103_UTC-x86_64", - "job_name": "prod-device-csit-shim", - "mem": "4096" - } - }, - "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": [ - "0c5c6e61-f8e5-bc82-0de9-5ac202d3600c", - "f9058e31-91d4-4cde-cef8-25ce59f2f4b6", - "d89ab9c0-4c2c-8430-f7ea-b609fc8285ac", - "055428eb-e662-5e07-14f1-afc32a2a491f" - ], - "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 = \"fdiotools/csit_shim-ubuntu2004:2021_03_04_142103_UTC-x86_64\"\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 = 1500\n memory = 4096\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 = \"fdiotools/csit_shim-ubuntu2004:2021_03_02_143938_UTC-aarch64\"\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 = 1500\n memory = 4096\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": "7575030", - "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/fdio.infra.terraform/1n_nmd/variables.tf b/fdio.infra.terraform/1n_nmd/variables.tf index a575d0b51d..598770eb13 100644 --- a/fdio.infra.terraform/1n_nmd/variables.tf +++ b/fdio.infra.terraform/1n_nmd/variables.tf @@ -1,11 +1,35 @@ +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://nomad.service.consul:4646" } -variable "nomad_acl" { - description = "Nomad ACLs enabled/disabled" - type = bool - default = false +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 "token" { + description = "Vault root token" + type = string + sensitive = true }
\ No newline at end of file diff --git a/fdio.infra.terraform/1n_nmd/versions.tf b/fdio.infra.terraform/1n_nmd/versions.tf new file mode 100644 index 0000000000..556ddbaee4 --- /dev/null +++ b/fdio.infra.terraform/1n_nmd/versions.tf @@ -0,0 +1,21 @@ +terraform { + backend "consul" { + address = "consul.service.consul:8500" + scheme = "http" + path = "terraform/nomad" + } + required_providers { + nomad = { + source = "hashicorp/nomad" + version = "~> 1.4.9" + } + template = { + source = "hashicorp/template" + version = "~> 2.2.0" + } + vault = { + version = ">=2.14.0" + } + } + required_version = ">= 1.0.3" +}
\ No newline at end of file diff --git a/fdio.infra.terraform/1n_nmd/vpp_device/versions.tf b/fdio.infra.terraform/1n_nmd/vpp_device/versions.tf new file mode 100644 index 0000000000..b80610a525 --- /dev/null +++ b/fdio.infra.terraform/1n_nmd/vpp_device/versions.tf @@ -0,0 +1,13 @@ +terraform { + required_providers { + nomad = { + source = "hashicorp/nomad" + version = "~> 1.4.15" + } + template = { + source = "hashicorp/template" + version = "~> 2.2.0" + } + } + required_version = ">= 1.0.3" +} diff --git a/resources/tools/storage/__main__.py b/resources/tools/storage/__main__.py index e8452dc9d1..d17c9e2292 100644 --- a/resources/tools/storage/__main__.py +++ b/resources/tools/storage/__main__.py @@ -39,11 +39,11 @@ def main(): args = parser.parse_args() json_iterator = Storage( - endpoint_url=u"http://storage.service.consul:9000", - bucket=u"docs", - profile_name=u"nomad-s3" + endpoint_url=u"http://minio.service.consul:9001", + bucket=u"fdio-logs-s3-cloudfront-index", + profile_name=u"default" ).s3_file_processing( - prefix=u"", expression=args.expression + prefix=u"vex-yul-rot-jenkins-1/csit-vpp-perf", expression=args.expression ) for item in json_iterator: print(dumps(item, indent=4, sort_keys=False)) |