diff options
Diffstat (limited to 'fdio.infra.terraform')
| -rw-r--r-- | fdio.infra.terraform/1n_nmd/prometheus/conf/nomad/prometheus.hcl | 20 | ||||
| -rw-r--r-- | fdio.infra.terraform/1n_nmd/terraform.tfstate | 42 | ||||
| -rw-r--r-- | fdio.infra.terraform/1n_nmd/terraform.tfstate.backup | 38 |
3 files changed, 48 insertions, 52 deletions
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 3d0b2c2eef..4451d72f7a 100644 --- a/fdio.infra.terraform/1n_nmd/prometheus/conf/nomad/prometheus.hcl +++ b/fdio.infra.terraform/1n_nmd/prometheus/conf/nomad/prometheus.hcl @@ -476,13 +476,13 @@ scrape_configs: - job_name: 'Consul Cluster' static_configs: + - targets: [ '10.30.51.22:8500' ] + - targets: [ '10.30.51.24:8500' ] + - targets: [ '10.30.51.25:8500' ] + - targets: [ '10.30.51.26:8500' ] - targets: [ '10.30.51.28:8500' ] - targets: [ '10.30.51.29:8500' ] - targets: [ '10.30.51.30:8500' ] - - targets: [ '10.30.51.32:8500' ] - - targets: [ '10.30.51.33:8500' ] - - targets: [ '10.30.51.34:8500' ] - - targets: [ '10.30.51.35:8500' ] - targets: [ '10.30.51.39:8500' ] - targets: [ '10.30.51.40:8500' ] - targets: [ '10.30.51.50:8500' ] @@ -505,7 +505,7 @@ scrape_configs: static_configs: - targets: [ 'gerrit.fd.io' ] - targets: [ 'jenkins.fd.io' ] - - targets: [ '10.30.51.32' ] + - targets: [ '10.32.8.17' ] params: module: [ 'icmp_v4' ] relabel_configs: @@ -534,7 +534,7 @@ scrape_configs: - job_name: 'Jenkins Job Health Exporter' static_configs: - - targets: [ '10.30.51.32:9186' ] + - targets: [ '10.30.51.22:9186' ] metric_relabel_configs: - source_labels: [ __name__ ] regex: '^(vpp.*|csit.*)_(success|failure|total|unstable|reqtime_ms)$' @@ -548,13 +548,13 @@ scrape_configs: - job_name: 'Node Exporter' static_configs: + - targets: [ '10.30.51.22:9100' ] + - targets: [ '10.30.51.24:9100' ] + - targets: [ '10.30.51.25:9100' ] + - targets: [ '10.30.51.26:9100' ] - targets: [ '10.30.51.28:9100' ] - targets: [ '10.30.51.29:9100' ] - targets: [ '10.30.51.30:9100' ] - - targets: [ '10.30.51.32:9100' ] - - targets: [ '10.30.51.33:9100' ] - - targets: [ '10.30.51.34:9100' ] - - targets: [ '10.30.51.35:9100' ] - targets: [ '10.30.51.39:9100' ] - targets: [ '10.30.51.40:9100' ] - targets: [ '10.30.51.50:9100' ] diff --git a/fdio.infra.terraform/1n_nmd/terraform.tfstate b/fdio.infra.terraform/1n_nmd/terraform.tfstate index 7e4875858d..92b1b86c5f 100644 --- a/fdio.infra.terraform/1n_nmd/terraform.tfstate +++ b/fdio.infra.terraform/1n_nmd/terraform.tfstate @@ -1,7 +1,7 @@ { "version": 4, "terraform_version": "1.0.2", - "serial": 1178, + "serial": 1187, "lineage": "e4e7f30a-652d-7a31-e31c-5e3a3388c9b9", "outputs": {}, "resources": [ @@ -141,7 +141,7 @@ "schema_version": 0, "attributes": { "allocation_ids": [ - "24a62387-6e3e-2a43-0d90-a287f161b4d9" + "01d60c86-d59b-83ac-78c8-a903ac63816e" ], "datacenters": [ "yul1" @@ -270,7 +270,7 @@ "schema_version": 0, "attributes": { "allocation_ids": [ - "8e200c5b-97ee-20a0-3383-96af1adaef6a", + "844e34c1-13e6-3ddb-9402-e876230e5cdb", "44e1a0f0-5328-eafb-3beb-bfd53af2b618", "a6695ea0-2563-72ae-1791-a08ef933ff72", "51126acb-945c-2629-5787-76b85677ddd0" @@ -367,7 +367,7 @@ "schema_version": 0, "attributes": { "allocation_ids": [ - "0cb0b594-09c2-bad6-fca4-0fbc2479ef3e" + "8a81e41d-911d-e083-9bcd-b5b3c70b33fa" ], "datacenters": [ "yul1" @@ -380,7 +380,7 @@ "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": "8220180", + "modify_index": "8993958", "name": "prod-nginx", "namespace": "default", "policy_override": null, @@ -430,9 +430,9 @@ "schema_version": 0, "attributes": { "filename": null, - "id": "46dfbb29c15ad00720c6f4ce699529b7934bdd666bb7656d7c17b128e7609f07", - "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: [ '10.30.51.28:8500' ]\n - targets: [ '10.30.51.29:8500' ]\n - targets: [ '10.30.51.30:8500' ]\n - targets: [ '10.30.51.32:8500' ]\n - targets: [ '10.30.51.33:8500' ]\n - targets: [ '10.30.51.34:8500' ]\n - targets: [ '10.30.51.35:8500' ]\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: [ '10.30.51.32' ]\n params:\n module: [ 'icmp_v4' ]\n relabel_configs:\n - source_labels: [__address__]\n target_label: __param_target\n - source_labels: [__param_target]\n target_label: instance\n - target_label: __address__\n replacement: localhost:9115\n metrics_path: /probe\n\n - job_name: 'Blackbox Exporter (http)'\n static_configs:\n - targets: [ 'gerrit.fd.io' ]\n - targets: [ 'jenkins.fd.io' ]\n params:\n module: [ 'http_2xx' ]\n relabel_configs:\n - source_labels: [__address__]\n target_label: __param_target\n - source_labels: [__param_target]\n target_label: instance\n - target_label: __address__\n replacement: localhost:9115\n metrics_path: /probe\n\n - job_name: 'Jenkins Job Health Exporter'\n static_configs:\n - targets: [ '10.30.51.32:9186' ]\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_$2'\n target_label: __name__\n\n - job_name: 'Node Exporter'\n static_configs:\n - targets: [ '10.30.51.28:9100' ]\n - targets: [ '10.30.51.29:9100' ]\n - targets: [ '10.30.51.30:9100' ]\n - targets: [ '10.30.51.32:9100' ]\n - targets: [ '10.30.51.33:9100' ]\n - targets: [ '10.30.51.34:9100' ]\n - targets: [ '10.30.51.35:9100' ]\n - targets: [ '10.30.51.39:9100' ]\n - targets: [ '10.30.51.40:9100' ]\n - targets: [ '10.30.51.50:9100' ]\n - targets: [ '10.30.51.51:9100' ]\n - targets: [ '10.30.51.65:9100' ]\n - targets: [ '10.30.51.66:9100' ]\n - targets: [ '10.30.51.67:9100' ]\n - targets: [ '10.30.51.68:9100' ]\n - targets: [ '10.30.51.70:9100' ]\n - targets: [ '10.30.51.71:9100' ]\n - targets: [ '10.32.8.14:9100' ]\n - targets: [ '10.32.8.15:9100' ]\n - targets: [ '10.32.8.16:9100' ]\n - targets: [ '10.32.8.17:9100' ]\n\n - job_name: 'Alertmanager'\n consul_sd_configs:\n - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n services: [ 'alertmanager' ]\n\n - job_name: 'Grafana'\n consul_sd_configs:\n - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n services: [ 'grafana' ]\n\n - job_name: 'Prometheus'\n consul_sd_configs:\n - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n services: [ 'prometheus' ]\n\n - job_name: 'Minio'\n bearer_token: eyJhbGciOiJIUzUxMiIsInR5cCI6IkpXVCJ9.eyJleHAiOjQ3NjQ1ODEzMzcsImlzcyI6InByb21ldGhldXMiLCJzdWIiOiJtaW5pbyJ9.oeTw3EIaiFmlDikrHXWiWXMH2vxLfDLkfjEC7G2N3M_keH_xyA_l2ofLLNYtopa_3GCEZnxLQdPuFZrmgpkDWg\n consul_sd_configs:\n - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n services: [ 'storage' ]\n metrics_path: /minio/prometheus/metrics\nEOH\n }\n\n # The service stanza instructs Nomad to register a service with Consul.\n #\n # For more information and examples on the \"task\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/service\n #\n service {\n name = \"prometheus\"\n port = \"prometheus\"\n tags = [ \"prometheus${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: [ '10.30.51.28:8500' ]\n - targets: [ '10.30.51.29:8500' ]\n - targets: [ '10.30.51.30:8500' ]\n - targets: [ '10.30.51.32:8500' ]\n - targets: [ '10.30.51.33:8500' ]\n - targets: [ '10.30.51.34:8500' ]\n - targets: [ '10.30.51.35:8500' ]\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: [ '10.30.51.32' ]\n params:\n module: [ 'icmp_v4' ]\n relabel_configs:\n - source_labels: [__address__]\n target_label: __param_target\n - source_labels: [__param_target]\n target_label: instance\n - target_label: __address__\n replacement: localhost:9115\n metrics_path: /probe\n\n - job_name: 'Blackbox Exporter (http)'\n static_configs:\n - targets: [ 'gerrit.fd.io' ]\n - targets: [ 'jenkins.fd.io' ]\n params:\n module: [ 'http_2xx' ]\n relabel_configs:\n - source_labels: [__address__]\n target_label: __param_target\n - source_labels: [__param_target]\n target_label: instance\n - target_label: __address__\n replacement: localhost:9115\n metrics_path: /probe\n\n - job_name: 'Jenkins Job Health Exporter'\n static_configs:\n - targets: [ '10.30.51.32:9186' ]\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: [ '10.30.51.28:9100' ]\n - targets: [ '10.30.51.29:9100' ]\n - targets: [ '10.30.51.30:9100' ]\n - targets: [ '10.30.51.32:9100' ]\n - targets: [ '10.30.51.33:9100' ]\n - targets: [ '10.30.51.34:9100' ]\n - targets: [ '10.30.51.35:9100' ]\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}", + "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/", @@ -465,27 +465,27 @@ "schema_version": 0, "attributes": { "allocation_ids": [ - "06f831b0-4ee5-0f2b-5888-081f69d25efc", - "fd5bd3d9-7d24-5c99-d426-3f9e95a0ea3c", - "7c689e4b-4601-0299-4d5e-f906a3e1b30b", - "f355c50b-7702-e65b-e629-ffa41678b880", - "d4eae934-c539-fc71-b7db-16740286ea39", - "fe8466ca-c32a-d6a0-86f4-b12b7816a3ac", - "87ec193b-dc4d-2d39-8241-86a38ddaf827", - "ea93f680-7e8b-6e3e-d33a-5b0c71a73dd0" + "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": "c27f5df9-0819-f33a-fb30-180edcd2ffcd", + "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: [ '10.30.51.28:8500' ]\n - targets: [ '10.30.51.29:8500' ]\n - targets: [ '10.30.51.30:8500' ]\n - targets: [ '10.30.51.32:8500' ]\n - targets: [ '10.30.51.33:8500' ]\n - targets: [ '10.30.51.34:8500' ]\n - targets: [ '10.30.51.35:8500' ]\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: [ '10.30.51.32' ]\n params:\n module: [ 'icmp_v4' ]\n relabel_configs:\n - source_labels: [__address__]\n target_label: __param_target\n - source_labels: [__param_target]\n target_label: instance\n - target_label: __address__\n replacement: localhost:9115\n metrics_path: /probe\n\n - job_name: 'Blackbox Exporter (http)'\n static_configs:\n - targets: [ 'gerrit.fd.io' ]\n - targets: [ 'jenkins.fd.io' ]\n params:\n module: [ 'http_2xx' ]\n relabel_configs:\n - source_labels: [__address__]\n target_label: __param_target\n - source_labels: [__param_target]\n target_label: instance\n - target_label: __address__\n replacement: localhost:9115\n metrics_path: /probe\n\n - job_name: 'Jenkins Job Health Exporter'\n static_configs:\n - targets: [ '10.30.51.32:9186' ]\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_$2'\n target_label: __name__\n\n - job_name: 'Node Exporter'\n static_configs:\n - targets: [ '10.30.51.28:9100' ]\n - targets: [ '10.30.51.29:9100' ]\n - targets: [ '10.30.51.30:9100' ]\n - targets: [ '10.30.51.32:9100' ]\n - targets: [ '10.30.51.33:9100' ]\n - targets: [ '10.30.51.34:9100' ]\n - targets: [ '10.30.51.35:9100' ]\n - targets: [ '10.30.51.39:9100' ]\n - targets: [ '10.30.51.40:9100' ]\n - targets: [ '10.30.51.50:9100' ]\n - targets: [ '10.30.51.51:9100' ]\n - targets: [ '10.30.51.65:9100' ]\n - targets: [ '10.30.51.66:9100' ]\n - targets: [ '10.30.51.67:9100' ]\n - targets: [ '10.30.51.68:9100' ]\n - targets: [ '10.30.51.70:9100' ]\n - targets: [ '10.30.51.71:9100' ]\n - targets: [ '10.32.8.14:9100' ]\n - targets: [ '10.32.8.15:9100' ]\n - targets: [ '10.32.8.16:9100' ]\n - targets: [ '10.32.8.17:9100' ]\n\n - job_name: 'Alertmanager'\n consul_sd_configs:\n - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n services: [ 'alertmanager' ]\n\n - job_name: 'Grafana'\n consul_sd_configs:\n - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n services: [ 'grafana' ]\n\n - job_name: 'Prometheus'\n consul_sd_configs:\n - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n services: [ 'prometheus' ]\n\n - job_name: 'Minio'\n bearer_token: eyJhbGciOiJIUzUxMiIsInR5cCI6IkpXVCJ9.eyJleHAiOjQ3NjQ1ODEzMzcsImlzcyI6InByb21ldGhldXMiLCJzdWIiOiJtaW5pbyJ9.oeTw3EIaiFmlDikrHXWiWXMH2vxLfDLkfjEC7G2N3M_keH_xyA_l2ofLLNYtopa_3GCEZnxLQdPuFZrmgpkDWg\n consul_sd_configs:\n - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n services: [ 'storage' ]\n metrics_path: /minio/prometheus/metrics\nEOH\n }\n\n # The service stanza instructs Nomad to register a service with Consul.\n #\n # For more information and examples on the \"task\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/service\n #\n service {\n name = \"prometheus\"\n port = \"prometheus\"\n tags = [ \"prometheus${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}", + "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": "8949350", + "modify_index": "8995654", "name": "prod-prometheus", "namespace": "default", "policy_override": null, @@ -569,8 +569,8 @@ "schema_version": 0, "attributes": { "allocation_ids": [ - "4194fecb-5e83-0b00-09d9-7561ee7d57f4", - "314b725e-3907-d1f5-2538-72c7343f8cda", + "0c5c6e61-f8e5-bc82-0de9-5ac202d3600c", + "f9058e31-91d4-4cde-cef8-25ce59f2f4b6", "d89ab9c0-4c2c-8430-f7ea-b609fc8285ac", "055428eb-e662-5e07-14f1-afc32a2a491f" ], diff --git a/fdio.infra.terraform/1n_nmd/terraform.tfstate.backup b/fdio.infra.terraform/1n_nmd/terraform.tfstate.backup index e6522a5c42..5c3f0aeb41 100644 --- a/fdio.infra.terraform/1n_nmd/terraform.tfstate.backup +++ b/fdio.infra.terraform/1n_nmd/terraform.tfstate.backup @@ -1,7 +1,7 @@ { "version": 4, "terraform_version": "1.0.2", - "serial": 1176, + "serial": 1184, "lineage": "e4e7f30a-652d-7a31-e31c-5e3a3388c9b9", "outputs": {}, "resources": [ @@ -141,7 +141,7 @@ "schema_version": 0, "attributes": { "allocation_ids": [ - "24a62387-6e3e-2a43-0d90-a287f161b4d9" + "01d60c86-d59b-83ac-78c8-a903ac63816e" ], "datacenters": [ "yul1" @@ -270,7 +270,7 @@ "schema_version": 0, "attributes": { "allocation_ids": [ - "8e200c5b-97ee-20a0-3383-96af1adaef6a", + "844e34c1-13e6-3ddb-9402-e876230e5cdb", "44e1a0f0-5328-eafb-3beb-bfd53af2b618", "a6695ea0-2563-72ae-1791-a08ef933ff72", "51126acb-945c-2629-5787-76b85677ddd0" @@ -367,7 +367,7 @@ "schema_version": 0, "attributes": { "allocation_ids": [ - "0cb0b594-09c2-bad6-fca4-0fbc2479ef3e" + "8a81e41d-911d-e083-9bcd-b5b3c70b33fa" ], "datacenters": [ "yul1" @@ -380,7 +380,7 @@ "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": "8220180", + "modify_index": "8993958", "name": "prod-nginx", "namespace": "default", "policy_override": null, @@ -430,9 +430,9 @@ "schema_version": 0, "attributes": { "filename": null, - "id": "c41b13aaa5709d1a72ae0408a62304996e89730e7cb3311ca798d5a807a6295f", - "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: [ '10.30.51.28:8500' ]\n - targets: [ '10.30.51.29:8500' ]\n - targets: [ '10.30.51.30:8500' ]\n - targets: [ '10.30.51.32:8500' ]\n - targets: [ '10.30.51.33:8500' ]\n - targets: [ '10.30.51.34:8500' ]\n - targets: [ '10.30.51.35:8500' ]\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: [ '10.30.51.32' ]\n params:\n module: [ 'icmp_v4' ]\n relabel_configs:\n - source_labels: [__address__]\n target_label: __param_target\n - source_labels: [__param_target]\n target_label: instance\n - target_label: __address__\n replacement: localhost:9115\n metrics_path: /probe\n\n - job_name: 'Blackbox Exporter (http)'\n static_configs:\n - targets: [ 'gerrit.fd.io' ]\n - targets: [ 'jenkins.fd.io' ]\n params:\n module: [ 'http_2xx' ]\n relabel_configs:\n - source_labels: [__address__]\n target_label: __param_target\n - source_labels: [__param_target]\n target_label: instance\n - target_label: __address__\n replacement: localhost:9115\n metrics_path: /probe\n\n - job_name: 'cAdvisor Exporter'\n static_configs:\n - targets: [ '10.30.51.28:8080' ]\n - targets: [ '10.30.51.29:8080' ]\n - targets: [ '10.30.51.30:8080' ]\n #- targets: [ '10.30.51.32:8080' ]\n - targets: [ '10.30.51.33:8080' ]\n - targets: [ '10.30.51.34:8080' ]\n - targets: [ '10.30.51.35:8080' ]\n - targets: [ '10.30.51.39:8080' ]\n - targets: [ '10.30.51.40:8080' ]\n - targets: [ '10.30.51.50:8080' ]\n - targets: [ '10.30.51.51:8080' ]\n - targets: [ '10.30.51.65:8080' ]\n - targets: [ '10.30.51.66:8080' ]\n - targets: [ '10.30.51.67:8080' ]\n - targets: [ '10.30.51.68:8080' ]\n - targets: [ '10.30.51.70:8080' ]\n - targets: [ '10.30.51.71:8080' ]\n - targets: [ '10.32.8.14:8080' ]\n - targets: [ '10.32.8.15:8080' ]\n - targets: [ '10.32.8.16:8080' ]\n - targets: [ '10.32.8.17:8080' ]\n\n - job_name: 'Jenkins Job Health Exporter'\n static_configs:\n - targets: [ '10.30.51.32:9186' ]\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_$2'\n target_label: __name__\n\n - job_name: 'Node Exporter'\n static_configs:\n - targets: [ '10.30.51.28:9100' ]\n - targets: [ '10.30.51.29:9100' ]\n - targets: [ '10.30.51.30:9100' ]\n - targets: [ '10.30.51.32:9100' ]\n - targets: [ '10.30.51.33:9100' ]\n - targets: [ '10.30.51.34:9100' ]\n - targets: [ '10.30.51.35:9100' ]\n - targets: [ '10.30.51.39:9100' ]\n - targets: [ '10.30.51.40:9100' ]\n - targets: [ '10.30.51.50:9100' ]\n - targets: [ '10.30.51.51:9100' ]\n - targets: [ '10.30.51.65:9100' ]\n - targets: [ '10.30.51.66:9100' ]\n - targets: [ '10.30.51.67:9100' ]\n - targets: [ '10.30.51.68:9100' ]\n - targets: [ '10.30.51.70:9100' ]\n - targets: [ '10.30.51.71:9100' ]\n - targets: [ '10.32.8.14:9100' ]\n - targets: [ '10.32.8.15:9100' ]\n - targets: [ '10.32.8.16:9100' ]\n - targets: [ '10.32.8.17:9100' ]\n\n - job_name: 'Alertmanager'\n consul_sd_configs:\n - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n services: [ 'alertmanager' ]\n\n - job_name: 'Grafana'\n consul_sd_configs:\n - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n services: [ 'grafana' ]\n\n - job_name: 'Prometheus'\n consul_sd_configs:\n - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n services: [ 'prometheus' ]\n\n - job_name: 'Minio'\n bearer_token: eyJhbGciOiJIUzUxMiIsInR5cCI6IkpXVCJ9.eyJleHAiOjQ3NjQ1ODEzMzcsImlzcyI6InByb21ldGhldXMiLCJzdWIiOiJtaW5pbyJ9.oeTw3EIaiFmlDikrHXWiWXMH2vxLfDLkfjEC7G2N3M_keH_xyA_l2ofLLNYtopa_3GCEZnxLQdPuFZrmgpkDWg\n consul_sd_configs:\n - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n services: [ 'storage' ]\n metrics_path: /minio/prometheus/metrics\nEOH\n }\n\n # The service stanza instructs Nomad to register a service with Consul.\n #\n # For more information and examples on the \"task\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/service\n #\n service {\n name = \"prometheus\"\n port = \"prometheus\"\n tags = [ \"prometheus${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: [ '10.30.51.28:8500' ]\n - targets: [ '10.30.51.29:8500' ]\n - targets: [ '10.30.51.30:8500' ]\n - targets: [ '10.30.51.32:8500' ]\n - targets: [ '10.30.51.33:8500' ]\n - targets: [ '10.30.51.34:8500' ]\n - targets: [ '10.30.51.35:8500' ]\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: [ '10.30.51.32' ]\n params:\n module: [ 'icmp_v4' ]\n relabel_configs:\n - source_labels: [__address__]\n target_label: __param_target\n - source_labels: [__param_target]\n target_label: instance\n - target_label: __address__\n replacement: localhost:9115\n metrics_path: /probe\n\n - job_name: 'Blackbox Exporter (http)'\n static_configs:\n - targets: [ 'gerrit.fd.io' ]\n - targets: [ 'jenkins.fd.io' ]\n params:\n module: [ 'http_2xx' ]\n relabel_configs:\n - source_labels: [__address__]\n target_label: __param_target\n - source_labels: [__param_target]\n target_label: instance\n - target_label: __address__\n replacement: localhost:9115\n metrics_path: /probe\n\n - job_name: 'cAdvisor Exporter'\n static_configs:\n - targets: [ '10.30.51.28:8080' ]\n - targets: [ '10.30.51.29:8080' ]\n - targets: [ '10.30.51.30:8080' ]\n #- targets: [ '10.30.51.32:8080' ]\n - targets: [ '10.30.51.33:8080' ]\n - targets: [ '10.30.51.34:8080' ]\n - targets: [ '10.30.51.35:8080' ]\n - targets: [ '10.30.51.39:8080' ]\n - targets: [ '10.30.51.40:8080' ]\n - targets: [ '10.30.51.50:8080' ]\n - targets: [ '10.30.51.51:8080' ]\n - targets: [ '10.30.51.65:8080' ]\n - targets: [ '10.30.51.66:8080' ]\n - targets: [ '10.30.51.67:8080' ]\n - targets: [ '10.30.51.68:8080' ]\n - targets: [ '10.30.51.70:8080' ]\n - targets: [ '10.30.51.71:8080' ]\n - targets: [ '10.32.8.14:8080' ]\n - targets: [ '10.32.8.15:8080' ]\n - targets: [ '10.32.8.16:8080' ]\n - targets: [ '10.32.8.17:8080' ]\n\n - job_name: 'Jenkins Job Health Exporter'\n static_configs:\n - targets: [ '10.30.51.32:9186' ]\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: [ '10.30.51.28:9100' ]\n - targets: [ '10.30.51.29:9100' ]\n - targets: [ '10.30.51.30:9100' ]\n - targets: [ '10.30.51.32:9100' ]\n - targets: [ '10.30.51.33:9100' ]\n - targets: [ '10.30.51.34:9100' ]\n - targets: [ '10.30.51.35:9100' ]\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}", + "id": "ead2225fbdf17b54946cfd825a5b21205f7d98c776601d1a822a025b0cee042a", + "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/", @@ -465,27 +465,23 @@ "schema_version": 0, "attributes": { "allocation_ids": [ - "d4eae934-c539-fc71-b7db-16740286ea39", - "fe8466ca-c32a-d6a0-86f4-b12b7816a3ac", - "87ec193b-dc4d-2d39-8241-86a38ddaf827", - "ea93f680-7e8b-6e3e-d33a-5b0c71a73dd0", - "cc55245c-e81e-a5ba-fd64-899e4ef63f7e", - "828cc735-f166-62f9-64e5-7fcc3aa0010d", - "284ef377-252c-c03b-a4ab-76c7fba69b92", - "69e2ab96-b63c-24a3-555b-5fa95bf46e55" + "6776d9ca-70ba-129f-05a9-ca6fccdb6289", + "0fb06047-62e0-48e4-e352-63b4602407f2", + "ddb72c78-1f3f-2d1e-0157-7b7bb05aaa4a", + "67dfb1da-36a3-e442-5c66-8d6340f579c3" ], "datacenters": [ "yul1" ], - "deployment_id": "1526c7d4-16b3-45d7-4eec-a436cc272c7d", + "deployment_id": "8196f20a-50e5-c63a-36f5-0b2084c4b02a", "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: [ '10.30.51.28:8500' ]\n - targets: [ '10.30.51.29:8500' ]\n - targets: [ '10.30.51.30:8500' ]\n - targets: [ '10.30.51.32:8500' ]\n - targets: [ '10.30.51.33:8500' ]\n - targets: [ '10.30.51.34:8500' ]\n - targets: [ '10.30.51.35:8500' ]\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: [ '10.30.51.32' ]\n params:\n module: [ 'icmp_v4' ]\n relabel_configs:\n - source_labels: [__address__]\n target_label: __param_target\n - source_labels: [__param_target]\n target_label: instance\n - target_label: __address__\n replacement: localhost:9115\n metrics_path: /probe\n\n - job_name: 'Blackbox Exporter (http)'\n static_configs:\n - targets: [ 'gerrit.fd.io' ]\n - targets: [ 'jenkins.fd.io' ]\n params:\n module: [ 'http_2xx' ]\n relabel_configs:\n - source_labels: [__address__]\n target_label: __param_target\n - source_labels: [__param_target]\n target_label: instance\n - target_label: __address__\n replacement: localhost:9115\n metrics_path: /probe\n\n - job_name: 'cAdvisor Exporter'\n static_configs:\n - targets: [ '10.30.51.28:8080' ]\n - targets: [ '10.30.51.29:8080' ]\n - targets: [ '10.30.51.30:8080' ]\n #- targets: [ '10.30.51.32:8080' ]\n - targets: [ '10.30.51.33:8080' ]\n - targets: [ '10.30.51.34:8080' ]\n - targets: [ '10.30.51.35:8080' ]\n - targets: [ '10.30.51.39:8080' ]\n - targets: [ '10.30.51.40:8080' ]\n - targets: [ '10.30.51.50:8080' ]\n - targets: [ '10.30.51.51:8080' ]\n - targets: [ '10.30.51.65:8080' ]\n - targets: [ '10.30.51.66:8080' ]\n - targets: [ '10.30.51.67:8080' ]\n - targets: [ '10.30.51.68:8080' ]\n - targets: [ '10.30.51.70:8080' ]\n - targets: [ '10.30.51.71:8080' ]\n - targets: [ '10.32.8.14:8080' ]\n - targets: [ '10.32.8.15:8080' ]\n - targets: [ '10.32.8.16:8080' ]\n - targets: [ '10.32.8.17:8080' ]\n\n - job_name: 'Jenkins Job Health Exporter'\n static_configs:\n - targets: [ '10.30.51.32:9186' ]\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_$2'\n target_label: __name__\n\n - job_name: 'Node Exporter'\n static_configs:\n - targets: [ '10.30.51.28:9100' ]\n - targets: [ '10.30.51.29:9100' ]\n - targets: [ '10.30.51.30:9100' ]\n - targets: [ '10.30.51.32:9100' ]\n - targets: [ '10.30.51.33:9100' ]\n - targets: [ '10.30.51.34:9100' ]\n - targets: [ '10.30.51.35:9100' ]\n - targets: [ '10.30.51.39:9100' ]\n - targets: [ '10.30.51.40:9100' ]\n - targets: [ '10.30.51.50:9100' ]\n - targets: [ '10.30.51.51:9100' ]\n - targets: [ '10.30.51.65:9100' ]\n - targets: [ '10.30.51.66:9100' ]\n - targets: [ '10.30.51.67:9100' ]\n - targets: [ '10.30.51.68:9100' ]\n - targets: [ '10.30.51.70:9100' ]\n - targets: [ '10.30.51.71:9100' ]\n - targets: [ '10.32.8.14:9100' ]\n - targets: [ '10.32.8.15:9100' ]\n - targets: [ '10.32.8.16:9100' ]\n - targets: [ '10.32.8.17:9100' ]\n\n - job_name: 'Alertmanager'\n consul_sd_configs:\n - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n services: [ 'alertmanager' ]\n\n - job_name: 'Grafana'\n consul_sd_configs:\n - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n services: [ 'grafana' ]\n\n - job_name: 'Prometheus'\n consul_sd_configs:\n - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n services: [ 'prometheus' ]\n\n - job_name: 'Minio'\n bearer_token: eyJhbGciOiJIUzUxMiIsInR5cCI6IkpXVCJ9.eyJleHAiOjQ3NjQ1ODEzMzcsImlzcyI6InByb21ldGhldXMiLCJzdWIiOiJtaW5pbyJ9.oeTw3EIaiFmlDikrHXWiWXMH2vxLfDLkfjEC7G2N3M_keH_xyA_l2ofLLNYtopa_3GCEZnxLQdPuFZrmgpkDWg\n consul_sd_configs:\n - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n services: [ 'storage' ]\n metrics_path: /minio/prometheus/metrics\nEOH\n }\n\n # The service stanza instructs Nomad to register a service with Consul.\n #\n # For more information and examples on the \"task\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/service\n #\n service {\n name = \"prometheus\"\n port = \"prometheus\"\n tags = [ \"prometheus${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}", + "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": "8949256", + "modify_index": "8995420", "name": "prod-prometheus", "namespace": "default", "policy_override": null, @@ -569,8 +565,8 @@ "schema_version": 0, "attributes": { "allocation_ids": [ - "4194fecb-5e83-0b00-09d9-7561ee7d57f4", - "314b725e-3907-d1f5-2538-72c7343f8cda", + "0c5c6e61-f8e5-bc82-0de9-5ac202d3600c", + "f9058e31-91d4-4cde-cef8-25ce59f2f4b6", "d89ab9c0-4c2c-8430-f7ea-b609fc8285ac", "055428eb-e662-5e07-14f1-afc32a2a491f" ], |