diff options
Diffstat (limited to 'fdio.infra.terraform/terraform-nomad-prometheus/conf/nomad/prometheus.hcl.tftpl')
| -rw-r--r-- | fdio.infra.terraform/terraform-nomad-prometheus/conf/nomad/prometheus.hcl.tftpl | 676 |
1 files changed, 676 insertions, 0 deletions
diff --git a/fdio.infra.terraform/terraform-nomad-prometheus/conf/nomad/prometheus.hcl.tftpl b/fdio.infra.terraform/terraform-nomad-prometheus/conf/nomad/prometheus.hcl.tftpl new file mode 100644 index 0000000000..4eb4428988 --- /dev/null +++ b/fdio.infra.terraform/terraform-nomad-prometheus/conf/nomad/prometheus.hcl.tftpl @@ -0,0 +1,676 @@ +job "${job_name}" { + # The "region" parameter specifies the region in which to execute the job. + # If omitted, this inherits the default region name of "global". + # region = "${region}" + + # The "datacenters" parameter specifies the list of datacenters which should + # be considered when placing this task. This must be provided. + datacenters = "${datacenters}" + + # The "type" parameter controls the type of job, which impacts the scheduler's + # decision on placement. + # + # https://www.nomadproject.io/docs/jobspec/schedulers + # + type = "service" + + update { + # The "max_parallel" parameter specifies the maximum number of updates to + # perform in parallel. + max_parallel = ${max_parallel} + + health_check = "checks" + + # The "min_healthy_time" parameter specifies the minimum time the allocation + # must be in the healthy state before it is marked as healthy and unblocks + # further allocations from being updated. + min_healthy_time = "10s" + + # The "healthy_deadline" parameter specifies the deadline in which the + # allocation must be marked as healthy after which the allocation is + # automatically transitioned to unhealthy. Transitioning to unhealthy will + # fail the deployment and potentially roll back the job if "auto_revert" is + # set to true. + healthy_deadline = "3m" + + # The "progress_deadline" parameter specifies the deadline in which an + # allocation must be marked as healthy. The deadline begins when the first + # allocation for the deployment is created and is reset whenever an allocation + # as part of the deployment transitions to a healthy state. If no allocation + # transitions to the healthy state before the progress deadline, the + # deployment is marked as failed. + progress_deadline = "10m" + +%{ if use_canary } + # The "canary" parameter specifies that changes to the job that would result + # in destructive updates should create the specified number of canaries + # without stopping any previous allocations. Once the operator determines the + # canaries are healthy, they can be promoted which unblocks a rolling update + # of the remaining allocations at a rate of "max_parallel". + # + # Further, setting "canary" equal to the count of the task group allows + # blue/green deployments. When the job is updated, a full set of the new + # version is deployed and upon promotion the old version is stopped. + canary = ${canary} + + # Specifies if the job should auto-promote to the canary version when all + # canaries become healthy during a deployment. Defaults to false which means + # canaries must be manually updated with the nomad deployment promote + # command. + auto_promote = ${auto_promote} + + # The "auto_revert" parameter specifies if the job should auto-revert to the + # last stable job on deployment failure. A job is marked as stable if all the + # allocations as part of its deployment were marked healthy. + auto_revert = ${auto_revert} +%{ endif } + } + + # The "group" stanza defines a series of tasks that should be co-located on + # the same Nomad client. Any task within a group will be placed on the same + # client. + # + # https://www.nomadproject.io/docs/job-specification/group + # + group "${job_name}-group-1" { + # The "count" parameter specifies the number of the task groups that should + # be running under this group. This value must be non-negative. + count = ${group_count} + + # The volume stanza allows the group to specify that it requires a given + # volume from the cluster. The key of the stanza is the name of the volume + # as it will be exposed to task configuration. + # + # https://www.nomadproject.io/docs/job-specification/volume + # + %{ if use_host_volume } + volume "${job_name}-volume-1" { + type = "host" + read_only = false + source = "${volume_source}" + } + %{ endif } + + # The restart stanza configures a tasks's behavior on task failure. Restarts + # happen on the client that is running the task. + # + # https://www.nomadproject.io/docs/job-specification/restart + # + restart { + interval = "30m" + attempts = 40 + delay = "15s" + mode = "delay" + } + + # The constraint allows restricting the set of eligible nodes. Constraints + # may filter on attributes or client metadata. + # + # https://www.nomadproject.io/docs/job-specification/constraint + # + constraint { + attribute = "$${attr.cpu.arch}" + operator = "!=" + value = "arm64" + } + constraint { + attribute = "$${node.class}" + value = "builder" + } + + # The network stanza specifies the networking requirements for the task + # group, including the network mode and port allocations. When scheduling + # jobs in Nomad they are provisioned across your fleet of machines along + # with other jobs and services. Because you don't know in advance what host + # your job will be provisioned on, Nomad will provide your tasks with + # network configuration when they start up. + # + # https://www.nomadproject.io/docs/job-specification/network + # + network { + port "${service_name}" { + static = ${port} + to = ${port} + } + } + + # The "task" stanza creates an individual unit of work, such as a Docker + # container, web application, or batch processing. + # + # https://www.nomadproject.io/docs/job-specification/task + # + task "${job_name}-task-1" { + # The "driver" parameter specifies the task driver that should be used to + # run the task. + driver = "exec" + + %{ if use_host_volume } + volume_mount { + volume = "${job_name}-volume-1" + destination = "${volume_destination}" + read_only = false + } + %{ endif } + + %{ if use_vault_provider } + vault { + policies = "${vault_kv_policy_name}" + } + %{ endif } + + # The "config" stanza specifies the driver configuration, which is passed + # directly to the driver to start the task. The details of configurations + # are specific to each driver, so please see specific driver + # documentation for more information. + config { + command = "local/prometheus-${version}.linux-amd64/prometheus" + args = [ + "--config.file=secrets/prometheus.yml", + "--web.config.file=secrets/web-config.yml", + "--storage.tsdb.path=${volume_destination}prometheus/", + "--storage.tsdb.retention.time=7d" + ] + } + + # The artifact stanza instructs Nomad to fetch and unpack a remote + # resource, such as a file, tarball, or binary. Nomad downloads artifacts + # using the popular go-getter library, which permits downloading artifacts + # from a variety of locations using a URL as the input source. + # + # https://www.nomadproject.io/docs/job-specification/artifact + # + artifact { + source = "${artifact_source}" + options { + checksum = "sha256:${artifact_source_checksum}" + } + } + + # The "template" stanza instructs Nomad to manage a template, such as + # a configuration file or script. This template can optionally pull data + # from Consul or Vault to populate runtime configuration data. + # + # https://www.nomadproject.io/docs/job-specification/template + # + template { + change_mode = "noop" + change_signal = "SIGINT" + destination = "secrets/cert_file.crt" + left_delimiter = "{{{" + right_delimiter = "}}}" + data = <<EOH +-----BEGIN CERTIFICATE----- +MIIFszCCA5ugAwIBAgIUDtmFbbnYaXbXH5ddtHi9l25wM7owDQYJKoZIhvcNAQEL +BQAwaTELMAkGA1UEBhMCU0sxEzARBgNVBAgMClNvbWUtU3RhdGUxITAfBgNVBAoM +GEludGVybmV0IFdpZGdpdHMgUHR5IEx0ZDEiMCAGA1UEAwwZcHJvbWV0aGV1cy5z +ZXJ2aWNlLmNvbnN1bDAeFw0yMjEyMzEyMDMxMDFaFw0yMzAxMzAyMDMxMDFaMGkx +CzAJBgNVBAYTAlNLMRMwEQYDVQQIDApTb21lLVN0YXRlMSEwHwYDVQQKDBhJbnRl +cm5ldCBXaWRnaXRzIFB0eSBMdGQxIjAgBgNVBAMMGXByb21ldGhldXMuc2Vydmlj +ZS5jb25zdWwwggIiMA0GCSqGSIb3DQEBAQUAA4ICDwAwggIKAoICAQCGH4Tyj+9G +wYJNb3ubIdr5r0/DZL6XEnRIMiz88TN2QmdwAGKyQqQd7ka0IkdDHPhpRuK8IV1g +ELQhKab7YJCa6zWuy+rQ6JFlotGC+2tIXd3MDriUd1VPVoX6fw/5zUK/2j6exBk4 +iqxPXHchQLzZ0viUXhQIBS1IUMTbfc0vjA8U0uPgpmAR7ieePWFwmUDxjOLMvJw6 ++goeOfaHhW4yYgT+kg7L3rT62G+KG6Op/p7k7BNZ6G6Y6K6uJ7Z/AayAClF2sPZz +UIGr0uEDvD4IcAsfQgpR5vK/SVBFU5+DSO68mm11m+8IH/HA6GvNSEvCRC0Wtrsm +Dyq+9S3wZ7tNi7msjQWWKTB1GvTbCbPE1G/q5GJdoKUnioys6AMP4DTEV9o3lCSg +0sjYnkSTKgRplnuY/7Y2qSNnD1Rw0ZneSkF+8ocgiYcTvtyOY2fkhlT2VaQLX987 +m7892ikPvoCnc/LVeREWW7hCuIQ1E1CCqg304Kd9gCgKoOGXoYmC/3wgJW0RkaM0 +x5DpNLYx0y11CPVg315dvprOuedap6J3CNhBE3fO8ymwepFTzTcWLWgSVWrRLZnx +Lgb4SPhjxPg6cCZptkmXrPA+9SgW8iNHd/Fer6MAs82Kcp2T1C+qq9RurL/jjxTD +JaFrwZC2lgWELToMyVDrkBJJbA/2cU9CMQIDAQABo1MwUTAdBgNVHQ4EFgQUx1Mi +fylZExNnIz0EkrPRdXYmHmAwHwYDVR0jBBgwFoAUx1MifylZExNnIz0EkrPRdXYm +HmAwDwYDVR0TAQH/BAUwAwEB/zANBgkqhkiG9w0BAQsFAAOCAgEAbvlpMg4YRTNe +0cgqMZky/GpNjvE/zFManUGgYns8TKyZ8U0laBxRQ4XU/fASwAcOBJYtrkG7w8z+ +FaOUptaOlNGW1VWsPDJt8ZQ2gAcTwKSW2EsBWCmOUJVNH5F0f6fTSqIUIXyxhP2w +JVniSkfarhb/Y1EDCACdr7Xpu6iF+nQo2o4/HE4Wkto4qwvlrdApYv4dl5J1TWjq +72fO9axDlNnEGVxa3C3xvKOQqWrEUy/HqC9p4it1yCiq6IYVLyve0meVFBY9xNXU +137AN7ks4ouuR1FZQkhLtqFuIekSZ5l4G4alwdv1NB8vohJMuMJyk9DarTLqXcYU +1uypZSmgREn8ByYrj4ochkSpiPw7wgK4H1Aa2cy4KUuzmLLShYu6Mov7hyJDoJSe +JsDVNoEBuhql4jENATqbWT3pIgYwBvBEXuYXqekcNmVZkKiSOlsxKFfSz21HYDgA +lCu4SMtlRYHcm4TuoTuy/FEPxHSjFY3pMciJrnO/qUrv9LlWPe1wjKhZLRPEebTk +r+Oh+aVWpy3ps7shPTjczOrmQykWWBGAjndZjZi4VvZNRxkGZuNwzzZcEkzt0Db7 +l83pTRD58mvLHWl2QXoBS3t7IM6sOMwQvPx1Inp7hb7UIpNsJQaUrhhfKqy0sK18 +mXs4VRtrxYycXxsLbk0SaZGh+juT53M= +-----END CERTIFICATE----- +EOH + } + + template { + change_mode = "noop" + change_signal = "SIGINT" + destination = "secrets/key_file.key" + left_delimiter = "{{{" + right_delimiter = "}}}" + data = <<EOH +-----BEGIN PRIVATE KEY----- +MIIJQQIBADANBgkqhkiG9w0BAQEFAASCCSswggknAgEAAoICAQCGH4Tyj+9GwYJN +b3ubIdr5r0/DZL6XEnRIMiz88TN2QmdwAGKyQqQd7ka0IkdDHPhpRuK8IV1gELQh +Kab7YJCa6zWuy+rQ6JFlotGC+2tIXd3MDriUd1VPVoX6fw/5zUK/2j6exBk4iqxP +XHchQLzZ0viUXhQIBS1IUMTbfc0vjA8U0uPgpmAR7ieePWFwmUDxjOLMvJw6+goe +OfaHhW4yYgT+kg7L3rT62G+KG6Op/p7k7BNZ6G6Y6K6uJ7Z/AayAClF2sPZzUIGr +0uEDvD4IcAsfQgpR5vK/SVBFU5+DSO68mm11m+8IH/HA6GvNSEvCRC0WtrsmDyq+ +9S3wZ7tNi7msjQWWKTB1GvTbCbPE1G/q5GJdoKUnioys6AMP4DTEV9o3lCSg0sjY +nkSTKgRplnuY/7Y2qSNnD1Rw0ZneSkF+8ocgiYcTvtyOY2fkhlT2VaQLX987m789 +2ikPvoCnc/LVeREWW7hCuIQ1E1CCqg304Kd9gCgKoOGXoYmC/3wgJW0RkaM0x5Dp +NLYx0y11CPVg315dvprOuedap6J3CNhBE3fO8ymwepFTzTcWLWgSVWrRLZnxLgb4 +SPhjxPg6cCZptkmXrPA+9SgW8iNHd/Fer6MAs82Kcp2T1C+qq9RurL/jjxTDJaFr +wZC2lgWELToMyVDrkBJJbA/2cU9CMQIDAQABAoICAA5AQByT3Z07h3BZ5ZzUqpM4 +JPYCeNvNeqyHJE+WA11P7fSxHcuKGC0T+dA/Cipf5CcvgHzz4JuJ+tHBPrxcBNFp +J5GUmjUrWPOfKrrLoxkT3DLH56Xizh45d8/ne1eUD0EaW+f7tyBSX7+o+AGBAu/0 +IjSFkIRPpIGYD2qxAcHJFHsmc08V7oRJNU1zgSx5JDTmPtz5N3Juye9vQjohG9Xf +o183Pro7xigXIjbe+/NemhyB1waJE2NM6e6YSqRRFbafIgvF/tG+3qBWrlD6ye6U +lSHznuwX6XgYvp43Je5JrBA/Kl1CPdIzrrjMGVQ9F8ui+dV9ggInv2d93q06IGUU +D1o9XsZivYkn1EkLEhFXD5CYj6oR1M+MyvUrBD0bJePQCBUo+WJ2sEDt9PN2AtFL +9j7NKK/xXX5cTdAajeIvSS1PUGAHi7r1OF/c7bn3UFNOuOBEYzLsSZGP34AVglor +NON0ENCTuylmDSFd8vpaKFQpV5SK3M2k8dPRe7VEu2C9UlRvAq0xnabSHNxbwNLU +KuGDMSCKDc2npf3oCeQKU2PngAcePnwWSiapAkf5OqltQ/vMbrEpROpfzXLlRxLZ +76MDMFMQkT7m0hik6aPBHTitcWRalxHhK0ze8GvO0wesIBdyYShPKg+VDNg3qFMm +epVXzoi8xNzW8S6yi9DJAoIBAQC2l90VF5evDsv8nwsWMIa/rFGGLitpw23+oNcZ +xsIDMsGie06GYwzYHNRsd3sqK5TNLtl2vJGaVNbeDcC5T22NAYPRjNas7I5svIki +SnT4K68ICIVVxtfETbh2qoXSu+O3pyWJmHqqcQrvW2DlUvs0nxk/v3GukFjTVbuU +qmXp1KjPAVMNYoWNCJkHLEpq6e3K3q4YhEImGhMbN8suvVR9+fkKx8QvKHcqT2kn +9AlK7t57IPqovbni9KMfMZ+wPqw6HsYTL8lQE5NaqMB5q9Pl3SnzcRR0FSadNAiD +/W9jWyMazE0UsNDn241X81tVlU78Kx9S/IN97m/FSeDA1XudAoIBAQC8CzVeHxTw +U+ts/fi1XEuWOph2cIm6qd4aiyGX/riux0O6GUFuIQkosP5StWJyNPLBohWHC6eq +hPk7b0vPWmxuhttUPLA/+6+CICC0jEMWvnDAd5aJULfT0pTLZyizVu2f/GbVaiL6 +pgsqeGyKnuh9cNTW5w7Mc45fXkgyKrB4W5aPfjoHN51n+jUqaDrfrp3CoWFviNDn +n3WNFtgrkj/jzQM8XFixhwxADfjd8+sZVmHT4GYjIDS4pCqs5gtIZYKhXDb0Dydj +fH/HiEXC63z0SuFjGNbomC/Era7kI3+1aK2qs6dyASzZKDN6dHKYoalHReUe/Cxk +prRcyYRWhA6lAoIBAEVrLy5Zrd1sLrl4beqdwF0W0lfFLdQj7Kml1KGEIza8EUoI +vy3wcm2naEtkkXrS3tuzOBIgVurp3lbFu8O4Ito8/TSp6uQLe4pzk19qF1ZSpVTU +iHy4AEgtlDfpVL9tl4G3FlpdkiVCnPmrMAd/qOm0oxDNZBcN4fdW3N4EeoKPyy4I +Pt8T2dpormU/vXswPKuoRWAkyFFcEG+Eosa+TGUoqDolAL09ETEQx9XcvbuzXPpK +64FDwGw8vdeaMi/7Y9ck5AFfZZYAG0GYbrTTUthNYSmgkDoh4HBb2/DyZWrMt2f0 +zElVf9bmbbJGXy8GeOT+MAaI4iT6hZvoHn6xqzECggEABoQg6k0LbbSKwPEgEDDN +kbwgEmKd8zD1uFe/50N1ZOEU0LsVUFqmtZlEhtswOSLqkpkqQ868laUb+dpGdz37 +6eyUZxvfQ6hWEZ1JZNhDbuNUhubd+Y4pgJaYf1/owiYt/9BAQ/70jVj5pBQeNsOA +7O/fAD9rfNw4P8fFmq9uBA2wbvKB0kQ0GSlLdFe+SogDgX4UIUhNbOlSqnvzK7da +rWsqRIoyrJwwaXvSduZ/7BXZN/1brLXt/cP6kpk6JN0XpL3MTbLEu6bRyrlHKZT9 +dH2vx75RnCfB5//YwqEUSNYCxpqJH+M4iaHh/slQO0fG1OhwIx278BTyxRBanKDg +3QKCAQBoVnM3PDqaSAT1g3f3neYiXyZektJganRLj5wmDXYAySM2ag/oDacswmP/ +J0BQ9KYK+dSgXldlaXtC05oxdhxY5cawbCFNfbjGDZ6zGwgLDocyFtqOBZf6UXCV +Gtj/9r6iyD2/2wbo/lrS0d3yNcNN0nkZUxoyl+J6uGB1o8bo+cfL+mi4pkALKV8L +Oa/fPazAQtikZBHSWtdQamyUMFSAdMUeYIhaXBfkNUZG4sz9nKD5UGBOmquLMBt6 +zBPM+4dv4x/MEAEnSC2ANW8vDGFBgG/5H5+j2F0RM6O1MlkDzrOAIvUTrMJlJDBt +775JbZNCKpaELqxy4BNPfRDEJGBh +-----END PRIVATE KEY----- +EOH + } + + # The "template" stanza instructs Nomad to manage a template, such as + # a configuration file or script. This template can optionally pull data + # from Consul or Vault to populate runtime configuration data. + # + # https://www.nomadproject.io/docs/job-specification/template + # + template { + change_mode = "noop" + change_signal = "SIGINT" + destination = "secrets/alerts.yml" + left_delimiter = "{{{" + right_delimiter = "}}}" + data = <<EOH +--- +groups: +- name: "Jenkins Job Health Exporter" + rules: + - alert: JenkinsJobHealthExporterFailures + expr: jenkins_job_failure{id=~".*"} > jenkins_job_success{id=~".*"} + for: 0m + labels: + severity: critical + annotations: + summary: "Jenkins Job Health detected high failure rate on jenkins jobs." + description: "Job: {{ $labels.id }}" + - alert: JenkinsJobHealthExporterUnstable + expr: jenkins_job_unstable{id=~".*"} > jenkins_job_success{id=~".*"} + for: 0m + labels: + severity: warning + annotations: + summary: "Jenkins Job Health detected high unstable rate on jenkins jobs." + description: "Job: {{ $labels.id }}" +- name: "Consul" + rules: + - alert: ConsulServiceHealthcheckFailed + expr: consul_catalog_service_node_healthy == 0 + for: 0m + labels: + severity: critical + annotations: + summary: "Consul service healthcheck failed (instance {{ $labels.instance }})." + description: "Service: `{{ $labels.service_name }}` Healthcheck: `{{ $labels.service_id }}`." + - alert: ConsulMissingMasterNode + expr: consul_raft_peers < 3 + for: 0m + labels: + severity: critical + annotations: + summary: "Consul missing master node (instance {{ $labels.instance }})." + description: "Numbers of consul raft peers should be 3, in order to preserve quorum." + - alert: ConsulAgentUnhealthy + expr: consul_health_node_status{status="critical"} == 1 + for: 0m + labels: + severity: critical + annotations: + summary: "Consul agent unhealthy (instance {{ $labels.instance }})." + description: "A Consul agent is down." +- name: "Hosts" + rules: + - alert: NodeDown + expr: up == 0 + for: 0m + labels: + severity: critical + annotations: + summary: "Prometheus target missing (instance {{ $labels.instance }})." + description: "A Prometheus target has disappeared. An exporter might be crashed." + - alert: HostOutOfMemory + expr: node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes * 100 < 10 + for: 2m + labels: + severity: warning + annotations: + summary: "Host out of memory (instance {{ $labels.instance }})." + description: "Node memory is filling up (< 10% left)." + - alert: HostOomKillDetected + expr: increase(node_vmstat_oom_kill[1m]) > 0 + for: 0m + labels: + severity: warning + annotations: + summary: "Host OOM kill detected (instance {{ $labels.instance }})." + description: "OOM kill detected." + - alert: HostMemoryUnderMemoryPressure + expr: rate(node_vmstat_pgmajfault[1m]) > 1000 + for: 2m + labels: + severity: warning + annotations: + summary: "Host memory under memory pressure (instance {{ $labels.instance }})." + description: "The node is under heavy memory pressure. High rate of major page faults." + - alert: HostOutOfDiskSpace + expr: (node_filesystem_avail_bytes * 100) / node_filesystem_size_bytes < 10 and ON (instance, device, mountpoint) node_filesystem_readonly == 0 + for: 2m + labels: + severity: warning + annotations: + summary: "Host out of disk space (instance {{ $labels.instance }})." + description: "Disk is almost full (< 10% left)." + - alert: HostRaidDiskFailure + expr: node_md_disks{state="failed"} > 0 + for: 2m + labels: + severity: warning + annotations: + summary: "Host RAID disk failure (instance {{ $labels.instance }})." + description: "At least one device in RAID array on {{ $labels.instance }} failed. Array {{ $labels.md_device }} needs attention and possibly a disk swap." + - alert: HostConntrackLimit + expr: node_nf_conntrack_entries / node_nf_conntrack_entries_limit > 0.8 + for: 5m + labels: + severity: warning + annotations: + summary: "Host conntrack limit (instance {{ $labels.instance }})." + description: "The number of conntrack is approching limit." + - alert: HostNetworkInterfaceSaturated + expr: (rate(node_network_receive_bytes_total{device!~"^tap.*"}[1m]) + rate(node_network_transmit_bytes_total{device!~"^tap.*"}[1m])) / node_network_speed_bytes{device!~"^tap.*"} > 0.8 + for: 1m + labels: + severity: warning + annotations: + summary: "Host Network Interface Saturated (instance {{ $labels.instance }})." + description: "The network interface {{ $labels.interface }} on {{ $labels.instance }} is getting overloaded." + - alert: HostSystemdServiceCrashed + expr: node_systemd_unit_state{state="failed"} == 1 + for: 0m + labels: + severity: warning + annotations: + summary: "Host SystemD service crashed (instance {{ $labels.instance }})." + description: "SystemD service crashed." + - alert: HostEdacCorrectableErrorsDetected + expr: increase(node_edac_correctable_errors_total[1m]) > 0 + for: 0m + labels: + severity: info + annotations: + summary: "Host EDAC Correctable Errors detected (instance {{ $labels.instance }})." + description: '{{ $labels.instance }} has had {{ printf "%.0f" $value }} correctable memory errors reported by EDAC in the last 5 minutes.' + - alert: HostEdacUncorrectableErrorsDetected + expr: node_edac_uncorrectable_errors_total > 0 + for: 0m + labels: + severity: warning + annotations: + summary: "Host EDAC Uncorrectable Errors detected (instance {{ $labels.instance }})." + description: '{{ $labels.instance }} has had {{ printf "%.0f" $value }} uncorrectable memory errors reported by EDAC in the last 5 minutes.' +- name: "Prometheus" + rules: + - alert: PrometheusConfigurationReloadFailure + expr: prometheus_config_last_reload_successful != 1 + for: 0m + labels: + severity: warning + annotations: + summary: "Prometheus configuration reload failure (instance {{ $labels.instance }})." + description: "Prometheus configuration reload error." + - alert: PrometheusTooManyRestarts + expr: changes(process_start_time_seconds{job=~"prometheus|pushgateway|alertmanager"}[15m]) > 2 + for: 0m + labels: + severity: warning + annotations: + summary: "Prometheus too many restarts (instance {{ $labels.instance }})." + description: "Prometheus has restarted more than twice in the last 15 minutes. It might be crashlooping." + - alert: PrometheusAlertmanagerConfigurationReloadFailure + expr: alertmanager_config_last_reload_successful != 1 + for: 0m + labels: + severity: warning + annotations: + summary: "Prometheus AlertManager configuration reload failure (instance {{ $labels.instance }})." + description: "AlertManager configuration reload error." + - alert: PrometheusRuleEvaluationFailures + expr: increase(prometheus_rule_evaluation_failures_total[3m]) > 0 + for: 0m + labels: + severity: critical + annotations: + summary: "Prometheus rule evaluation failures (instance {{ $labels.instance }})." + description: "Prometheus encountered {{ $value }} rule evaluation failures, leading to potentially ignored alerts." + - alert: PrometheusTargetScrapingSlow + expr: prometheus_target_interval_length_seconds{quantile="0.9"} > 60 + for: 5m + labels: + severity: warning + annotations: + summary: "Prometheus target scraping slow (instance {{ $labels.instance }})." + description: "Prometheus is scraping exporters slowly." + - alert: PrometheusTsdbCompactionsFailed + expr: increase(prometheus_tsdb_compactions_failed_total[1m]) > 0 + for: 0m + labels: + severity: critical + annotations: + summary: "Prometheus TSDB compactions failed (instance {{ $labels.instance }})." + description: "Prometheus encountered {{ $value }} TSDB compactions failures." + - alert: PrometheusTsdbHeadTruncationsFailed + expr: increase(prometheus_tsdb_head_truncations_failed_total[1m]) > 0 + for: 0m + labels: + severity: critical + annotations: + summary: "Prometheus TSDB head truncations failed (instance {{ $labels.instance }})." + description: "Prometheus encountered {{ $value }} TSDB head truncation failures." + - alert: PrometheusTsdbWalCorruptions + expr: increase(prometheus_tsdb_wal_corruptions_total[1m]) > 0 + for: 0m + labels: + severity: critical + annotations: + summary: "Prometheus TSDB WAL corruptions (instance {{ $labels.instance }})." + description: "Prometheus encountered {{ $value }} TSDB WAL corruptions." + - alert: PrometheusTsdbWalTruncationsFailed + expr: increase(prometheus_tsdb_wal_truncations_failed_total[1m]) > 0 + for: 0m + labels: + severity: critical + annotations: + summary: "Prometheus TSDB WAL truncations failed (instance {{ $labels.instance }})." + description: "Prometheus encountered {{ $value }} TSDB WAL truncation failures." +EOH + } + + template { + change_mode = "noop" + change_signal = "SIGINT" + destination = "secrets/prometheus.yml" + data = <<EOH +--- +global: + scrape_interval: 5s + scrape_timeout: 5s + evaluation_interval: 5s + +alerting: + alertmanagers: + - consul_sd_configs: + - server: '{{ env "NOMAD_IP_prometheus" }}:8500' + services: [ 'alertmanager' ] + +rule_files: + - 'alerts.yml' + +scrape_configs: + - job_name: 'Nomad Cluster' + consul_sd_configs: + - server: '{{ env "NOMAD_IP_prometheus" }}:8500' + services: [ 'nomad-client', 'nomad' ] + relabel_configs: + - source_labels: [__meta_consul_tags] + regex: '(.*)http(.*)' + action: keep + metrics_path: /v1/metrics + params: + format: [ 'prometheus' ] + + - job_name: 'Consul Cluster' + static_configs: + - targets: [ '10.30.51.23:8500' ] + - targets: [ '10.30.51.24:8500' ] + - targets: [ '10.30.51.25:8500' ] + - targets: [ '10.30.51.26:8500' ] + - targets: [ '10.30.51.27:8500' ] + - targets: [ '10.30.51.28:8500' ] + - targets: [ '10.30.51.50:8500' ] + - targets: [ '10.30.51.51:8500' ] + - targets: [ '10.30.51.70:8500' ] + - targets: [ '10.30.51.71:8500' ] + - targets: [ '10.30.51.91:8500' ] + - targets: [ '10.30.51.92:8500' ] + metrics_path: /v1/agent/metrics + params: + format: [ 'prometheus' ] + + - job_name: 'Jenkins Job Health Exporter' + static_configs: + - targets: [ '10.30.51.22:9186' ] + metric_relabel_configs: + - source_labels: [ __name__ ] + regex: '^(vpp.*|csit.*)_(success|failure|total|unstable|reqtime_ms)$' + action: replace + replacement: '$1' + target_label: id + - source_labels: [ __name__ ] + regex: '^(vpp.*|csit.*)_(success|failure|total|unstable|reqtime_ms)$' + replacement: 'jenkins_job_$2' + target_label: __name__ + + - job_name: 'Node Exporter' + static_configs: + - targets: [ '10.30.51.23:9100' ] + - targets: [ '10.30.51.24:9100' ] + - targets: [ '10.30.51.25:9100' ] + - targets: [ '10.30.51.26:9100' ] + - targets: [ '10.30.51.27:9100' ] + - targets: [ '10.30.51.28:9100' ] + - targets: [ '10.30.51.50:9100' ] + - targets: [ '10.30.51.51:9100' ] + - targets: [ '10.30.51.70:9100' ] + - targets: [ '10.30.51.71:9100' ] + - targets: [ '10.30.51.91:9100' ] + - targets: [ '10.30.51.92:9100' ] + + - job_name: 'Alertmanager' + consul_sd_configs: + - server: '{{ env "NOMAD_IP_prometheus" }}:8500' + services: [ 'alertmanager' ] + + - job_name: 'Prometheus' + honor_timestamps: true + params: + format: + - prometheus + scheme: https + follow_redirects: true + enable_http2: true + consul_sd_configs: + - server: {{ env "CONSUL_HTTP_ADDR" }} + services: + - prometheus + tls_config: + cert_file: cert_file.crt + key_file: key_file.key + insecure_skip_verify: true +EOH + } + + template { + change_mode = "noop" + change_signal = "SIGINT" + destination = "secrets/web-config.yml" + left_delimiter = "{{{" + right_delimiter = "}}}" + data = <<EOH +--- +tls_server_config: + cert_file: cert_file.crt + key_file: key_file.key +EOH + } + + # The service stanza instructs Nomad to register a service with Consul. + # + # https://www.nomadproject.io/docs/job-specification/service + # + service { + name = "${service_name}" + port = "${service_name}" + tags = [ "${service_name}$${NOMAD_ALLOC_INDEX}" ] + check { + name = "Prometheus Check Live" + type = "http" + path = "/-/healthy" + protocol = "https" + tls_skip_verify = true + interval = "10s" + timeout = "2s" + } + } + + # The "resources" stanza describes the requirements a task needs to + # execute. Resource requirements include memory, network, cpu, and more. + # This ensures the task will execute on a machine that contains enough + # resource capacity. + # + # https://www.nomadproject.io/docs/job-specification/resources + # + resources { + cpu = ${cpu} + memory = ${memory} + } + } + } +} |