From 8843893ca7531cbb2212a5ed79882909c8374381 Mon Sep 17 00:00:00 2001 From: pmikus Date: Wed, 28 Jul 2021 10:44:43 +0000 Subject: Infra: upgrade monitoring solution + bump versions - remove cadvisor Signed-off-by: pmikus Change-Id: I3de95531f1b09f7254152254e92f225dde653e45 --- fdio.infra.ansible/nomad.yaml | 2 - .../roles/prometheus_exporter/defaults/main.yaml | 32 +++++++--- .../roles/prometheus_exporter/handlers/main.yaml | 16 ----- .../roles/prometheus_exporter/tasks/main.yaml | 69 +++++++++++++++++++-- .../prometheus_exporter/tasks/ubuntu_bionic.yaml | 33 ---------- .../prometheus_exporter/tasks/ubuntu_focal.yaml | 33 ---------- fdio.infra.ansible/vpp_device.yaml | 2 - fdio.infra.terraform/1n_nmd/main.tf | 6 +- .../1n_nmd/prometheus/conf/nomad/prometheus.hcl | 34 +---------- .../1n_nmd/prometheus/variables.tf | 2 +- fdio.infra.terraform/1n_nmd/terraform.tfstate | 70 ++++++++++----------- .../1n_nmd/terraform.tfstate.backup | 71 ++++++++++++---------- 12 files changed, 164 insertions(+), 206 deletions(-) delete mode 100644 fdio.infra.ansible/roles/prometheus_exporter/handlers/main.yaml delete mode 100644 fdio.infra.ansible/roles/prometheus_exporter/tasks/ubuntu_bionic.yaml delete mode 100644 fdio.infra.ansible/roles/prometheus_exporter/tasks/ubuntu_focal.yaml diff --git a/fdio.infra.ansible/nomad.yaml b/fdio.infra.ansible/nomad.yaml index dc13386756..1ebbb417cd 100644 --- a/fdio.infra.ansible/nomad.yaml +++ b/fdio.infra.ansible/nomad.yaml @@ -26,7 +26,5 @@ tags: prometheus_exporter - role: jenkins_job_health_exporter tags: jenkins_job_health_exporter - - role: cadvisor - tags: cadvisor - role: cleanup tags: cleanup diff --git a/fdio.infra.ansible/roles/prometheus_exporter/defaults/main.yaml b/fdio.infra.ansible/roles/prometheus_exporter/defaults/main.yaml index eb2b94cb26..e97ad2b0c7 100644 --- a/fdio.infra.ansible/roles/prometheus_exporter/defaults/main.yaml +++ b/fdio.infra.ansible/roles/prometheus_exporter/defaults/main.yaml @@ -2,16 +2,30 @@ # file: roles/prometheus_exporter/defaults/main.yaml # Inst - Exporters. -ne_packages: "{{ ne_packages_by_distro[ansible_distribution | lower][ansible_machine] }}" +packages: "{{ packages_base + packages_by_distro[ansible_distribution | lower] + packages_by_arch[ansible_machine] }}" -ne_packages_by_distro: +packages_base: + - [] + +packages_by_distro: ubuntu: - aarch64: "http://ports.ubuntu.com/pool/universe/p/prometheus-node-exporter/prometheus-node-exporter_1.0.1+ds-1_arm64.deb" - x86_64: "http://archive.ubuntu.com/ubuntu/pool/universe/p/prometheus-node-exporter/prometheus-node-exporter_1.0.1+ds-1_amd64.deb" + - "python3-docker" + - "python3-dockerpty" -be_packages: "{{ be_packages_by_distro[ansible_distribution | lower][ansible_machine] }}" +packages_by_arch: + aarch64: + - [] + x86_64: + - [] -be_packages_by_distro: - ubuntu: - aarch64: "http://ports.ubuntu.com/pool/universe/p/prometheus-blackbox-exporter/prometheus-blackbox-exporter_0.17.0+ds-1_arm64.deb" - x86_64: "http://archive.ubuntu.com/ubuntu/pool/universe/p/prometheus-blackbox-exporter/prometheus-blackbox-exporter_0.17.0+ds-1_amd64.deb" +ne_image: "{{ ne_image_by_arch[ansible_machine] }}" + +ne_image_by_arch: + aarch64: "prom/node-exporter:v1.2.0" + x86_64: "prom/node-exporter:v1.2.0" + +be_image: "{{ be_image_by_arch[ansible_machine] }}" + +be_image_by_arch: + aarch64: "prom/blackbox-exporter:v0.19.0" + x86_64: "prom/blackbox-exporter:v0.19.0" diff --git a/fdio.infra.ansible/roles/prometheus_exporter/handlers/main.yaml b/fdio.infra.ansible/roles/prometheus_exporter/handlers/main.yaml deleted file mode 100644 index 9c374eaa61..0000000000 --- a/fdio.infra.ansible/roles/prometheus_exporter/handlers/main.yaml +++ /dev/null @@ -1,16 +0,0 @@ ---- -# file roles/prometheus_exporter/handlers/main.yaml - -- name: Restart Prometheus Node Exporter - systemd: - daemon_reload: true - enabled: true - name: "prometheus-node-exporter" - state: "restarted" - -- name: Restart Prometheus Blackbox Exporter - systemd: - daemon_reload: true - enabled: true - name: "prometheus-blackbox-exporter" - state: "restarted" \ No newline at end of file diff --git a/fdio.infra.ansible/roles/prometheus_exporter/tasks/main.yaml b/fdio.infra.ansible/roles/prometheus_exporter/tasks/main.yaml index b38215c4a2..3f4b563352 100644 --- a/fdio.infra.ansible/roles/prometheus_exporter/tasks/main.yaml +++ b/fdio.infra.ansible/roles/prometheus_exporter/tasks/main.yaml @@ -1,15 +1,72 @@ --- # file: roles/prometheus_exporter/tasks/main.yaml -- include_tasks: "{{ ansible_distribution|lower }}_{{ ansible_distribution_release }}.yaml" +- name: Inst - Update Package Cache (APT) + apt: + update_cache: yes + cache_valid_time: 3600 + when: + - ansible_distribution|lower == 'ubuntu' tags: - prometheus-inst +- name: Inst - Prerequisites + package: + name: "{{ packages | flatten(levels=1) }}" + state: latest + tags: + - prometheus-inst + +- name: Inst - Start a NodeExporter container + docker_container: + name: "NodeExporter" + image: "{{ ne_image }}" + state: "started" + restart_policy: "unless-stopped" + detach: yes + ports: + - "9100:9100" + privileged: yes + command: + - "--path.procfs=/host/proc" + - "--path.rootfs=/rootfs" + - "--path.sysfs=/host/sys" + - "--collector.filesystem.mount-points-exclude=^/(sys|proc|dev|host|etc)($$|/)" + volumes: + - "/:/rootfs:ro" + - "/proc:/host/proc:ro" + - "/sys:/host/sys:ro" + tags: + - prometheus-inst + +- name: Inst - Create a Config Directory + ansible.builtin.file: + path: "/etc/prometheus/" + state: "directory" + mode: "0755" + tags: + - prometheus-conf-blackbox-exporter + - name: Conf - Prometheus Blackbox Exporter copy: - src: 'files/blackbox.yml' - dest: '/etc/prometheus/blackbox.yml' - notify: - - "Restart Prometheus Blackbox Exporter" + src: "files/blackbox.yml" + dest: "/etc/prometheus/blackbox.yml" + tags: + - prometheus-conf-blackbox-exporter + +- name: Inst - Start a BlackBoxExporter container + docker_container: + name: "BlackBoxExporter" + image: "{{ be_image }}" + state: "started" + restart_policy: "unless-stopped" + detach: yes + ports: + - "9115:9115" + privileged: yes + command: + - "--config.file=/config/blackbox.yml" + volumes: + - "/etc/prometheus/blackbox.yml:/config/blackbox.yml:ro" tags: - - prometheus-conf-blackbox-exporter \ No newline at end of file + - prometheus-inst \ No newline at end of file diff --git a/fdio.infra.ansible/roles/prometheus_exporter/tasks/ubuntu_bionic.yaml b/fdio.infra.ansible/roles/prometheus_exporter/tasks/ubuntu_bionic.yaml deleted file mode 100644 index 566753e272..0000000000 --- a/fdio.infra.ansible/roles/prometheus_exporter/tasks/ubuntu_bionic.yaml +++ /dev/null @@ -1,33 +0,0 @@ ---- -# file: roles/prometheus_exporter/tasks/ubuntu_bionic.yaml - -- name: Inst - Update Package Cache (APT) - apt: - update_cache: yes - cache_valid_time: 3600 - tags: - - prometheus-inst-prerequisites - -- name: Inst - Prerequisites - package: - name: "init-system-helpers" - default_release: "bionic-backports" - state: latest - tags: - - prometheus-inst-prerequisites - -- name: Inst - Prometheus Node Exporter - apt: - deb: "{{ ne_packages }}" - notify: - - "Restart Prometheus Node Exporter" - tags: - - prometheus-inst-node-exporter - -- name: Inst - Prometheus Blackbox Exporter - apt: - deb: "{{ be_packages }}" - notify: - - "Restart Prometheus Blackbox Exporter" - tags: - - prometheus-inst-blackbox-exporter \ No newline at end of file diff --git a/fdio.infra.ansible/roles/prometheus_exporter/tasks/ubuntu_focal.yaml b/fdio.infra.ansible/roles/prometheus_exporter/tasks/ubuntu_focal.yaml deleted file mode 100644 index 3d7064355e..0000000000 --- a/fdio.infra.ansible/roles/prometheus_exporter/tasks/ubuntu_focal.yaml +++ /dev/null @@ -1,33 +0,0 @@ ---- -# file: roles/prometheus_exporter/tasks/ubuntu_focal.yaml - -- name: Inst - Update Package Cache (APT) - apt: - update_cache: yes - cache_valid_time: 3600 - tags: - - prometheus-inst-prerequisites - -- name: Inst - Prerequisites - package: - name: "init-system-helpers" - default_release: "focal-backports" - state: latest - tags: - - prometheus-inst-prerequisites - -- name: Inst - Prometheus Node Exporter - apt: - deb: "{{ ne_packages }}" - notify: - - "Restart Prometheus Node Exporter" - tags: - - prometheus-inst-node-exporter - -- name: Inst - Prometheus Blackbox Exporter - apt: - deb: "{{ be_packages }}" - notify: - - "Restart Prometheus Blackbox Exporter" - tags: - - prometheus-inst-blackbox-exporter \ No newline at end of file diff --git a/fdio.infra.ansible/vpp_device.yaml b/fdio.infra.ansible/vpp_device.yaml index 9e334e1749..ae54669ae9 100644 --- a/fdio.infra.ansible/vpp_device.yaml +++ b/fdio.infra.ansible/vpp_device.yaml @@ -30,8 +30,6 @@ tags: prometheus_exporter - role: jenkins_job_health_exporter tags: jenkins_job_health_exporter - - role: cadvisor - tags: cadvisor - role: vpp_device tags: vpp_device - role: kernel_vm diff --git a/fdio.infra.terraform/1n_nmd/main.tf b/fdio.infra.terraform/1n_nmd/main.tf index 1d5c3e4f7d..d48f12a046 100644 --- a/fdio.infra.terraform/1n_nmd/main.tf +++ b/fdio.infra.terraform/1n_nmd/main.tf @@ -76,7 +76,7 @@ module "minio" { minio_service_name = "storage" minio_host = "http://10.32.8.1{4...7}" minio_port = 9000 - minio_container_image = "minio/minio:RELEASE.2021-07-08T01-15-01Z" + minio_container_image = "minio/minio:RELEASE.2021-07-27T02-40-15Z" minio_vault_secret = { use_vault_provider = false, vault_kv_policy_name = "kv-secret", @@ -91,7 +91,7 @@ module "minio" { # minio client mc_job_name = "prod-mc" - mc_container_image = "minio/mc:RELEASE.2021-07-08T01-15-01Z" + mc_container_image = "minio/mc:RELEASE.2021-07-27T02-40-15Z" mc_extra_commands = [ "mc policy set public LOCALMINIO/logs.fd.io", "mc policy set public LOCALMINIO/docs.fd.io", @@ -140,7 +140,7 @@ module "prometheus" { } prometheus_data_dir = "/data/" prometheus_use_host_volume = true - prometheus_version = "2.24.0" + prometheus_version = "2.28.1" prometheus_cpu = 2000 prometheus_mem = 8192 prometheus_port = 9090 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 adc30318c4..3d0b2c2eef 100644 --- a/fdio.infra.terraform/1n_nmd/prometheus/conf/nomad/prometheus.hcl +++ b/fdio.infra.terraform/1n_nmd/prometheus/conf/nomad/prometheus.hcl @@ -175,7 +175,7 @@ job "${job_name}" { args = [ "--config.file=secrets/prometheus.yml", "--storage.tsdb.path=${data_dir}prometheus/", - "--storage.tsdb.retention.time=15d" + "--storage.tsdb.retention.time=7d" ] } @@ -265,14 +265,6 @@ groups: annotations: summary: "Prometheus target missing (instance {{ $labels.instance }})." description: "A Prometheus target has disappeared. An exporter might be crashed." - - alert: HostHighCpuLoad - expr: 100 - (avg by(instance) (rate(node_cpu_seconds_total{mode="idle"}[5m])) * 100) > 95 - for: 0m - labels: - severity: warning - annotations: - summary: "Host high CPU load (instance {{ $labels.instance }})." - description: "CPU load is > 95%." - alert: HostOutOfMemory expr: node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes * 100 < 10 for: 2m @@ -540,30 +532,6 @@ scrape_configs: replacement: localhost:9115 metrics_path: /probe - - job_name: 'cAdvisor Exporter' - static_configs: - - targets: [ '10.30.51.28:8080' ] - - targets: [ '10.30.51.29:8080' ] - - targets: [ '10.30.51.30:8080' ] - #- targets: [ '10.30.51.32:8080' ] - - targets: [ '10.30.51.33:8080' ] - - targets: [ '10.30.51.34:8080' ] - - targets: [ '10.30.51.35:8080' ] - - targets: [ '10.30.51.39:8080' ] - - targets: [ '10.30.51.40:8080' ] - - targets: [ '10.30.51.50:8080' ] - - targets: [ '10.30.51.51:8080' ] - - targets: [ '10.30.51.65:8080' ] - - targets: [ '10.30.51.66:8080' ] - - targets: [ '10.30.51.67:8080' ] - - targets: [ '10.30.51.68:8080' ] - - targets: [ '10.30.51.70:8080' ] - - targets: [ '10.30.51.71:8080' ] - - targets: [ '10.32.8.14:8080' ] - - targets: [ '10.32.8.15:8080' ] - - targets: [ '10.32.8.16:8080' ] - - targets: [ '10.32.8.17:8080' ] - - job_name: 'Jenkins Job Health Exporter' static_configs: - targets: [ '10.30.51.32:9186' ] diff --git a/fdio.infra.terraform/1n_nmd/prometheus/variables.tf b/fdio.infra.terraform/1n_nmd/prometheus/variables.tf index a509533ccd..55ffa33856 100644 --- a/fdio.infra.terraform/1n_nmd/prometheus/variables.tf +++ b/fdio.infra.terraform/1n_nmd/prometheus/variables.tf @@ -33,7 +33,7 @@ variable "prometheus_service_name" { variable "prometheus_version" { description = "Prometheus version" type = string - default = "v2.24.0" + default = "v2.28.1" } variable "prometheus_use_canary" { diff --git a/fdio.infra.terraform/1n_nmd/terraform.tfstate b/fdio.infra.terraform/1n_nmd/terraform.tfstate index 2a90a2d90e..7e4875858d 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": "1.0.0", - "serial": 1170, + "terraform_version": "1.0.2", + "serial": 1178, "lineage": "e4e7f30a-652d-7a31-e31c-5e3a3388c9b9", "outputs": {}, "resources": [ @@ -197,15 +197,15 @@ "schema_version": 0, "attributes": { "filename": null, - "id": "558e3a2e96b2b0f9d94e57f74a784d89020ce8d1d877e7adb82301065dfbacb7", - "rendered": "job \"prod-mc\" {\n # The \"region\" parameter specifies the region in which to execute the job.\n # If omitted, this inherits the default region name of \"global\".\n # region = \"global\"\n #\n # The \"datacenters\" parameter specifies the list of datacenters which should\n # be considered when placing this task. This must be provided.\n datacenters = \"yul1\"\n\n # The \"type\" parameter controls the type of job, which impacts the scheduler's\n # decision on placement. This configuration is optional and defaults to\n # \"service\". For a full list of job types and their differences, please see\n # the online documentation.\n #\n # For more information, please see the online documentation at:\n #\n # https://www.nomadproject.io/docs/jobspec/schedulers.html\n #\n type = \"batch\"\n\n # The \"group\" stanza defines a series of tasks that should be co-located on\n # the same Nomad client. Any task within a group will be placed on the same\n # client.\n #\n # For more information and examples on the \"group\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/group.html\n #\n group \"prod-group1-mc\" {\n task \"prod-task1-create-buckets\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"docker\"\n\n \n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n image = \"minio/mc:RELEASE.2021-07-08T01-15-01Z\"\n entrypoint = [\n \"/bin/sh\",\n \"-c\",\n \"mc config host add LOCALMINIO http://storage.service.consul:9000 $MINIO_ACCESS_KEY $MINIO_SECRET_KEY \u0026\u0026 mc mb -p LOCALMINIO/logs.fd.io LOCALMINIO/docs.fd.io ; mc policy set public LOCALMINIO/logs.fd.io mc policy set public LOCALMINIO/docs.fd.io mc ilm add --expiry-days '180' LOCALMINIO/logs.fd.io mc admin user add LOCALMINIO storage Storage1234 mc admin policy set LOCALMINIO writeonly user=storage\"\n ]\n dns_servers = [ \"${attr.unique.network.ip-address}\" ]\n privileged = false\n }\n\n # The env stanza configures a list of environment variables to populate\n # the task's environment before starting.\n env {\n \n MINIO_ACCESS_KEY = \"minio\"\n MINIO_SECRET_KEY = \"minio123\"\n \n \n }\n }\n }\n}\n", + "id": "e9e956124e6fed4268bec199b9d7fd7aaff506e906b53621c6dc0e3116c40f52", + "rendered": "job \"prod-mc\" {\n # The \"region\" parameter specifies the region in which to execute the job.\n # If omitted, this inherits the default region name of \"global\".\n # region = \"global\"\n #\n # The \"datacenters\" parameter specifies the list of datacenters which should\n # be considered when placing this task. This must be provided.\n datacenters = \"yul1\"\n\n # The \"type\" parameter controls the type of job, which impacts the scheduler's\n # decision on placement. This configuration is optional and defaults to\n # \"service\". For a full list of job types and their differences, please see\n # the online documentation.\n #\n # For more information, please see the online documentation at:\n #\n # https://www.nomadproject.io/docs/jobspec/schedulers.html\n #\n type = \"batch\"\n\n # The \"group\" stanza defines a series of tasks that should be co-located on\n # the same Nomad client. Any task within a group will be placed on the same\n # client.\n #\n # For more information and examples on the \"group\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/group.html\n #\n group \"prod-group1-mc\" {\n task \"prod-task1-create-buckets\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"docker\"\n\n \n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n image = \"minio/mc:RELEASE.2021-07-27T02-40-15Z\"\n entrypoint = [\n \"/bin/sh\",\n \"-c\",\n \"mc config host add LOCALMINIO http://storage.service.consul:9000 $MINIO_ACCESS_KEY $MINIO_SECRET_KEY \u0026\u0026 mc mb -p LOCALMINIO/logs.fd.io LOCALMINIO/docs.fd.io ; mc policy set public LOCALMINIO/logs.fd.io mc policy set public LOCALMINIO/docs.fd.io mc ilm add --expiry-days '180' LOCALMINIO/logs.fd.io mc admin user add LOCALMINIO storage Storage1234 mc admin policy set LOCALMINIO writeonly user=storage\"\n ]\n dns_servers = [ \"${attr.unique.network.ip-address}\" ]\n privileged = false\n }\n\n # The env stanza configures a list of environment variables to populate\n # the task's environment before starting.\n env {\n \n MINIO_ACCESS_KEY = \"minio\"\n MINIO_SECRET_KEY = \"minio123\"\n \n \n }\n }\n }\n}\n", "template": "job \"${job_name}\" {\n # The \"region\" parameter specifies the region in which to execute the job.\n # If omitted, this inherits the default region name of \"global\".\n # region = \"global\"\n #\n # The \"datacenters\" parameter specifies the list of datacenters which should\n # be considered when placing this task. This must be provided.\n datacenters = \"${datacenters}\"\n\n # The \"type\" parameter controls the type of job, which impacts the scheduler's\n # decision on placement. This configuration is optional and defaults to\n # \"service\". For a full list of job types and their differences, please see\n # the online documentation.\n #\n # For more information, please see the online documentation at:\n #\n # https://www.nomadproject.io/docs/jobspec/schedulers.html\n #\n type = \"batch\"\n\n # The \"group\" stanza defines a series of tasks that should be co-located on\n # the same Nomad client. Any task within a group will be placed on the same\n # client.\n #\n # For more information and examples on the \"group\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/group.html\n #\n group \"prod-group1-mc\" {\n task \"prod-task1-create-buckets\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"docker\"\n\n %{ if use_vault_provider }\n vault {\n policies = \"${vault_kv_policy_name}\"\n }\n %{ endif }\n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n image = \"${image}\"\n entrypoint = [\n \"/bin/sh\",\n \"-c\",\n \"${command}\"\n ]\n dns_servers = [ \"$${attr.unique.network.ip-address}\" ]\n privileged = false\n }\n\n # The env stanza configures a list of environment variables to populate\n # the task's environment before starting.\n env {\n %{ if use_vault_provider }\n {{ with secret \"${vault_kv_path}\" }}\n MINIO_ACCESS_KEY = \"{{ .Data.data.${vault_kv_field_access_key} }}\"\n MINIO_SECRET_KEY = \"{{ .Data.data.${vault_kv_field_secret_key} }}\"\n {{ end }}\n %{ else }\n MINIO_ACCESS_KEY = \"${access_key}\"\n MINIO_SECRET_KEY = \"${secret_key}\"\n %{ endif }\n ${ envs }\n }\n }\n }\n}\n", "vars": { "access_key": "minio", "command": "mc config host add LOCALMINIO http://storage.service.consul:9000 $MINIO_ACCESS_KEY $MINIO_SECRET_KEY \u0026\u0026 mc mb -p LOCALMINIO/logs.fd.io LOCALMINIO/docs.fd.io ; mc policy set public LOCALMINIO/logs.fd.io mc policy set public LOCALMINIO/docs.fd.io mc ilm add --expiry-days '180' LOCALMINIO/logs.fd.io mc admin user add LOCALMINIO storage Storage1234 mc admin policy set LOCALMINIO writeonly user=storage", "datacenters": "yul1", "envs": "", - "image": "minio/mc:RELEASE.2021-07-08T01-15-01Z", + "image": "minio/mc:RELEASE.2021-07-27T02-40-15Z", "job_name": "prod-mc", "minio_port": "9000", "minio_service_name": "storage", @@ -229,8 +229,8 @@ "schema_version": 0, "attributes": { "filename": null, - "id": "3df2a58bed278738e5280a087b9d56413910e767c60d6702506bd7820cfdd5b4", - "rendered": "job \"prod-minio\" {\n # The \"region\" parameter specifies the region in which to execute the job.\n # If omitted, this inherits the default region name of \"global\".\n # region = \"global\"\n #\n # The \"datacenters\" parameter specifies the list of datacenters which should\n # be considered when placing this task. This must be provided.\n datacenters = \"yul1\"\n\n # The \"type\" parameter controls the type of job, which impacts the scheduler's\n # decision on placement. This configuration is optional and defaults to\n # \"service\". For a full list of job types and their differences, please see\n # the online documentation.\n #\n # https://www.nomadproject.io/docs/jobspec/schedulers\n #\n type = \"service\"\n\n update {\n # The \"max_parallel\" parameter specifies the maximum number of updates to\n # perform in parallel. In this case, this specifies to update a single task\n # at a time.\n max_parallel = 1\n\n health_check = \"checks\"\n\n # The \"min_healthy_time\" parameter specifies the minimum time the allocation\n # must be in the healthy state before it is marked as healthy and unblocks\n # further allocations from being updated.\n min_healthy_time = \"10s\"\n\n # The \"healthy_deadline\" parameter specifies the deadline in which the\n # allocation must be marked as healthy after which the allocation is\n # automatically transitioned to unhealthy. Transitioning to unhealthy will\n # fail the deployment and potentially roll back the job if \"auto_revert\" is\n # set to true.\n healthy_deadline = \"3m\"\n\n # The \"progress_deadline\" parameter specifies the deadline in which an\n # allocation must be marked as healthy. The deadline begins when the first\n # allocation for the deployment is created and is reset whenever an allocation\n # as part of the deployment transitions to a healthy state. If no allocation\n # transitions to the healthy state before the progress deadline, the\n # deployment is marked as failed.\n progress_deadline = \"10m\"\n\n\n # The \"canary\" parameter specifies that changes to the job that would result\n # in destructive updates should create the specified number of canaries\n # without stopping any previous allocations. Once the operator determines the\n # canaries are healthy, they can be promoted which unblocks a rolling update\n # of the remaining allocations at a rate of \"max_parallel\".\n #\n # Further, setting \"canary\" equal to the count of the task group allows\n # blue/green deployments. When the job is updated, a full set of the new\n # version is deployed and upon promotion the old version is stopped.\n canary = 1\n\n # Specifies if the job should auto-promote to the canary version when all\n # canaries become healthy during a deployment. Defaults to false which means\n # canaries must be manually updated with the nomad deployment promote\n # command.\n auto_promote = true\n\n # The \"auto_revert\" parameter specifies if the job should auto-revert to the\n # last stable job on deployment failure. A job is marked as stable if all the\n # allocations as part of its deployment were marked healthy.\n auto_revert = true\n\n }\n\n # All groups in this job should be scheduled on different hosts.\n constraint {\n operator = \"distinct_hosts\"\n value = \"true\"\n }\n\n # The \"group\" stanza defines a series of tasks that should be co-located on\n # the same Nomad client. Any task within a group will be placed on the same\n # client.\n #\n # https://www.nomadproject.io/docs/job-specification/group\n #\n group \"prod-group1-minio\" {\n # The \"count\" parameter specifies the number of the task groups that should\n # be running under this group. This value must be non-negative and defaults\n # to 1.\n count = 4\n\n # https://www.nomadproject.io/docs/job-specification/volume\n \n volume \"prod-volume1-minio\" {\n type = \"host\"\n read_only = false\n source = \"prod-volume-data1-1\"\n }\n \n\n # The restart stanza configures a tasks's behavior on task failure. Restarts\n # happen on the client that is running the task.\n #\n # https://www.nomadproject.io/docs/job-specification/restart\n #\n restart {\n interval = \"30m\"\n attempts = 40\n delay = \"15s\"\n mode = \"delay\"\n }\n\n # The \"task\" stanza creates an individual unit of work, such as a Docker\n # container, web application, or batch processing.\n #\n # https://www.nomadproject.io/docs/job-specification/task.html\n #\n task \"prod-task1-minio\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"docker\"\n\n \n volume_mount {\n volume = \"prod-volume1-minio\"\n destination = \"/data/\"\n read_only = false\n }\n \n\n \n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n image = \"minio/minio:RELEASE.2021-07-08T01-15-01Z\"\n dns_servers = [ \"172.17.0.1\" ]\n network_mode = \"host\"\n command = \"server\"\n args = [ \"http://10.32.8.1{4...7}:9000/data/\" ]\n port_map {\n http = 9000\n }\n privileged = false\n }\n\n # The env stanza configures a list of environment variables to populate\n # the task's environment before starting.\n env {\n\n MINIO_ACCESS_KEY = \"minio\"\n MINIO_SECRET_KEY = \"minio123\"\n\n MINIO_BROWSER=\"off\"\n }\n\n # The service stanza instructs Nomad to register a service with Consul.\n #\n # https://www.nomadproject.io/docs/job-specification/service\n #\n service {\n name = \"storage\"\n port = \"http\"\n tags = [ \"storage${NOMAD_ALLOC_INDEX}\" ]\n check {\n name = \"Min.io Server HTTP Check Live\"\n type = \"http\"\n port = \"http\"\n protocol = \"http\"\n method = \"GET\"\n path = \"/minio/health/live\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n check {\n name = \"Min.io Server HTTP Check Ready\"\n type = \"http\"\n port = \"http\"\n protocol = \"http\"\n method = \"GET\"\n path = \"/minio/health/ready\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # https://www.nomadproject.io/docs/job-specification/resources\n #\n resources {\n cpu = 40000\n memory = 40000\n # The network stanza specifies the networking requirements for the task\n # group, including the network mode and port allocations. When scheduling\n # jobs in Nomad they are provisioned across your fleet of machines along\n # with other jobs and services. Because you don't know in advance what host\n # your job will be provisioned on, Nomad will provide your tasks with\n # network configuration when they start up.\n #\n # https://www.nomadproject.io/docs/job-specification/network\n #\n network {\n port \"http\" {\n static = 9000\n }\n }\n }\n }\n }\n}\n", + "id": "68243169c0df15ef6b56803101ed0c744a84545c34df366ee4036052c6292ef3", + "rendered": "job \"prod-minio\" {\n # The \"region\" parameter specifies the region in which to execute the job.\n # If omitted, this inherits the default region name of \"global\".\n # region = \"global\"\n #\n # The \"datacenters\" parameter specifies the list of datacenters which should\n # be considered when placing this task. This must be provided.\n datacenters = \"yul1\"\n\n # The \"type\" parameter controls the type of job, which impacts the scheduler's\n # decision on placement. This configuration is optional and defaults to\n # \"service\". For a full list of job types and their differences, please see\n # the online documentation.\n #\n # https://www.nomadproject.io/docs/jobspec/schedulers\n #\n type = \"service\"\n\n update {\n # The \"max_parallel\" parameter specifies the maximum number of updates to\n # perform in parallel. In this case, this specifies to update a single task\n # at a time.\n max_parallel = 1\n\n health_check = \"checks\"\n\n # The \"min_healthy_time\" parameter specifies the minimum time the allocation\n # must be in the healthy state before it is marked as healthy and unblocks\n # further allocations from being updated.\n min_healthy_time = \"10s\"\n\n # The \"healthy_deadline\" parameter specifies the deadline in which the\n # allocation must be marked as healthy after which the allocation is\n # automatically transitioned to unhealthy. Transitioning to unhealthy will\n # fail the deployment and potentially roll back the job if \"auto_revert\" is\n # set to true.\n healthy_deadline = \"3m\"\n\n # The \"progress_deadline\" parameter specifies the deadline in which an\n # allocation must be marked as healthy. The deadline begins when the first\n # allocation for the deployment is created and is reset whenever an allocation\n # as part of the deployment transitions to a healthy state. If no allocation\n # transitions to the healthy state before the progress deadline, the\n # deployment is marked as failed.\n progress_deadline = \"10m\"\n\n\n # The \"canary\" parameter specifies that changes to the job that would result\n # in destructive updates should create the specified number of canaries\n # without stopping any previous allocations. Once the operator determines the\n # canaries are healthy, they can be promoted which unblocks a rolling update\n # of the remaining allocations at a rate of \"max_parallel\".\n #\n # Further, setting \"canary\" equal to the count of the task group allows\n # blue/green deployments. When the job is updated, a full set of the new\n # version is deployed and upon promotion the old version is stopped.\n canary = 1\n\n # Specifies if the job should auto-promote to the canary version when all\n # canaries become healthy during a deployment. Defaults to false which means\n # canaries must be manually updated with the nomad deployment promote\n # command.\n auto_promote = true\n\n # The \"auto_revert\" parameter specifies if the job should auto-revert to the\n # last stable job on deployment failure. A job is marked as stable if all the\n # allocations as part of its deployment were marked healthy.\n auto_revert = true\n\n }\n\n # All groups in this job should be scheduled on different hosts.\n constraint {\n operator = \"distinct_hosts\"\n value = \"true\"\n }\n\n # The \"group\" stanza defines a series of tasks that should be co-located on\n # the same Nomad client. Any task within a group will be placed on the same\n # client.\n #\n # https://www.nomadproject.io/docs/job-specification/group\n #\n group \"prod-group1-minio\" {\n # The \"count\" parameter specifies the number of the task groups that should\n # be running under this group. This value must be non-negative and defaults\n # to 1.\n count = 4\n\n # https://www.nomadproject.io/docs/job-specification/volume\n \n volume \"prod-volume1-minio\" {\n type = \"host\"\n read_only = false\n source = \"prod-volume-data1-1\"\n }\n \n\n # The restart stanza configures a tasks's behavior on task failure. Restarts\n # happen on the client that is running the task.\n #\n # https://www.nomadproject.io/docs/job-specification/restart\n #\n restart {\n interval = \"30m\"\n attempts = 40\n delay = \"15s\"\n mode = \"delay\"\n }\n\n # The \"task\" stanza creates an individual unit of work, such as a Docker\n # container, web application, or batch processing.\n #\n # https://www.nomadproject.io/docs/job-specification/task.html\n #\n task \"prod-task1-minio\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"docker\"\n\n \n volume_mount {\n volume = \"prod-volume1-minio\"\n destination = \"/data/\"\n read_only = false\n }\n \n\n \n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n image = \"minio/minio:RELEASE.2021-07-27T02-40-15Z\"\n dns_servers = [ \"172.17.0.1\" ]\n network_mode = \"host\"\n command = \"server\"\n args = [ \"http://10.32.8.1{4...7}:9000/data/\" ]\n port_map {\n http = 9000\n }\n privileged = false\n }\n\n # The env stanza configures a list of environment variables to populate\n # the task's environment before starting.\n env {\n\n MINIO_ACCESS_KEY = \"minio\"\n MINIO_SECRET_KEY = \"minio123\"\n\n MINIO_BROWSER=\"off\"\n }\n\n # The service stanza instructs Nomad to register a service with Consul.\n #\n # https://www.nomadproject.io/docs/job-specification/service\n #\n service {\n name = \"storage\"\n port = \"http\"\n tags = [ \"storage${NOMAD_ALLOC_INDEX}\" ]\n check {\n name = \"Min.io Server HTTP Check Live\"\n type = \"http\"\n port = \"http\"\n protocol = \"http\"\n method = \"GET\"\n path = \"/minio/health/live\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n check {\n name = \"Min.io Server HTTP Check Ready\"\n type = \"http\"\n port = \"http\"\n protocol = \"http\"\n method = \"GET\"\n path = \"/minio/health/ready\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # https://www.nomadproject.io/docs/job-specification/resources\n #\n resources {\n cpu = 40000\n memory = 40000\n # The network stanza specifies the networking requirements for the task\n # group, including the network mode and port allocations. When scheduling\n # jobs in Nomad they are provisioned across your fleet of machines along\n # with other jobs and services. Because you don't know in advance what host\n # your job will be provisioned on, Nomad will provide your tasks with\n # network configuration when they start up.\n #\n # https://www.nomadproject.io/docs/job-specification/network\n #\n network {\n port \"http\" {\n static = 9000\n }\n }\n }\n }\n }\n}\n", "template": "job \"${job_name}\" {\n # The \"region\" parameter specifies the region in which to execute the job.\n # If omitted, this inherits the default region name of \"global\".\n # region = \"global\"\n #\n # The \"datacenters\" parameter specifies the list of datacenters which should\n # be considered when placing this task. This must be provided.\n datacenters = \"${datacenters}\"\n\n # The \"type\" parameter controls the type of job, which impacts the scheduler's\n # decision on placement. This configuration is optional and defaults to\n # \"service\". For a full list of job types and their differences, please see\n # the online documentation.\n #\n # https://www.nomadproject.io/docs/jobspec/schedulers\n #\n type = \"service\"\n\n update {\n # The \"max_parallel\" parameter specifies the maximum number of updates to\n # perform in parallel. In this case, this specifies to update a single task\n # at a time.\n max_parallel = 1\n\n health_check = \"checks\"\n\n # The \"min_healthy_time\" parameter specifies the minimum time the allocation\n # must be in the healthy state before it is marked as healthy and unblocks\n # further allocations from being updated.\n min_healthy_time = \"10s\"\n\n # The \"healthy_deadline\" parameter specifies the deadline in which the\n # allocation must be marked as healthy after which the allocation is\n # automatically transitioned to unhealthy. Transitioning to unhealthy will\n # fail the deployment and potentially roll back the job if \"auto_revert\" is\n # set to true.\n healthy_deadline = \"3m\"\n\n # The \"progress_deadline\" parameter specifies the deadline in which an\n # allocation must be marked as healthy. The deadline begins when the first\n # allocation for the deployment is created and is reset whenever an allocation\n # as part of the deployment transitions to a healthy state. If no allocation\n # transitions to the healthy state before the progress deadline, the\n # deployment is marked as failed.\n progress_deadline = \"10m\"\n\n%{ if use_canary }\n # The \"canary\" parameter specifies that changes to the job that would result\n # in destructive updates should create the specified number of canaries\n # without stopping any previous allocations. Once the operator determines the\n # canaries are healthy, they can be promoted which unblocks a rolling update\n # of the remaining allocations at a rate of \"max_parallel\".\n #\n # Further, setting \"canary\" equal to the count of the task group allows\n # blue/green deployments. When the job is updated, a full set of the new\n # version is deployed and upon promotion the old version is stopped.\n canary = 1\n\n # Specifies if the job should auto-promote to the canary version when all\n # canaries become healthy during a deployment. Defaults to false which means\n # canaries must be manually updated with the nomad deployment promote\n # command.\n auto_promote = true\n\n # The \"auto_revert\" parameter specifies if the job should auto-revert to the\n # last stable job on deployment failure. A job is marked as stable if all the\n # allocations as part of its deployment were marked healthy.\n auto_revert = true\n%{ endif }\n }\n\n # All groups in this job should be scheduled on different hosts.\n constraint {\n operator = \"distinct_hosts\"\n value = \"true\"\n }\n\n # The \"group\" stanza defines a series of tasks that should be co-located on\n # the same Nomad client. Any task within a group will be placed on the same\n # client.\n #\n # https://www.nomadproject.io/docs/job-specification/group\n #\n group \"prod-group1-minio\" {\n # The \"count\" parameter specifies the number of the task groups that should\n # be running under this group. This value must be non-negative and defaults\n # to 1.\n count = ${group_count}\n\n # https://www.nomadproject.io/docs/job-specification/volume\n %{ if use_host_volume }\n volume \"prod-volume1-minio\" {\n type = \"host\"\n read_only = false\n source = \"${host_volume}\"\n }\n %{ endif }\n\n # The restart stanza configures a tasks's behavior on task failure. Restarts\n # happen on the client that is running the task.\n #\n # https://www.nomadproject.io/docs/job-specification/restart\n #\n restart {\n interval = \"30m\"\n attempts = 40\n delay = \"15s\"\n mode = \"delay\"\n }\n\n # The \"task\" stanza creates an individual unit of work, such as a Docker\n # container, web application, or batch processing.\n #\n # https://www.nomadproject.io/docs/job-specification/task.html\n #\n task \"prod-task1-minio\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"docker\"\n\n %{ if use_host_volume }\n volume_mount {\n volume = \"prod-volume1-minio\"\n destination = \"${data_dir}\"\n read_only = false\n }\n %{ endif }\n\n %{ if use_vault_provider }\n vault {\n policies = \"${vault_kv_policy_name}\"\n }\n %{ endif }\n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n image = \"${image}\"\n dns_servers = [ \"172.17.0.1\" ]\n network_mode = \"host\"\n command = \"server\"\n args = [ \"${host}:${port}${data_dir}\" ]\n port_map {\n http = ${port}\n }\n privileged = false\n }\n\n # The env stanza configures a list of environment variables to populate\n # the task's environment before starting.\n env {\n%{ if use_vault_provider }\n{{ with secret \"${vault_kv_path}\" }}\n MINIO_ACCESS_KEY = \"{{ .Data.data.${vault_kv_field_access_key} }}\"\n MINIO_SECRET_KEY = \"{{ .Data.data.${vault_kv_field_secret_key} }}\"\n{{ end }}\n%{ else }\n MINIO_ACCESS_KEY = \"${access_key}\"\n MINIO_SECRET_KEY = \"${secret_key}\"\n%{ endif }\n ${ envs }\n }\n\n # The service stanza instructs Nomad to register a service with Consul.\n #\n # https://www.nomadproject.io/docs/job-specification/service\n #\n service {\n name = \"${service_name}\"\n port = \"http\"\n tags = [ \"storage$${NOMAD_ALLOC_INDEX}\" ]\n check {\n name = \"Min.io Server HTTP Check Live\"\n type = \"http\"\n port = \"http\"\n protocol = \"http\"\n method = \"GET\"\n path = \"/minio/health/live\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n check {\n name = \"Min.io Server HTTP Check Ready\"\n type = \"http\"\n port = \"http\"\n protocol = \"http\"\n method = \"GET\"\n path = \"/minio/health/ready\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # https://www.nomadproject.io/docs/job-specification/resources\n #\n resources {\n cpu = ${cpu}\n memory = ${memory}\n # The network stanza specifies the networking requirements for the task\n # group, including the network mode and port allocations. When scheduling\n # jobs in Nomad they are provisioned across your fleet of machines along\n # with other jobs and services. Because you don't know in advance what host\n # your job will be provisioned on, Nomad will provide your tasks with\n # network configuration when they start up.\n #\n # https://www.nomadproject.io/docs/job-specification/network\n #\n network {\n port \"http\" {\n static = ${port}\n }\n }\n }\n }\n }\n}\n", "vars": { "access_key": "minio", @@ -242,7 +242,7 @@ "group_count": "4", "host": "http://10.32.8.1{4...7}", "host_volume": "prod-volume-data1-1", - "image": "minio/minio:RELEASE.2021-07-08T01-15-01Z", + "image": "minio/minio:RELEASE.2021-07-27T02-40-15Z", "job_name": "prod-minio", "memory": "40000", "memory_proxy": "128", @@ -270,27 +270,23 @@ "schema_version": 0, "attributes": { "allocation_ids": [ - "da0b1991-d59e-dfe5-3dec-ec64dd9b8ec2", - "3a53d56a-fb8e-7218-99fe-0798241aea0d", - "59658812-d06d-29bd-e5f3-d35f6ff4def9", - "263d4e38-c44c-26c0-451d-c5b1679f5250", - "b66d7688-6fdb-2f49-f5d5-24719386531f", - "7b3c5ce9-996e-0dc3-3e9e-aced1dd928ca", - "732074da-1082-4cc3-8717-e83421a97739", - "3172e318-19f8-c9d7-17af-7cab03429e6f" + "8e200c5b-97ee-20a0-3383-96af1adaef6a", + "44e1a0f0-5328-eafb-3beb-bfd53af2b618", + "a6695ea0-2563-72ae-1791-a08ef933ff72", + "51126acb-945c-2629-5787-76b85677ddd0" ], "datacenters": [ "yul1" ], - "deployment_id": "2d18d058-a30a-a944-feb9-3e2ed8804600", + "deployment_id": "33d8013c-7c7c-6828-a204-58d9286b61ef", "deployment_status": "successful", "deregister_on_destroy": true, "deregister_on_id_change": true, "detach": false, "id": "prod-minio", - "jobspec": "job \"prod-minio\" {\n # The \"region\" parameter specifies the region in which to execute the job.\n # If omitted, this inherits the default region name of \"global\".\n # region = \"global\"\n #\n # The \"datacenters\" parameter specifies the list of datacenters which should\n # be considered when placing this task. This must be provided.\n datacenters = \"yul1\"\n\n # The \"type\" parameter controls the type of job, which impacts the scheduler's\n # decision on placement. This configuration is optional and defaults to\n # \"service\". For a full list of job types and their differences, please see\n # the online documentation.\n #\n # https://www.nomadproject.io/docs/jobspec/schedulers\n #\n type = \"service\"\n\n update {\n # The \"max_parallel\" parameter specifies the maximum number of updates to\n # perform in parallel. In this case, this specifies to update a single task\n # at a time.\n max_parallel = 1\n\n health_check = \"checks\"\n\n # The \"min_healthy_time\" parameter specifies the minimum time the allocation\n # must be in the healthy state before it is marked as healthy and unblocks\n # further allocations from being updated.\n min_healthy_time = \"10s\"\n\n # The \"healthy_deadline\" parameter specifies the deadline in which the\n # allocation must be marked as healthy after which the allocation is\n # automatically transitioned to unhealthy. Transitioning to unhealthy will\n # fail the deployment and potentially roll back the job if \"auto_revert\" is\n # set to true.\n healthy_deadline = \"3m\"\n\n # The \"progress_deadline\" parameter specifies the deadline in which an\n # allocation must be marked as healthy. The deadline begins when the first\n # allocation for the deployment is created and is reset whenever an allocation\n # as part of the deployment transitions to a healthy state. If no allocation\n # transitions to the healthy state before the progress deadline, the\n # deployment is marked as failed.\n progress_deadline = \"10m\"\n\n\n # The \"canary\" parameter specifies that changes to the job that would result\n # in destructive updates should create the specified number of canaries\n # without stopping any previous allocations. Once the operator determines the\n # canaries are healthy, they can be promoted which unblocks a rolling update\n # of the remaining allocations at a rate of \"max_parallel\".\n #\n # Further, setting \"canary\" equal to the count of the task group allows\n # blue/green deployments. When the job is updated, a full set of the new\n # version is deployed and upon promotion the old version is stopped.\n canary = 1\n\n # Specifies if the job should auto-promote to the canary version when all\n # canaries become healthy during a deployment. Defaults to false which means\n # canaries must be manually updated with the nomad deployment promote\n # command.\n auto_promote = true\n\n # The \"auto_revert\" parameter specifies if the job should auto-revert to the\n # last stable job on deployment failure. A job is marked as stable if all the\n # allocations as part of its deployment were marked healthy.\n auto_revert = true\n\n }\n\n # All groups in this job should be scheduled on different hosts.\n constraint {\n operator = \"distinct_hosts\"\n value = \"true\"\n }\n\n # The \"group\" stanza defines a series of tasks that should be co-located on\n # the same Nomad client. Any task within a group will be placed on the same\n # client.\n #\n # https://www.nomadproject.io/docs/job-specification/group\n #\n group \"prod-group1-minio\" {\n # The \"count\" parameter specifies the number of the task groups that should\n # be running under this group. This value must be non-negative and defaults\n # to 1.\n count = 4\n\n # https://www.nomadproject.io/docs/job-specification/volume\n \n volume \"prod-volume1-minio\" {\n type = \"host\"\n read_only = false\n source = \"prod-volume-data1-1\"\n }\n \n\n # The restart stanza configures a tasks's behavior on task failure. Restarts\n # happen on the client that is running the task.\n #\n # https://www.nomadproject.io/docs/job-specification/restart\n #\n restart {\n interval = \"30m\"\n attempts = 40\n delay = \"15s\"\n mode = \"delay\"\n }\n\n # The \"task\" stanza creates an individual unit of work, such as a Docker\n # container, web application, or batch processing.\n #\n # https://www.nomadproject.io/docs/job-specification/task.html\n #\n task \"prod-task1-minio\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"docker\"\n\n \n volume_mount {\n volume = \"prod-volume1-minio\"\n destination = \"/data/\"\n read_only = false\n }\n \n\n \n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n image = \"minio/minio:RELEASE.2021-07-08T01-15-01Z\"\n dns_servers = [ \"172.17.0.1\" ]\n network_mode = \"host\"\n command = \"server\"\n args = [ \"http://10.32.8.1{4...7}:9000/data/\" ]\n port_map {\n http = 9000\n }\n privileged = false\n }\n\n # The env stanza configures a list of environment variables to populate\n # the task's environment before starting.\n env {\n\n MINIO_ACCESS_KEY = \"minio\"\n MINIO_SECRET_KEY = \"minio123\"\n\n MINIO_BROWSER=\"off\"\n }\n\n # The service stanza instructs Nomad to register a service with Consul.\n #\n # https://www.nomadproject.io/docs/job-specification/service\n #\n service {\n name = \"storage\"\n port = \"http\"\n tags = [ \"storage${NOMAD_ALLOC_INDEX}\" ]\n check {\n name = \"Min.io Server HTTP Check Live\"\n type = \"http\"\n port = \"http\"\n protocol = \"http\"\n method = \"GET\"\n path = \"/minio/health/live\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n check {\n name = \"Min.io Server HTTP Check Ready\"\n type = \"http\"\n port = \"http\"\n protocol = \"http\"\n method = \"GET\"\n path = \"/minio/health/ready\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # https://www.nomadproject.io/docs/job-specification/resources\n #\n resources {\n cpu = 40000\n memory = 40000\n # The network stanza specifies the networking requirements for the task\n # group, including the network mode and port allocations. When scheduling\n # jobs in Nomad they are provisioned across your fleet of machines along\n # with other jobs and services. Because you don't know in advance what host\n # your job will be provisioned on, Nomad will provide your tasks with\n # network configuration when they start up.\n #\n # https://www.nomadproject.io/docs/job-specification/network\n #\n network {\n port \"http\" {\n static = 9000\n }\n }\n }\n }\n }\n}\n", + "jobspec": "job \"prod-minio\" {\n # The \"region\" parameter specifies the region in which to execute the job.\n # If omitted, this inherits the default region name of \"global\".\n # region = \"global\"\n #\n # The \"datacenters\" parameter specifies the list of datacenters which should\n # be considered when placing this task. This must be provided.\n datacenters = \"yul1\"\n\n # The \"type\" parameter controls the type of job, which impacts the scheduler's\n # decision on placement. This configuration is optional and defaults to\n # \"service\". For a full list of job types and their differences, please see\n # the online documentation.\n #\n # https://www.nomadproject.io/docs/jobspec/schedulers\n #\n type = \"service\"\n\n update {\n # The \"max_parallel\" parameter specifies the maximum number of updates to\n # perform in parallel. In this case, this specifies to update a single task\n # at a time.\n max_parallel = 1\n\n health_check = \"checks\"\n\n # The \"min_healthy_time\" parameter specifies the minimum time the allocation\n # must be in the healthy state before it is marked as healthy and unblocks\n # further allocations from being updated.\n min_healthy_time = \"10s\"\n\n # The \"healthy_deadline\" parameter specifies the deadline in which the\n # allocation must be marked as healthy after which the allocation is\n # automatically transitioned to unhealthy. Transitioning to unhealthy will\n # fail the deployment and potentially roll back the job if \"auto_revert\" is\n # set to true.\n healthy_deadline = \"3m\"\n\n # The \"progress_deadline\" parameter specifies the deadline in which an\n # allocation must be marked as healthy. The deadline begins when the first\n # allocation for the deployment is created and is reset whenever an allocation\n # as part of the deployment transitions to a healthy state. If no allocation\n # transitions to the healthy state before the progress deadline, the\n # deployment is marked as failed.\n progress_deadline = \"10m\"\n\n\n # The \"canary\" parameter specifies that changes to the job that would result\n # in destructive updates should create the specified number of canaries\n # without stopping any previous allocations. Once the operator determines the\n # canaries are healthy, they can be promoted which unblocks a rolling update\n # of the remaining allocations at a rate of \"max_parallel\".\n #\n # Further, setting \"canary\" equal to the count of the task group allows\n # blue/green deployments. When the job is updated, a full set of the new\n # version is deployed and upon promotion the old version is stopped.\n canary = 1\n\n # Specifies if the job should auto-promote to the canary version when all\n # canaries become healthy during a deployment. Defaults to false which means\n # canaries must be manually updated with the nomad deployment promote\n # command.\n auto_promote = true\n\n # The \"auto_revert\" parameter specifies if the job should auto-revert to the\n # last stable job on deployment failure. A job is marked as stable if all the\n # allocations as part of its deployment were marked healthy.\n auto_revert = true\n\n }\n\n # All groups in this job should be scheduled on different hosts.\n constraint {\n operator = \"distinct_hosts\"\n value = \"true\"\n }\n\n # The \"group\" stanza defines a series of tasks that should be co-located on\n # the same Nomad client. Any task within a group will be placed on the same\n # client.\n #\n # https://www.nomadproject.io/docs/job-specification/group\n #\n group \"prod-group1-minio\" {\n # The \"count\" parameter specifies the number of the task groups that should\n # be running under this group. This value must be non-negative and defaults\n # to 1.\n count = 4\n\n # https://www.nomadproject.io/docs/job-specification/volume\n \n volume \"prod-volume1-minio\" {\n type = \"host\"\n read_only = false\n source = \"prod-volume-data1-1\"\n }\n \n\n # The restart stanza configures a tasks's behavior on task failure. Restarts\n # happen on the client that is running the task.\n #\n # https://www.nomadproject.io/docs/job-specification/restart\n #\n restart {\n interval = \"30m\"\n attempts = 40\n delay = \"15s\"\n mode = \"delay\"\n }\n\n # The \"task\" stanza creates an individual unit of work, such as a Docker\n # container, web application, or batch processing.\n #\n # https://www.nomadproject.io/docs/job-specification/task.html\n #\n task \"prod-task1-minio\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"docker\"\n\n \n volume_mount {\n volume = \"prod-volume1-minio\"\n destination = \"/data/\"\n read_only = false\n }\n \n\n \n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n image = \"minio/minio:RELEASE.2021-07-27T02-40-15Z\"\n dns_servers = [ \"172.17.0.1\" ]\n network_mode = \"host\"\n command = \"server\"\n args = [ \"http://10.32.8.1{4...7}:9000/data/\" ]\n port_map {\n http = 9000\n }\n privileged = false\n }\n\n # The env stanza configures a list of environment variables to populate\n # the task's environment before starting.\n env {\n\n MINIO_ACCESS_KEY = \"minio\"\n MINIO_SECRET_KEY = \"minio123\"\n\n MINIO_BROWSER=\"off\"\n }\n\n # The service stanza instructs Nomad to register a service with Consul.\n #\n # https://www.nomadproject.io/docs/job-specification/service\n #\n service {\n name = \"storage\"\n port = \"http\"\n tags = [ \"storage${NOMAD_ALLOC_INDEX}\" ]\n check {\n name = \"Min.io Server HTTP Check Live\"\n type = \"http\"\n port = \"http\"\n protocol = \"http\"\n method = \"GET\"\n path = \"/minio/health/live\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n check {\n name = \"Min.io Server HTTP Check Ready\"\n type = \"http\"\n port = \"http\"\n protocol = \"http\"\n method = \"GET\"\n path = \"/minio/health/ready\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # https://www.nomadproject.io/docs/job-specification/resources\n #\n resources {\n cpu = 40000\n memory = 40000\n # The network stanza specifies the networking requirements for the task\n # group, including the network mode and port allocations. When scheduling\n # jobs in Nomad they are provisioned across your fleet of machines along\n # with other jobs and services. Because you don't know in advance what host\n # your job will be provisioned on, Nomad will provide your tasks with\n # network configuration when they start up.\n #\n # https://www.nomadproject.io/docs/job-specification/network\n #\n network {\n port \"http\" {\n static = 9000\n }\n }\n }\n }\n }\n}\n", "json": null, - "modify_index": "8769570", + "modify_index": "8949013", "name": "prod-minio", "namespace": "default", "policy_override": null, @@ -434,9 +430,9 @@ "schema_version": 0, "attributes": { "filename": null, - "id": "113240c48bda39b1664958a0b9fb6058f6e613ae612cc61ff958d1a78c94c46b", - "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-2.24.0.linux-amd64/prometheus\"\n args = [\n \"--config.file=secrets/prometheus.yml\",\n \"--storage.tsdb.path=/data/prometheus/\",\n \"--storage.tsdb.retention.time=15d\"\n ]\n }\n\n # The artifact stanza instructs Nomad to fetch and unpack a remote resource,\n # such as a file, tarball, or binary. Nomad downloads artifacts using the\n # popular go-getter library, which permits downloading artifacts from a\n # variety of locations using a URL as the input source.\n #\n # For more information and examples on the \"artifact\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/artifact\n #\n artifact {\n source = \"https://github.com/prometheus/prometheus/releases/download/v2.24.0/prometheus-2.24.0.linux-amd64.tar.gz\"\n }\n\n # The \"template\" stanza instructs Nomad to manage a template, such as\n # a configuration file or script. This template can optionally pull data\n # from Consul or Vault to populate runtime configuration data.\n #\n # For more information and examples on the \"template\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/template\n #\n template {\n change_mode = \"noop\"\n change_signal = \"SIGINT\"\n destination = \"secrets/alerts.yml\"\n left_delimiter = \"{{{\"\n right_delimiter = \"}}}\"\n data = \u003c\u003cEOH\n---\ngroups:\n- name: \"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: HostHighCpuLoad\n expr: 100 - (avg by(instance) (rate(node_cpu_seconds_total{mode=\"idle\"}[5m])) * 100) \u003e 95\n for: 0m\n labels:\n severity: warning\n annotations:\n summary: \"Host high CPU load (instance {{ $labels.instance }}).\"\n description: \"CPU load is \u003e 95%.\"\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=15d\"\n ]\n }\n\n # The artifact stanza instructs Nomad to fetch and unpack a remote resource,\n # such as a file, tarball, or binary. Nomad downloads artifacts using the\n # popular go-getter library, which permits downloading artifacts from a\n # variety of locations using a URL as the input source.\n #\n # For more information and examples on the \"artifact\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/artifact\n #\n artifact {\n source = \"${url}\"\n }\n\n # The \"template\" stanza instructs Nomad to manage a template, such as\n # a configuration file or script. This template can optionally pull data\n # from Consul or Vault to populate runtime configuration data.\n #\n # For more information and examples on the \"template\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/template\n #\n template {\n change_mode = \"noop\"\n change_signal = \"SIGINT\"\n destination = \"secrets/alerts.yml\"\n left_delimiter = \"{{{\"\n right_delimiter = \"}}}\"\n data = \u003c\u003cEOH\n---\ngroups:\n- name: \"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: HostHighCpuLoad\n expr: 100 - (avg by(instance) (rate(node_cpu_seconds_total{mode=\"idle\"}[5m])) * 100) \u003e 95\n for: 0m\n labels:\n severity: warning\n annotations:\n summary: \"Host high CPU load (instance {{ $labels.instance }}).\"\n description: \"CPU load is \u003e 95%.\"\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": "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}", "vars": { "cpu": "2000", "data_dir": "/data/", @@ -447,11 +443,11 @@ "mem": "8192", "port": "9090", "service_name": "prometheus", - "url": "https://github.com/prometheus/prometheus/releases/download/v2.24.0/prometheus-2.24.0.linux-amd64.tar.gz", + "url": "https://github.com/prometheus/prometheus/releases/download/v2.28.1/prometheus-2.28.1.linux-amd64.tar.gz", "use_canary": "true", "use_host_volume": "true", "use_vault_provider": "false", - "version": "2.24.0" + "version": "2.28.1" } }, "sensitive_attributes": [] @@ -469,23 +465,27 @@ "schema_version": 0, "attributes": { "allocation_ids": [ - "20d22188-d04e-2f7d-57e7-62b79c39156d", - "050b4a00-1192-4a2b-4a06-ca8916d09597", - "dd7ade6e-43c4-cac3-3294-9bd32d6b9764", - "037ac779-c647-2dba-5b64-d11e2243066c" + "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" ], "datacenters": [ "yul1" ], - "deployment_id": "9a4c9dd4-e3b9-33db-26f7-6e1e05962d90", + "deployment_id": "c27f5df9-0819-f33a-fb30-180edcd2ffcd", "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-2.24.0.linux-amd64/prometheus\"\n args = [\n \"--config.file=secrets/prometheus.yml\",\n \"--storage.tsdb.path=/data/prometheus/\",\n \"--storage.tsdb.retention.time=15d\"\n ]\n }\n\n # The artifact stanza instructs Nomad to fetch and unpack a remote resource,\n # such as a file, tarball, or binary. Nomad downloads artifacts using the\n # popular go-getter library, which permits downloading artifacts from a\n # variety of locations using a URL as the input source.\n #\n # For more information and examples on the \"artifact\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/artifact\n #\n artifact {\n source = \"https://github.com/prometheus/prometheus/releases/download/v2.24.0/prometheus-2.24.0.linux-amd64.tar.gz\"\n }\n\n # The \"template\" stanza instructs Nomad to manage a template, such as\n # a configuration file or script. This template can optionally pull data\n # from Consul or Vault to populate runtime configuration data.\n #\n # For more information and examples on the \"template\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/template\n #\n template {\n change_mode = \"noop\"\n change_signal = \"SIGINT\"\n destination = \"secrets/alerts.yml\"\n left_delimiter = \"{{{\"\n right_delimiter = \"}}}\"\n data = \u003c\u003cEOH\n---\ngroups:\n- name: \"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: HostHighCpuLoad\n expr: 100 - (avg by(instance) (rate(node_cpu_seconds_total{mode=\"idle\"}[5m])) * 100) \u003e 95\n for: 0m\n labels:\n severity: warning\n annotations:\n summary: \"Host high CPU load (instance {{ $labels.instance }}).\"\n description: \"CPU load is \u003e 95%.\"\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: [ '10.30.51.28:8500' ]\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}", "json": null, - "modify_index": "7575038", + "modify_index": "8949350", "name": "prod-prometheus", "namespace": "default", "policy_override": null, @@ -569,10 +569,10 @@ "schema_version": 0, "attributes": { "allocation_ids": [ - "7d13dda4-e47f-e2b5-5ebe-e4c2c57f6a66", - "e41391a1-bfbf-f1cf-831d-d87da6da8b94", - "c9753985-b97f-5d58-79f3-843b63411333", - "aa511cae-fa5b-1127-1718-819660c5702b" + "4194fecb-5e83-0b00-09d9-7561ee7d57f4", + "314b725e-3907-d1f5-2538-72c7343f8cda", + "d89ab9c0-4c2c-8430-f7ea-b609fc8285ac", + "055428eb-e662-5e07-14f1-afc32a2a491f" ], "datacenters": [ "yul1" diff --git a/fdio.infra.terraform/1n_nmd/terraform.tfstate.backup b/fdio.infra.terraform/1n_nmd/terraform.tfstate.backup index c58139acf0..e6522a5c42 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": "1.0.0", - "serial": 1167, + "terraform_version": "1.0.2", + "serial": 1176, "lineage": "e4e7f30a-652d-7a31-e31c-5e3a3388c9b9", "outputs": {}, "resources": [ @@ -59,7 +59,7 @@ "datacenters": [ "yul1" ], - "deployment_id": "1cd42f80-d43d-96cf-bce9-c1f77872e48b", + "deployment_id": "4dc972fd-cb2c-51d8-f730-08b5f7554ceb", "deployment_status": "successful", "deregister_on_destroy": true, "deregister_on_id_change": true, @@ -67,7 +67,7 @@ "id": "prod-alertmanager", "jobspec": "job \"prod-alertmanager\" {\n # The \"region\" parameter specifies the region in which to execute the job.\n # If omitted, this inherits the default region name of \"global\".\n # region = \"global\"\n #\n # The \"datacenters\" parameter specifies the list of datacenters which should\n # be considered when placing this task. This must be provided.\n datacenters = \"yul1\"\n\n # The \"type\" parameter controls the type of job, which impacts the scheduler's\n # decision on placement. This configuration is optional and defaults to\n # \"service\". For a full list of job types and their differences, please see\n # the online documentation.\n #\n # For more information, please see the online documentation at:\n #\n # https://www.nomadproject.io/docs/jobspec/schedulers\n #\n type = \"service\"\n\n update {\n # The \"max_parallel\" parameter specifies the maximum number of updates to\n # perform in parallel. In this case, this specifies to update a single task\n # at a time.\n max_parallel = 1\n\n health_check = \"checks\"\n\n # The \"min_healthy_time\" parameter specifies the minimum time the allocation\n # must be in the healthy state before it is marked as healthy and unblocks\n # further allocations from being updated.\n min_healthy_time = \"10s\"\n\n # The \"healthy_deadline\" parameter specifies the deadline in which the\n # allocation must be marked as healthy after which the allocation is\n # automatically transitioned to unhealthy. Transitioning to unhealthy will\n # fail the deployment and potentially roll back the job if \"auto_revert\" is\n # set to true.\n healthy_deadline = \"3m\"\n\n # The \"progress_deadline\" parameter specifies the deadline in which an\n # allocation must be marked as healthy. The deadline begins when the first\n # allocation for the deployment is created and is reset whenever an allocation\n # as part of the deployment transitions to a healthy state. If no allocation\n # transitions to the healthy state before the progress deadline, the\n # deployment is marked as failed.\n progress_deadline = \"10m\"\n\n\n # The \"canary\" parameter specifies that changes to the job that would result\n # in destructive updates should create the specified number of canaries\n # without stopping any previous allocations. Once the operator determines the\n # canaries are healthy, they can be promoted which unblocks a rolling update\n # of the remaining allocations at a rate of \"max_parallel\".\n #\n # Further, setting \"canary\" equal to the count of the task group allows\n # blue/green deployments. When the job is updated, a full set of the new\n # version is deployed and upon promotion the old version is stopped.\n canary = 1\n\n # Specifies if the job should auto-promote to the canary version when all\n # canaries become healthy during a deployment. Defaults to false which means\n # canaries must be manually updated with the nomad deployment promote\n # command.\n auto_promote = true\n\n # The \"auto_revert\" parameter specifies if the job should auto-revert to the\n # last stable job on deployment failure. A job is marked as stable if all the\n # allocations as part of its deployment were marked healthy.\n auto_revert = true\n\n }\n\n # The reschedule stanza specifies the group's rescheduling strategy. If\n # specified at the job level, the configuration will apply to all groups\n # within the job. If the reschedule stanza is present on both the job and the\n # group, they are merged with the group stanza taking the highest precedence\n # and then the job.\n reschedule {\n delay = \"30s\"\n delay_function = \"constant\"\n unlimited = true\n }\n\n # The \"group\" stanza defines a series of tasks that should be co-located on\n # the same Nomad client. Any task within a group will be placed on the same\n # client.\n #\n # For more information and examples on the \"group\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/group\n #\n group \"prod-group1-alertmanager\" {\n # The \"count\" parameter specifies the number of the task groups that should\n # be running under this group. This value must be non-negative and defaults\n # to 1.\n count = 1\n\n # The restart stanza configures a tasks's behavior on task failure. Restarts\n # happen on the client that is running the task.\n #\n # https://www.nomadproject.io/docs/job-specification/restart\n #\n restart {\n interval = \"30m\"\n attempts = 40\n delay = \"15s\"\n mode = \"delay\"\n }\n\n # The constraint allows restricting the set of eligible nodes. Constraints\n # may filter on attributes or client metadata.\n #\n # For more information and examples on the \"volume\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/constraint\n #\n constraint {\n attribute = \"${attr.cpu.arch}\"\n operator = \"!=\"\n value = \"arm64\"\n }\n\n # The \"task\" stanza creates an individual unit of work, such as a Docker\n # container, web application, or batch processing.\n #\n # For more information and examples on the \"task\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/task\n #\n task \"prod-task1-alertmanager\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"exec\"\n\n \n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n command = \"local/alertmanager-0.21.0.linux-amd64/alertmanager\"\n args = [\n \"--config.file=secrets/alertmanager.yml\"\n ]\n }\n\n # The artifact stanza instructs Nomad to fetch and unpack a remote resource,\n # such as a file, tarball, or binary. Nomad downloads artifacts using the\n # popular go-getter library, which permits downloading artifacts from a\n # variety of locations using a URL as the input source.\n #\n # For more information and examples on the \"artifact\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/artifact\n #\n artifact {\n source = \"https://github.com/prometheus/alertmanager/releases/download/v0.21.0/alertmanager-0.21.0.linux-amd64.tar.gz\"\n }\n\n # The \"template\" stanza instructs Nomad to manage a template, such as\n # a configuration file or script. This template can optionally pull data\n # from Consul or Vault to populate runtime configuration data.\n #\n # For more information and examples on the \"template\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/template\n #\n template {\n change_mode = \"noop\"\n change_signal = \"SIGINT\"\n destination = \"secrets/alertmanager.yml\"\n left_delimiter = \"{{{\"\n right_delimiter = \"}}}\"\n data = \u003c\u003cEOH\n# The directory from which notification templates are read.\ntemplates:\n- '/etc/alertmanager/template/*.tmpl'\n\n#tls_config:\n# # CA certificate to validate the server certificate with.\n# ca_file: \u003cfilepath\u003e ]\n#\n# # Certificate and key files for client cert authentication to the server.\n# cert_file: \u003cfilepath\u003e\n# key_file: \u003cfilepath\u003e\n#\n# # ServerName extension to indicate the name of the server.\n# # http://tools.ietf.org/html/rfc4366#section-3.1\n# server_name: \u003cstring\u003e\n#\n# # Disable validation of the server certificate.\n# insecure_skip_verify: true\n\n# The root route on which each incoming alert enters.\nroute:\n receiver: 'default-slack-receiver'\n\n # The labels by which incoming alerts are grouped together. For example,\n # multiple alerts coming in for cluster=A and alertname=LatencyHigh would\n # be batched into a single group.\n #\n # To aggregate by all possible labels use '...' as the sole label name.\n # This effectively disables aggregation entirely, passing through all\n # alerts as-is. This is unlikely to be what you want, unless you have\n # a very low alert volume or your upstream notification system performs\n # its own grouping. Example: group_by: [...]\n group_by: ['alertname']\n\n # When a new group of alerts is created by an incoming alert, wait at\n # least 'group_wait' to send the initial notification.\n # This way ensures that you get multiple alerts for the same group that start\n # firing shortly after another are batched together on the first\n # notification.\n group_wait: 30s\n\n # When the first notification was sent, wait 'group_interval' to send a batch\n # of new alerts that started firing for that group.\n group_interval: 5m\n\n # If an alert has successfully been sent, wait 'repeat_interval' to\n # resend them.\n repeat_interval: 3h\n\n # All the above attributes are inherited by all child routes and can\n # overwritten on each.\n # The child route trees.\n routes:\n - match_re:\n alertname: JenkinsJob.*\n receiver: jenkins-slack-receiver\n routes:\n - match:\n severity: critical\n receiver: 'jenkins-slack-receiver'\n\n - match_re:\n service: .*\n receiver: default-slack-receiver\n routes:\n - match:\n severity: critical\n receiver: 'default-slack-receiver'\n\n# Inhibition rules allow to mute a set of alerts given that another alert is\n# firing.\n# We use this to mute any warning-level notifications if the same alert is\n# already critical.\ninhibit_rules:\n- source_match:\n severity: 'critical'\n target_match:\n severity: 'warning'\n equal: ['alertname', 'instance']\n\nreceivers:\n- name: 'jenkins-slack-receiver'\n slack_configs:\n - api_url: 'TE07RD1V1/B01U1NV9HV3/hKZXJJ74g2JcISq4K3QC1eG9'\n channel: '#fdio-jobs-monitoring'\n send_resolved: true\n icon_url: https://avatars3.githubusercontent.com/u/3380462\n title: |-\n [{{ .Status | toUpper }}{{ if eq .Status \"firing\" }}:{{ .Alerts.Firing | len }}{{ end }}] {{ .CommonLabels.alertname }} for {{ .CommonLabels.job }}\n {{- if gt (len .CommonLabels) (len .GroupLabels) -}}\n {{\" \"}}(\n {{- with .CommonLabels.Remove .GroupLabels.Names }}\n {{- range $index, $label := .SortedPairs -}}\n {{ if $index }}, {{ end }}\n {{- $label.Name }}=\"{{ $label.Value -}}\"\n {{- end }}\n {{- end -}}\n )\n {{- end }}\n text: \u003e-\n {{ range .Alerts -}}\n *Alert:* {{ .Annotations.summary }}{{ if .Labels.severity }} - `{{ .Labels.severity }}`{{ end }}\n\n *Description:* {{ .Annotations.description }}\n\n *Details:*\n {{ range .Labels.SortedPairs }} • *{{ .Name }}:* `{{ .Value }}`\n {{ end }}\n {{ end }}\n\n- name: 'default-slack-receiver'\n slack_configs:\n - api_url: 'TE07RD1V1/B01UUK23B6C/hZTcCu42FUv8d6rtirHtcYIi'\n channel: '#fdio-infra-monitoring'\n send_resolved: true\n icon_url: https://avatars3.githubusercontent.com/u/3380462\n title: |-\n [{{ .Status | toUpper }}{{ if eq .Status \"firing\" }}:{{ .Alerts.Firing | len }}{{ end }}] {{ .CommonLabels.alertname }} for {{ .CommonLabels.job }}\n {{- if gt (len .CommonLabels) (len .GroupLabels) -}}\n {{\" \"}}(\n {{- with .CommonLabels.Remove .GroupLabels.Names }}\n {{- range $index, $label := .SortedPairs -}}\n {{ if $index }}, {{ end }}\n {{- $label.Name }}=\"{{ $label.Value -}}\"\n {{- end }}\n {{- end -}}\n )\n {{- end }}\n text: \u003e-\n {{ range .Alerts -}}\n *Alert:* {{ .Annotations.summary }}{{ if .Labels.severity }} - `{{ .Labels.severity }}`{{ end }}\n\n *Description:* {{ .Annotations.description }}\n\n *Details:*\n {{ range .Labels.SortedPairs }} • *{{ .Name }}:* `{{ .Value }}`\n {{ end }}\n {{ end }}\nEOH\n }\n\n # The service stanza instructs Nomad to register a service with Consul.\n #\n # For more information and examples on the \"task\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/service\n #\n service {\n name = \"alertmanager\"\n port = \"alertmanager\"\n tags = [ \"alertmanager${NOMAD_ALLOC_INDEX}\" ]\n check {\n name = \"Alertmanager Check Live\"\n type = \"http\"\n path = \"/-/healthy\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # For more information and examples on the \"resources\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/resources\n #\n resources {\n cpu = 1000\n memory = 1024\n # The network stanza specifies the networking requirements for the task\n # group, including the network mode and port allocations. When scheduling\n # jobs in Nomad they are provisioned across your fleet of machines along\n # with other jobs and services. Because you don't know in advance what host\n # your job will be provisioned on, Nomad will provide your tasks with\n # network configuration when they start up.\n #\n # For more information and examples on the \"template\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/network\n #\n network {\n port \"alertmanager\" {\n static = 9093\n }\n }\n }\n }\n }\n}", "json": null, - "modify_index": "8219920", + "modify_index": "8259282", "name": "prod-alertmanager", "namespace": "default", "policy_override": null, @@ -197,15 +197,15 @@ "schema_version": 0, "attributes": { "filename": null, - "id": "ca0c95bbe91c4ac393d5cd5bef8efb90fb5f176f266ba233542fd4338b51c6cc", - "rendered": "job \"prod-mc\" {\n # The \"region\" parameter specifies the region in which to execute the job.\n # If omitted, this inherits the default region name of \"global\".\n # region = \"global\"\n #\n # The \"datacenters\" parameter specifies the list of datacenters which should\n # be considered when placing this task. This must be provided.\n datacenters = \"yul1\"\n\n # The \"type\" parameter controls the type of job, which impacts the scheduler's\n # decision on placement. This configuration is optional and defaults to\n # \"service\". For a full list of job types and their differences, please see\n # the online documentation.\n #\n # For more information, please see the online documentation at:\n #\n # https://www.nomadproject.io/docs/jobspec/schedulers.html\n #\n type = \"batch\"\n\n # The \"group\" stanza defines a series of tasks that should be co-located on\n # the same Nomad client. Any task within a group will be placed on the same\n # client.\n #\n # For more information and examples on the \"group\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/group.html\n #\n group \"prod-group1-mc\" {\n task \"prod-task1-create-buckets\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"docker\"\n\n \n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n image = \"minio/mc:RELEASE.2020-12-10T01-26-17Z\"\n entrypoint = [\n \"/bin/sh\",\n \"-c\",\n \"mc config host add LOCALMINIO http://storage.service.consul:9000 $MINIO_ACCESS_KEY $MINIO_SECRET_KEY \u0026\u0026 mc mb -p LOCALMINIO/logs.fd.io LOCALMINIO/docs.fd.io ; mc policy set public LOCALMINIO/logs.fd.io mc policy set public LOCALMINIO/docs.fd.io mc ilm add --expiry-days '180' LOCALMINIO/logs.fd.io mc admin user add LOCALMINIO storage Storage1234 mc admin policy set LOCALMINIO writeonly user=storage\"\n ]\n dns_servers = [ \"${attr.unique.network.ip-address}\" ]\n privileged = false\n }\n\n # The env stanza configures a list of environment variables to populate\n # the task's environment before starting.\n env {\n \n MINIO_ACCESS_KEY = \"minio\"\n MINIO_SECRET_KEY = \"minio123\"\n \n \n }\n }\n }\n}\n", + "id": "e9e956124e6fed4268bec199b9d7fd7aaff506e906b53621c6dc0e3116c40f52", + "rendered": "job \"prod-mc\" {\n # The \"region\" parameter specifies the region in which to execute the job.\n # If omitted, this inherits the default region name of \"global\".\n # region = \"global\"\n #\n # The \"datacenters\" parameter specifies the list of datacenters which should\n # be considered when placing this task. This must be provided.\n datacenters = \"yul1\"\n\n # The \"type\" parameter controls the type of job, which impacts the scheduler's\n # decision on placement. This configuration is optional and defaults to\n # \"service\". For a full list of job types and their differences, please see\n # the online documentation.\n #\n # For more information, please see the online documentation at:\n #\n # https://www.nomadproject.io/docs/jobspec/schedulers.html\n #\n type = \"batch\"\n\n # The \"group\" stanza defines a series of tasks that should be co-located on\n # the same Nomad client. Any task within a group will be placed on the same\n # client.\n #\n # For more information and examples on the \"group\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/group.html\n #\n group \"prod-group1-mc\" {\n task \"prod-task1-create-buckets\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"docker\"\n\n \n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n image = \"minio/mc:RELEASE.2021-07-27T02-40-15Z\"\n entrypoint = [\n \"/bin/sh\",\n \"-c\",\n \"mc config host add LOCALMINIO http://storage.service.consul:9000 $MINIO_ACCESS_KEY $MINIO_SECRET_KEY \u0026\u0026 mc mb -p LOCALMINIO/logs.fd.io LOCALMINIO/docs.fd.io ; mc policy set public LOCALMINIO/logs.fd.io mc policy set public LOCALMINIO/docs.fd.io mc ilm add --expiry-days '180' LOCALMINIO/logs.fd.io mc admin user add LOCALMINIO storage Storage1234 mc admin policy set LOCALMINIO writeonly user=storage\"\n ]\n dns_servers = [ \"${attr.unique.network.ip-address}\" ]\n privileged = false\n }\n\n # The env stanza configures a list of environment variables to populate\n # the task's environment before starting.\n env {\n \n MINIO_ACCESS_KEY = \"minio\"\n MINIO_SECRET_KEY = \"minio123\"\n \n \n }\n }\n }\n}\n", "template": "job \"${job_name}\" {\n # The \"region\" parameter specifies the region in which to execute the job.\n # If omitted, this inherits the default region name of \"global\".\n # region = \"global\"\n #\n # The \"datacenters\" parameter specifies the list of datacenters which should\n # be considered when placing this task. This must be provided.\n datacenters = \"${datacenters}\"\n\n # The \"type\" parameter controls the type of job, which impacts the scheduler's\n # decision on placement. This configuration is optional and defaults to\n # \"service\". For a full list of job types and their differences, please see\n # the online documentation.\n #\n # For more information, please see the online documentation at:\n #\n # https://www.nomadproject.io/docs/jobspec/schedulers.html\n #\n type = \"batch\"\n\n # The \"group\" stanza defines a series of tasks that should be co-located on\n # the same Nomad client. Any task within a group will be placed on the same\n # client.\n #\n # For more information and examples on the \"group\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/group.html\n #\n group \"prod-group1-mc\" {\n task \"prod-task1-create-buckets\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"docker\"\n\n %{ if use_vault_provider }\n vault {\n policies = \"${vault_kv_policy_name}\"\n }\n %{ endif }\n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n image = \"${image}\"\n entrypoint = [\n \"/bin/sh\",\n \"-c\",\n \"${command}\"\n ]\n dns_servers = [ \"$${attr.unique.network.ip-address}\" ]\n privileged = false\n }\n\n # The env stanza configures a list of environment variables to populate\n # the task's environment before starting.\n env {\n %{ if use_vault_provider }\n {{ with secret \"${vault_kv_path}\" }}\n MINIO_ACCESS_KEY = \"{{ .Data.data.${vault_kv_field_access_key} }}\"\n MINIO_SECRET_KEY = \"{{ .Data.data.${vault_kv_field_secret_key} }}\"\n {{ end }}\n %{ else }\n MINIO_ACCESS_KEY = \"${access_key}\"\n MINIO_SECRET_KEY = \"${secret_key}\"\n %{ endif }\n ${ envs }\n }\n }\n }\n}\n", "vars": { "access_key": "minio", "command": "mc config host add LOCALMINIO http://storage.service.consul:9000 $MINIO_ACCESS_KEY $MINIO_SECRET_KEY \u0026\u0026 mc mb -p LOCALMINIO/logs.fd.io LOCALMINIO/docs.fd.io ; mc policy set public LOCALMINIO/logs.fd.io mc policy set public LOCALMINIO/docs.fd.io mc ilm add --expiry-days '180' LOCALMINIO/logs.fd.io mc admin user add LOCALMINIO storage Storage1234 mc admin policy set LOCALMINIO writeonly user=storage", "datacenters": "yul1", "envs": "", - "image": "minio/mc:RELEASE.2020-12-10T01-26-17Z", + "image": "minio/mc:RELEASE.2021-07-27T02-40-15Z", "job_name": "prod-mc", "minio_port": "9000", "minio_service_name": "storage", @@ -229,8 +229,8 @@ "schema_version": 0, "attributes": { "filename": null, - "id": "159eaa53aac72f9e698b899822c1bc37e57a815560e0c075a5ce4222752e71e4", - "rendered": "job \"prod-minio\" {\n # The \"region\" parameter specifies the region in which to execute the job.\n # If omitted, this inherits the default region name of \"global\".\n # region = \"global\"\n #\n # The \"datacenters\" parameter specifies the list of datacenters which should\n # be considered when placing this task. This must be provided.\n datacenters = \"yul1\"\n\n # The \"type\" parameter controls the type of job, which impacts the scheduler's\n # decision on placement. This configuration is optional and defaults to\n # \"service\". For a full list of job types and their differences, please see\n # the online documentation.\n #\n # https://www.nomadproject.io/docs/jobspec/schedulers\n #\n type = \"service\"\n\n update {\n # The \"max_parallel\" parameter specifies the maximum number of updates to\n # perform in parallel. In this case, this specifies to update a single task\n # at a time.\n max_parallel = 1\n\n health_check = \"checks\"\n\n # The \"min_healthy_time\" parameter specifies the minimum time the allocation\n # must be in the healthy state before it is marked as healthy and unblocks\n # further allocations from being updated.\n min_healthy_time = \"10s\"\n\n # The \"healthy_deadline\" parameter specifies the deadline in which the\n # allocation must be marked as healthy after which the allocation is\n # automatically transitioned to unhealthy. Transitioning to unhealthy will\n # fail the deployment and potentially roll back the job if \"auto_revert\" is\n # set to true.\n healthy_deadline = \"3m\"\n\n # The \"progress_deadline\" parameter specifies the deadline in which an\n # allocation must be marked as healthy. The deadline begins when the first\n # allocation for the deployment is created and is reset whenever an allocation\n # as part of the deployment transitions to a healthy state. If no allocation\n # transitions to the healthy state before the progress deadline, the\n # deployment is marked as failed.\n progress_deadline = \"10m\"\n\n\n # The \"canary\" parameter specifies that changes to the job that would result\n # in destructive updates should create the specified number of canaries\n # without stopping any previous allocations. Once the operator determines the\n # canaries are healthy, they can be promoted which unblocks a rolling update\n # of the remaining allocations at a rate of \"max_parallel\".\n #\n # Further, setting \"canary\" equal to the count of the task group allows\n # blue/green deployments. When the job is updated, a full set of the new\n # version is deployed and upon promotion the old version is stopped.\n canary = 1\n\n # Specifies if the job should auto-promote to the canary version when all\n # canaries become healthy during a deployment. Defaults to false which means\n # canaries must be manually updated with the nomad deployment promote\n # command.\n auto_promote = true\n\n # The \"auto_revert\" parameter specifies if the job should auto-revert to the\n # last stable job on deployment failure. A job is marked as stable if all the\n # allocations as part of its deployment were marked healthy.\n auto_revert = true\n\n }\n\n # All groups in this job should be scheduled on different hosts.\n constraint {\n operator = \"distinct_hosts\"\n value = \"true\"\n }\n\n # The \"group\" stanza defines a series of tasks that should be co-located on\n # the same Nomad client. Any task within a group will be placed on the same\n # client.\n #\n # https://www.nomadproject.io/docs/job-specification/group\n #\n group \"prod-group1-minio\" {\n # The \"count\" parameter specifies the number of the task groups that should\n # be running under this group. This value must be non-negative and defaults\n # to 1.\n count = 4\n\n # https://www.nomadproject.io/docs/job-specification/volume\n \n volume \"prod-volume1-minio\" {\n type = \"host\"\n read_only = false\n source = \"prod-volume-data1-1\"\n }\n \n\n # The restart stanza configures a tasks's behavior on task failure. Restarts\n # happen on the client that is running the task.\n #\n # https://www.nomadproject.io/docs/job-specification/restart\n #\n restart {\n interval = \"30m\"\n attempts = 40\n delay = \"15s\"\n mode = \"delay\"\n }\n\n # The \"task\" stanza creates an individual unit of work, such as a Docker\n # container, web application, or batch processing.\n #\n # https://www.nomadproject.io/docs/job-specification/task.html\n #\n task \"prod-task1-minio\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"docker\"\n\n \n volume_mount {\n volume = \"prod-volume1-minio\"\n destination = \"/data/\"\n read_only = false\n }\n \n\n \n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n image = \"minio/minio:RELEASE.2020-12-03T05-49-24Z\"\n dns_servers = [ \"172.17.0.1\" ]\n network_mode = \"host\"\n command = \"server\"\n args = [ \"http://10.32.8.1{4...7}:9000/data/\" ]\n port_map {\n http = 9000\n }\n privileged = false\n }\n\n # The env stanza configures a list of environment variables to populate\n # the task's environment before starting.\n env {\n\n MINIO_ACCESS_KEY = \"minio\"\n MINIO_SECRET_KEY = \"minio123\"\n\n MINIO_BROWSER=\"off\"\n }\n\n # The service stanza instructs Nomad to register a service with Consul.\n #\n # https://www.nomadproject.io/docs/job-specification/service\n #\n service {\n name = \"storage\"\n port = \"http\"\n tags = [ \"storage${NOMAD_ALLOC_INDEX}\" ]\n check {\n name = \"Min.io Server HTTP Check Live\"\n type = \"http\"\n port = \"http\"\n protocol = \"http\"\n method = \"GET\"\n path = \"/minio/health/live\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n check {\n name = \"Min.io Server HTTP Check Ready\"\n type = \"http\"\n port = \"http\"\n protocol = \"http\"\n method = \"GET\"\n path = \"/minio/health/ready\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # https://www.nomadproject.io/docs/job-specification/resources\n #\n resources {\n cpu = 40000\n memory = 40000\n # The network stanza specifies the networking requirements for the task\n # group, including the network mode and port allocations. When scheduling\n # jobs in Nomad they are provisioned across your fleet of machines along\n # with other jobs and services. Because you don't know in advance what host\n # your job will be provisioned on, Nomad will provide your tasks with\n # network configuration when they start up.\n #\n # https://www.nomadproject.io/docs/job-specification/network\n #\n network {\n port \"http\" {\n static = 9000\n }\n }\n }\n }\n }\n}\n", + "id": "68243169c0df15ef6b56803101ed0c744a84545c34df366ee4036052c6292ef3", + "rendered": "job \"prod-minio\" {\n # The \"region\" parameter specifies the region in which to execute the job.\n # If omitted, this inherits the default region name of \"global\".\n # region = \"global\"\n #\n # The \"datacenters\" parameter specifies the list of datacenters which should\n # be considered when placing this task. This must be provided.\n datacenters = \"yul1\"\n\n # The \"type\" parameter controls the type of job, which impacts the scheduler's\n # decision on placement. This configuration is optional and defaults to\n # \"service\". For a full list of job types and their differences, please see\n # the online documentation.\n #\n # https://www.nomadproject.io/docs/jobspec/schedulers\n #\n type = \"service\"\n\n update {\n # The \"max_parallel\" parameter specifies the maximum number of updates to\n # perform in parallel. In this case, this specifies to update a single task\n # at a time.\n max_parallel = 1\n\n health_check = \"checks\"\n\n # The \"min_healthy_time\" parameter specifies the minimum time the allocation\n # must be in the healthy state before it is marked as healthy and unblocks\n # further allocations from being updated.\n min_healthy_time = \"10s\"\n\n # The \"healthy_deadline\" parameter specifies the deadline in which the\n # allocation must be marked as healthy after which the allocation is\n # automatically transitioned to unhealthy. Transitioning to unhealthy will\n # fail the deployment and potentially roll back the job if \"auto_revert\" is\n # set to true.\n healthy_deadline = \"3m\"\n\n # The \"progress_deadline\" parameter specifies the deadline in which an\n # allocation must be marked as healthy. The deadline begins when the first\n # allocation for the deployment is created and is reset whenever an allocation\n # as part of the deployment transitions to a healthy state. If no allocation\n # transitions to the healthy state before the progress deadline, the\n # deployment is marked as failed.\n progress_deadline = \"10m\"\n\n\n # The \"canary\" parameter specifies that changes to the job that would result\n # in destructive updates should create the specified number of canaries\n # without stopping any previous allocations. Once the operator determines the\n # canaries are healthy, they can be promoted which unblocks a rolling update\n # of the remaining allocations at a rate of \"max_parallel\".\n #\n # Further, setting \"canary\" equal to the count of the task group allows\n # blue/green deployments. When the job is updated, a full set of the new\n # version is deployed and upon promotion the old version is stopped.\n canary = 1\n\n # Specifies if the job should auto-promote to the canary version when all\n # canaries become healthy during a deployment. Defaults to false which means\n # canaries must be manually updated with the nomad deployment promote\n # command.\n auto_promote = true\n\n # The \"auto_revert\" parameter specifies if the job should auto-revert to the\n # last stable job on deployment failure. A job is marked as stable if all the\n # allocations as part of its deployment were marked healthy.\n auto_revert = true\n\n }\n\n # All groups in this job should be scheduled on different hosts.\n constraint {\n operator = \"distinct_hosts\"\n value = \"true\"\n }\n\n # The \"group\" stanza defines a series of tasks that should be co-located on\n # the same Nomad client. Any task within a group will be placed on the same\n # client.\n #\n # https://www.nomadproject.io/docs/job-specification/group\n #\n group \"prod-group1-minio\" {\n # The \"count\" parameter specifies the number of the task groups that should\n # be running under this group. This value must be non-negative and defaults\n # to 1.\n count = 4\n\n # https://www.nomadproject.io/docs/job-specification/volume\n \n volume \"prod-volume1-minio\" {\n type = \"host\"\n read_only = false\n source = \"prod-volume-data1-1\"\n }\n \n\n # The restart stanza configures a tasks's behavior on task failure. Restarts\n # happen on the client that is running the task.\n #\n # https://www.nomadproject.io/docs/job-specification/restart\n #\n restart {\n interval = \"30m\"\n attempts = 40\n delay = \"15s\"\n mode = \"delay\"\n }\n\n # The \"task\" stanza creates an individual unit of work, such as a Docker\n # container, web application, or batch processing.\n #\n # https://www.nomadproject.io/docs/job-specification/task.html\n #\n task \"prod-task1-minio\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"docker\"\n\n \n volume_mount {\n volume = \"prod-volume1-minio\"\n destination = \"/data/\"\n read_only = false\n }\n \n\n \n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n image = \"minio/minio:RELEASE.2021-07-27T02-40-15Z\"\n dns_servers = [ \"172.17.0.1\" ]\n network_mode = \"host\"\n command = \"server\"\n args = [ \"http://10.32.8.1{4...7}:9000/data/\" ]\n port_map {\n http = 9000\n }\n privileged = false\n }\n\n # The env stanza configures a list of environment variables to populate\n # the task's environment before starting.\n env {\n\n MINIO_ACCESS_KEY = \"minio\"\n MINIO_SECRET_KEY = \"minio123\"\n\n MINIO_BROWSER=\"off\"\n }\n\n # The service stanza instructs Nomad to register a service with Consul.\n #\n # https://www.nomadproject.io/docs/job-specification/service\n #\n service {\n name = \"storage\"\n port = \"http\"\n tags = [ \"storage${NOMAD_ALLOC_INDEX}\" ]\n check {\n name = \"Min.io Server HTTP Check Live\"\n type = \"http\"\n port = \"http\"\n protocol = \"http\"\n method = \"GET\"\n path = \"/minio/health/live\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n check {\n name = \"Min.io Server HTTP Check Ready\"\n type = \"http\"\n port = \"http\"\n protocol = \"http\"\n method = \"GET\"\n path = \"/minio/health/ready\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # https://www.nomadproject.io/docs/job-specification/resources\n #\n resources {\n cpu = 40000\n memory = 40000\n # The network stanza specifies the networking requirements for the task\n # group, including the network mode and port allocations. When scheduling\n # jobs in Nomad they are provisioned across your fleet of machines along\n # with other jobs and services. Because you don't know in advance what host\n # your job will be provisioned on, Nomad will provide your tasks with\n # network configuration when they start up.\n #\n # https://www.nomadproject.io/docs/job-specification/network\n #\n network {\n port \"http\" {\n static = 9000\n }\n }\n }\n }\n }\n}\n", "template": "job \"${job_name}\" {\n # The \"region\" parameter specifies the region in which to execute the job.\n # If omitted, this inherits the default region name of \"global\".\n # region = \"global\"\n #\n # The \"datacenters\" parameter specifies the list of datacenters which should\n # be considered when placing this task. This must be provided.\n datacenters = \"${datacenters}\"\n\n # The \"type\" parameter controls the type of job, which impacts the scheduler's\n # decision on placement. This configuration is optional and defaults to\n # \"service\". For a full list of job types and their differences, please see\n # the online documentation.\n #\n # https://www.nomadproject.io/docs/jobspec/schedulers\n #\n type = \"service\"\n\n update {\n # The \"max_parallel\" parameter specifies the maximum number of updates to\n # perform in parallel. In this case, this specifies to update a single task\n # at a time.\n max_parallel = 1\n\n health_check = \"checks\"\n\n # The \"min_healthy_time\" parameter specifies the minimum time the allocation\n # must be in the healthy state before it is marked as healthy and unblocks\n # further allocations from being updated.\n min_healthy_time = \"10s\"\n\n # The \"healthy_deadline\" parameter specifies the deadline in which the\n # allocation must be marked as healthy after which the allocation is\n # automatically transitioned to unhealthy. Transitioning to unhealthy will\n # fail the deployment and potentially roll back the job if \"auto_revert\" is\n # set to true.\n healthy_deadline = \"3m\"\n\n # The \"progress_deadline\" parameter specifies the deadline in which an\n # allocation must be marked as healthy. The deadline begins when the first\n # allocation for the deployment is created and is reset whenever an allocation\n # as part of the deployment transitions to a healthy state. If no allocation\n # transitions to the healthy state before the progress deadline, the\n # deployment is marked as failed.\n progress_deadline = \"10m\"\n\n%{ if use_canary }\n # The \"canary\" parameter specifies that changes to the job that would result\n # in destructive updates should create the specified number of canaries\n # without stopping any previous allocations. Once the operator determines the\n # canaries are healthy, they can be promoted which unblocks a rolling update\n # of the remaining allocations at a rate of \"max_parallel\".\n #\n # Further, setting \"canary\" equal to the count of the task group allows\n # blue/green deployments. When the job is updated, a full set of the new\n # version is deployed and upon promotion the old version is stopped.\n canary = 1\n\n # Specifies if the job should auto-promote to the canary version when all\n # canaries become healthy during a deployment. Defaults to false which means\n # canaries must be manually updated with the nomad deployment promote\n # command.\n auto_promote = true\n\n # The \"auto_revert\" parameter specifies if the job should auto-revert to the\n # last stable job on deployment failure. A job is marked as stable if all the\n # allocations as part of its deployment were marked healthy.\n auto_revert = true\n%{ endif }\n }\n\n # All groups in this job should be scheduled on different hosts.\n constraint {\n operator = \"distinct_hosts\"\n value = \"true\"\n }\n\n # The \"group\" stanza defines a series of tasks that should be co-located on\n # the same Nomad client. Any task within a group will be placed on the same\n # client.\n #\n # https://www.nomadproject.io/docs/job-specification/group\n #\n group \"prod-group1-minio\" {\n # The \"count\" parameter specifies the number of the task groups that should\n # be running under this group. This value must be non-negative and defaults\n # to 1.\n count = ${group_count}\n\n # https://www.nomadproject.io/docs/job-specification/volume\n %{ if use_host_volume }\n volume \"prod-volume1-minio\" {\n type = \"host\"\n read_only = false\n source = \"${host_volume}\"\n }\n %{ endif }\n\n # The restart stanza configures a tasks's behavior on task failure. Restarts\n # happen on the client that is running the task.\n #\n # https://www.nomadproject.io/docs/job-specification/restart\n #\n restart {\n interval = \"30m\"\n attempts = 40\n delay = \"15s\"\n mode = \"delay\"\n }\n\n # The \"task\" stanza creates an individual unit of work, such as a Docker\n # container, web application, or batch processing.\n #\n # https://www.nomadproject.io/docs/job-specification/task.html\n #\n task \"prod-task1-minio\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"docker\"\n\n %{ if use_host_volume }\n volume_mount {\n volume = \"prod-volume1-minio\"\n destination = \"${data_dir}\"\n read_only = false\n }\n %{ endif }\n\n %{ if use_vault_provider }\n vault {\n policies = \"${vault_kv_policy_name}\"\n }\n %{ endif }\n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n image = \"${image}\"\n dns_servers = [ \"172.17.0.1\" ]\n network_mode = \"host\"\n command = \"server\"\n args = [ \"${host}:${port}${data_dir}\" ]\n port_map {\n http = ${port}\n }\n privileged = false\n }\n\n # The env stanza configures a list of environment variables to populate\n # the task's environment before starting.\n env {\n%{ if use_vault_provider }\n{{ with secret \"${vault_kv_path}\" }}\n MINIO_ACCESS_KEY = \"{{ .Data.data.${vault_kv_field_access_key} }}\"\n MINIO_SECRET_KEY = \"{{ .Data.data.${vault_kv_field_secret_key} }}\"\n{{ end }}\n%{ else }\n MINIO_ACCESS_KEY = \"${access_key}\"\n MINIO_SECRET_KEY = \"${secret_key}\"\n%{ endif }\n ${ envs }\n }\n\n # The service stanza instructs Nomad to register a service with Consul.\n #\n # https://www.nomadproject.io/docs/job-specification/service\n #\n service {\n name = \"${service_name}\"\n port = \"http\"\n tags = [ \"storage$${NOMAD_ALLOC_INDEX}\" ]\n check {\n name = \"Min.io Server HTTP Check Live\"\n type = \"http\"\n port = \"http\"\n protocol = \"http\"\n method = \"GET\"\n path = \"/minio/health/live\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n check {\n name = \"Min.io Server HTTP Check Ready\"\n type = \"http\"\n port = \"http\"\n protocol = \"http\"\n method = \"GET\"\n path = \"/minio/health/ready\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # https://www.nomadproject.io/docs/job-specification/resources\n #\n resources {\n cpu = ${cpu}\n memory = ${memory}\n # The network stanza specifies the networking requirements for the task\n # group, including the network mode and port allocations. When scheduling\n # jobs in Nomad they are provisioned across your fleet of machines along\n # with other jobs and services. Because you don't know in advance what host\n # your job will be provisioned on, Nomad will provide your tasks with\n # network configuration when they start up.\n #\n # https://www.nomadproject.io/docs/job-specification/network\n #\n network {\n port \"http\" {\n static = ${port}\n }\n }\n }\n }\n }\n}\n", "vars": { "access_key": "minio", @@ -242,7 +242,7 @@ "group_count": "4", "host": "http://10.32.8.1{4...7}", "host_volume": "prod-volume-data1-1", - "image": "minio/minio:RELEASE.2020-12-03T05-49-24Z", + "image": "minio/minio:RELEASE.2021-07-27T02-40-15Z", "job_name": "prod-minio", "memory": "40000", "memory_proxy": "128", @@ -270,22 +270,23 @@ "schema_version": 0, "attributes": { "allocation_ids": [ - "bd315c5e-035d-3a08-698d-d119fb48035f", - "e82e0119-4d2e-89eb-baa3-0ec6bde71661", - "24e462a6-6d55-a109-47bf-4c83ad5596a7" + "8e200c5b-97ee-20a0-3383-96af1adaef6a", + "44e1a0f0-5328-eafb-3beb-bfd53af2b618", + "a6695ea0-2563-72ae-1791-a08ef933ff72", + "51126acb-945c-2629-5787-76b85677ddd0" ], "datacenters": [ "yul1" ], - "deployment_id": "3d2b1511-51ee-f7e8-5e23-36a0e1022776", + "deployment_id": "33d8013c-7c7c-6828-a204-58d9286b61ef", "deployment_status": "successful", "deregister_on_destroy": true, "deregister_on_id_change": true, "detach": false, "id": "prod-minio", - "jobspec": "job \"prod-minio\" {\n # The \"region\" parameter specifies the region in which to execute the job.\n # If omitted, this inherits the default region name of \"global\".\n # region = \"global\"\n #\n # The \"datacenters\" parameter specifies the list of datacenters which should\n # be considered when placing this task. This must be provided.\n datacenters = \"yul1\"\n\n # The \"type\" parameter controls the type of job, which impacts the scheduler's\n # decision on placement. This configuration is optional and defaults to\n # \"service\". For a full list of job types and their differences, please see\n # the online documentation.\n #\n # https://www.nomadproject.io/docs/jobspec/schedulers\n #\n type = \"service\"\n\n update {\n # The \"max_parallel\" parameter specifies the maximum number of updates to\n # perform in parallel. In this case, this specifies to update a single task\n # at a time.\n max_parallel = 1\n\n health_check = \"checks\"\n\n # The \"min_healthy_time\" parameter specifies the minimum time the allocation\n # must be in the healthy state before it is marked as healthy and unblocks\n # further allocations from being updated.\n min_healthy_time = \"10s\"\n\n # The \"healthy_deadline\" parameter specifies the deadline in which the\n # allocation must be marked as healthy after which the allocation is\n # automatically transitioned to unhealthy. Transitioning to unhealthy will\n # fail the deployment and potentially roll back the job if \"auto_revert\" is\n # set to true.\n healthy_deadline = \"3m\"\n\n # The \"progress_deadline\" parameter specifies the deadline in which an\n # allocation must be marked as healthy. The deadline begins when the first\n # allocation for the deployment is created and is reset whenever an allocation\n # as part of the deployment transitions to a healthy state. If no allocation\n # transitions to the healthy state before the progress deadline, the\n # deployment is marked as failed.\n progress_deadline = \"10m\"\n\n\n # The \"canary\" parameter specifies that changes to the job that would result\n # in destructive updates should create the specified number of canaries\n # without stopping any previous allocations. Once the operator determines the\n # canaries are healthy, they can be promoted which unblocks a rolling update\n # of the remaining allocations at a rate of \"max_parallel\".\n #\n # Further, setting \"canary\" equal to the count of the task group allows\n # blue/green deployments. When the job is updated, a full set of the new\n # version is deployed and upon promotion the old version is stopped.\n canary = 1\n\n # Specifies if the job should auto-promote to the canary version when all\n # canaries become healthy during a deployment. Defaults to false which means\n # canaries must be manually updated with the nomad deployment promote\n # command.\n auto_promote = true\n\n # The \"auto_revert\" parameter specifies if the job should auto-revert to the\n # last stable job on deployment failure. A job is marked as stable if all the\n # allocations as part of its deployment were marked healthy.\n auto_revert = true\n\n }\n\n # All groups in this job should be scheduled on different hosts.\n constraint {\n operator = \"distinct_hosts\"\n value = \"true\"\n }\n\n # The \"group\" stanza defines a series of tasks that should be co-located on\n # the same Nomad client. Any task within a group will be placed on the same\n # client.\n #\n # https://www.nomadproject.io/docs/job-specification/group\n #\n group \"prod-group1-minio\" {\n # The \"count\" parameter specifies the number of the task groups that should\n # be running under this group. This value must be non-negative and defaults\n # to 1.\n count = 4\n\n # https://www.nomadproject.io/docs/job-specification/volume\n \n volume \"prod-volume1-minio\" {\n type = \"host\"\n read_only = false\n source = \"prod-volume-data1-1\"\n }\n \n\n # The restart stanza configures a tasks's behavior on task failure. Restarts\n # happen on the client that is running the task.\n #\n # https://www.nomadproject.io/docs/job-specification/restart\n #\n restart {\n interval = \"30m\"\n attempts = 40\n delay = \"15s\"\n mode = \"delay\"\n }\n\n # The \"task\" stanza creates an individual unit of work, such as a Docker\n # container, web application, or batch processing.\n #\n # https://www.nomadproject.io/docs/job-specification/task.html\n #\n task \"prod-task1-minio\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"docker\"\n\n \n volume_mount {\n volume = \"prod-volume1-minio\"\n destination = \"/data/\"\n read_only = false\n }\n \n\n \n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n image = \"minio/minio:RELEASE.2020-12-03T05-49-24Z\"\n dns_servers = [ \"172.17.0.1\" ]\n network_mode = \"host\"\n command = \"server\"\n args = [ \"http://10.32.8.1{4...7}:9000/data/\" ]\n port_map {\n http = 9000\n }\n privileged = false\n }\n\n # The env stanza configures a list of environment variables to populate\n # the task's environment before starting.\n env {\n\n MINIO_ACCESS_KEY = \"minio\"\n MINIO_SECRET_KEY = \"minio123\"\n\n MINIO_BROWSER=\"off\"\n }\n\n # The service stanza instructs Nomad to register a service with Consul.\n #\n # https://www.nomadproject.io/docs/job-specification/service\n #\n service {\n name = \"storage\"\n port = \"http\"\n tags = [ \"storage${NOMAD_ALLOC_INDEX}\" ]\n check {\n name = \"Min.io Server HTTP Check Live\"\n type = \"http\"\n port = \"http\"\n protocol = \"http\"\n method = \"GET\"\n path = \"/minio/health/live\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n check {\n name = \"Min.io Server HTTP Check Ready\"\n type = \"http\"\n port = \"http\"\n protocol = \"http\"\n method = \"GET\"\n path = \"/minio/health/ready\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # https://www.nomadproject.io/docs/job-specification/resources\n #\n resources {\n cpu = 40000\n memory = 40000\n # The network stanza specifies the networking requirements for the task\n # group, including the network mode and port allocations. When scheduling\n # jobs in Nomad they are provisioned across your fleet of machines along\n # with other jobs and services. Because you don't know in advance what host\n # your job will be provisioned on, Nomad will provide your tasks with\n # network configuration when they start up.\n #\n # https://www.nomadproject.io/docs/job-specification/network\n #\n network {\n port \"http\" {\n static = 9000\n }\n }\n }\n }\n }\n}\n", + "jobspec": "job \"prod-minio\" {\n # The \"region\" parameter specifies the region in which to execute the job.\n # If omitted, this inherits the default region name of \"global\".\n # region = \"global\"\n #\n # The \"datacenters\" parameter specifies the list of datacenters which should\n # be considered when placing this task. This must be provided.\n datacenters = \"yul1\"\n\n # The \"type\" parameter controls the type of job, which impacts the scheduler's\n # decision on placement. This configuration is optional and defaults to\n # \"service\". For a full list of job types and their differences, please see\n # the online documentation.\n #\n # https://www.nomadproject.io/docs/jobspec/schedulers\n #\n type = \"service\"\n\n update {\n # The \"max_parallel\" parameter specifies the maximum number of updates to\n # perform in parallel. In this case, this specifies to update a single task\n # at a time.\n max_parallel = 1\n\n health_check = \"checks\"\n\n # The \"min_healthy_time\" parameter specifies the minimum time the allocation\n # must be in the healthy state before it is marked as healthy and unblocks\n # further allocations from being updated.\n min_healthy_time = \"10s\"\n\n # The \"healthy_deadline\" parameter specifies the deadline in which the\n # allocation must be marked as healthy after which the allocation is\n # automatically transitioned to unhealthy. Transitioning to unhealthy will\n # fail the deployment and potentially roll back the job if \"auto_revert\" is\n # set to true.\n healthy_deadline = \"3m\"\n\n # The \"progress_deadline\" parameter specifies the deadline in which an\n # allocation must be marked as healthy. The deadline begins when the first\n # allocation for the deployment is created and is reset whenever an allocation\n # as part of the deployment transitions to a healthy state. If no allocation\n # transitions to the healthy state before the progress deadline, the\n # deployment is marked as failed.\n progress_deadline = \"10m\"\n\n\n # The \"canary\" parameter specifies that changes to the job that would result\n # in destructive updates should create the specified number of canaries\n # without stopping any previous allocations. Once the operator determines the\n # canaries are healthy, they can be promoted which unblocks a rolling update\n # of the remaining allocations at a rate of \"max_parallel\".\n #\n # Further, setting \"canary\" equal to the count of the task group allows\n # blue/green deployments. When the job is updated, a full set of the new\n # version is deployed and upon promotion the old version is stopped.\n canary = 1\n\n # Specifies if the job should auto-promote to the canary version when all\n # canaries become healthy during a deployment. Defaults to false which means\n # canaries must be manually updated with the nomad deployment promote\n # command.\n auto_promote = true\n\n # The \"auto_revert\" parameter specifies if the job should auto-revert to the\n # last stable job on deployment failure. A job is marked as stable if all the\n # allocations as part of its deployment were marked healthy.\n auto_revert = true\n\n }\n\n # All groups in this job should be scheduled on different hosts.\n constraint {\n operator = \"distinct_hosts\"\n value = \"true\"\n }\n\n # The \"group\" stanza defines a series of tasks that should be co-located on\n # the same Nomad client. Any task within a group will be placed on the same\n # client.\n #\n # https://www.nomadproject.io/docs/job-specification/group\n #\n group \"prod-group1-minio\" {\n # The \"count\" parameter specifies the number of the task groups that should\n # be running under this group. This value must be non-negative and defaults\n # to 1.\n count = 4\n\n # https://www.nomadproject.io/docs/job-specification/volume\n \n volume \"prod-volume1-minio\" {\n type = \"host\"\n read_only = false\n source = \"prod-volume-data1-1\"\n }\n \n\n # The restart stanza configures a tasks's behavior on task failure. Restarts\n # happen on the client that is running the task.\n #\n # https://www.nomadproject.io/docs/job-specification/restart\n #\n restart {\n interval = \"30m\"\n attempts = 40\n delay = \"15s\"\n mode = \"delay\"\n }\n\n # The \"task\" stanza creates an individual unit of work, such as a Docker\n # container, web application, or batch processing.\n #\n # https://www.nomadproject.io/docs/job-specification/task.html\n #\n task \"prod-task1-minio\" {\n # The \"driver\" parameter specifies the task driver that should be used to\n # run the task.\n driver = \"docker\"\n\n \n volume_mount {\n volume = \"prod-volume1-minio\"\n destination = \"/data/\"\n read_only = false\n }\n \n\n \n\n # The \"config\" stanza specifies the driver configuration, which is passed\n # directly to the driver to start the task. The details of configurations\n # are specific to each driver, so please see specific driver\n # documentation for more information.\n config {\n image = \"minio/minio:RELEASE.2021-07-27T02-40-15Z\"\n dns_servers = [ \"172.17.0.1\" ]\n network_mode = \"host\"\n command = \"server\"\n args = [ \"http://10.32.8.1{4...7}:9000/data/\" ]\n port_map {\n http = 9000\n }\n privileged = false\n }\n\n # The env stanza configures a list of environment variables to populate\n # the task's environment before starting.\n env {\n\n MINIO_ACCESS_KEY = \"minio\"\n MINIO_SECRET_KEY = \"minio123\"\n\n MINIO_BROWSER=\"off\"\n }\n\n # The service stanza instructs Nomad to register a service with Consul.\n #\n # https://www.nomadproject.io/docs/job-specification/service\n #\n service {\n name = \"storage\"\n port = \"http\"\n tags = [ \"storage${NOMAD_ALLOC_INDEX}\" ]\n check {\n name = \"Min.io Server HTTP Check Live\"\n type = \"http\"\n port = \"http\"\n protocol = \"http\"\n method = \"GET\"\n path = \"/minio/health/live\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n check {\n name = \"Min.io Server HTTP Check Ready\"\n type = \"http\"\n port = \"http\"\n protocol = \"http\"\n method = \"GET\"\n path = \"/minio/health/ready\"\n interval = \"10s\"\n timeout = \"2s\"\n }\n }\n\n # The \"resources\" stanza describes the requirements a task needs to\n # execute. Resource requirements include memory, network, cpu, and more.\n # This ensures the task will execute on a machine that contains enough\n # resource capacity.\n #\n # https://www.nomadproject.io/docs/job-specification/resources\n #\n resources {\n cpu = 40000\n memory = 40000\n # The network stanza specifies the networking requirements for the task\n # group, including the network mode and port allocations. When scheduling\n # jobs in Nomad they are provisioned across your fleet of machines along\n # with other jobs and services. Because you don't know in advance what host\n # your job will be provisioned on, Nomad will provide your tasks with\n # network configuration when they start up.\n #\n # https://www.nomadproject.io/docs/job-specification/network\n #\n network {\n port \"http\" {\n static = 9000\n }\n }\n }\n }\n }\n}\n", "json": null, - "modify_index": "7541139", + "modify_index": "8949013", "name": "prod-minio", "namespace": "default", "policy_override": null, @@ -366,8 +367,7 @@ "schema_version": 0, "attributes": { "allocation_ids": [ - "0cb0b594-09c2-bad6-fca4-0fbc2479ef3e", - "99dab0de-0e97-4ad8-56eb-ffdd062ef656" + "0cb0b594-09c2-bad6-fca4-0fbc2479ef3e" ], "datacenters": [ "yul1" @@ -430,9 +430,9 @@ "schema_version": 0, "attributes": { "filename": null, - "id": "113240c48bda39b1664958a0b9fb6058f6e613ae612cc61ff958d1a78c94c46b", - "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-2.24.0.linux-amd64/prometheus\"\n args = [\n \"--config.file=secrets/prometheus.yml\",\n \"--storage.tsdb.path=/data/prometheus/\",\n \"--storage.tsdb.retention.time=15d\"\n ]\n }\n\n # The artifact stanza instructs Nomad to fetch and unpack a remote resource,\n # such as a file, tarball, or binary. Nomad downloads artifacts using the\n # popular go-getter library, which permits downloading artifacts from a\n # variety of locations using a URL as the input source.\n #\n # For more information and examples on the \"artifact\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/artifact\n #\n artifact {\n source = \"https://github.com/prometheus/prometheus/releases/download/v2.24.0/prometheus-2.24.0.linux-amd64.tar.gz\"\n }\n\n # The \"template\" stanza instructs Nomad to manage a template, such as\n # a configuration file or script. This template can optionally pull data\n # from Consul or Vault to populate runtime configuration data.\n #\n # For more information and examples on the \"template\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/template\n #\n template {\n change_mode = \"noop\"\n change_signal = \"SIGINT\"\n destination = \"secrets/alerts.yml\"\n left_delimiter = \"{{{\"\n right_delimiter = \"}}}\"\n data = \u003c\u003cEOH\n---\ngroups:\n- name: \"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: HostHighCpuLoad\n expr: 100 - (avg by(instance) (rate(node_cpu_seconds_total{mode=\"idle\"}[5m])) * 100) \u003e 95\n for: 0m\n labels:\n severity: warning\n annotations:\n summary: \"Host high CPU load (instance {{ $labels.instance }}).\"\n description: \"CPU load is \u003e 95%.\"\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=15d\"\n ]\n }\n\n # The artifact stanza instructs Nomad to fetch and unpack a remote resource,\n # such as a file, tarball, or binary. Nomad downloads artifacts using the\n # popular go-getter library, which permits downloading artifacts from a\n # variety of locations using a URL as the input source.\n #\n # For more information and examples on the \"artifact\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/artifact\n #\n artifact {\n source = \"${url}\"\n }\n\n # The \"template\" stanza instructs Nomad to manage a template, such as\n # a configuration file or script. This template can optionally pull data\n # from Consul or Vault to populate runtime configuration data.\n #\n # For more information and examples on the \"template\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/template\n #\n template {\n change_mode = \"noop\"\n change_signal = \"SIGINT\"\n destination = \"secrets/alerts.yml\"\n left_delimiter = \"{{{\"\n right_delimiter = \"}}}\"\n data = \u003c\u003cEOH\n---\ngroups:\n- name: \"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: HostHighCpuLoad\n expr: 100 - (avg by(instance) (rate(node_cpu_seconds_total{mode=\"idle\"}[5m])) * 100) \u003e 95\n for: 0m\n labels:\n severity: warning\n annotations:\n summary: \"Host high CPU load (instance {{ $labels.instance }}).\"\n description: \"CPU load is \u003e 95%.\"\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": "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}", "vars": { "cpu": "2000", "data_dir": "/data/", @@ -443,11 +443,11 @@ "mem": "8192", "port": "9090", "service_name": "prometheus", - "url": "https://github.com/prometheus/prometheus/releases/download/v2.24.0/prometheus-2.24.0.linux-amd64.tar.gz", + "url": "https://github.com/prometheus/prometheus/releases/download/v2.28.1/prometheus-2.28.1.linux-amd64.tar.gz", "use_canary": "true", "use_host_volume": "true", "use_vault_provider": "false", - "version": "2.24.0" + "version": "2.28.1" } }, "sensitive_attributes": [] @@ -465,22 +465,27 @@ "schema_version": 0, "attributes": { "allocation_ids": [ - "dd7ade6e-43c4-cac3-3294-9bd32d6b9764", - "d4ad3ff3-7b2d-b257-e24e-93955addefad", - "037ac779-c647-2dba-5b64-d11e2243066c" + "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" ], "datacenters": [ "yul1" ], - "deployment_id": "9a4c9dd4-e3b9-33db-26f7-6e1e05962d90", + "deployment_id": "1526c7d4-16b3-45d7-4eec-a436cc272c7d", "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-2.24.0.linux-amd64/prometheus\"\n args = [\n \"--config.file=secrets/prometheus.yml\",\n \"--storage.tsdb.path=/data/prometheus/\",\n \"--storage.tsdb.retention.time=15d\"\n ]\n }\n\n # The artifact stanza instructs Nomad to fetch and unpack a remote resource,\n # such as a file, tarball, or binary. Nomad downloads artifacts using the\n # popular go-getter library, which permits downloading artifacts from a\n # variety of locations using a URL as the input source.\n #\n # For more information and examples on the \"artifact\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/artifact\n #\n artifact {\n source = \"https://github.com/prometheus/prometheus/releases/download/v2.24.0/prometheus-2.24.0.linux-amd64.tar.gz\"\n }\n\n # The \"template\" stanza instructs Nomad to manage a template, such as\n # a configuration file or script. This template can optionally pull data\n # from Consul or Vault to populate runtime configuration data.\n #\n # For more information and examples on the \"template\" stanza, please see\n # the online documentation at:\n #\n # https://www.nomadproject.io/docs/job-specification/template\n #\n template {\n change_mode = \"noop\"\n change_signal = \"SIGINT\"\n destination = \"secrets/alerts.yml\"\n left_delimiter = \"{{{\"\n right_delimiter = \"}}}\"\n data = \u003c\u003cEOH\n---\ngroups:\n- name: \"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: HostHighCpuLoad\n expr: 100 - (avg by(instance) (rate(node_cpu_seconds_total{mode=\"idle\"}[5m])) * 100) \u003e 95\n for: 0m\n labels:\n severity: warning\n annotations:\n summary: \"Host high CPU load (instance {{ $labels.instance }}).\"\n description: \"CPU load is \u003e 95%.\"\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: [ '10.30.51.28:8500' ]\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}", "json": null, - "modify_index": "7575038", + "modify_index": "8949256", "name": "prod-prometheus", "namespace": "default", "policy_override": null, @@ -564,10 +569,10 @@ "schema_version": 0, "attributes": { "allocation_ids": [ - "516e389c-e3ce-92ed-217d-68fceb56f61e", - "93db39cc-26d0-ef8a-02af-f10d0e7d8db0", - "a8ee42a1-ff17-8a57-6276-75dc9498653e", - "a497e3ee-2d8b-2750-620e-223d23114ba0" + "4194fecb-5e83-0b00-09d9-7561ee7d57f4", + "314b725e-3907-d1f5-2538-72c7343f8cda", + "d89ab9c0-4c2c-8430-f7ea-b609fc8285ac", + "055428eb-e662-5e07-14f1-afc32a2a491f" ], "datacenters": [ "yul1" -- cgit 1.2.3-korg