Infra: Minor terraform cleanup

Signed-off-by: pmikus <pmikus@cisco.com>
Change-Id: I1f6c9b2f9e3ac607fac76b12100992d901820e38

14 files changed, 154 insertions, 140 deletions

diff --git a/fdio.infra.terraform/1n_nmd/alertmanager/conf/nomad/alertmanager.hcl b/fdio.infra.terraform/1n_nmd/alertmanager/conf/nomad/alertmanager.hcl
index 6b0d669d0e..ab92761ac2 100644
--- a/fdio.infra.terraform/1n_nmd/alertmanager/conf/nomad/alertmanager.hcl
+++ b/fdio.infra.terraform/1n_nmd/alertmanager/conf/nomad/alertmanager.hcl
@@ -123,6 +123,11 @@ job "${job_name}" {
       value           = "arm64"
     }
 
+    constraint {
+      attribute      = "$${node.class}"
+      value          = "builder"
+    }
+
     # The "task" stanza creates an individual unit of work, such as a Docker
     # container, web application, or batch processing.
     #
diff --git a/fdio.infra.terraform/1n_nmd/alertmanager/versions.tf b/fdio.infra.terraform/1n_nmd/alertmanager/providers.tf
index 960bd4bba6..1399201d21 100644
--- a/fdio.infra.terraform/1n_nmd/alertmanager/versions.tf
+++ b/fdio.infra.terraform/1n_nmd/alertmanager/providers.tf
@@ -9,5 +9,5 @@ terraform {
       version = "~> 2.1.2"
     }
   }
-  required_version = ">= 0.13"
+  required_version = ">= 1.0.3"
 }
diff --git a/fdio.infra.terraform/1n_nmd/grafana/conf/nomad/grafana.hcl b/fdio.infra.terraform/1n_nmd/grafana/conf/nomad/grafana.hcl
index a759abc4f7..0faace1b62 100644
--- a/fdio.infra.terraform/1n_nmd/grafana/conf/nomad/grafana.hcl
+++ b/fdio.infra.terraform/1n_nmd/grafana/conf/nomad/grafana.hcl
@@ -123,6 +123,11 @@ job "${job_name}" {
       value           = "arm64"
     }
 
+    constraint {
+      attribute      = "$${node.class}"
+      value          = "builder"
+    }
+
     # The "task" stanza creates an individual unit of work, such as a Docker
     # container, web application, or batch processing.
     #
@@ -148,7 +153,6 @@ job "${job_name}" {
           "secrets/dashboards.yml:/etc/grafana/provisioning/dashboards/dashboards.yml",
           "secrets/grafana.ini:/etc/grafana/grafana.ini",
           "secrets/node_exporter.json:/etc/grafana/provisioning/dashboards/node_exporter.json",
-          "secrets/docker_cadvisor.json:/etc/grafana/provisioning/dashboards/docker_cadvisor.json",
           "secrets/nomad.json:/etc/grafana/provisioning/dashboards/nomad.json",
           "secrets/consul.json:/etc/grafana/provisioning/dashboards/consul.json",
           "secrets/prometheus.json:/etc/grafana/provisioning/dashboards/prometheus.json",
@@ -164,12 +168,6 @@ job "${job_name}" {
       }
 
       artifact {
-        # Docker cAdvisor
-        source        = "https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/docker_cadvisor.json"
-        destination   = "secrets/"
-      }
-
-      artifact {
         # Nomad
         source        = "https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/nomad.json"
         destination   = "secrets/"
diff --git a/fdio.infra.terraform/1n_nmd/grafana/versions.tf b/fdio.infra.terraform/1n_nmd/grafana/providers.tf
index 960bd4bba6..1399201d21 100644
--- a/fdio.infra.terraform/1n_nmd/grafana/versions.tf
+++ b/fdio.infra.terraform/1n_nmd/grafana/providers.tf
@@ -9,5 +9,5 @@ terraform {
       version = "~> 2.1.2"
     }
   }
-  required_version = ">= 0.13"
+  required_version = ">= 1.0.3"
 }
diff --git a/fdio.infra.terraform/1n_nmd/minio/versions.tf b/fdio.infra.terraform/1n_nmd/minio/providers.tf
index 960bd4bba6..1399201d21 100644
--- a/fdio.infra.terraform/1n_nmd/minio/versions.tf
+++ b/fdio.infra.terraform/1n_nmd/minio/providers.tf
@@ -9,5 +9,5 @@ terraform {
       version = "~> 2.1.2"
     }
   }
-  required_version = ">= 0.13"
+  required_version = ">= 1.0.3"
 }
diff --git a/fdio.infra.terraform/1n_nmd/nginx/conf/nomad/nginx.hcl b/fdio.infra.terraform/1n_nmd/nginx/conf/nomad/nginx.hcl
index 1382060ba6..3bbbe5309f 100644
--- a/fdio.infra.terraform/1n_nmd/nginx/conf/nomad/nginx.hcl
+++ b/fdio.infra.terraform/1n_nmd/nginx/conf/nomad/nginx.hcl
@@ -85,14 +85,14 @@ job "${job_name}" {
     # The "count" parameter specifies the number of the task groups that should
     # be running under this group. This value must be non-negative and defaults
     # to 1.
-    count = 1
+    count             = 1
 
     # https://www.nomadproject.io/docs/job-specification/volume
     %{ if use_host_volume }
     volume "prod-volume1-nginx" {
-      type      = "host"
-      read_only = false
-      source    = "${host_volume}"
+      type            = "host"
+      read_only       = false
+      source          = "${host_volume}"
     }
     %{ endif }
 
@@ -102,10 +102,29 @@ job "${job_name}" {
     # https://www.nomadproject.io/docs/job-specification/restart
     #
     restart {
-      interval  = "30m"
-      attempts  = 40
-      delay     = "15s"
-      mode      = "delay"
+      interval        = "30m"
+      attempts        = 40
+      delay           = "15s"
+      mode            = "delay"
+    }
+
+    # The constraint allows restricting the set of eligible nodes. Constraints
+    # may filter on attributes or client metadata.
+    #
+    # For more information and examples on the "volume" stanza, please see
+    # the online documentation at:
+    #
+    #     https://www.nomadproject.io/docs/job-specification/constraint
+    #
+    constraint {
+      attribute       = "$${attr.cpu.arch}"
+      operator        = "!="
+      value           = "arm64"
+    }
+
+    constraint {
+      attribute      = "$${node.class}"
+      value          = "builder"
     }
 
     # The "task" stanza creates an individual unit of work, such as a Docker
@@ -119,26 +138,23 @@ job "${job_name}" {
     task "prod-task1-nginx" {
       # The "driver" parameter specifies the task driver that should be used to
       # run the task.
-      driver = "docker"
+      driver          = "docker"
 
       # The "config" stanza specifies the driver configuration, which is passed
       # directly to the driver to start the task. The details of configurations
       # are specific to each driver, so please see specific driver
       # documentation for more information.
       config {
-        image        = "nginx:stable"
+        image         = "nginx:stable"
         port_map {
-          https      = 443
+          https       = 443
         }
-        privileged   = false
-        volumes      = [
-          "/etc/ssl/certs/docs.nginx.service.consul.crt:/etc/ssl/certs/docs.nginx.service.consul.crt",
-          "/etc/ssl/private/docs.nginx.service.consul.key:/etc/ssl/private/docs.nginx.service.consul.key",
+        privileged    = false
+        volumes       = [
           "/etc/ssl/certs/logs.nginx.service.consul.crt:/etc/ssl/certs/logs.nginx.service.consul.crt",
           "/etc/ssl/private/logs.nginx.service.consul.key:/etc/ssl/private/logs.nginx.service.consul.key",
           "custom/upstream.conf:/etc/nginx/conf.d/upstream.conf",
-          "custom/logs.conf:/etc/nginx/conf.d/logs.conf",
-          "custom/docs.conf:/etc/nginx/conf.d/docs.conf"
+          "custom/server_logs.conf:/etc/nginx/conf.d/server_logs.conf"
         ]
       }
 
@@ -166,14 +182,30 @@ job "${job_name}" {
           server {
             listen 443 ssl default_server;
             server_name logs.nginx.service.consul;
-            keepalive_timeout 70;
-            ssl_session_cache shared:SSL:10m;
-            ssl_session_timeout 10m;
+
+            ssl_certificate /etc/ssl/certs/logs.nginx.service.consul.crt;
+            ssl_certificate_key /etc/ssl/private/logs.nginx.service.consul.key;
             ssl_protocols TLSv1.2;
             ssl_prefer_server_ciphers on;
             ssl_ciphers "ECDHE-ECDSA-AES256-GCM-SHA384:ECDHE-RSA-AES256-GCM-SHA384:ECDHE-ECDSA-CHACHA20-POLY1305:ECDHE-RSA-CHACHA20-POLY1305:ECDHE-ECDSA-AES256-SHA384:ECDHE-RSA-AES256-SHA384";
-            ssl_certificate /etc/ssl/certs/logs.nginx.service.consul.crt;
-            ssl_certificate_key /etc/ssl/private/logs.nginx.service.consul.key;
+            ssl_session_timeout 10m;
+            ssl_session_cache shared:SSL:10m;
+            ssl_session_tickets off;
+            ssl_stapling on;
+            ssl_stapling_verify on;
+
+            fastcgi_hide_header X-Powered-By;
+
+            client_max_body_size 0;
+            client_header_timeout 60;
+            client_body_timeout 86400;
+            fastcgi_read_timeout 86400;
+            proxy_connect_timeout 60;
+            proxy_read_timeout 86400;
+            proxy_send_timeout 86400;
+            send_timeout 86400;
+
+            keepalive_timeout 70;
             location / {
               chunked_transfer_encoding off;
               proxy_connect_timeout 300;
@@ -220,32 +252,6 @@ job "${job_name}" {
         EOH
         destination = "custom/logs.conf"
       }
-      template {
-        data = <<EOH
-          server {
-            listen 443 ssl;
-            server_name docs.nginx.service.consul;
-            keepalive_timeout 70;
-            ssl_session_cache shared:SSL:10m;
-            ssl_session_timeout 10m;
-            ssl_protocols TLSv1.2;
-            ssl_prefer_server_ciphers on;
-            ssl_ciphers "ECDHE-ECDSA-AES256-GCM-SHA384:ECDHE-RSA-AES256-GCM-SHA384:ECDHE-ECDSA-CHACHA20-POLY1305:ECDHE-RSA-CHACHA20-POLY1305:ECDHE-ECDSA-AES256-SHA384:ECDHE-RSA-AES256-SHA384";
-            ssl_certificate /etc/ssl/certs/docs.nginx.service.consul.crt;
-            ssl_certificate_key /etc/ssl/private/docs.nginx.service.consul.key;
-            location / {
-              chunked_transfer_encoding off;
-              proxy_connect_timeout 300;
-              proxy_http_version 1.1;
-              proxy_set_header Host $host:$server_port;
-              proxy_set_header Connection "";
-              proxy_pass http://storage/docs.fd.io/;
-              server_name_in_redirect off;
-            }
-          }
-        EOH
-        destination = "custom/docs.conf"
-      }
 
       # The service stanza instructs Nomad to register a service with Consul.
       #
@@ -257,7 +263,7 @@ job "${job_name}" {
       service {
         name       = "nginx"
         port       = "https"
-        tags       = [ "docs", "logs" ]
+        tags       = [ "logs" ]
       }
 
       # The "resources" stanza describes the requirements a task needs to
diff --git a/fdio.infra.terraform/1n_nmd/nginx/versions.tf b/fdio.infra.terraform/1n_nmd/nginx/providers.tf
index 960bd4bba6..1399201d21 100644
--- a/fdio.infra.terraform/1n_nmd/nginx/versions.tf
+++ b/fdio.infra.terraform/1n_nmd/nginx/providers.tf
@@ -9,5 +9,5 @@ terraform {
       version = "~> 2.1.2"
     }
   }
-  required_version = ">= 0.13"
+  required_version = ">= 1.0.3"
 }
diff --git a/fdio.infra.terraform/1n_nmd/prometheus/conf/nomad/prometheus.hcl b/fdio.infra.terraform/1n_nmd/prometheus/conf/nomad/prometheus.hcl
index 4451d72f7a..368a361184 100644
--- a/fdio.infra.terraform/1n_nmd/prometheus/conf/nomad/prometheus.hcl
+++ b/fdio.infra.terraform/1n_nmd/prometheus/conf/nomad/prometheus.hcl
@@ -139,6 +139,11 @@ job "${job_name}" {
       value             = "arm64"
     }
 
+    constraint {
+      attribute      = "$${node.class}"
+      value          = "builder"
+    }
+
     # The "task" stanza creates an individual unit of work, such as a Docker
     # container, web application, or batch processing.
     #
diff --git a/fdio.infra.terraform/1n_nmd/prometheus/providers.tf b/fdio.infra.terraform/1n_nmd/prometheus/providers.tf
new file mode 100644
index 0000000000..1399201d21
--- /dev/null
+++ b/fdio.infra.terraform/1n_nmd/prometheus/providers.tf
@@ -0,0 +1,13 @@
+terraform {
+  required_providers {
+    nomad = {
+      source  = "hashicorp/nomad"
+      version = "~> 1.4.9"
+    }
+    template = {
+      source  = "hashicorp/template"
+      version = "~> 2.1.2"
+    }
+  }
+  required_version = ">= 1.0.3"
+}
diff --git a/fdio.infra.terraform/1n_nmd/prometheus/versions.tf b/fdio.infra.terraform/1n_nmd/prometheus/versions.tf
deleted file mode 100644
index 960bd4bba6..0000000000
--- a/fdio.infra.terraform/1n_nmd/prometheus/versions.tf
+++ /dev/null
@@ -1,13 +0,0 @@
-terraform {
-  required_providers {
-    nomad = {
-      source  = "hashicorp/nomad"
-      version = "~> 1.4.9"
-    }
-    template = {
-      source  = "hashicorp/template"
-      version = "~> 2.1.2"
-    }
-  }
-  required_version = ">= 0.13"
-}
diff --git a/fdio.infra.terraform/1n_nmd/terraform.tfstate b/fdio.infra.terraform/1n_nmd/terraform.tfstate
index 92b1b86c5f..701b8a34ae 100644
--- a/fdio.infra.terraform/1n_nmd/terraform.tfstate
+++ b/fdio.infra.terraform/1n_nmd/terraform.tfstate
@@ -1,7 +1,7 @@
 {
   "version": 4,
-  "terraform_version": "1.0.2",
-  "serial": 1187,
+  "terraform_version": "1.0.4",
+  "serial": 1192,
   "lineage": "e4e7f30a-652d-7a31-e31c-5e3a3388c9b9",
   "outputs": {},
   "resources": [
@@ -16,9 +16,9 @@
           "schema_version": 0,
           "attributes": {
             "filename": null,
-            "id": "7e96dc4e316a25b07430e5ffc2ecdb94ae41f06770ba8667ae4d5f77ef25c6f7",
-            "rendered": "job \"prod-alertmanager\" {\n  # The \"region\" parameter specifies the region in which to execute the job.\n  # If omitted, this inherits the default region name of \"global\".\n  # region = \"global\"\n  #\n  # The \"datacenters\" parameter specifies the list of datacenters which should\n  # be considered when placing this task. This must be provided.\n  datacenters         = \"yul1\"\n\n  # The \"type\" parameter controls the type of job, which impacts the scheduler's\n  # decision on placement. This configuration is optional and defaults to\n  # \"service\". For a full list of job types and their differences, please see\n  # the online documentation.\n  #\n  # For more information, please see the online documentation at:\n  #\n  #     https://www.nomadproject.io/docs/jobspec/schedulers\n  #\n  type                = \"service\"\n\n  update {\n    # The \"max_parallel\" parameter specifies the maximum number of updates to\n    # perform in parallel. In this case, this specifies to update a single task\n    # at a time.\n    max_parallel      = 1\n\n    health_check      = \"checks\"\n\n    # The \"min_healthy_time\" parameter specifies the minimum time the allocation\n    # must be in the healthy state before it is marked as healthy and unblocks\n    # further allocations from being updated.\n    min_healthy_time  = \"10s\"\n\n    # The \"healthy_deadline\" parameter specifies the deadline in which the\n    # allocation must be marked as healthy after which the allocation is\n    # automatically transitioned to unhealthy. Transitioning to unhealthy will\n    # fail the deployment and potentially roll back the job if \"auto_revert\" is\n    # set to true.\n    healthy_deadline  = \"3m\"\n\n    # The \"progress_deadline\" parameter specifies the deadline in which an\n    # allocation must be marked as healthy. The deadline begins when the first\n    # allocation for the deployment is created and is reset whenever an allocation\n    # as part of the deployment transitions to a healthy state. If no allocation\n    # transitions to the healthy state before the progress deadline, the\n    # deployment is marked as failed.\n    progress_deadline = \"10m\"\n\n\n    # The \"canary\" parameter specifies that changes to the job that would result\n    # in destructive updates should create the specified number of canaries\n    # without stopping any previous allocations. Once the operator determines the\n    # canaries are healthy, they can be promoted which unblocks a rolling update\n    # of the remaining allocations at a rate of \"max_parallel\".\n    #\n    # Further, setting \"canary\" equal to the count of the task group allows\n    # blue/green deployments. When the job is updated, a full set of the new\n    # version is deployed and upon promotion the old version is stopped.\n    canary            = 1\n\n    # Specifies if the job should auto-promote to the canary version when all\n    # canaries become healthy during a deployment. Defaults to false which means\n    # canaries must be manually updated with the nomad deployment promote\n    # command.\n    auto_promote      = true\n\n    # The \"auto_revert\" parameter specifies if the job should auto-revert to the\n    # last stable job on deployment failure. A job is marked as stable if all the\n    # allocations as part of its deployment were marked healthy.\n    auto_revert       = true\n\n  }\n\n  # The reschedule stanza specifies the group's rescheduling strategy. If\n  # specified at the job level, the configuration will apply to all groups\n  # within the job. If the reschedule stanza is present on both the job and the\n  # group, they are merged with the group stanza taking the highest precedence\n  # and then the job.\n  reschedule {\n    delay             = \"30s\"\n    delay_function    = \"constant\"\n    unlimited         = true\n  }\n\n  # The \"group\" stanza defines a series of tasks that should be co-located on\n  # the same Nomad client. Any task within a group will be placed on the same\n  # client.\n  #\n  # For more information and examples on the \"group\" stanza, please see\n  # the online documentation at:\n  #\n  #     https://www.nomadproject.io/docs/job-specification/group\n  #\n  group \"prod-group1-alertmanager\" {\n    # The \"count\" parameter specifies the number of the task groups that should\n    # be running under this group. This value must be non-negative and defaults\n    # to 1.\n    count             = 1\n\n    # The restart stanza configures a tasks's behavior on task failure. Restarts\n    # happen on the client that is running the task.\n    #\n    # https://www.nomadproject.io/docs/job-specification/restart\n    #\n    restart {\n      interval  = \"30m\"\n      attempts  = 40\n      delay     = \"15s\"\n      mode      = \"delay\"\n    }\n\n    # The constraint allows restricting the set of eligible nodes. Constraints\n    # may filter on attributes or client metadata.\n    #\n    # For more information and examples on the \"volume\" stanza, please see\n    # the online documentation at:\n    #\n    #     https://www.nomadproject.io/docs/job-specification/constraint\n    #\n    constraint {\n      attribute       = \"${attr.cpu.arch}\"\n      operator        = \"!=\"\n      value           = \"arm64\"\n    }\n\n    # The \"task\" stanza creates an individual unit of work, such as a Docker\n    # container, web application, or batch processing.\n    #\n    # For more information and examples on the \"task\" stanza, please see\n    # the online documentation at:\n    #\n    #     https://www.nomadproject.io/docs/job-specification/task\n    #\n    task \"prod-task1-alertmanager\" {\n      # The \"driver\" parameter specifies the task driver that should be used to\n      # run the task.\n      driver          = \"exec\"\n\n      \n\n      # The \"config\" stanza specifies the driver configuration, which is passed\n      # directly to the driver to start the task. The details of configurations\n      # are specific to each driver, so please see specific driver\n      # documentation for more information.\n      config {\n        command       = \"local/alertmanager-0.21.0.linux-amd64/alertmanager\"\n        args          = [\n          \"--config.file=secrets/alertmanager.yml\"\n        ]\n      }\n\n      # The artifact stanza instructs Nomad to fetch and unpack a remote resource,\n      # such as a file, tarball, or binary. Nomad downloads artifacts using the\n      # popular go-getter library, which permits downloading artifacts from a\n      # variety of locations using a URL as the input source.\n      #\n      # For more information and examples on the \"artifact\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/artifact\n      #\n      artifact {\n        source          = \"https://github.com/prometheus/alertmanager/releases/download/v0.21.0/alertmanager-0.21.0.linux-amd64.tar.gz\"\n      }\n\n      # The \"template\" stanza instructs Nomad to manage a template, such as\n      # a configuration file or script. This template can optionally pull data\n      # from Consul or Vault to populate runtime configuration data.\n      #\n      # For more information and examples on the \"template\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/template\n      #\n      template {\n        change_mode     = \"noop\"\n        change_signal   = \"SIGINT\"\n        destination     = \"secrets/alertmanager.yml\"\n        left_delimiter  = \"{{{\"\n        right_delimiter = \"}}}\"\n        data            = \u003c\u003cEOH\n# The directory from which notification templates are read.\ntemplates:\n- '/etc/alertmanager/template/*.tmpl'\n\n#tls_config:\n#  # CA certificate to validate the server certificate with.\n#  ca_file: \u003cfilepath\u003e ]\n#\n#  # Certificate and key files for client cert authentication to the server.\n#  cert_file: \u003cfilepath\u003e\n#  key_file: \u003cfilepath\u003e\n#\n#  # ServerName extension to indicate the name of the server.\n#  # http://tools.ietf.org/html/rfc4366#section-3.1\n#  server_name: \u003cstring\u003e\n#\n#  # Disable validation of the server certificate.\n#  insecure_skip_verify: true\n\n# The root route on which each incoming alert enters.\nroute:\n  receiver: 'default-slack-receiver'\n\n  # The labels by which incoming alerts are grouped together. For example,\n  # multiple alerts coming in for cluster=A and alertname=LatencyHigh would\n  # be batched into a single group.\n  #\n  # To aggregate by all possible labels use '...' as the sole label name.\n  # This effectively disables aggregation entirely, passing through all\n  # alerts as-is. This is unlikely to be what you want, unless you have\n  # a very low alert volume or your upstream notification system performs\n  # its own grouping. Example: group_by: [...]\n  group_by: ['alertname']\n\n  # When a new group of alerts is created by an incoming alert, wait at\n  # least 'group_wait' to send the initial notification.\n  # This way ensures that you get multiple alerts for the same group that start\n  # firing shortly after another are batched together on the first\n  # notification.\n  group_wait: 30s\n\n  # When the first notification was sent, wait 'group_interval' to send a batch\n  # of new alerts that started firing for that group.\n  group_interval: 5m\n\n  # If an alert has successfully been sent, wait 'repeat_interval' to\n  # resend them.\n  repeat_interval: 3h\n\n  # All the above attributes are inherited by all child routes and can\n  # overwritten on each.\n  # The child route trees.\n  routes:\n  - match_re:\n      alertname: JenkinsJob.*\n    receiver: jenkins-slack-receiver\n    routes:\n    - match:\n        severity: critical\n      receiver: 'jenkins-slack-receiver'\n\n  - match_re:\n      service: .*\n    receiver: default-slack-receiver\n    routes:\n    - match:\n        severity: critical\n      receiver: 'default-slack-receiver'\n\n# Inhibition rules allow to mute a set of alerts given that another alert is\n# firing.\n# We use this to mute any warning-level notifications if the same alert is\n# already critical.\ninhibit_rules:\n- source_match:\n    severity: 'critical'\n  target_match:\n    severity: 'warning'\n  equal: ['alertname', 'instance']\n\nreceivers:\n- name: 'jenkins-slack-receiver'\n  slack_configs:\n  - api_url: 'TE07RD1V1/B01U1NV9HV3/hKZXJJ74g2JcISq4K3QC1eG9'\n    channel: '#fdio-jobs-monitoring'\n    send_resolved: true\n    icon_url: https://avatars3.githubusercontent.com/u/3380462\n    title: |-\n     [{{ .Status | toUpper }}{{ if eq .Status \"firing\" }}:{{ .Alerts.Firing | len }}{{ end }}] {{ .CommonLabels.alertname }} for {{ .CommonLabels.job }}\n     {{- if gt (len .CommonLabels) (len .GroupLabels) -}}\n       {{\" \"}}(\n       {{- with .CommonLabels.Remove .GroupLabels.Names }}\n         {{- range $index, $label := .SortedPairs -}}\n           {{ if $index }}, {{ end }}\n           {{- $label.Name }}=\"{{ $label.Value -}}\"\n         {{- end }}\n       {{- end -}}\n       )\n     {{- end }}\n    text: \u003e-\n     {{ range .Alerts -}}\n     *Alert:* {{ .Annotations.summary }}{{ if .Labels.severity }} - `{{ .Labels.severity }}`{{ end }}\n\n     *Description:* {{ .Annotations.description }}\n\n     *Details:*\n       {{ range .Labels.SortedPairs }} • *{{ .Name }}:* `{{ .Value }}`\n       {{ end }}\n     {{ end }}\n\n- name: 'default-slack-receiver'\n  slack_configs:\n  - api_url: 'TE07RD1V1/B01UUK23B6C/hZTcCu42FUv8d6rtirHtcYIi'\n    channel: '#fdio-infra-monitoring'\n    send_resolved: true\n    icon_url: https://avatars3.githubusercontent.com/u/3380462\n    title: |-\n     [{{ .Status | toUpper }}{{ if eq .Status \"firing\" }}:{{ .Alerts.Firing | len }}{{ end }}] {{ .CommonLabels.alertname }} for {{ .CommonLabels.job }}\n     {{- if gt (len .CommonLabels) (len .GroupLabels) -}}\n       {{\" \"}}(\n       {{- with .CommonLabels.Remove .GroupLabels.Names }}\n         {{- range $index, $label := .SortedPairs -}}\n           {{ if $index }}, {{ end }}\n           {{- $label.Name }}=\"{{ $label.Value -}}\"\n         {{- end }}\n       {{- end -}}\n       )\n     {{- end }}\n    text: \u003e-\n     {{ range .Alerts -}}\n     *Alert:* {{ .Annotations.summary }}{{ if .Labels.severity }} - `{{ .Labels.severity }}`{{ end }}\n\n     *Description:* {{ .Annotations.description }}\n\n     *Details:*\n       {{ range .Labels.SortedPairs }} • *{{ .Name }}:* `{{ .Value }}`\n       {{ end }}\n     {{ end }}\nEOH\n      }\n\n      # The service stanza instructs Nomad to register a service with Consul.\n      #\n      # For more information and examples on the \"task\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/service\n      #\n      service {\n        name            = \"alertmanager\"\n        port            = \"alertmanager\"\n        tags            = [ \"alertmanager${NOMAD_ALLOC_INDEX}\" ]\n        check {\n          name          = \"Alertmanager Check Live\"\n          type          = \"http\"\n          path          = \"/-/healthy\"\n          interval      = \"10s\"\n          timeout       = \"2s\"\n        }\n      }\n\n      # The \"resources\" stanza describes the requirements a task needs to\n      # execute. Resource requirements include memory, network, cpu, and more.\n      # This ensures the task will execute on a machine that contains enough\n      # resource capacity.\n      #\n      # For more information and examples on the \"resources\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/resources\n      #\n      resources {\n        cpu             = 1000\n        memory          = 1024\n        # The network stanza specifies the networking requirements for the task\n        # group, including the network mode and port allocations. When scheduling\n        # jobs in Nomad they are provisioned across your fleet of machines along\n        # with other jobs and services. Because you don't know in advance what host\n        # your job will be provisioned on, Nomad will provide your tasks with\n        # network configuration when they start up.\n        #\n        # For more information and examples on the \"template\" stanza, please see\n        # the online documentation at:\n        #\n        #     https://www.nomadproject.io/docs/job-specification/network\n        #\n        network {\n          port \"alertmanager\" {\n            static      = 9093\n          }\n        }\n      }\n    }\n  }\n}",
-            "template": "job \"${job_name}\" {\n  # The \"region\" parameter specifies the region in which to execute the job.\n  # If omitted, this inherits the default region name of \"global\".\n  # region = \"global\"\n  #\n  # The \"datacenters\" parameter specifies the list of datacenters which should\n  # be considered when placing this task. This must be provided.\n  datacenters         = \"${datacenters}\"\n\n  # The \"type\" parameter controls the type of job, which impacts the scheduler's\n  # decision on placement. This configuration is optional and defaults to\n  # \"service\". For a full list of job types and their differences, please see\n  # the online documentation.\n  #\n  # For more information, please see the online documentation at:\n  #\n  #     https://www.nomadproject.io/docs/jobspec/schedulers\n  #\n  type                = \"service\"\n\n  update {\n    # The \"max_parallel\" parameter specifies the maximum number of updates to\n    # perform in parallel. In this case, this specifies to update a single task\n    # at a time.\n    max_parallel      = 1\n\n    health_check      = \"checks\"\n\n    # The \"min_healthy_time\" parameter specifies the minimum time the allocation\n    # must be in the healthy state before it is marked as healthy and unblocks\n    # further allocations from being updated.\n    min_healthy_time  = \"10s\"\n\n    # The \"healthy_deadline\" parameter specifies the deadline in which the\n    # allocation must be marked as healthy after which the allocation is\n    # automatically transitioned to unhealthy. Transitioning to unhealthy will\n    # fail the deployment and potentially roll back the job if \"auto_revert\" is\n    # set to true.\n    healthy_deadline  = \"3m\"\n\n    # The \"progress_deadline\" parameter specifies the deadline in which an\n    # allocation must be marked as healthy. The deadline begins when the first\n    # allocation for the deployment is created and is reset whenever an allocation\n    # as part of the deployment transitions to a healthy state. If no allocation\n    # transitions to the healthy state before the progress deadline, the\n    # deployment is marked as failed.\n    progress_deadline = \"10m\"\n\n%{ if use_canary }\n    # The \"canary\" parameter specifies that changes to the job that would result\n    # in destructive updates should create the specified number of canaries\n    # without stopping any previous allocations. Once the operator determines the\n    # canaries are healthy, they can be promoted which unblocks a rolling update\n    # of the remaining allocations at a rate of \"max_parallel\".\n    #\n    # Further, setting \"canary\" equal to the count of the task group allows\n    # blue/green deployments. When the job is updated, a full set of the new\n    # version is deployed and upon promotion the old version is stopped.\n    canary            = 1\n\n    # Specifies if the job should auto-promote to the canary version when all\n    # canaries become healthy during a deployment. Defaults to false which means\n    # canaries must be manually updated with the nomad deployment promote\n    # command.\n    auto_promote      = true\n\n    # The \"auto_revert\" parameter specifies if the job should auto-revert to the\n    # last stable job on deployment failure. A job is marked as stable if all the\n    # allocations as part of its deployment were marked healthy.\n    auto_revert       = true\n%{ endif }\n  }\n\n  # The reschedule stanza specifies the group's rescheduling strategy. If\n  # specified at the job level, the configuration will apply to all groups\n  # within the job. If the reschedule stanza is present on both the job and the\n  # group, they are merged with the group stanza taking the highest precedence\n  # and then the job.\n  reschedule {\n    delay             = \"30s\"\n    delay_function    = \"constant\"\n    unlimited         = true\n  }\n\n  # The \"group\" stanza defines a series of tasks that should be co-located on\n  # the same Nomad client. Any task within a group will be placed on the same\n  # client.\n  #\n  # For more information and examples on the \"group\" stanza, please see\n  # the online documentation at:\n  #\n  #     https://www.nomadproject.io/docs/job-specification/group\n  #\n  group \"prod-group1-${service_name}\" {\n    # The \"count\" parameter specifies the number of the task groups that should\n    # be running under this group. This value must be non-negative and defaults\n    # to 1.\n    count             = ${group_count}\n\n    # The restart stanza configures a tasks's behavior on task failure. Restarts\n    # happen on the client that is running the task.\n    #\n    # https://www.nomadproject.io/docs/job-specification/restart\n    #\n    restart {\n      interval  = \"30m\"\n      attempts  = 40\n      delay     = \"15s\"\n      mode      = \"delay\"\n    }\n\n    # The constraint allows restricting the set of eligible nodes. Constraints\n    # may filter on attributes or client metadata.\n    #\n    # For more information and examples on the \"volume\" stanza, please see\n    # the online documentation at:\n    #\n    #     https://www.nomadproject.io/docs/job-specification/constraint\n    #\n    constraint {\n      attribute       = \"$${attr.cpu.arch}\"\n      operator        = \"!=\"\n      value           = \"arm64\"\n    }\n\n    # The \"task\" stanza creates an individual unit of work, such as a Docker\n    # container, web application, or batch processing.\n    #\n    # For more information and examples on the \"task\" stanza, please see\n    # the online documentation at:\n    #\n    #     https://www.nomadproject.io/docs/job-specification/task\n    #\n    task \"prod-task1-${service_name}\" {\n      # The \"driver\" parameter specifies the task driver that should be used to\n      # run the task.\n      driver          = \"exec\"\n\n      %{ if use_vault_provider }\n      vault {\n        policies        = \"${vault_kv_policy_name}\"\n      }\n      %{ endif }\n\n      # The \"config\" stanza specifies the driver configuration, which is passed\n      # directly to the driver to start the task. The details of configurations\n      # are specific to each driver, so please see specific driver\n      # documentation for more information.\n      config {\n        command       = \"local/alertmanager-${version}.linux-amd64/alertmanager\"\n        args          = [\n          \"--config.file=secrets/alertmanager.yml\"\n        ]\n      }\n\n      # The artifact stanza instructs Nomad to fetch and unpack a remote resource,\n      # such as a file, tarball, or binary. Nomad downloads artifacts using the\n      # popular go-getter library, which permits downloading artifacts from a\n      # variety of locations using a URL as the input source.\n      #\n      # For more information and examples on the \"artifact\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/artifact\n      #\n      artifact {\n        source          = \"${url}\"\n      }\n\n      # The \"template\" stanza instructs Nomad to manage a template, such as\n      # a configuration file or script. This template can optionally pull data\n      # from Consul or Vault to populate runtime configuration data.\n      #\n      # For more information and examples on the \"template\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/template\n      #\n      template {\n        change_mode     = \"noop\"\n        change_signal   = \"SIGINT\"\n        destination     = \"secrets/alertmanager.yml\"\n        left_delimiter  = \"{{{\"\n        right_delimiter = \"}}}\"\n        data            = \u003c\u003cEOH\n# The directory from which notification templates are read.\ntemplates:\n- '/etc/alertmanager/template/*.tmpl'\n\n#tls_config:\n#  # CA certificate to validate the server certificate with.\n#  ca_file: \u003cfilepath\u003e ]\n#\n#  # Certificate and key files for client cert authentication to the server.\n#  cert_file: \u003cfilepath\u003e\n#  key_file: \u003cfilepath\u003e\n#\n#  # ServerName extension to indicate the name of the server.\n#  # http://tools.ietf.org/html/rfc4366#section-3.1\n#  server_name: \u003cstring\u003e\n#\n#  # Disable validation of the server certificate.\n#  insecure_skip_verify: true\n\n# The root route on which each incoming alert enters.\nroute:\n  receiver: '${slack_default_receiver}'\n\n  # The labels by which incoming alerts are grouped together. For example,\n  # multiple alerts coming in for cluster=A and alertname=LatencyHigh would\n  # be batched into a single group.\n  #\n  # To aggregate by all possible labels use '...' as the sole label name.\n  # This effectively disables aggregation entirely, passing through all\n  # alerts as-is. This is unlikely to be what you want, unless you have\n  # a very low alert volume or your upstream notification system performs\n  # its own grouping. Example: group_by: [...]\n  group_by: ['alertname']\n\n  # When a new group of alerts is created by an incoming alert, wait at\n  # least 'group_wait' to send the initial notification.\n  # This way ensures that you get multiple alerts for the same group that start\n  # firing shortly after another are batched together on the first\n  # notification.\n  group_wait: 30s\n\n  # When the first notification was sent, wait 'group_interval' to send a batch\n  # of new alerts that started firing for that group.\n  group_interval: 5m\n\n  # If an alert has successfully been sent, wait 'repeat_interval' to\n  # resend them.\n  repeat_interval: 3h\n\n  # All the above attributes are inherited by all child routes and can\n  # overwritten on each.\n  # The child route trees.\n  routes:\n  - match_re:\n      alertname: JenkinsJob.*\n    receiver: ${slack_jenkins_receiver}\n    routes:\n    - match:\n        severity: critical\n      receiver: '${slack_jenkins_receiver}'\n\n  - match_re:\n      service: .*\n    receiver: ${slack_default_receiver}\n    routes:\n    - match:\n        severity: critical\n      receiver: '${slack_default_receiver}'\n\n# Inhibition rules allow to mute a set of alerts given that another alert is\n# firing.\n# We use this to mute any warning-level notifications if the same alert is\n# already critical.\ninhibit_rules:\n- source_match:\n    severity: 'critical'\n  target_match:\n    severity: 'warning'\n  equal: ['alertname', 'instance']\n\nreceivers:\n- name: '${slack_jenkins_receiver}'\n  slack_configs:\n  - api_url: '${slack_jenkins_api_key}'\n    channel: '#${slack_jenkins_channel}'\n    send_resolved: true\n    icon_url: https://avatars3.githubusercontent.com/u/3380462\n    title: |-\n     [{{ .Status | toUpper }}{{ if eq .Status \"firing\" }}:{{ .Alerts.Firing | len }}{{ end }}] {{ .CommonLabels.alertname }} for {{ .CommonLabels.job }}\n     {{- if gt (len .CommonLabels) (len .GroupLabels) -}}\n       {{\" \"}}(\n       {{- with .CommonLabels.Remove .GroupLabels.Names }}\n         {{- range $index, $label := .SortedPairs -}}\n           {{ if $index }}, {{ end }}\n           {{- $label.Name }}=\"{{ $label.Value -}}\"\n         {{- end }}\n       {{- end -}}\n       )\n     {{- end }}\n    text: \u003e-\n     {{ range .Alerts -}}\n     *Alert:* {{ .Annotations.summary }}{{ if .Labels.severity }} - `{{ .Labels.severity }}`{{ end }}\n\n     *Description:* {{ .Annotations.description }}\n\n     *Details:*\n       {{ range .Labels.SortedPairs }} • *{{ .Name }}:* `{{ .Value }}`\n       {{ end }}\n     {{ end }}\n\n- name: '${slack_default_receiver}'\n  slack_configs:\n  - api_url: '${slack_default_api_key}'\n    channel: '#${slack_default_channel}'\n    send_resolved: true\n    icon_url: https://avatars3.githubusercontent.com/u/3380462\n    title: |-\n     [{{ .Status | toUpper }}{{ if eq .Status \"firing\" }}:{{ .Alerts.Firing | len }}{{ end }}] {{ .CommonLabels.alertname }} for {{ .CommonLabels.job }}\n     {{- if gt (len .CommonLabels) (len .GroupLabels) -}}\n       {{\" \"}}(\n       {{- with .CommonLabels.Remove .GroupLabels.Names }}\n         {{- range $index, $label := .SortedPairs -}}\n           {{ if $index }}, {{ end }}\n           {{- $label.Name }}=\"{{ $label.Value -}}\"\n         {{- end }}\n       {{- end -}}\n       )\n     {{- end }}\n    text: \u003e-\n     {{ range .Alerts -}}\n     *Alert:* {{ .Annotations.summary }}{{ if .Labels.severity }} - `{{ .Labels.severity }}`{{ end }}\n\n     *Description:* {{ .Annotations.description }}\n\n     *Details:*\n       {{ range .Labels.SortedPairs }} • *{{ .Name }}:* `{{ .Value }}`\n       {{ end }}\n     {{ end }}\nEOH\n      }\n\n      # The service stanza instructs Nomad to register a service with Consul.\n      #\n      # For more information and examples on the \"task\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/service\n      #\n      service {\n        name            = \"${service_name}\"\n        port            = \"${service_name}\"\n        tags            = [ \"${service_name}$${NOMAD_ALLOC_INDEX}\" ]\n        check {\n          name          = \"Alertmanager Check Live\"\n          type          = \"http\"\n          path          = \"/-/healthy\"\n          interval      = \"10s\"\n          timeout       = \"2s\"\n        }\n      }\n\n      # The \"resources\" stanza describes the requirements a task needs to\n      # execute. Resource requirements include memory, network, cpu, and more.\n      # This ensures the task will execute on a machine that contains enough\n      # resource capacity.\n      #\n      # For more information and examples on the \"resources\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/resources\n      #\n      resources {\n        cpu             = ${cpu}\n        memory          = ${mem}\n        # The network stanza specifies the networking requirements for the task\n        # group, including the network mode and port allocations. When scheduling\n        # jobs in Nomad they are provisioned across your fleet of machines along\n        # with other jobs and services. Because you don't know in advance what host\n        # your job will be provisioned on, Nomad will provide your tasks with\n        # network configuration when they start up.\n        #\n        # For more information and examples on the \"template\" stanza, please see\n        # the online documentation at:\n        #\n        #     https://www.nomadproject.io/docs/job-specification/network\n        #\n        network {\n          port \"${service_name}\" {\n            static      = ${port}\n          }\n        }\n      }\n    }\n  }\n}",
+            "id": "2cd0a107978c5fd503445b71a5ad611daf96b7b57ad1bc15e3cb5c7dee391806",
+            "rendered": "job \"prod-alertmanager\" {\n  # The \"region\" parameter specifies the region in which to execute the job.\n  # If omitted, this inherits the default region name of \"global\".\n  # region = \"global\"\n  #\n  # The \"datacenters\" parameter specifies the list of datacenters which should\n  # be considered when placing this task. This must be provided.\n  datacenters         = \"yul1\"\n\n  # The \"type\" parameter controls the type of job, which impacts the scheduler's\n  # decision on placement. This configuration is optional and defaults to\n  # \"service\". For a full list of job types and their differences, please see\n  # the online documentation.\n  #\n  # For more information, please see the online documentation at:\n  #\n  #     https://www.nomadproject.io/docs/jobspec/schedulers\n  #\n  type                = \"service\"\n\n  update {\n    # The \"max_parallel\" parameter specifies the maximum number of updates to\n    # perform in parallel. In this case, this specifies to update a single task\n    # at a time.\n    max_parallel      = 1\n\n    health_check      = \"checks\"\n\n    # The \"min_healthy_time\" parameter specifies the minimum time the allocation\n    # must be in the healthy state before it is marked as healthy and unblocks\n    # further allocations from being updated.\n    min_healthy_time  = \"10s\"\n\n    # The \"healthy_deadline\" parameter specifies the deadline in which the\n    # allocation must be marked as healthy after which the allocation is\n    # automatically transitioned to unhealthy. Transitioning to unhealthy will\n    # fail the deployment and potentially roll back the job if \"auto_revert\" is\n    # set to true.\n    healthy_deadline  = \"3m\"\n\n    # The \"progress_deadline\" parameter specifies the deadline in which an\n    # allocation must be marked as healthy. The deadline begins when the first\n    # allocation for the deployment is created and is reset whenever an allocation\n    # as part of the deployment transitions to a healthy state. If no allocation\n    # transitions to the healthy state before the progress deadline, the\n    # deployment is marked as failed.\n    progress_deadline = \"10m\"\n\n\n    # The \"canary\" parameter specifies that changes to the job that would result\n    # in destructive updates should create the specified number of canaries\n    # without stopping any previous allocations. Once the operator determines the\n    # canaries are healthy, they can be promoted which unblocks a rolling update\n    # of the remaining allocations at a rate of \"max_parallel\".\n    #\n    # Further, setting \"canary\" equal to the count of the task group allows\n    # blue/green deployments. When the job is updated, a full set of the new\n    # version is deployed and upon promotion the old version is stopped.\n    canary            = 1\n\n    # Specifies if the job should auto-promote to the canary version when all\n    # canaries become healthy during a deployment. Defaults to false which means\n    # canaries must be manually updated with the nomad deployment promote\n    # command.\n    auto_promote      = true\n\n    # The \"auto_revert\" parameter specifies if the job should auto-revert to the\n    # last stable job on deployment failure. A job is marked as stable if all the\n    # allocations as part of its deployment were marked healthy.\n    auto_revert       = true\n\n  }\n\n  # The reschedule stanza specifies the group's rescheduling strategy. If\n  # specified at the job level, the configuration will apply to all groups\n  # within the job. If the reschedule stanza is present on both the job and the\n  # group, they are merged with the group stanza taking the highest precedence\n  # and then the job.\n  reschedule {\n    delay             = \"30s\"\n    delay_function    = \"constant\"\n    unlimited         = true\n  }\n\n  # The \"group\" stanza defines a series of tasks that should be co-located on\n  # the same Nomad client. Any task within a group will be placed on the same\n  # client.\n  #\n  # For more information and examples on the \"group\" stanza, please see\n  # the online documentation at:\n  #\n  #     https://www.nomadproject.io/docs/job-specification/group\n  #\n  group \"prod-group1-alertmanager\" {\n    # The \"count\" parameter specifies the number of the task groups that should\n    # be running under this group. This value must be non-negative and defaults\n    # to 1.\n    count             = 1\n\n    # The restart stanza configures a tasks's behavior on task failure. Restarts\n    # happen on the client that is running the task.\n    #\n    # https://www.nomadproject.io/docs/job-specification/restart\n    #\n    restart {\n      interval  = \"30m\"\n      attempts  = 40\n      delay     = \"15s\"\n      mode      = \"delay\"\n    }\n\n    # The constraint allows restricting the set of eligible nodes. Constraints\n    # may filter on attributes or client metadata.\n    #\n    # For more information and examples on the \"volume\" stanza, please see\n    # the online documentation at:\n    #\n    #     https://www.nomadproject.io/docs/job-specification/constraint\n    #\n    constraint {\n      attribute       = \"${attr.cpu.arch}\"\n      operator        = \"!=\"\n      value           = \"arm64\"\n    }\n\n    constraint {\n      attribute      = \"${node.class}\"\n      value          = \"builder\"\n    }\n\n    # The \"task\" stanza creates an individual unit of work, such as a Docker\n    # container, web application, or batch processing.\n    #\n    # For more information and examples on the \"task\" stanza, please see\n    # the online documentation at:\n    #\n    #     https://www.nomadproject.io/docs/job-specification/task\n    #\n    task \"prod-task1-alertmanager\" {\n      # The \"driver\" parameter specifies the task driver that should be used to\n      # run the task.\n      driver          = \"exec\"\n\n      \n\n      # The \"config\" stanza specifies the driver configuration, which is passed\n      # directly to the driver to start the task. The details of configurations\n      # are specific to each driver, so please see specific driver\n      # documentation for more information.\n      config {\n        command       = \"local/alertmanager-0.21.0.linux-amd64/alertmanager\"\n        args          = [\n          \"--config.file=secrets/alertmanager.yml\"\n        ]\n      }\n\n      # The artifact stanza instructs Nomad to fetch and unpack a remote resource,\n      # such as a file, tarball, or binary. Nomad downloads artifacts using the\n      # popular go-getter library, which permits downloading artifacts from a\n      # variety of locations using a URL as the input source.\n      #\n      # For more information and examples on the \"artifact\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/artifact\n      #\n      artifact {\n        source          = \"https://github.com/prometheus/alertmanager/releases/download/v0.21.0/alertmanager-0.21.0.linux-amd64.tar.gz\"\n      }\n\n      # The \"template\" stanza instructs Nomad to manage a template, such as\n      # a configuration file or script. This template can optionally pull data\n      # from Consul or Vault to populate runtime configuration data.\n      #\n      # For more information and examples on the \"template\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/template\n      #\n      template {\n        change_mode     = \"noop\"\n        change_signal   = \"SIGINT\"\n        destination     = \"secrets/alertmanager.yml\"\n        left_delimiter  = \"{{{\"\n        right_delimiter = \"}}}\"\n        data            = \u003c\u003cEOH\n# The directory from which notification templates are read.\ntemplates:\n- '/etc/alertmanager/template/*.tmpl'\n\n#tls_config:\n#  # CA certificate to validate the server certificate with.\n#  ca_file: \u003cfilepath\u003e ]\n#\n#  # Certificate and key files for client cert authentication to the server.\n#  cert_file: \u003cfilepath\u003e\n#  key_file: \u003cfilepath\u003e\n#\n#  # ServerName extension to indicate the name of the server.\n#  # http://tools.ietf.org/html/rfc4366#section-3.1\n#  server_name: \u003cstring\u003e\n#\n#  # Disable validation of the server certificate.\n#  insecure_skip_verify: true\n\n# The root route on which each incoming alert enters.\nroute:\n  receiver: 'default-slack-receiver'\n\n  # The labels by which incoming alerts are grouped together. For example,\n  # multiple alerts coming in for cluster=A and alertname=LatencyHigh would\n  # be batched into a single group.\n  #\n  # To aggregate by all possible labels use '...' as the sole label name.\n  # This effectively disables aggregation entirely, passing through all\n  # alerts as-is. This is unlikely to be what you want, unless you have\n  # a very low alert volume or your upstream notification system performs\n  # its own grouping. Example: group_by: [...]\n  group_by: ['alertname']\n\n  # When a new group of alerts is created by an incoming alert, wait at\n  # least 'group_wait' to send the initial notification.\n  # This way ensures that you get multiple alerts for the same group that start\n  # firing shortly after another are batched together on the first\n  # notification.\n  group_wait: 30s\n\n  # When the first notification was sent, wait 'group_interval' to send a batch\n  # of new alerts that started firing for that group.\n  group_interval: 5m\n\n  # If an alert has successfully been sent, wait 'repeat_interval' to\n  # resend them.\n  repeat_interval: 3h\n\n  # All the above attributes are inherited by all child routes and can\n  # overwritten on each.\n  # The child route trees.\n  routes:\n  - match_re:\n      alertname: JenkinsJob.*\n    receiver: jenkins-slack-receiver\n    routes:\n    - match:\n        severity: critical\n      receiver: 'jenkins-slack-receiver'\n\n  - match_re:\n      service: .*\n    receiver: default-slack-receiver\n    routes:\n    - match:\n        severity: critical\n      receiver: 'default-slack-receiver'\n\n# Inhibition rules allow to mute a set of alerts given that another alert is\n# firing.\n# We use this to mute any warning-level notifications if the same alert is\n# already critical.\ninhibit_rules:\n- source_match:\n    severity: 'critical'\n  target_match:\n    severity: 'warning'\n  equal: ['alertname', 'instance']\n\nreceivers:\n- name: 'jenkins-slack-receiver'\n  slack_configs:\n  - api_url: 'TE07RD1V1/B01U1NV9HV3/hKZXJJ74g2JcISq4K3QC1eG9'\n    channel: '#fdio-jobs-monitoring'\n    send_resolved: true\n    icon_url: https://avatars3.githubusercontent.com/u/3380462\n    title: |-\n     [{{ .Status | toUpper }}{{ if eq .Status \"firing\" }}:{{ .Alerts.Firing | len }}{{ end }}] {{ .CommonLabels.alertname }} for {{ .CommonLabels.job }}\n     {{- if gt (len .CommonLabels) (len .GroupLabels) -}}\n       {{\" \"}}(\n       {{- with .CommonLabels.Remove .GroupLabels.Names }}\n         {{- range $index, $label := .SortedPairs -}}\n           {{ if $index }}, {{ end }}\n           {{- $label.Name }}=\"{{ $label.Value -}}\"\n         {{- end }}\n       {{- end -}}\n       )\n     {{- end }}\n    text: \u003e-\n     {{ range .Alerts -}}\n     *Alert:* {{ .Annotations.summary }}{{ if .Labels.severity }} - `{{ .Labels.severity }}`{{ end }}\n\n     *Description:* {{ .Annotations.description }}\n\n     *Details:*\n       {{ range .Labels.SortedPairs }} • *{{ .Name }}:* `{{ .Value }}`\n       {{ end }}\n     {{ end }}\n\n- name: 'default-slack-receiver'\n  slack_configs:\n  - api_url: 'TE07RD1V1/B01UUK23B6C/hZTcCu42FUv8d6rtirHtcYIi'\n    channel: '#fdio-infra-monitoring'\n    send_resolved: true\n    icon_url: https://avatars3.githubusercontent.com/u/3380462\n    title: |-\n     [{{ .Status | toUpper }}{{ if eq .Status \"firing\" }}:{{ .Alerts.Firing | len }}{{ end }}] {{ .CommonLabels.alertname }} for {{ .CommonLabels.job }}\n     {{- if gt (len .CommonLabels) (len .GroupLabels) -}}\n       {{\" \"}}(\n       {{- with .CommonLabels.Remove .GroupLabels.Names }}\n         {{- range $index, $label := .SortedPairs -}}\n           {{ if $index }}, {{ end }}\n           {{- $label.Name }}=\"{{ $label.Value -}}\"\n         {{- end }}\n       {{- end -}}\n       )\n     {{- end }}\n    text: \u003e-\n     {{ range .Alerts -}}\n     *Alert:* {{ .Annotations.summary }}{{ if .Labels.severity }} - `{{ .Labels.severity }}`{{ end }}\n\n     *Description:* {{ .Annotations.description }}\n\n     *Details:*\n       {{ range .Labels.SortedPairs }} • *{{ .Name }}:* `{{ .Value }}`\n       {{ end }}\n     {{ end }}\nEOH\n      }\n\n      # The service stanza instructs Nomad to register a service with Consul.\n      #\n      # For more information and examples on the \"task\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/service\n      #\n      service {\n        name            = \"alertmanager\"\n        port            = \"alertmanager\"\n        tags            = [ \"alertmanager${NOMAD_ALLOC_INDEX}\" ]\n        check {\n          name          = \"Alertmanager Check Live\"\n          type          = \"http\"\n          path          = \"/-/healthy\"\n          interval      = \"10s\"\n          timeout       = \"2s\"\n        }\n      }\n\n      # The \"resources\" stanza describes the requirements a task needs to\n      # execute. Resource requirements include memory, network, cpu, and more.\n      # This ensures the task will execute on a machine that contains enough\n      # resource capacity.\n      #\n      # For more information and examples on the \"resources\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/resources\n      #\n      resources {\n        cpu             = 1000\n        memory          = 1024\n        # The network stanza specifies the networking requirements for the task\n        # group, including the network mode and port allocations. When scheduling\n        # jobs in Nomad they are provisioned across your fleet of machines along\n        # with other jobs and services. Because you don't know in advance what host\n        # your job will be provisioned on, Nomad will provide your tasks with\n        # network configuration when they start up.\n        #\n        # For more information and examples on the \"template\" stanza, please see\n        # the online documentation at:\n        #\n        #     https://www.nomadproject.io/docs/job-specification/network\n        #\n        network {\n          port \"alertmanager\" {\n            static      = 9093\n          }\n        }\n      }\n    }\n  }\n}",
+            "template": "job \"${job_name}\" {\n  # The \"region\" parameter specifies the region in which to execute the job.\n  # If omitted, this inherits the default region name of \"global\".\n  # region = \"global\"\n  #\n  # The \"datacenters\" parameter specifies the list of datacenters which should\n  # be considered when placing this task. This must be provided.\n  datacenters         = \"${datacenters}\"\n\n  # The \"type\" parameter controls the type of job, which impacts the scheduler's\n  # decision on placement. This configuration is optional and defaults to\n  # \"service\". For a full list of job types and their differences, please see\n  # the online documentation.\n  #\n  # For more information, please see the online documentation at:\n  #\n  #     https://www.nomadproject.io/docs/jobspec/schedulers\n  #\n  type                = \"service\"\n\n  update {\n    # The \"max_parallel\" parameter specifies the maximum number of updates to\n    # perform in parallel. In this case, this specifies to update a single task\n    # at a time.\n    max_parallel      = 1\n\n    health_check      = \"checks\"\n\n    # The \"min_healthy_time\" parameter specifies the minimum time the allocation\n    # must be in the healthy state before it is marked as healthy and unblocks\n    # further allocations from being updated.\n    min_healthy_time  = \"10s\"\n\n    # The \"healthy_deadline\" parameter specifies the deadline in which the\n    # allocation must be marked as healthy after which the allocation is\n    # automatically transitioned to unhealthy. Transitioning to unhealthy will\n    # fail the deployment and potentially roll back the job if \"auto_revert\" is\n    # set to true.\n    healthy_deadline  = \"3m\"\n\n    # The \"progress_deadline\" parameter specifies the deadline in which an\n    # allocation must be marked as healthy. The deadline begins when the first\n    # allocation for the deployment is created and is reset whenever an allocation\n    # as part of the deployment transitions to a healthy state. If no allocation\n    # transitions to the healthy state before the progress deadline, the\n    # deployment is marked as failed.\n    progress_deadline = \"10m\"\n\n%{ if use_canary }\n    # The \"canary\" parameter specifies that changes to the job that would result\n    # in destructive updates should create the specified number of canaries\n    # without stopping any previous allocations. Once the operator determines the\n    # canaries are healthy, they can be promoted which unblocks a rolling update\n    # of the remaining allocations at a rate of \"max_parallel\".\n    #\n    # Further, setting \"canary\" equal to the count of the task group allows\n    # blue/green deployments. When the job is updated, a full set of the new\n    # version is deployed and upon promotion the old version is stopped.\n    canary            = 1\n\n    # Specifies if the job should auto-promote to the canary version when all\n    # canaries become healthy during a deployment. Defaults to false which means\n    # canaries must be manually updated with the nomad deployment promote\n    # command.\n    auto_promote      = true\n\n    # The \"auto_revert\" parameter specifies if the job should auto-revert to the\n    # last stable job on deployment failure. A job is marked as stable if all the\n    # allocations as part of its deployment were marked healthy.\n    auto_revert       = true\n%{ endif }\n  }\n\n  # The reschedule stanza specifies the group's rescheduling strategy. If\n  # specified at the job level, the configuration will apply to all groups\n  # within the job. If the reschedule stanza is present on both the job and the\n  # group, they are merged with the group stanza taking the highest precedence\n  # and then the job.\n  reschedule {\n    delay             = \"30s\"\n    delay_function    = \"constant\"\n    unlimited         = true\n  }\n\n  # The \"group\" stanza defines a series of tasks that should be co-located on\n  # the same Nomad client. Any task within a group will be placed on the same\n  # client.\n  #\n  # For more information and examples on the \"group\" stanza, please see\n  # the online documentation at:\n  #\n  #     https://www.nomadproject.io/docs/job-specification/group\n  #\n  group \"prod-group1-${service_name}\" {\n    # The \"count\" parameter specifies the number of the task groups that should\n    # be running under this group. This value must be non-negative and defaults\n    # to 1.\n    count             = ${group_count}\n\n    # The restart stanza configures a tasks's behavior on task failure. Restarts\n    # happen on the client that is running the task.\n    #\n    # https://www.nomadproject.io/docs/job-specification/restart\n    #\n    restart {\n      interval  = \"30m\"\n      attempts  = 40\n      delay     = \"15s\"\n      mode      = \"delay\"\n    }\n\n    # The constraint allows restricting the set of eligible nodes. Constraints\n    # may filter on attributes or client metadata.\n    #\n    # For more information and examples on the \"volume\" stanza, please see\n    # the online documentation at:\n    #\n    #     https://www.nomadproject.io/docs/job-specification/constraint\n    #\n    constraint {\n      attribute       = \"$${attr.cpu.arch}\"\n      operator        = \"!=\"\n      value           = \"arm64\"\n    }\n\n    constraint {\n      attribute      = \"$${node.class}\"\n      value          = \"builder\"\n    }\n\n    # The \"task\" stanza creates an individual unit of work, such as a Docker\n    # container, web application, or batch processing.\n    #\n    # For more information and examples on the \"task\" stanza, please see\n    # the online documentation at:\n    #\n    #     https://www.nomadproject.io/docs/job-specification/task\n    #\n    task \"prod-task1-${service_name}\" {\n      # The \"driver\" parameter specifies the task driver that should be used to\n      # run the task.\n      driver          = \"exec\"\n\n      %{ if use_vault_provider }\n      vault {\n        policies        = \"${vault_kv_policy_name}\"\n      }\n      %{ endif }\n\n      # The \"config\" stanza specifies the driver configuration, which is passed\n      # directly to the driver to start the task. The details of configurations\n      # are specific to each driver, so please see specific driver\n      # documentation for more information.\n      config {\n        command       = \"local/alertmanager-${version}.linux-amd64/alertmanager\"\n        args          = [\n          \"--config.file=secrets/alertmanager.yml\"\n        ]\n      }\n\n      # The artifact stanza instructs Nomad to fetch and unpack a remote resource,\n      # such as a file, tarball, or binary. Nomad downloads artifacts using the\n      # popular go-getter library, which permits downloading artifacts from a\n      # variety of locations using a URL as the input source.\n      #\n      # For more information and examples on the \"artifact\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/artifact\n      #\n      artifact {\n        source          = \"${url}\"\n      }\n\n      # The \"template\" stanza instructs Nomad to manage a template, such as\n      # a configuration file or script. This template can optionally pull data\n      # from Consul or Vault to populate runtime configuration data.\n      #\n      # For more information and examples on the \"template\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/template\n      #\n      template {\n        change_mode     = \"noop\"\n        change_signal   = \"SIGINT\"\n        destination     = \"secrets/alertmanager.yml\"\n        left_delimiter  = \"{{{\"\n        right_delimiter = \"}}}\"\n        data            = \u003c\u003cEOH\n# The directory from which notification templates are read.\ntemplates:\n- '/etc/alertmanager/template/*.tmpl'\n\n#tls_config:\n#  # CA certificate to validate the server certificate with.\n#  ca_file: \u003cfilepath\u003e ]\n#\n#  # Certificate and key files for client cert authentication to the server.\n#  cert_file: \u003cfilepath\u003e\n#  key_file: \u003cfilepath\u003e\n#\n#  # ServerName extension to indicate the name of the server.\n#  # http://tools.ietf.org/html/rfc4366#section-3.1\n#  server_name: \u003cstring\u003e\n#\n#  # Disable validation of the server certificate.\n#  insecure_skip_verify: true\n\n# The root route on which each incoming alert enters.\nroute:\n  receiver: '${slack_default_receiver}'\n\n  # The labels by which incoming alerts are grouped together. For example,\n  # multiple alerts coming in for cluster=A and alertname=LatencyHigh would\n  # be batched into a single group.\n  #\n  # To aggregate by all possible labels use '...' as the sole label name.\n  # This effectively disables aggregation entirely, passing through all\n  # alerts as-is. This is unlikely to be what you want, unless you have\n  # a very low alert volume or your upstream notification system performs\n  # its own grouping. Example: group_by: [...]\n  group_by: ['alertname']\n\n  # When a new group of alerts is created by an incoming alert, wait at\n  # least 'group_wait' to send the initial notification.\n  # This way ensures that you get multiple alerts for the same group that start\n  # firing shortly after another are batched together on the first\n  # notification.\n  group_wait: 30s\n\n  # When the first notification was sent, wait 'group_interval' to send a batch\n  # of new alerts that started firing for that group.\n  group_interval: 5m\n\n  # If an alert has successfully been sent, wait 'repeat_interval' to\n  # resend them.\n  repeat_interval: 3h\n\n  # All the above attributes are inherited by all child routes and can\n  # overwritten on each.\n  # The child route trees.\n  routes:\n  - match_re:\n      alertname: JenkinsJob.*\n    receiver: ${slack_jenkins_receiver}\n    routes:\n    - match:\n        severity: critical\n      receiver: '${slack_jenkins_receiver}'\n\n  - match_re:\n      service: .*\n    receiver: ${slack_default_receiver}\n    routes:\n    - match:\n        severity: critical\n      receiver: '${slack_default_receiver}'\n\n# Inhibition rules allow to mute a set of alerts given that another alert is\n# firing.\n# We use this to mute any warning-level notifications if the same alert is\n# already critical.\ninhibit_rules:\n- source_match:\n    severity: 'critical'\n  target_match:\n    severity: 'warning'\n  equal: ['alertname', 'instance']\n\nreceivers:\n- name: '${slack_jenkins_receiver}'\n  slack_configs:\n  - api_url: '${slack_jenkins_api_key}'\n    channel: '#${slack_jenkins_channel}'\n    send_resolved: true\n    icon_url: https://avatars3.githubusercontent.com/u/3380462\n    title: |-\n     [{{ .Status | toUpper }}{{ if eq .Status \"firing\" }}:{{ .Alerts.Firing | len }}{{ end }}] {{ .CommonLabels.alertname }} for {{ .CommonLabels.job }}\n     {{- if gt (len .CommonLabels) (len .GroupLabels) -}}\n       {{\" \"}}(\n       {{- with .CommonLabels.Remove .GroupLabels.Names }}\n         {{- range $index, $label := .SortedPairs -}}\n           {{ if $index }}, {{ end }}\n           {{- $label.Name }}=\"{{ $label.Value -}}\"\n         {{- end }}\n       {{- end -}}\n       )\n     {{- end }}\n    text: \u003e-\n     {{ range .Alerts -}}\n     *Alert:* {{ .Annotations.summary }}{{ if .Labels.severity }} - `{{ .Labels.severity }}`{{ end }}\n\n     *Description:* {{ .Annotations.description }}\n\n     *Details:*\n       {{ range .Labels.SortedPairs }} • *{{ .Name }}:* `{{ .Value }}`\n       {{ end }}\n     {{ end }}\n\n- name: '${slack_default_receiver}'\n  slack_configs:\n  - api_url: '${slack_default_api_key}'\n    channel: '#${slack_default_channel}'\n    send_resolved: true\n    icon_url: https://avatars3.githubusercontent.com/u/3380462\n    title: |-\n     [{{ .Status | toUpper }}{{ if eq .Status \"firing\" }}:{{ .Alerts.Firing | len }}{{ end }}] {{ .CommonLabels.alertname }} for {{ .CommonLabels.job }}\n     {{- if gt (len .CommonLabels) (len .GroupLabels) -}}\n       {{\" \"}}(\n       {{- with .CommonLabels.Remove .GroupLabels.Names }}\n         {{- range $index, $label := .SortedPairs -}}\n           {{ if $index }}, {{ end }}\n           {{- $label.Name }}=\"{{ $label.Value -}}\"\n         {{- end }}\n       {{- end -}}\n       )\n     {{- end }}\n    text: \u003e-\n     {{ range .Alerts -}}\n     *Alert:* {{ .Annotations.summary }}{{ if .Labels.severity }} - `{{ .Labels.severity }}`{{ end }}\n\n     *Description:* {{ .Annotations.description }}\n\n     *Details:*\n       {{ range .Labels.SortedPairs }} • *{{ .Name }}:* `{{ .Value }}`\n       {{ end }}\n     {{ end }}\nEOH\n      }\n\n      # The service stanza instructs Nomad to register a service with Consul.\n      #\n      # For more information and examples on the \"task\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/service\n      #\n      service {\n        name            = \"${service_name}\"\n        port            = \"${service_name}\"\n        tags            = [ \"${service_name}$${NOMAD_ALLOC_INDEX}\" ]\n        check {\n          name          = \"Alertmanager Check Live\"\n          type          = \"http\"\n          path          = \"/-/healthy\"\n          interval      = \"10s\"\n          timeout       = \"2s\"\n        }\n      }\n\n      # The \"resources\" stanza describes the requirements a task needs to\n      # execute. Resource requirements include memory, network, cpu, and more.\n      # This ensures the task will execute on a machine that contains enough\n      # resource capacity.\n      #\n      # For more information and examples on the \"resources\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/resources\n      #\n      resources {\n        cpu             = ${cpu}\n        memory          = ${mem}\n        # The network stanza specifies the networking requirements for the task\n        # group, including the network mode and port allocations. When scheduling\n        # jobs in Nomad they are provisioned across your fleet of machines along\n        # with other jobs and services. Because you don't know in advance what host\n        # your job will be provisioned on, Nomad will provide your tasks with\n        # network configuration when they start up.\n        #\n        # For more information and examples on the \"template\" stanza, please see\n        # the online documentation at:\n        #\n        #     https://www.nomadproject.io/docs/job-specification/network\n        #\n        network {\n          port \"${service_name}\" {\n            static      = ${port}\n          }\n        }\n      }\n    }\n  }\n}",
             "vars": {
               "cpu": "1000",
               "datacenters": "yul1",
@@ -54,20 +54,21 @@
           "schema_version": 0,
           "attributes": {
             "allocation_ids": [
-              "778f4f9d-dea8-e5bd-c9cf-f7a7e2d3a24e"
+              "74fdbd88-0e34-f990-3181-0413a373dcb2",
+              "412155f9-a6d4-f17c-3898-1e1c7cc1912b"
             ],
             "datacenters": [
               "yul1"
             ],
-            "deployment_id": "4dc972fd-cb2c-51d8-f730-08b5f7554ceb",
+            "deployment_id": "9b9e24ac-9932-f3eb-cc6e-cd64d41f8327",
             "deployment_status": "successful",
             "deregister_on_destroy": true,
             "deregister_on_id_change": true,
             "detach": false,
             "id": "prod-alertmanager",
-            "jobspec": "job \"prod-alertmanager\" {\n  # The \"region\" parameter specifies the region in which to execute the job.\n  # If omitted, this inherits the default region name of \"global\".\n  # region = \"global\"\n  #\n  # The \"datacenters\" parameter specifies the list of datacenters which should\n  # be considered when placing this task. This must be provided.\n  datacenters         = \"yul1\"\n\n  # The \"type\" parameter controls the type of job, which impacts the scheduler's\n  # decision on placement. This configuration is optional and defaults to\n  # \"service\". For a full list of job types and their differences, please see\n  # the online documentation.\n  #\n  # For more information, please see the online documentation at:\n  #\n  #     https://www.nomadproject.io/docs/jobspec/schedulers\n  #\n  type                = \"service\"\n\n  update {\n    # The \"max_parallel\" parameter specifies the maximum number of updates to\n    # perform in parallel. In this case, this specifies to update a single task\n    # at a time.\n    max_parallel      = 1\n\n    health_check      = \"checks\"\n\n    # The \"min_healthy_time\" parameter specifies the minimum time the allocation\n    # must be in the healthy state before it is marked as healthy and unblocks\n    # further allocations from being updated.\n    min_healthy_time  = \"10s\"\n\n    # The \"healthy_deadline\" parameter specifies the deadline in which the\n    # allocation must be marked as healthy after which the allocation is\n    # automatically transitioned to unhealthy. Transitioning to unhealthy will\n    # fail the deployment and potentially roll back the job if \"auto_revert\" is\n    # set to true.\n    healthy_deadline  = \"3m\"\n\n    # The \"progress_deadline\" parameter specifies the deadline in which an\n    # allocation must be marked as healthy. The deadline begins when the first\n    # allocation for the deployment is created and is reset whenever an allocation\n    # as part of the deployment transitions to a healthy state. If no allocation\n    # transitions to the healthy state before the progress deadline, the\n    # deployment is marked as failed.\n    progress_deadline = \"10m\"\n\n\n    # The \"canary\" parameter specifies that changes to the job that would result\n    # in destructive updates should create the specified number of canaries\n    # without stopping any previous allocations. Once the operator determines the\n    # canaries are healthy, they can be promoted which unblocks a rolling update\n    # of the remaining allocations at a rate of \"max_parallel\".\n    #\n    # Further, setting \"canary\" equal to the count of the task group allows\n    # blue/green deployments. When the job is updated, a full set of the new\n    # version is deployed and upon promotion the old version is stopped.\n    canary            = 1\n\n    # Specifies if the job should auto-promote to the canary version when all\n    # canaries become healthy during a deployment. Defaults to false which means\n    # canaries must be manually updated with the nomad deployment promote\n    # command.\n    auto_promote      = true\n\n    # The \"auto_revert\" parameter specifies if the job should auto-revert to the\n    # last stable job on deployment failure. A job is marked as stable if all the\n    # allocations as part of its deployment were marked healthy.\n    auto_revert       = true\n\n  }\n\n  # The reschedule stanza specifies the group's rescheduling strategy. If\n  # specified at the job level, the configuration will apply to all groups\n  # within the job. If the reschedule stanza is present on both the job and the\n  # group, they are merged with the group stanza taking the highest precedence\n  # and then the job.\n  reschedule {\n    delay             = \"30s\"\n    delay_function    = \"constant\"\n    unlimited         = true\n  }\n\n  # The \"group\" stanza defines a series of tasks that should be co-located on\n  # the same Nomad client. Any task within a group will be placed on the same\n  # client.\n  #\n  # For more information and examples on the \"group\" stanza, please see\n  # the online documentation at:\n  #\n  #     https://www.nomadproject.io/docs/job-specification/group\n  #\n  group \"prod-group1-alertmanager\" {\n    # The \"count\" parameter specifies the number of the task groups that should\n    # be running under this group. This value must be non-negative and defaults\n    # to 1.\n    count             = 1\n\n    # The restart stanza configures a tasks's behavior on task failure. Restarts\n    # happen on the client that is running the task.\n    #\n    # https://www.nomadproject.io/docs/job-specification/restart\n    #\n    restart {\n      interval  = \"30m\"\n      attempts  = 40\n      delay     = \"15s\"\n      mode      = \"delay\"\n    }\n\n    # The constraint allows restricting the set of eligible nodes. Constraints\n    # may filter on attributes or client metadata.\n    #\n    # For more information and examples on the \"volume\" stanza, please see\n    # the online documentation at:\n    #\n    #     https://www.nomadproject.io/docs/job-specification/constraint\n    #\n    constraint {\n      attribute       = \"${attr.cpu.arch}\"\n      operator        = \"!=\"\n      value           = \"arm64\"\n    }\n\n    # 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}",
+            "jobspec": "job \"prod-alertmanager\" {\n  # The \"region\" parameter specifies the region in which to execute the job.\n  # If omitted, this inherits the default region name of \"global\".\n  # region = \"global\"\n  #\n  # The \"datacenters\" parameter specifies the list of datacenters which should\n  # be considered when placing this task. This must be provided.\n  datacenters         = \"yul1\"\n\n  # The \"type\" parameter controls the type of job, which impacts the scheduler's\n  # decision on placement. This configuration is optional and defaults to\n  # \"service\". For a full list of job types and their differences, please see\n  # the online documentation.\n  #\n  # For more information, please see the online documentation at:\n  #\n  #     https://www.nomadproject.io/docs/jobspec/schedulers\n  #\n  type                = \"service\"\n\n  update {\n    # The \"max_parallel\" parameter specifies the maximum number of updates to\n    # perform in parallel. In this case, this specifies to update a single task\n    # at a time.\n    max_parallel      = 1\n\n    health_check      = \"checks\"\n\n    # The \"min_healthy_time\" parameter specifies the minimum time the allocation\n    # must be in the healthy state before it is marked as healthy and unblocks\n    # further allocations from being updated.\n    min_healthy_time  = \"10s\"\n\n    # The \"healthy_deadline\" parameter specifies the deadline in which the\n    # allocation must be marked as healthy after which the allocation is\n    # automatically transitioned to unhealthy. Transitioning to unhealthy will\n    # fail the deployment and potentially roll back the job if \"auto_revert\" is\n    # set to true.\n    healthy_deadline  = \"3m\"\n\n    # The \"progress_deadline\" parameter specifies the deadline in which an\n    # allocation must be marked as healthy. The deadline begins when the first\n    # allocation for the deployment is created and is reset whenever an allocation\n    # as part of the deployment transitions to a healthy state. If no allocation\n    # transitions to the healthy state before the progress deadline, the\n    # deployment is marked as failed.\n    progress_deadline = \"10m\"\n\n\n    # The \"canary\" parameter specifies that changes to the job that would result\n    # in destructive updates should create the specified number of canaries\n    # without stopping any previous allocations. Once the operator determines the\n    # canaries are healthy, they can be promoted which unblocks a rolling update\n    # of the remaining allocations at a rate of \"max_parallel\".\n    #\n    # Further, setting \"canary\" equal to the count of the task group allows\n    # blue/green deployments. When the job is updated, a full set of the new\n    # version is deployed and upon promotion the old version is stopped.\n    canary            = 1\n\n    # Specifies if the job should auto-promote to the canary version when all\n    # canaries become healthy during a deployment. Defaults to false which means\n    # canaries must be manually updated with the nomad deployment promote\n    # command.\n    auto_promote      = true\n\n    # The \"auto_revert\" parameter specifies if the job should auto-revert to the\n    # last stable job on deployment failure. A job is marked as stable if all the\n    # allocations as part of its deployment were marked healthy.\n    auto_revert       = true\n\n  }\n\n  # The reschedule stanza specifies the group's rescheduling strategy. If\n  # specified at the job level, the configuration will apply to all groups\n  # within the job. If the reschedule stanza is present on both the job and the\n  # group, they are merged with the group stanza taking the highest precedence\n  # and then the job.\n  reschedule {\n    delay             = \"30s\"\n    delay_function    = \"constant\"\n    unlimited         = true\n  }\n\n  # The \"group\" stanza defines a series of tasks that should be co-located on\n  # the same Nomad client. Any task within a group will be placed on the same\n  # client.\n  #\n  # For more information and examples on the \"group\" stanza, please see\n  # the online documentation at:\n  #\n  #     https://www.nomadproject.io/docs/job-specification/group\n  #\n  group \"prod-group1-alertmanager\" {\n    # The \"count\" parameter specifies the number of the task groups that should\n    # be running under this group. This value must be non-negative and defaults\n    # to 1.\n    count             = 1\n\n    # The restart stanza configures a tasks's behavior on task failure. Restarts\n    # happen on the client that is running the task.\n    #\n    # https://www.nomadproject.io/docs/job-specification/restart\n    #\n    restart {\n      interval  = \"30m\"\n      attempts  = 40\n      delay     = \"15s\"\n      mode      = \"delay\"\n    }\n\n    # The constraint allows restricting the set of eligible nodes. Constraints\n    # may filter on attributes or client metadata.\n    #\n    # For more information and examples on the \"volume\" stanza, please see\n    # the online documentation at:\n    #\n    #     https://www.nomadproject.io/docs/job-specification/constraint\n    #\n    constraint {\n      attribute       = \"${attr.cpu.arch}\"\n      operator        = \"!=\"\n      value           = \"arm64\"\n    }\n\n    constraint {\n      attribute      = \"${node.class}\"\n      value          = \"builder\"\n    }\n\n    # The \"task\" stanza creates an individual unit of work, such as a Docker\n    # container, web application, or batch processing.\n    #\n    # For more information and examples on the \"task\" stanza, please see\n    # the online documentation at:\n    #\n    #     https://www.nomadproject.io/docs/job-specification/task\n    #\n    task \"prod-task1-alertmanager\" {\n      # The \"driver\" parameter specifies the task driver that should be used to\n      # run the task.\n      driver          = \"exec\"\n\n      \n\n      # The \"config\" stanza specifies the driver configuration, which is passed\n      # directly to the driver to start the task. The details of configurations\n      # are specific to each driver, so please see specific driver\n      # documentation for more information.\n      config {\n        command       = \"local/alertmanager-0.21.0.linux-amd64/alertmanager\"\n        args          = [\n          \"--config.file=secrets/alertmanager.yml\"\n        ]\n      }\n\n      # The artifact stanza instructs Nomad to fetch and unpack a remote resource,\n      # such as a file, tarball, or binary. Nomad downloads artifacts using the\n      # popular go-getter library, which permits downloading artifacts from a\n      # variety of locations using a URL as the input source.\n      #\n      # For more information and examples on the \"artifact\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/artifact\n      #\n      artifact {\n        source          = \"https://github.com/prometheus/alertmanager/releases/download/v0.21.0/alertmanager-0.21.0.linux-amd64.tar.gz\"\n      }\n\n      # The \"template\" stanza instructs Nomad to manage a template, such as\n      # a configuration file or script. This template can optionally pull data\n      # from Consul or Vault to populate runtime configuration data.\n      #\n      # For more information and examples on the \"template\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/template\n      #\n      template {\n        change_mode     = \"noop\"\n        change_signal   = \"SIGINT\"\n        destination     = \"secrets/alertmanager.yml\"\n        left_delimiter  = \"{{{\"\n        right_delimiter = \"}}}\"\n        data            = \u003c\u003cEOH\n# The directory from which notification templates are read.\ntemplates:\n- '/etc/alertmanager/template/*.tmpl'\n\n#tls_config:\n#  # CA certificate to validate the server certificate with.\n#  ca_file: \u003cfilepath\u003e ]\n#\n#  # Certificate and key files for client cert authentication to the server.\n#  cert_file: \u003cfilepath\u003e\n#  key_file: \u003cfilepath\u003e\n#\n#  # ServerName extension to indicate the name of the server.\n#  # http://tools.ietf.org/html/rfc4366#section-3.1\n#  server_name: \u003cstring\u003e\n#\n#  # Disable validation of the server certificate.\n#  insecure_skip_verify: true\n\n# The root route on which each incoming alert enters.\nroute:\n  receiver: 'default-slack-receiver'\n\n  # The labels by which incoming alerts are grouped together. For example,\n  # multiple alerts coming in for cluster=A and alertname=LatencyHigh would\n  # be batched into a single group.\n  #\n  # To aggregate by all possible labels use '...' as the sole label name.\n  # This effectively disables aggregation entirely, passing through all\n  # alerts as-is. This is unlikely to be what you want, unless you have\n  # a very low alert volume or your upstream notification system performs\n  # its own grouping. Example: group_by: [...]\n  group_by: ['alertname']\n\n  # When a new group of alerts is created by an incoming alert, wait at\n  # least 'group_wait' to send the initial notification.\n  # This way ensures that you get multiple alerts for the same group that start\n  # firing shortly after another are batched together on the first\n  # notification.\n  group_wait: 30s\n\n  # When the first notification was sent, wait 'group_interval' to send a batch\n  # of new alerts that started firing for that group.\n  group_interval: 5m\n\n  # If an alert has successfully been sent, wait 'repeat_interval' to\n  # resend them.\n  repeat_interval: 3h\n\n  # All the above attributes are inherited by all child routes and can\n  # overwritten on each.\n  # The child route trees.\n  routes:\n  - match_re:\n      alertname: JenkinsJob.*\n    receiver: jenkins-slack-receiver\n    routes:\n    - match:\n        severity: critical\n      receiver: 'jenkins-slack-receiver'\n\n  - match_re:\n      service: .*\n    receiver: default-slack-receiver\n    routes:\n    - match:\n        severity: critical\n      receiver: 'default-slack-receiver'\n\n# Inhibition rules allow to mute a set of alerts given that another alert is\n# firing.\n# We use this to mute any warning-level notifications if the same alert is\n# already critical.\ninhibit_rules:\n- source_match:\n    severity: 'critical'\n  target_match:\n    severity: 'warning'\n  equal: ['alertname', 'instance']\n\nreceivers:\n- name: 'jenkins-slack-receiver'\n  slack_configs:\n  - api_url: 'TE07RD1V1/B01U1NV9HV3/hKZXJJ74g2JcISq4K3QC1eG9'\n    channel: '#fdio-jobs-monitoring'\n    send_resolved: true\n    icon_url: https://avatars3.githubusercontent.com/u/3380462\n    title: |-\n     [{{ .Status | toUpper }}{{ if eq .Status \"firing\" }}:{{ .Alerts.Firing | len }}{{ end }}] {{ .CommonLabels.alertname }} for {{ .CommonLabels.job }}\n     {{- if gt (len .CommonLabels) (len .GroupLabels) -}}\n       {{\" \"}}(\n       {{- with .CommonLabels.Remove .GroupLabels.Names }}\n         {{- range $index, $label := .SortedPairs -}}\n           {{ if $index }}, {{ end }}\n           {{- $label.Name }}=\"{{ $label.Value -}}\"\n         {{- end }}\n       {{- end -}}\n       )\n     {{- end }}\n    text: \u003e-\n     {{ range .Alerts -}}\n     *Alert:* {{ .Annotations.summary }}{{ if .Labels.severity }} - `{{ .Labels.severity }}`{{ end }}\n\n     *Description:* {{ .Annotations.description }}\n\n     *Details:*\n       {{ range .Labels.SortedPairs }} • *{{ .Name }}:* `{{ .Value }}`\n       {{ end }}\n     {{ end }}\n\n- name: 'default-slack-receiver'\n  slack_configs:\n  - api_url: 'TE07RD1V1/B01UUK23B6C/hZTcCu42FUv8d6rtirHtcYIi'\n    channel: '#fdio-infra-monitoring'\n    send_resolved: true\n    icon_url: https://avatars3.githubusercontent.com/u/3380462\n    title: |-\n     [{{ .Status | toUpper }}{{ if eq .Status \"firing\" }}:{{ .Alerts.Firing | len }}{{ end }}] {{ .CommonLabels.alertname }} for {{ .CommonLabels.job }}\n     {{- if gt (len .CommonLabels) (len .GroupLabels) -}}\n       {{\" \"}}(\n       {{- with .CommonLabels.Remove .GroupLabels.Names }}\n         {{- range $index, $label := .SortedPairs -}}\n           {{ if $index }}, {{ end }}\n           {{- $label.Name }}=\"{{ $label.Value -}}\"\n         {{- end }}\n       {{- end -}}\n       )\n     {{- end }}\n    text: \u003e-\n     {{ range .Alerts -}}\n     *Alert:* {{ .Annotations.summary }}{{ if .Labels.severity }} - `{{ .Labels.severity }}`{{ end }}\n\n     *Description:* {{ .Annotations.description }}\n\n     *Details:*\n       {{ range .Labels.SortedPairs }} • *{{ .Name }}:* `{{ .Value }}`\n       {{ end }}\n     {{ end }}\nEOH\n      }\n\n      # The service stanza instructs Nomad to register a service with Consul.\n      #\n      # For more information and examples on the \"task\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/service\n      #\n      service {\n        name            = \"alertmanager\"\n        port            = \"alertmanager\"\n        tags            = [ \"alertmanager${NOMAD_ALLOC_INDEX}\" ]\n        check {\n          name          = \"Alertmanager Check Live\"\n          type          = \"http\"\n          path          = \"/-/healthy\"\n          interval      = \"10s\"\n          timeout       = \"2s\"\n        }\n      }\n\n      # The \"resources\" stanza describes the requirements a task needs to\n      # execute. Resource requirements include memory, network, cpu, and more.\n      # This ensures the task will execute on a machine that contains enough\n      # resource capacity.\n      #\n      # For more information and examples on the \"resources\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/resources\n      #\n      resources {\n        cpu             = 1000\n        memory          = 1024\n        # The network stanza specifies the networking requirements for the task\n        # group, including the network mode and port allocations. When scheduling\n        # jobs in Nomad they are provisioned across your fleet of machines along\n        # with other jobs and services. Because you don't know in advance what host\n        # your job will be provisioned on, Nomad will provide your tasks with\n        # network configuration when they start up.\n        #\n        # For more information and examples on the \"template\" stanza, please see\n        # the online documentation at:\n        #\n        #     https://www.nomadproject.io/docs/job-specification/network\n        #\n        network {\n          port \"alertmanager\" {\n            static      = 9093\n          }\n        }\n      }\n    }\n  }\n}",
             "json": null,
-            "modify_index": "8259282",
+            "modify_index": "9138748",
             "name": "prod-alertmanager",
             "namespace": "default",
             "policy_override": null,
@@ -110,9 +111,9 @@
           "schema_version": 0,
           "attributes": {
             "filename": null,
-            "id": "cf7f3cd265a99a6f72f774f25564f1ec0e9e2c268a8f76112aed6cffe73bc4d4",
-            "rendered": "job \"prod-grafana\" {\n  # The \"region\" parameter specifies the region in which to execute the job.\n  # If omitted, this inherits the default region name of \"global\".\n  # region = \"global\"\n  #\n  # The \"datacenters\" parameter specifies the list of datacenters which should\n  # be considered when placing this task. This must be provided.\n  datacenters         = \"yul1\"\n\n  # The \"type\" parameter controls the type of job, which impacts the scheduler's\n  # decision on placement. This configuration is optional and defaults to\n  # \"service\". For a full list of job types and their differences, please see\n  # the online documentation.\n  #\n  # For more information, please see the online documentation at:\n  #\n  #     https://www.nomadproject.io/docs/jobspec/schedulers\n  #\n  type                = \"service\"\n\n  update {\n    # The \"max_parallel\" parameter specifies the maximum number of updates to\n    # perform in parallel. In this case, this specifies to update a single task\n    # at a time.\n    max_parallel      = 1\n\n    health_check      = \"checks\"\n\n    # The \"min_healthy_time\" parameter specifies the minimum time the allocation\n    # must be in the healthy state before it is marked as healthy and unblocks\n    # further allocations from being updated.\n    min_healthy_time  = \"10s\"\n\n    # The \"healthy_deadline\" parameter specifies the deadline in which the\n    # allocation must be marked as healthy after which the allocation is\n    # automatically transitioned to unhealthy. Transitioning to unhealthy will\n    # fail the deployment and potentially roll back the job if \"auto_revert\" is\n    # set to true.\n    healthy_deadline  = \"3m\"\n\n    # The \"progress_deadline\" parameter specifies the deadline in which an\n    # allocation must be marked as healthy. The deadline begins when the first\n    # allocation for the deployment is created and is reset whenever an allocation\n    # as part of the deployment transitions to a healthy state. If no allocation\n    # transitions to the healthy state before the progress deadline, the\n    # deployment is marked as failed.\n    progress_deadline = \"10m\"\n\n\n    # The \"canary\" parameter specifies that changes to the job that would result\n    # in destructive updates should create the specified number of canaries\n    # without stopping any previous allocations. Once the operator determines the\n    # canaries are healthy, they can be promoted which unblocks a rolling update\n    # of the remaining allocations at a rate of \"max_parallel\".\n    #\n    # Further, setting \"canary\" equal to the count of the task group allows\n    # blue/green deployments. When the job is updated, a full set of the new\n    # version is deployed and upon promotion the old version is stopped.\n    canary            = 1\n\n    # Specifies if the job should auto-promote to the canary version when all\n    # canaries become healthy during a deployment. Defaults to false which means\n    # canaries must be manually updated with the nomad deployment promote\n    # command.\n    auto_promote      = true\n\n    # The \"auto_revert\" parameter specifies if the job should auto-revert to the\n    # last stable job on deployment failure. A job is marked as stable if all the\n    # allocations as part of its deployment were marked healthy.\n    auto_revert       = true\n\n  }\n\n  # The reschedule stanza specifies the group's rescheduling strategy. If\n  # specified at the job level, the configuration will apply to all groups\n  # within the job. If the reschedule stanza is present on both the job and the\n  # group, they are merged with the group stanza taking the highest precedence\n  # and then the job.\n  reschedule {\n    delay             = \"30s\"\n    delay_function    = \"constant\"\n    unlimited         = true\n  }\n\n  # The \"group\" stanza defines a series of tasks that should be co-located on\n  # the same Nomad client. Any task within a group will be placed on the same\n  # client.\n  #\n  # For more information and examples on the \"group\" stanza, please see\n  # the online documentation at:\n  #\n  #     https://www.nomadproject.io/docs/job-specification/group\n  #\n  group \"prod-group1-grafana\" {\n    # The \"count\" parameter specifies the number of the task groups that should\n    # be running under this group. This value must be non-negative and defaults\n    # to 1.\n    count             = 1\n\n    # The restart stanza configures a tasks's behavior on task failure. Restarts\n    # happen on the client that is running the task.\n    #\n    # https://www.nomadproject.io/docs/job-specification/restart\n    #\n    restart {\n      interval        = \"30m\"\n      attempts        = 40\n      delay           = \"15s\"\n      mode            = \"delay\"\n    }\n\n    # The constraint allows restricting the set of eligible nodes. Constraints\n    # may filter on attributes or client metadata.\n    #\n    # For more information and examples on the \"volume\" stanza, please see\n    # the online documentation at:\n    #\n    #     https://www.nomadproject.io/docs/job-specification/constraint\n    #\n    constraint {\n      attribute       = \"${attr.cpu.arch}\"\n      operator        = \"!=\"\n      value           = \"arm64\"\n    }\n\n    # The \"task\" stanza creates an individual unit of work, such as a Docker\n    # container, web application, or batch processing.\n    #\n    # For more information and examples on the \"task\" stanza, please see\n    # the online documentation at:\n    #\n    #     https://www.nomadproject.io/docs/job-specification/task\n    #\n    task \"prod-task1-grafana\" {\n      # The \"driver\" parameter specifies the task driver that should be used to\n      # run the task.\n      driver          = \"docker\"\n\n      # The \"config\" stanza specifies the driver configuration, which is passed\n      # directly to the driver to start the task. The details of configurations\n      # are specific to each driver, so please see specific driver\n      # documentation for more information.\n      config {\n        image         = \"grafana/grafana:7.3.7\"\n        dns_servers   = [ \"172.17.0.1\" ]\n        volumes       = [\n          \"secrets/prometheus.yml:/etc/grafana/provisioning/datasources/prometheus.yml\",\n          \"secrets/dashboards.yml:/etc/grafana/provisioning/dashboards/dashboards.yml\",\n          \"secrets/grafana.ini:/etc/grafana/grafana.ini\",\n          \"secrets/node_exporter.json:/etc/grafana/provisioning/dashboards/node_exporter.json\",\n          \"secrets/docker_cadvisor.json:/etc/grafana/provisioning/dashboards/docker_cadvisor.json\",\n          \"secrets/nomad.json:/etc/grafana/provisioning/dashboards/nomad.json\",\n          \"secrets/consul.json:/etc/grafana/provisioning/dashboards/consul.json\",\n          \"secrets/prometheus.json:/etc/grafana/provisioning/dashboards/prometheus.json\",\n          \"secrets/blackbox_exporter_http.json:/etc/grafana/provisioning/dashboards/blackbox_exporter_http.json\",\n          \"secrets/blackbox_exporter_icmp.json:/etc/grafana/provisioning/dashboards/blackbox_exporter_icmp.json\"\n        ]\n      }\n\n      artifact {\n        # Prometheus Node Exporter\n        source        = \"https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/node_exporter.json\"\n        destination   = \"secrets/\"\n      }\n\n      artifact {\n        # Docker cAdvisor\n        source        = \"https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/docker_cadvisor.json\"\n        destination   = \"secrets/\"\n      }\n\n      artifact {\n        # Nomad\n        source        = \"https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/nomad.json\"\n        destination   = \"secrets/\"\n      }\n\n      artifact {\n        # Consul\n        source        = \"https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/consul.json\"\n        destination   = \"secrets/\"\n      }\n\n      artifact {\n        # Prometheus\n        source        = \"https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/prometheus.json\"\n        destination   = \"secrets/\"\n      }\n\n      artifact {\n        # Prometheus Blackbox Exporter HTTP\n        source        = \"https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/blackbox_exporter_http.json\"\n        destination   = \"secrets/\"\n      }\n\n      artifact {\n        # Prometheus Blackbox Exporter ICMP\n        source        = \"https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/blackbox_exporter_icmp.json\"\n        destination   = \"secrets/\"\n      }\n\n      # The \"template\" stanza instructs Nomad to manage a template, such as\n      # a configuration file or script. This template can optionally pull data\n      # from Consul or Vault to populate runtime configuration data.\n      #\n      # For more information and examples on the \"template\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/template\n      #\n      template {\n        change_mode   = \"noop\"\n        change_signal = \"SIGINT\"\n        destination   = \"secrets/prometheus.yml\"\n        data          = \u003c\u003cEOH\napiVersion: 1\ndatasources:\n- name: Prometheus\n  type: prometheus\n  access: direct\n  orgId: 1\n  url: http://prometheus.service.consul:9090\n  basicAuth: false\n  isDefault: true\n  version: 1\n  editable: false\nEOH\n      }\n\n      template {\n        change_mode   = \"noop\"\n        change_signal = \"SIGINT\"\n        destination   = \"secrets/dashboards.yml\"\n        data          = \u003c\u003cEOH\napiVersion: 1\nproviders:\n- name: dashboards\n  type: file\n  disableDeletion: false\n  updateIntervalSeconds: 10\n  allowUiUpdates: false\n  options:\n    path: /etc/grafana/provisioning/dashboards\n    foldersFromFilesStructure: true\nEOH\n      }\n\n      template {\n        change_mode   = \"noop\"\n        change_signal = \"SIGINT\"\n        destination   = \"secrets/grafana.ini\"\n        data          = \u003c\u003cEOH\napp_mode = production\n\n[metrics]\nenabled = true\n\n[server]\nprotocol = http\nhttp_port = 3000\nroot_url = http://grafana.service.consul:3000\nenable_gzip = true\n;cert_file =\n;cert_key =\n\n[security]\nadmin_user = grafanauser\nadmin_password = Grafana1234\nsecret_key = SW2YcwTIb9zpOOhoPsMm\n\n[users]\nallow_sign_up = false\nallow_org_create = false\nauto_assign_org = true\nauto_assign_org_role = Viewer\ndefault_theme = dark\n\n[auth.basic]\nenabled = true\n\n[auth]\ndisable_login_form = false\ndisable_signout_menu = false\n\n[auth.anonymous]\nenabled = false\n\n[log]\nmode = console\nlevel = info\n\n[log.console]\nlevel = info\nformat = console\nEOH\n      }\n\n      # The service stanza instructs Nomad to register a service with Consul.\n      #\n      # For more information and examples on the \"task\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/service\n      #\n      service {\n        name              = \"grafana\"\n        port              = \"grafana\"\n        tags              = [ \"grafana${NOMAD_ALLOC_INDEX}\" ]\n        check {\n          name            = \"Grafana Check Live\"\n          type            = \"http\"\n          protocol        = \"http\"\n          tls_skip_verify = true\n          path            = \"/api/health\"\n          interval        = \"10s\"\n          timeout         = \"2s\"\n        }\n      }\n\n      # The \"resources\" stanza describes the requirements a task needs to\n      # execute. Resource requirements include memory, network, cpu, and more.\n      # This ensures the task will execute on a machine that contains enough\n      # resource capacity.\n      #\n      # For more information and examples on the \"resources\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/resources\n      #\n      resources {\n        cpu               = 1000\n        memory            = 2048\n        # The network stanza specifies the networking requirements for the task\n        # group, including the network mode and port allocations. When scheduling\n        # jobs in Nomad they are provisioned across your fleet of machines along\n        # with other jobs and services. Because you don't know in advance what host\n        # your job will be provisioned on, Nomad will provide your tasks with\n        # network configuration when they start up.\n        #\n        # For more information and examples on the \"template\" stanza, please see\n        # the online documentation at:\n        #\n        #     https://www.nomadproject.io/docs/job-specification/network\n        #\n        network {\n          port \"grafana\" {\n            static        = 3000\n          }\n        }\n      }\n    }\n  }\n}",
-            "template": "job \"${job_name}\" {\n  # The \"region\" parameter specifies the region in which to execute the job.\n  # If omitted, this inherits the default region name of \"global\".\n  # region = \"global\"\n  #\n  # The \"datacenters\" parameter specifies the list of datacenters which should\n  # be considered when placing this task. This must be provided.\n  datacenters         = \"${datacenters}\"\n\n  # The \"type\" parameter controls the type of job, which impacts the scheduler's\n  # decision on placement. This configuration is optional and defaults to\n  # \"service\". For a full list of job types and their differences, please see\n  # the online documentation.\n  #\n  # For more information, please see the online documentation at:\n  #\n  #     https://www.nomadproject.io/docs/jobspec/schedulers\n  #\n  type                = \"service\"\n\n  update {\n    # The \"max_parallel\" parameter specifies the maximum number of updates to\n    # perform in parallel. In this case, this specifies to update a single task\n    # at a time.\n    max_parallel      = 1\n\n    health_check      = \"checks\"\n\n    # The \"min_healthy_time\" parameter specifies the minimum time the allocation\n    # must be in the healthy state before it is marked as healthy and unblocks\n    # further allocations from being updated.\n    min_healthy_time  = \"10s\"\n\n    # The \"healthy_deadline\" parameter specifies the deadline in which the\n    # allocation must be marked as healthy after which the allocation is\n    # automatically transitioned to unhealthy. Transitioning to unhealthy will\n    # fail the deployment and potentially roll back the job if \"auto_revert\" is\n    # set to true.\n    healthy_deadline  = \"3m\"\n\n    # The \"progress_deadline\" parameter specifies the deadline in which an\n    # allocation must be marked as healthy. The deadline begins when the first\n    # allocation for the deployment is created and is reset whenever an allocation\n    # as part of the deployment transitions to a healthy state. If no allocation\n    # transitions to the healthy state before the progress deadline, the\n    # deployment is marked as failed.\n    progress_deadline = \"10m\"\n\n%{ if use_canary }\n    # The \"canary\" parameter specifies that changes to the job that would result\n    # in destructive updates should create the specified number of canaries\n    # without stopping any previous allocations. Once the operator determines the\n    # canaries are healthy, they can be promoted which unblocks a rolling update\n    # of the remaining allocations at a rate of \"max_parallel\".\n    #\n    # Further, setting \"canary\" equal to the count of the task group allows\n    # blue/green deployments. When the job is updated, a full set of the new\n    # version is deployed and upon promotion the old version is stopped.\n    canary            = 1\n\n    # Specifies if the job should auto-promote to the canary version when all\n    # canaries become healthy during a deployment. Defaults to false which means\n    # canaries must be manually updated with the nomad deployment promote\n    # command.\n    auto_promote      = true\n\n    # The \"auto_revert\" parameter specifies if the job should auto-revert to the\n    # last stable job on deployment failure. A job is marked as stable if all the\n    # allocations as part of its deployment were marked healthy.\n    auto_revert       = true\n%{ endif }\n  }\n\n  # The reschedule stanza specifies the group's rescheduling strategy. If\n  # specified at the job level, the configuration will apply to all groups\n  # within the job. If the reschedule stanza is present on both the job and the\n  # group, they are merged with the group stanza taking the highest precedence\n  # and then the job.\n  reschedule {\n    delay             = \"30s\"\n    delay_function    = \"constant\"\n    unlimited         = true\n  }\n\n  # The \"group\" stanza defines a series of tasks that should be co-located on\n  # the same Nomad client. Any task within a group will be placed on the same\n  # client.\n  #\n  # For more information and examples on the \"group\" stanza, please see\n  # the online documentation at:\n  #\n  #     https://www.nomadproject.io/docs/job-specification/group\n  #\n  group \"prod-group1-${service_name}\" {\n    # The \"count\" parameter specifies the number of the task groups that should\n    # be running under this group. This value must be non-negative and defaults\n    # to 1.\n    count             = ${group_count}\n\n    # The restart stanza configures a tasks's behavior on task failure. Restarts\n    # happen on the client that is running the task.\n    #\n    # https://www.nomadproject.io/docs/job-specification/restart\n    #\n    restart {\n      interval        = \"30m\"\n      attempts        = 40\n      delay           = \"15s\"\n      mode            = \"delay\"\n    }\n\n    # The constraint allows restricting the set of eligible nodes. Constraints\n    # may filter on attributes or client metadata.\n    #\n    # For more information and examples on the \"volume\" stanza, please see\n    # the online documentation at:\n    #\n    #     https://www.nomadproject.io/docs/job-specification/constraint\n    #\n    constraint {\n      attribute       = \"$${attr.cpu.arch}\"\n      operator        = \"!=\"\n      value           = \"arm64\"\n    }\n\n    # The \"task\" stanza creates an individual unit of work, such as a Docker\n    # container, web application, or batch processing.\n    #\n    # For more information and examples on the \"task\" stanza, please see\n    # the online documentation at:\n    #\n    #     https://www.nomadproject.io/docs/job-specification/task\n    #\n    task \"prod-task1-${service_name}\" {\n      # The \"driver\" parameter specifies the task driver that should be used to\n      # run the task.\n      driver          = \"docker\"\n\n      # The \"config\" stanza specifies the driver configuration, which is passed\n      # directly to the driver to start the task. The details of configurations\n      # are specific to each driver, so please see specific driver\n      # documentation for more information.\n      config {\n        image         = \"${image}\"\n        dns_servers   = [ \"172.17.0.1\" ]\n        volumes       = [\n          \"secrets/prometheus.yml:/etc/grafana/provisioning/datasources/prometheus.yml\",\n          \"secrets/dashboards.yml:/etc/grafana/provisioning/dashboards/dashboards.yml\",\n          \"secrets/grafana.ini:/etc/grafana/grafana.ini\",\n          \"secrets/node_exporter.json:/etc/grafana/provisioning/dashboards/node_exporter.json\",\n          \"secrets/docker_cadvisor.json:/etc/grafana/provisioning/dashboards/docker_cadvisor.json\",\n          \"secrets/nomad.json:/etc/grafana/provisioning/dashboards/nomad.json\",\n          \"secrets/consul.json:/etc/grafana/provisioning/dashboards/consul.json\",\n          \"secrets/prometheus.json:/etc/grafana/provisioning/dashboards/prometheus.json\",\n          \"secrets/blackbox_exporter_http.json:/etc/grafana/provisioning/dashboards/blackbox_exporter_http.json\",\n          \"secrets/blackbox_exporter_icmp.json:/etc/grafana/provisioning/dashboards/blackbox_exporter_icmp.json\"\n        ]\n      }\n\n      artifact {\n        # Prometheus Node Exporter\n        source        = \"https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/node_exporter.json\"\n        destination   = \"secrets/\"\n      }\n\n      artifact {\n        # Docker cAdvisor\n        source        = \"https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/docker_cadvisor.json\"\n        destination   = \"secrets/\"\n      }\n\n      artifact {\n        # Nomad\n        source        = \"https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/nomad.json\"\n        destination   = \"secrets/\"\n      }\n\n      artifact {\n        # Consul\n        source        = \"https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/consul.json\"\n        destination   = \"secrets/\"\n      }\n\n      artifact {\n        # Prometheus\n        source        = \"https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/prometheus.json\"\n        destination   = \"secrets/\"\n      }\n\n      artifact {\n        # Prometheus Blackbox Exporter HTTP\n        source        = \"https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/blackbox_exporter_http.json\"\n        destination   = \"secrets/\"\n      }\n\n      artifact {\n        # Prometheus Blackbox Exporter ICMP\n        source        = \"https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/blackbox_exporter_icmp.json\"\n        destination   = \"secrets/\"\n      }\n\n      # The \"template\" stanza instructs Nomad to manage a template, such as\n      # a configuration file or script. This template can optionally pull data\n      # from Consul or Vault to populate runtime configuration data.\n      #\n      # For more information and examples on the \"template\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/template\n      #\n      template {\n        change_mode   = \"noop\"\n        change_signal = \"SIGINT\"\n        destination   = \"secrets/prometheus.yml\"\n        data          = \u003c\u003cEOH\napiVersion: 1\ndatasources:\n- name: Prometheus\n  type: prometheus\n  access: direct\n  orgId: 1\n  url: http://prometheus.service.consul:9090\n  basicAuth: false\n  isDefault: true\n  version: 1\n  editable: false\nEOH\n      }\n\n      template {\n        change_mode   = \"noop\"\n        change_signal = \"SIGINT\"\n        destination   = \"secrets/dashboards.yml\"\n        data          = \u003c\u003cEOH\napiVersion: 1\nproviders:\n- name: dashboards\n  type: file\n  disableDeletion: false\n  updateIntervalSeconds: 10\n  allowUiUpdates: false\n  options:\n    path: /etc/grafana/provisioning/dashboards\n    foldersFromFilesStructure: true\nEOH\n      }\n\n      template {\n        change_mode   = \"noop\"\n        change_signal = \"SIGINT\"\n        destination   = \"secrets/grafana.ini\"\n        data          = \u003c\u003cEOH\napp_mode = production\n\n[metrics]\nenabled = true\n\n[server]\nprotocol = http\nhttp_port = ${port}\nroot_url = http://${service_name}.service.consul:${port}\nenable_gzip = true\n;cert_file =\n;cert_key =\n\n[security]\nadmin_user = grafanauser\nadmin_password = Grafana1234\nsecret_key = SW2YcwTIb9zpOOhoPsMm\n\n[users]\nallow_sign_up = false\nallow_org_create = false\nauto_assign_org = true\nauto_assign_org_role = Viewer\ndefault_theme = dark\n\n[auth.basic]\nenabled = true\n\n[auth]\ndisable_login_form = false\ndisable_signout_menu = false\n\n[auth.anonymous]\nenabled = false\n\n[log]\nmode = console\nlevel = info\n\n[log.console]\nlevel = info\nformat = console\nEOH\n      }\n\n      # The service stanza instructs Nomad to register a service with Consul.\n      #\n      # For more information and examples on the \"task\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/service\n      #\n      service {\n        name              = \"${service_name}\"\n        port              = \"${service_name}\"\n        tags              = [ \"${service_name}$${NOMAD_ALLOC_INDEX}\" ]\n        check {\n          name            = \"Grafana Check Live\"\n          type            = \"http\"\n          protocol        = \"http\"\n          tls_skip_verify = true\n          path            = \"/api/health\"\n          interval        = \"10s\"\n          timeout         = \"2s\"\n        }\n      }\n\n      # The \"resources\" stanza describes the requirements a task needs to\n      # execute. Resource requirements include memory, network, cpu, and more.\n      # This ensures the task will execute on a machine that contains enough\n      # resource capacity.\n      #\n      # For more information and examples on the \"resources\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/resources\n      #\n      resources {\n        cpu               = ${cpu}\n        memory            = ${mem}\n        # The network stanza specifies the networking requirements for the task\n        # group, including the network mode and port allocations. When scheduling\n        # jobs in Nomad they are provisioned across your fleet of machines along\n        # with other jobs and services. Because you don't know in advance what host\n        # your job will be provisioned on, Nomad will provide your tasks with\n        # network configuration when they start up.\n        #\n        # For more information and examples on the \"template\" stanza, please see\n        # the online documentation at:\n        #\n        #     https://www.nomadproject.io/docs/job-specification/network\n        #\n        network {\n          port \"${service_name}\" {\n            static        = ${port}\n          }\n        }\n      }\n    }\n  }\n}",
+            "id": "ce0ab0b08359da392c19c0f354b0f082630aa887ad51701986b5ce80b8aa39ea",
+            "rendered": "job \"prod-grafana\" {\n  # The \"region\" parameter specifies the region in which to execute the job.\n  # If omitted, this inherits the default region name of \"global\".\n  # region = \"global\"\n  #\n  # The \"datacenters\" parameter specifies the list of datacenters which should\n  # be considered when placing this task. This must be provided.\n  datacenters         = \"yul1\"\n\n  # The \"type\" parameter controls the type of job, which impacts the scheduler's\n  # decision on placement. This configuration is optional and defaults to\n  # \"service\". For a full list of job types and their differences, please see\n  # the online documentation.\n  #\n  # For more information, please see the online documentation at:\n  #\n  #     https://www.nomadproject.io/docs/jobspec/schedulers\n  #\n  type                = \"service\"\n\n  update {\n    # The \"max_parallel\" parameter specifies the maximum number of updates to\n    # perform in parallel. In this case, this specifies to update a single task\n    # at a time.\n    max_parallel      = 1\n\n    health_check      = \"checks\"\n\n    # The \"min_healthy_time\" parameter specifies the minimum time the allocation\n    # must be in the healthy state before it is marked as healthy and unblocks\n    # further allocations from being updated.\n    min_healthy_time  = \"10s\"\n\n    # The \"healthy_deadline\" parameter specifies the deadline in which the\n    # allocation must be marked as healthy after which the allocation is\n    # automatically transitioned to unhealthy. Transitioning to unhealthy will\n    # fail the deployment and potentially roll back the job if \"auto_revert\" is\n    # set to true.\n    healthy_deadline  = \"3m\"\n\n    # The \"progress_deadline\" parameter specifies the deadline in which an\n    # allocation must be marked as healthy. The deadline begins when the first\n    # allocation for the deployment is created and is reset whenever an allocation\n    # as part of the deployment transitions to a healthy state. If no allocation\n    # transitions to the healthy state before the progress deadline, the\n    # deployment is marked as failed.\n    progress_deadline = \"10m\"\n\n\n    # The \"canary\" parameter specifies that changes to the job that would result\n    # in destructive updates should create the specified number of canaries\n    # without stopping any previous allocations. Once the operator determines the\n    # canaries are healthy, they can be promoted which unblocks a rolling update\n    # of the remaining allocations at a rate of \"max_parallel\".\n    #\n    # Further, setting \"canary\" equal to the count of the task group allows\n    # blue/green deployments. When the job is updated, a full set of the new\n    # version is deployed and upon promotion the old version is stopped.\n    canary            = 1\n\n    # Specifies if the job should auto-promote to the canary version when all\n    # canaries become healthy during a deployment. Defaults to false which means\n    # canaries must be manually updated with the nomad deployment promote\n    # command.\n    auto_promote      = true\n\n    # The \"auto_revert\" parameter specifies if the job should auto-revert to the\n    # last stable job on deployment failure. A job is marked as stable if all the\n    # allocations as part of its deployment were marked healthy.\n    auto_revert       = true\n\n  }\n\n  # The reschedule stanza specifies the group's rescheduling strategy. If\n  # specified at the job level, the configuration will apply to all groups\n  # within the job. If the reschedule stanza is present on both the job and the\n  # group, they are merged with the group stanza taking the highest precedence\n  # and then the job.\n  reschedule {\n    delay             = \"30s\"\n    delay_function    = \"constant\"\n    unlimited         = true\n  }\n\n  # The \"group\" stanza defines a series of tasks that should be co-located on\n  # the same Nomad client. Any task within a group will be placed on the same\n  # client.\n  #\n  # For more information and examples on the \"group\" stanza, please see\n  # the online documentation at:\n  #\n  #     https://www.nomadproject.io/docs/job-specification/group\n  #\n  group \"prod-group1-grafana\" {\n    # The \"count\" parameter specifies the number of the task groups that should\n    # be running under this group. This value must be non-negative and defaults\n    # to 1.\n    count             = 1\n\n    # The restart stanza configures a tasks's behavior on task failure. Restarts\n    # happen on the client that is running the task.\n    #\n    # https://www.nomadproject.io/docs/job-specification/restart\n    #\n    restart {\n      interval        = \"30m\"\n      attempts        = 40\n      delay           = \"15s\"\n      mode            = \"delay\"\n    }\n\n    # The constraint allows restricting the set of eligible nodes. Constraints\n    # may filter on attributes or client metadata.\n    #\n    # For more information and examples on the \"volume\" stanza, please see\n    # the online documentation at:\n    #\n    #     https://www.nomadproject.io/docs/job-specification/constraint\n    #\n    constraint {\n      attribute       = \"${attr.cpu.arch}\"\n      operator        = \"!=\"\n      value           = \"arm64\"\n    }\n\n    constraint {\n      attribute      = \"${node.class}\"\n      value          = \"builder\"\n    }\n\n    # The \"task\" stanza creates an individual unit of work, such as a Docker\n    # container, web application, or batch processing.\n    #\n    # For more information and examples on the \"task\" stanza, please see\n    # the online documentation at:\n    #\n    #     https://www.nomadproject.io/docs/job-specification/task\n    #\n    task \"prod-task1-grafana\" {\n      # The \"driver\" parameter specifies the task driver that should be used to\n      # run the task.\n      driver          = \"docker\"\n\n      # The \"config\" stanza specifies the driver configuration, which is passed\n      # directly to the driver to start the task. The details of configurations\n      # are specific to each driver, so please see specific driver\n      # documentation for more information.\n      config {\n        image         = \"grafana/grafana:7.3.7\"\n        dns_servers   = [ \"172.17.0.1\" ]\n        volumes       = [\n          \"secrets/prometheus.yml:/etc/grafana/provisioning/datasources/prometheus.yml\",\n          \"secrets/dashboards.yml:/etc/grafana/provisioning/dashboards/dashboards.yml\",\n          \"secrets/grafana.ini:/etc/grafana/grafana.ini\",\n          \"secrets/node_exporter.json:/etc/grafana/provisioning/dashboards/node_exporter.json\",\n          \"secrets/nomad.json:/etc/grafana/provisioning/dashboards/nomad.json\",\n          \"secrets/consul.json:/etc/grafana/provisioning/dashboards/consul.json\",\n          \"secrets/prometheus.json:/etc/grafana/provisioning/dashboards/prometheus.json\",\n          \"secrets/blackbox_exporter_http.json:/etc/grafana/provisioning/dashboards/blackbox_exporter_http.json\",\n          \"secrets/blackbox_exporter_icmp.json:/etc/grafana/provisioning/dashboards/blackbox_exporter_icmp.json\"\n        ]\n      }\n\n      artifact {\n        # Prometheus Node Exporter\n        source        = \"https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/node_exporter.json\"\n        destination   = \"secrets/\"\n      }\n\n      artifact {\n        # Nomad\n        source        = \"https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/nomad.json\"\n        destination   = \"secrets/\"\n      }\n\n      artifact {\n        # Consul\n        source        = \"https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/consul.json\"\n        destination   = \"secrets/\"\n      }\n\n      artifact {\n        # Prometheus\n        source        = \"https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/prometheus.json\"\n        destination   = \"secrets/\"\n      }\n\n      artifact {\n        # Prometheus Blackbox Exporter HTTP\n        source        = \"https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/blackbox_exporter_http.json\"\n        destination   = \"secrets/\"\n      }\n\n      artifact {\n        # Prometheus Blackbox Exporter ICMP\n        source        = \"https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/blackbox_exporter_icmp.json\"\n        destination   = \"secrets/\"\n      }\n\n      # The \"template\" stanza instructs Nomad to manage a template, such as\n      # a configuration file or script. This template can optionally pull data\n      # from Consul or Vault to populate runtime configuration data.\n      #\n      # For more information and examples on the \"template\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/template\n      #\n      template {\n        change_mode   = \"noop\"\n        change_signal = \"SIGINT\"\n        destination   = \"secrets/prometheus.yml\"\n        data          = \u003c\u003cEOH\napiVersion: 1\ndatasources:\n- name: Prometheus\n  type: prometheus\n  access: direct\n  orgId: 1\n  url: http://prometheus.service.consul:9090\n  basicAuth: false\n  isDefault: true\n  version: 1\n  editable: false\nEOH\n      }\n\n      template {\n        change_mode   = \"noop\"\n        change_signal = \"SIGINT\"\n        destination   = \"secrets/dashboards.yml\"\n        data          = \u003c\u003cEOH\napiVersion: 1\nproviders:\n- name: dashboards\n  type: file\n  disableDeletion: false\n  updateIntervalSeconds: 10\n  allowUiUpdates: false\n  options:\n    path: /etc/grafana/provisioning/dashboards\n    foldersFromFilesStructure: true\nEOH\n      }\n\n      template {\n        change_mode   = \"noop\"\n        change_signal = \"SIGINT\"\n        destination   = \"secrets/grafana.ini\"\n        data          = \u003c\u003cEOH\napp_mode = production\n\n[metrics]\nenabled = true\n\n[server]\nprotocol = http\nhttp_port = 3000\nroot_url = http://grafana.service.consul:3000\nenable_gzip = true\n;cert_file =\n;cert_key =\n\n[security]\nadmin_user = grafanauser\nadmin_password = Grafana1234\nsecret_key = SW2YcwTIb9zpOOhoPsMm\n\n[users]\nallow_sign_up = false\nallow_org_create = false\nauto_assign_org = true\nauto_assign_org_role = Viewer\ndefault_theme = dark\n\n[auth.basic]\nenabled = true\n\n[auth]\ndisable_login_form = false\ndisable_signout_menu = false\n\n[auth.anonymous]\nenabled = false\n\n[log]\nmode = console\nlevel = info\n\n[log.console]\nlevel = info\nformat = console\nEOH\n      }\n\n      # The service stanza instructs Nomad to register a service with Consul.\n      #\n      # For more information and examples on the \"task\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/service\n      #\n      service {\n        name              = \"grafana\"\n        port              = \"grafana\"\n        tags              = [ \"grafana${NOMAD_ALLOC_INDEX}\" ]\n        check {\n          name            = \"Grafana Check Live\"\n          type            = \"http\"\n          protocol        = \"http\"\n          tls_skip_verify = true\n          path            = \"/api/health\"\n          interval        = \"10s\"\n          timeout         = \"2s\"\n        }\n      }\n\n      # The \"resources\" stanza describes the requirements a task needs to\n      # execute. Resource requirements include memory, network, cpu, and more.\n      # This ensures the task will execute on a machine that contains enough\n      # resource capacity.\n      #\n      # For more information and examples on the \"resources\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/resources\n      #\n      resources {\n        cpu               = 1000\n        memory            = 2048\n        # The network stanza specifies the networking requirements for the task\n        # group, including the network mode and port allocations. When scheduling\n        # jobs in Nomad they are provisioned across your fleet of machines along\n        # with other jobs and services. Because you don't know in advance what host\n        # your job will be provisioned on, Nomad will provide your tasks with\n        # network configuration when they start up.\n        #\n        # For more information and examples on the \"template\" stanza, please see\n        # the online documentation at:\n        #\n        #     https://www.nomadproject.io/docs/job-specification/network\n        #\n        network {\n          port \"grafana\" {\n            static        = 3000\n          }\n        }\n      }\n    }\n  }\n}",
+            "template": "job \"${job_name}\" {\n  # The \"region\" parameter specifies the region in which to execute the job.\n  # If omitted, this inherits the default region name of \"global\".\n  # region = \"global\"\n  #\n  # The \"datacenters\" parameter specifies the list of datacenters which should\n  # be considered when placing this task. This must be provided.\n  datacenters         = \"${datacenters}\"\n\n  # The \"type\" parameter controls the type of job, which impacts the scheduler's\n  # decision on placement. This configuration is optional and defaults to\n  # \"service\". For a full list of job types and their differences, please see\n  # the online documentation.\n  #\n  # For more information, please see the online documentation at:\n  #\n  #     https://www.nomadproject.io/docs/jobspec/schedulers\n  #\n  type                = \"service\"\n\n  update {\n    # The \"max_parallel\" parameter specifies the maximum number of updates to\n    # perform in parallel. In this case, this specifies to update a single task\n    # at a time.\n    max_parallel      = 1\n\n    health_check      = \"checks\"\n\n    # The \"min_healthy_time\" parameter specifies the minimum time the allocation\n    # must be in the healthy state before it is marked as healthy and unblocks\n    # further allocations from being updated.\n    min_healthy_time  = \"10s\"\n\n    # The \"healthy_deadline\" parameter specifies the deadline in which the\n    # allocation must be marked as healthy after which the allocation is\n    # automatically transitioned to unhealthy. Transitioning to unhealthy will\n    # fail the deployment and potentially roll back the job if \"auto_revert\" is\n    # set to true.\n    healthy_deadline  = \"3m\"\n\n    # The \"progress_deadline\" parameter specifies the deadline in which an\n    # allocation must be marked as healthy. The deadline begins when the first\n    # allocation for the deployment is created and is reset whenever an allocation\n    # as part of the deployment transitions to a healthy state. If no allocation\n    # transitions to the healthy state before the progress deadline, the\n    # deployment is marked as failed.\n    progress_deadline = \"10m\"\n\n%{ if use_canary }\n    # The \"canary\" parameter specifies that changes to the job that would result\n    # in destructive updates should create the specified number of canaries\n    # without stopping any previous allocations. Once the operator determines the\n    # canaries are healthy, they can be promoted which unblocks a rolling update\n    # of the remaining allocations at a rate of \"max_parallel\".\n    #\n    # Further, setting \"canary\" equal to the count of the task group allows\n    # blue/green deployments. When the job is updated, a full set of the new\n    # version is deployed and upon promotion the old version is stopped.\n    canary            = 1\n\n    # Specifies if the job should auto-promote to the canary version when all\n    # canaries become healthy during a deployment. Defaults to false which means\n    # canaries must be manually updated with the nomad deployment promote\n    # command.\n    auto_promote      = true\n\n    # The \"auto_revert\" parameter specifies if the job should auto-revert to the\n    # last stable job on deployment failure. A job is marked as stable if all the\n    # allocations as part of its deployment were marked healthy.\n    auto_revert       = true\n%{ endif }\n  }\n\n  # The reschedule stanza specifies the group's rescheduling strategy. If\n  # specified at the job level, the configuration will apply to all groups\n  # within the job. If the reschedule stanza is present on both the job and the\n  # group, they are merged with the group stanza taking the highest precedence\n  # and then the job.\n  reschedule {\n    delay             = \"30s\"\n    delay_function    = \"constant\"\n    unlimited         = true\n  }\n\n  # The \"group\" stanza defines a series of tasks that should be co-located on\n  # the same Nomad client. Any task within a group will be placed on the same\n  # client.\n  #\n  # For more information and examples on the \"group\" stanza, please see\n  # the online documentation at:\n  #\n  #     https://www.nomadproject.io/docs/job-specification/group\n  #\n  group \"prod-group1-${service_name}\" {\n    # The \"count\" parameter specifies the number of the task groups that should\n    # be running under this group. This value must be non-negative and defaults\n    # to 1.\n    count             = ${group_count}\n\n    # The restart stanza configures a tasks's behavior on task failure. Restarts\n    # happen on the client that is running the task.\n    #\n    # https://www.nomadproject.io/docs/job-specification/restart\n    #\n    restart {\n      interval        = \"30m\"\n      attempts        = 40\n      delay           = \"15s\"\n      mode            = \"delay\"\n    }\n\n    # The constraint allows restricting the set of eligible nodes. Constraints\n    # may filter on attributes or client metadata.\n    #\n    # For more information and examples on the \"volume\" stanza, please see\n    # the online documentation at:\n    #\n    #     https://www.nomadproject.io/docs/job-specification/constraint\n    #\n    constraint {\n      attribute       = \"$${attr.cpu.arch}\"\n      operator        = \"!=\"\n      value           = \"arm64\"\n    }\n\n    constraint {\n      attribute      = \"$${node.class}\"\n      value          = \"builder\"\n    }\n\n    # The \"task\" stanza creates an individual unit of work, such as a Docker\n    # container, web application, or batch processing.\n    #\n    # For more information and examples on the \"task\" stanza, please see\n    # the online documentation at:\n    #\n    #     https://www.nomadproject.io/docs/job-specification/task\n    #\n    task \"prod-task1-${service_name}\" {\n      # The \"driver\" parameter specifies the task driver that should be used to\n      # run the task.\n      driver          = \"docker\"\n\n      # The \"config\" stanza specifies the driver configuration, which is passed\n      # directly to the driver to start the task. The details of configurations\n      # are specific to each driver, so please see specific driver\n      # documentation for more information.\n      config {\n        image         = \"${image}\"\n        dns_servers   = [ \"172.17.0.1\" ]\n        volumes       = [\n          \"secrets/prometheus.yml:/etc/grafana/provisioning/datasources/prometheus.yml\",\n          \"secrets/dashboards.yml:/etc/grafana/provisioning/dashboards/dashboards.yml\",\n          \"secrets/grafana.ini:/etc/grafana/grafana.ini\",\n          \"secrets/node_exporter.json:/etc/grafana/provisioning/dashboards/node_exporter.json\",\n          \"secrets/nomad.json:/etc/grafana/provisioning/dashboards/nomad.json\",\n          \"secrets/consul.json:/etc/grafana/provisioning/dashboards/consul.json\",\n          \"secrets/prometheus.json:/etc/grafana/provisioning/dashboards/prometheus.json\",\n          \"secrets/blackbox_exporter_http.json:/etc/grafana/provisioning/dashboards/blackbox_exporter_http.json\",\n          \"secrets/blackbox_exporter_icmp.json:/etc/grafana/provisioning/dashboards/blackbox_exporter_icmp.json\"\n        ]\n      }\n\n      artifact {\n        # Prometheus Node Exporter\n        source        = \"https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/node_exporter.json\"\n        destination   = \"secrets/\"\n      }\n\n      artifact {\n        # Nomad\n        source        = \"https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/nomad.json\"\n        destination   = \"secrets/\"\n      }\n\n      artifact {\n        # Consul\n        source        = \"https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/consul.json\"\n        destination   = \"secrets/\"\n      }\n\n      artifact {\n        # Prometheus\n        source        = \"https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/prometheus.json\"\n        destination   = \"secrets/\"\n      }\n\n      artifact {\n        # Prometheus Blackbox Exporter HTTP\n        source        = \"https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/blackbox_exporter_http.json\"\n        destination   = \"secrets/\"\n      }\n\n      artifact {\n        # Prometheus Blackbox Exporter ICMP\n        source        = \"https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/blackbox_exporter_icmp.json\"\n        destination   = \"secrets/\"\n      }\n\n      # The \"template\" stanza instructs Nomad to manage a template, such as\n      # a configuration file or script. This template can optionally pull data\n      # from Consul or Vault to populate runtime configuration data.\n      #\n      # For more information and examples on the \"template\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/template\n      #\n      template {\n        change_mode   = \"noop\"\n        change_signal = \"SIGINT\"\n        destination   = \"secrets/prometheus.yml\"\n        data          = \u003c\u003cEOH\napiVersion: 1\ndatasources:\n- name: Prometheus\n  type: prometheus\n  access: direct\n  orgId: 1\n  url: http://prometheus.service.consul:9090\n  basicAuth: false\n  isDefault: true\n  version: 1\n  editable: false\nEOH\n      }\n\n      template {\n        change_mode   = \"noop\"\n        change_signal = \"SIGINT\"\n        destination   = \"secrets/dashboards.yml\"\n        data          = \u003c\u003cEOH\napiVersion: 1\nproviders:\n- name: dashboards\n  type: file\n  disableDeletion: false\n  updateIntervalSeconds: 10\n  allowUiUpdates: false\n  options:\n    path: /etc/grafana/provisioning/dashboards\n    foldersFromFilesStructure: true\nEOH\n      }\n\n      template {\n        change_mode   = \"noop\"\n        change_signal = \"SIGINT\"\n        destination   = \"secrets/grafana.ini\"\n        data          = \u003c\u003cEOH\napp_mode = production\n\n[metrics]\nenabled = true\n\n[server]\nprotocol = http\nhttp_port = ${port}\nroot_url = http://${service_name}.service.consul:${port}\nenable_gzip = true\n;cert_file =\n;cert_key =\n\n[security]\nadmin_user = grafanauser\nadmin_password = Grafana1234\nsecret_key = SW2YcwTIb9zpOOhoPsMm\n\n[users]\nallow_sign_up = false\nallow_org_create = false\nauto_assign_org = true\nauto_assign_org_role = Viewer\ndefault_theme = dark\n\n[auth.basic]\nenabled = true\n\n[auth]\ndisable_login_form = false\ndisable_signout_menu = false\n\n[auth.anonymous]\nenabled = false\n\n[log]\nmode = console\nlevel = info\n\n[log.console]\nlevel = info\nformat = console\nEOH\n      }\n\n      # The service stanza instructs Nomad to register a service with Consul.\n      #\n      # For more information and examples on the \"task\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/service\n      #\n      service {\n        name              = \"${service_name}\"\n        port              = \"${service_name}\"\n        tags              = [ \"${service_name}$${NOMAD_ALLOC_INDEX}\" ]\n        check {\n          name            = \"Grafana Check Live\"\n          type            = \"http\"\n          protocol        = \"http\"\n          tls_skip_verify = true\n          path            = \"/api/health\"\n          interval        = \"10s\"\n          timeout         = \"2s\"\n        }\n      }\n\n      # The \"resources\" stanza describes the requirements a task needs to\n      # execute. Resource requirements include memory, network, cpu, and more.\n      # This ensures the task will execute on a machine that contains enough\n      # resource capacity.\n      #\n      # For more information and examples on the \"resources\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/resources\n      #\n      resources {\n        cpu               = ${cpu}\n        memory            = ${mem}\n        # The network stanza specifies the networking requirements for the task\n        # group, including the network mode and port allocations. When scheduling\n        # jobs in Nomad they are provisioned across your fleet of machines along\n        # with other jobs and services. Because you don't know in advance what host\n        # your job will be provisioned on, Nomad will provide your tasks with\n        # network configuration when they start up.\n        #\n        # For more information and examples on the \"template\" stanza, please see\n        # the online documentation at:\n        #\n        #     https://www.nomadproject.io/docs/job-specification/network\n        #\n        network {\n          port \"${service_name}\" {\n            static        = ${port}\n          }\n        }\n      }\n    }\n  }\n}",
             "vars": {
               "cpu": "1000",
               "datacenters": "yul1",
@@ -141,20 +142,21 @@
           "schema_version": 0,
           "attributes": {
             "allocation_ids": [
-              "01d60c86-d59b-83ac-78c8-a903ac63816e"
+              "218d0f2c-ecf3-30bd-edc0-eaa3a4d8b384",
+              "18869dde-8c4e-3aa0-1baa-ddcb5c6dc5bc"
             ],
             "datacenters": [
               "yul1"
             ],
-            "deployment_id": "6d9fa6f6-7f84-4765-9488-7d92f32ec4df",
+            "deployment_id": "9bd732cd-ec36-7f96-1b82-24e60b51c048",
             "deployment_status": "successful",
             "deregister_on_destroy": true,
             "deregister_on_id_change": true,
             "detach": false,
             "id": "prod-grafana",
-            "jobspec": "job \"prod-grafana\" {\n  # The \"region\" parameter specifies the region in which to execute the job.\n  # If omitted, this inherits the default region name of \"global\".\n  # region = \"global\"\n  #\n  # The \"datacenters\" parameter specifies the list of datacenters which should\n  # be considered when placing this task. This must be provided.\n  datacenters         = \"yul1\"\n\n  # The \"type\" parameter controls the type of job, which impacts the scheduler's\n  # decision on placement. This configuration is optional and defaults to\n  # \"service\". For a full list of job types and their differences, please see\n  # the online documentation.\n  #\n  # For more information, please see the online documentation at:\n  #\n  #     https://www.nomadproject.io/docs/jobspec/schedulers\n  #\n  type                = \"service\"\n\n  update {\n    # The \"max_parallel\" parameter specifies the maximum number of updates to\n    # perform in parallel. In this case, this specifies to update a single task\n    # at a time.\n    max_parallel      = 1\n\n    health_check      = \"checks\"\n\n    # The \"min_healthy_time\" parameter specifies the minimum time the allocation\n    # must be in the healthy state before it is marked as healthy and unblocks\n    # further allocations from being updated.\n    min_healthy_time  = \"10s\"\n\n    # The \"healthy_deadline\" parameter specifies the deadline in which the\n    # allocation must be marked as healthy after which the allocation is\n    # automatically transitioned to unhealthy. Transitioning to unhealthy will\n    # fail the deployment and potentially roll back the job if \"auto_revert\" is\n    # set to true.\n    healthy_deadline  = \"3m\"\n\n    # The \"progress_deadline\" parameter specifies the deadline in which an\n    # allocation must be marked as healthy. The deadline begins when the first\n    # allocation for the deployment is created and is reset whenever an allocation\n    # as part of the deployment transitions to a healthy state. If no allocation\n    # transitions to the healthy state before the progress deadline, the\n    # deployment is marked as failed.\n    progress_deadline = \"10m\"\n\n\n    # The \"canary\" parameter specifies that changes to the job that would result\n    # in destructive updates should create the specified number of canaries\n    # without stopping any previous allocations. Once the operator determines the\n    # canaries are healthy, they can be promoted which unblocks a rolling update\n    # of the remaining allocations at a rate of \"max_parallel\".\n    #\n    # Further, setting \"canary\" equal to the count of the task group allows\n    # blue/green deployments. When the job is updated, a full set of the new\n    # version is deployed and upon promotion the old version is stopped.\n    canary            = 1\n\n    # Specifies if the job should auto-promote to the canary version when all\n    # canaries become healthy during a deployment. Defaults to false which means\n    # canaries must be manually updated with the nomad deployment promote\n    # command.\n    auto_promote      = true\n\n    # The \"auto_revert\" parameter specifies if the job should auto-revert to the\n    # last stable job on deployment failure. A job is marked as stable if all the\n    # allocations as part of its deployment were marked healthy.\n    auto_revert       = true\n\n  }\n\n  # The reschedule stanza specifies the group's rescheduling strategy. If\n  # specified at the job level, the configuration will apply to all groups\n  # within the job. If the reschedule stanza is present on both the job and the\n  # group, they are merged with the group stanza taking the highest precedence\n  # and then the job.\n  reschedule {\n    delay             = \"30s\"\n    delay_function    = \"constant\"\n    unlimited         = true\n  }\n\n  # The \"group\" stanza defines a series of tasks that should be co-located on\n  # the same Nomad client. Any task within a group will be placed on the same\n  # client.\n  #\n  # For more information and examples on the \"group\" stanza, please see\n  # the online documentation at:\n  #\n  #     https://www.nomadproject.io/docs/job-specification/group\n  #\n  group \"prod-group1-grafana\" {\n    # The \"count\" parameter specifies the number of the task groups that should\n    # be running under this group. This value must be non-negative and defaults\n    # to 1.\n    count             = 1\n\n    # The restart stanza configures a tasks's behavior on task failure. Restarts\n    # happen on the client that is running the task.\n    #\n    # https://www.nomadproject.io/docs/job-specification/restart\n    #\n    restart {\n      interval        = \"30m\"\n      attempts        = 40\n      delay           = \"15s\"\n      mode            = \"delay\"\n    }\n\n    # The constraint allows restricting the set of eligible nodes. Constraints\n    # may filter on attributes or client metadata.\n    #\n    # For more information and examples on the \"volume\" stanza, please see\n    # the online documentation at:\n    #\n    #     https://www.nomadproject.io/docs/job-specification/constraint\n    #\n    constraint {\n      attribute       = \"${attr.cpu.arch}\"\n      operator        = \"!=\"\n      value           = \"arm64\"\n    }\n\n    # The \"task\" stanza creates an individual unit of work, such as a Docker\n    # container, web application, or batch processing.\n    #\n    # For more information and examples on the \"task\" stanza, please see\n    # the online documentation at:\n    #\n    #     https://www.nomadproject.io/docs/job-specification/task\n    #\n    task \"prod-task1-grafana\" {\n      # The \"driver\" parameter specifies the task driver that should be used to\n      # run the task.\n      driver          = \"docker\"\n\n      # The \"config\" stanza specifies the driver configuration, which is passed\n      # directly to the driver to start the task. The details of configurations\n      # are specific to each driver, so please see specific driver\n      # documentation for more information.\n      config {\n        image         = \"grafana/grafana:7.3.7\"\n        dns_servers   = [ \"172.17.0.1\" ]\n        volumes       = [\n          \"secrets/prometheus.yml:/etc/grafana/provisioning/datasources/prometheus.yml\",\n          \"secrets/dashboards.yml:/etc/grafana/provisioning/dashboards/dashboards.yml\",\n          \"secrets/grafana.ini:/etc/grafana/grafana.ini\",\n          \"secrets/node_exporter.json:/etc/grafana/provisioning/dashboards/node_exporter.json\",\n          \"secrets/docker_cadvisor.json:/etc/grafana/provisioning/dashboards/docker_cadvisor.json\",\n          \"secrets/nomad.json:/etc/grafana/provisioning/dashboards/nomad.json\",\n          \"secrets/consul.json:/etc/grafana/provisioning/dashboards/consul.json\",\n          \"secrets/prometheus.json:/etc/grafana/provisioning/dashboards/prometheus.json\",\n          \"secrets/blackbox_exporter_http.json:/etc/grafana/provisioning/dashboards/blackbox_exporter_http.json\",\n          \"secrets/blackbox_exporter_icmp.json:/etc/grafana/provisioning/dashboards/blackbox_exporter_icmp.json\"\n        ]\n      }\n\n      artifact {\n        # Prometheus Node Exporter\n        source        = \"https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/node_exporter.json\"\n        destination   = \"secrets/\"\n      }\n\n      artifact {\n        # Docker cAdvisor\n        source        = \"https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/docker_cadvisor.json\"\n        destination   = \"secrets/\"\n      }\n\n      artifact {\n        # Nomad\n        source        = \"https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/nomad.json\"\n        destination   = \"secrets/\"\n      }\n\n      artifact {\n        # Consul\n        source        = \"https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/consul.json\"\n        destination   = \"secrets/\"\n      }\n\n      artifact {\n        # Prometheus\n        source        = \"https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/prometheus.json\"\n        destination   = \"secrets/\"\n      }\n\n      artifact {\n        # Prometheus Blackbox Exporter HTTP\n        source        = \"https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/blackbox_exporter_http.json\"\n        destination   = \"secrets/\"\n      }\n\n      artifact {\n        # Prometheus Blackbox Exporter ICMP\n        source        = \"https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/blackbox_exporter_icmp.json\"\n        destination   = \"secrets/\"\n      }\n\n      # The \"template\" stanza instructs Nomad to manage a template, such as\n      # a configuration file or script. This template can optionally pull data\n      # from Consul or Vault to populate runtime configuration data.\n      #\n      # For more information and examples on the \"template\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/template\n      #\n      template {\n        change_mode   = \"noop\"\n        change_signal = \"SIGINT\"\n        destination   = \"secrets/prometheus.yml\"\n        data          = \u003c\u003cEOH\napiVersion: 1\ndatasources:\n- name: Prometheus\n  type: prometheus\n  access: direct\n  orgId: 1\n  url: http://prometheus.service.consul:9090\n  basicAuth: false\n  isDefault: true\n  version: 1\n  editable: false\nEOH\n      }\n\n      template {\n        change_mode   = \"noop\"\n        change_signal = \"SIGINT\"\n        destination   = \"secrets/dashboards.yml\"\n        data          = \u003c\u003cEOH\napiVersion: 1\nproviders:\n- name: dashboards\n  type: file\n  disableDeletion: false\n  updateIntervalSeconds: 10\n  allowUiUpdates: false\n  options:\n    path: /etc/grafana/provisioning/dashboards\n    foldersFromFilesStructure: true\nEOH\n      }\n\n      template {\n        change_mode   = \"noop\"\n        change_signal = \"SIGINT\"\n        destination   = \"secrets/grafana.ini\"\n        data          = \u003c\u003cEOH\napp_mode = production\n\n[metrics]\nenabled = true\n\n[server]\nprotocol = http\nhttp_port = 3000\nroot_url = http://grafana.service.consul:3000\nenable_gzip = true\n;cert_file =\n;cert_key =\n\n[security]\nadmin_user = grafanauser\nadmin_password = Grafana1234\nsecret_key = SW2YcwTIb9zpOOhoPsMm\n\n[users]\nallow_sign_up = false\nallow_org_create = false\nauto_assign_org = true\nauto_assign_org_role = Viewer\ndefault_theme = dark\n\n[auth.basic]\nenabled = true\n\n[auth]\ndisable_login_form = false\ndisable_signout_menu = false\n\n[auth.anonymous]\nenabled = false\n\n[log]\nmode = console\nlevel = info\n\n[log.console]\nlevel = info\nformat = console\nEOH\n      }\n\n      # The service stanza instructs Nomad to register a service with Consul.\n      #\n      # For more information and examples on the \"task\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/service\n      #\n      service {\n        name              = \"grafana\"\n        port              = \"grafana\"\n        tags              = [ \"grafana${NOMAD_ALLOC_INDEX}\" ]\n        check {\n          name            = \"Grafana Check Live\"\n          type            = \"http\"\n          protocol        = \"http\"\n          tls_skip_verify = true\n          path            = \"/api/health\"\n          interval        = \"10s\"\n          timeout         = \"2s\"\n        }\n      }\n\n      # The \"resources\" stanza describes the requirements a task needs to\n      # execute. Resource requirements include memory, network, cpu, and more.\n      # This ensures the task will execute on a machine that contains enough\n      # resource capacity.\n      #\n      # For more information and examples on the \"resources\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/resources\n      #\n      resources {\n        cpu               = 1000\n        memory            = 2048\n        # The network stanza specifies the networking requirements for the task\n        # group, including the network mode and port allocations. When scheduling\n        # jobs in Nomad they are provisioned across your fleet of machines along\n        # with other jobs and services. Because you don't know in advance what host\n        # your job will be provisioned on, Nomad will provide your tasks with\n        # network configuration when they start up.\n        #\n        # For more information and examples on the \"template\" stanza, please see\n        # the online documentation at:\n        #\n        #     https://www.nomadproject.io/docs/job-specification/network\n        #\n        network {\n          port \"grafana\" {\n            static        = 3000\n          }\n        }\n      }\n    }\n  }\n}",
+            "jobspec": "job \"prod-grafana\" {\n  # The \"region\" parameter specifies the region in which to execute the job.\n  # If omitted, this inherits the default region name of \"global\".\n  # region = \"global\"\n  #\n  # The \"datacenters\" parameter specifies the list of datacenters which should\n  # be considered when placing this task. This must be provided.\n  datacenters         = \"yul1\"\n\n  # The \"type\" parameter controls the type of job, which impacts the scheduler's\n  # decision on placement. This configuration is optional and defaults to\n  # \"service\". For a full list of job types and their differences, please see\n  # the online documentation.\n  #\n  # For more information, please see the online documentation at:\n  #\n  #     https://www.nomadproject.io/docs/jobspec/schedulers\n  #\n  type                = \"service\"\n\n  update {\n    # The \"max_parallel\" parameter specifies the maximum number of updates to\n    # perform in parallel. In this case, this specifies to update a single task\n    # at a time.\n    max_parallel      = 1\n\n    health_check      = \"checks\"\n\n    # The \"min_healthy_time\" parameter specifies the minimum time the allocation\n    # must be in the healthy state before it is marked as healthy and unblocks\n    # further allocations from being updated.\n    min_healthy_time  = \"10s\"\n\n    # The \"healthy_deadline\" parameter specifies the deadline in which the\n    # allocation must be marked as healthy after which the allocation is\n    # automatically transitioned to unhealthy. Transitioning to unhealthy will\n    # fail the deployment and potentially roll back the job if \"auto_revert\" is\n    # set to true.\n    healthy_deadline  = \"3m\"\n\n    # The \"progress_deadline\" parameter specifies the deadline in which an\n    # allocation must be marked as healthy. The deadline begins when the first\n    # allocation for the deployment is created and is reset whenever an allocation\n    # as part of the deployment transitions to a healthy state. If no allocation\n    # transitions to the healthy state before the progress deadline, the\n    # deployment is marked as failed.\n    progress_deadline = \"10m\"\n\n\n    # The \"canary\" parameter specifies that changes to the job that would result\n    # in destructive updates should create the specified number of canaries\n    # without stopping any previous allocations. Once the operator determines the\n    # canaries are healthy, they can be promoted which unblocks a rolling update\n    # of the remaining allocations at a rate of \"max_parallel\".\n    #\n    # Further, setting \"canary\" equal to the count of the task group allows\n    # blue/green deployments. When the job is updated, a full set of the new\n    # version is deployed and upon promotion the old version is stopped.\n    canary            = 1\n\n    # Specifies if the job should auto-promote to the canary version when all\n    # canaries become healthy during a deployment. Defaults to false which means\n    # canaries must be manually updated with the nomad deployment promote\n    # command.\n    auto_promote      = true\n\n    # The \"auto_revert\" parameter specifies if the job should auto-revert to the\n    # last stable job on deployment failure. A job is marked as stable if all the\n    # allocations as part of its deployment were marked healthy.\n    auto_revert       = true\n\n  }\n\n  # The reschedule stanza specifies the group's rescheduling strategy. If\n  # specified at the job level, the configuration will apply to all groups\n  # within the job. If the reschedule stanza is present on both the job and the\n  # group, they are merged with the group stanza taking the highest precedence\n  # and then the job.\n  reschedule {\n    delay             = \"30s\"\n    delay_function    = \"constant\"\n    unlimited         = true\n  }\n\n  # The \"group\" stanza defines a series of tasks that should be co-located on\n  # the same Nomad client. Any task within a group will be placed on the same\n  # client.\n  #\n  # For more information and examples on the \"group\" stanza, please see\n  # the online documentation at:\n  #\n  #     https://www.nomadproject.io/docs/job-specification/group\n  #\n  group \"prod-group1-grafana\" {\n    # The \"count\" parameter specifies the number of the task groups that should\n    # be running under this group. This value must be non-negative and defaults\n    # to 1.\n    count             = 1\n\n    # The restart stanza configures a tasks's behavior on task failure. Restarts\n    # happen on the client that is running the task.\n    #\n    # https://www.nomadproject.io/docs/job-specification/restart\n    #\n    restart {\n      interval        = \"30m\"\n      attempts        = 40\n      delay           = \"15s\"\n      mode            = \"delay\"\n    }\n\n    # The constraint allows restricting the set of eligible nodes. Constraints\n    # may filter on attributes or client metadata.\n    #\n    # For more information and examples on the \"volume\" stanza, please see\n    # the online documentation at:\n    #\n    #     https://www.nomadproject.io/docs/job-specification/constraint\n    #\n    constraint {\n      attribute       = \"${attr.cpu.arch}\"\n      operator        = \"!=\"\n      value           = \"arm64\"\n    }\n\n    constraint {\n      attribute      = \"${node.class}\"\n      value          = \"builder\"\n    }\n\n    # The \"task\" stanza creates an individual unit of work, such as a Docker\n    # container, web application, or batch processing.\n    #\n    # For more information and examples on the \"task\" stanza, please see\n    # the online documentation at:\n    #\n    #     https://www.nomadproject.io/docs/job-specification/task\n    #\n    task \"prod-task1-grafana\" {\n      # The \"driver\" parameter specifies the task driver that should be used to\n      # run the task.\n      driver          = \"docker\"\n\n      # The \"config\" stanza specifies the driver configuration, which is passed\n      # directly to the driver to start the task. The details of configurations\n      # are specific to each driver, so please see specific driver\n      # documentation for more information.\n      config {\n        image         = \"grafana/grafana:7.3.7\"\n        dns_servers   = [ \"172.17.0.1\" ]\n        volumes       = [\n          \"secrets/prometheus.yml:/etc/grafana/provisioning/datasources/prometheus.yml\",\n          \"secrets/dashboards.yml:/etc/grafana/provisioning/dashboards/dashboards.yml\",\n          \"secrets/grafana.ini:/etc/grafana/grafana.ini\",\n          \"secrets/node_exporter.json:/etc/grafana/provisioning/dashboards/node_exporter.json\",\n          \"secrets/nomad.json:/etc/grafana/provisioning/dashboards/nomad.json\",\n          \"secrets/consul.json:/etc/grafana/provisioning/dashboards/consul.json\",\n          \"secrets/prometheus.json:/etc/grafana/provisioning/dashboards/prometheus.json\",\n          \"secrets/blackbox_exporter_http.json:/etc/grafana/provisioning/dashboards/blackbox_exporter_http.json\",\n          \"secrets/blackbox_exporter_icmp.json:/etc/grafana/provisioning/dashboards/blackbox_exporter_icmp.json\"\n        ]\n      }\n\n      artifact {\n        # Prometheus Node Exporter\n        source        = \"https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/node_exporter.json\"\n        destination   = \"secrets/\"\n      }\n\n      artifact {\n        # Nomad\n        source        = \"https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/nomad.json\"\n        destination   = \"secrets/\"\n      }\n\n      artifact {\n        # Consul\n        source        = \"https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/consul.json\"\n        destination   = \"secrets/\"\n      }\n\n      artifact {\n        # Prometheus\n        source        = \"https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/prometheus.json\"\n        destination   = \"secrets/\"\n      }\n\n      artifact {\n        # Prometheus Blackbox Exporter HTTP\n        source        = \"https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/blackbox_exporter_http.json\"\n        destination   = \"secrets/\"\n      }\n\n      artifact {\n        # Prometheus Blackbox Exporter ICMP\n        source        = \"https://raw.githubusercontent.com/pmikus/grafana-dashboards/main/blackbox_exporter_icmp.json\"\n        destination   = \"secrets/\"\n      }\n\n      # The \"template\" stanza instructs Nomad to manage a template, such as\n      # a configuration file or script. This template can optionally pull data\n      # from Consul or Vault to populate runtime configuration data.\n      #\n      # For more information and examples on the \"template\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/template\n      #\n      template {\n        change_mode   = \"noop\"\n        change_signal = \"SIGINT\"\n        destination   = \"secrets/prometheus.yml\"\n        data          = \u003c\u003cEOH\napiVersion: 1\ndatasources:\n- name: Prometheus\n  type: prometheus\n  access: direct\n  orgId: 1\n  url: http://prometheus.service.consul:9090\n  basicAuth: false\n  isDefault: true\n  version: 1\n  editable: false\nEOH\n      }\n\n      template {\n        change_mode   = \"noop\"\n        change_signal = \"SIGINT\"\n        destination   = \"secrets/dashboards.yml\"\n        data          = \u003c\u003cEOH\napiVersion: 1\nproviders:\n- name: dashboards\n  type: file\n  disableDeletion: false\n  updateIntervalSeconds: 10\n  allowUiUpdates: false\n  options:\n    path: /etc/grafana/provisioning/dashboards\n    foldersFromFilesStructure: true\nEOH\n      }\n\n      template {\n        change_mode   = \"noop\"\n        change_signal = \"SIGINT\"\n        destination   = \"secrets/grafana.ini\"\n        data          = \u003c\u003cEOH\napp_mode = production\n\n[metrics]\nenabled = true\n\n[server]\nprotocol = http\nhttp_port = 3000\nroot_url = http://grafana.service.consul:3000\nenable_gzip = true\n;cert_file =\n;cert_key =\n\n[security]\nadmin_user = grafanauser\nadmin_password = Grafana1234\nsecret_key = SW2YcwTIb9zpOOhoPsMm\n\n[users]\nallow_sign_up = false\nallow_org_create = false\nauto_assign_org = true\nauto_assign_org_role = Viewer\ndefault_theme = dark\n\n[auth.basic]\nenabled = true\n\n[auth]\ndisable_login_form = false\ndisable_signout_menu = false\n\n[auth.anonymous]\nenabled = false\n\n[log]\nmode = console\nlevel = info\n\n[log.console]\nlevel = info\nformat = console\nEOH\n      }\n\n      # The service stanza instructs Nomad to register a service with Consul.\n      #\n      # For more information and examples on the \"task\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/service\n      #\n      service {\n        name              = \"grafana\"\n        port              = \"grafana\"\n        tags              = [ \"grafana${NOMAD_ALLOC_INDEX}\" ]\n        check {\n          name            = \"Grafana Check Live\"\n          type            = \"http\"\n          protocol        = \"http\"\n          tls_skip_verify = true\n          path            = \"/api/health\"\n          interval        = \"10s\"\n          timeout         = \"2s\"\n        }\n      }\n\n      # The \"resources\" stanza describes the requirements a task needs to\n      # execute. Resource requirements include memory, network, cpu, and more.\n      # This ensures the task will execute on a machine that contains enough\n      # resource capacity.\n      #\n      # For more information and examples on the \"resources\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/resources\n      #\n      resources {\n        cpu               = 1000\n        memory            = 2048\n        # The network stanza specifies the networking requirements for the task\n        # group, including the network mode and port allocations. When scheduling\n        # jobs in Nomad they are provisioned across your fleet of machines along\n        # with other jobs and services. Because you don't know in advance what host\n        # your job will be provisioned on, Nomad will provide your tasks with\n        # network configuration when they start up.\n        #\n        # For more information and examples on the \"template\" stanza, please see\n        # the online documentation at:\n        #\n        #     https://www.nomadproject.io/docs/job-specification/network\n        #\n        network {\n          port \"grafana\" {\n            static        = 3000\n          }\n        }\n      }\n    }\n  }\n}",
             "json": null,
-            "modify_index": "7575032",
+            "modify_index": "9138744",
             "name": "prod-grafana",
             "namespace": "default",
             "policy_override": null,
@@ -270,10 +272,10 @@
           "schema_version": 0,
           "attributes": {
             "allocation_ids": [
-              "844e34c1-13e6-3ddb-9402-e876230e5cdb",
-              "44e1a0f0-5328-eafb-3beb-bfd53af2b618",
-              "a6695ea0-2563-72ae-1791-a08ef933ff72",
-              "51126acb-945c-2629-5787-76b85677ddd0"
+              "924ac00a-b010-4af9-712d-1958c43c5363",
+              "1f464e9b-5892-45d8-9f6c-538ff61ac976",
+              "8b00df36-88c8-9cad-ce94-a2827b815be4",
+              "d257257b-4ed7-1a72-8ad5-7dc078e371b3"
             ],
             "datacenters": [
               "yul1"
@@ -342,9 +344,9 @@
           "schema_version": 0,
           "attributes": {
             "filename": null,
-            "id": "f6d48eb498752cd7c1c73a26a146961048a1b7f7d53602df55b413f27226e519",
-            "rendered": "job \"prod-nginx\" {\n  # The \"region\" parameter specifies the region in which to execute the job.\n  # If omitted, this inherits the default region name of \"global\".\n  # region = \"global\"\n  #\n  # The \"datacenters\" parameter specifies the list of datacenters which should\n  # be considered when placing this task. This must be provided.\n  datacenters = \"yul1\"\n\n  # The \"type\" parameter controls the type of job, which impacts the scheduler's\n  # decision on placement. This configuration is optional and defaults to\n  # \"service\". For a full list of job types and their differences, please see\n  # the online documentation.\n  #\n  # For more information, please see the online documentation at:\n  #\n  #     https://www.nomadproject.io/docs/jobspec/schedulers.html\n  #\n  type = \"service\"\n\n  update {\n    # The \"max_parallel\" parameter specifies the maximum number of updates to\n    # perform in parallel. In this case, this specifies to update a single task\n    # at a time.\n    max_parallel      = 0\n\n    # The \"min_healthy_time\" parameter specifies the minimum time the allocation\n    # must be in the healthy state before it is marked as healthy and unblocks\n    # further allocations from being updated.\n    min_healthy_time  = \"10s\"\n\n    # The \"healthy_deadline\" parameter specifies the deadline in which the\n    # allocation must be marked as healthy after which the allocation is\n    # automatically transitioned to unhealthy. Transitioning to unhealthy will\n    # fail the deployment and potentially roll back the job if \"auto_revert\" is\n    # set to true.\n    healthy_deadline  = \"3m\"\n\n    # The \"progress_deadline\" parameter specifies the deadline in which an\n    # allocation must be marked as healthy. The deadline begins when the first\n    # allocation for the deployment is created and is reset whenever an allocation\n    # as part of the deployment transitions to a healthy state. If no allocation\n    # transitions to the healthy state before the progress deadline, the\n    # deployment is marked as failed.\n    progress_deadline = \"10m\"\n\n    # The \"auto_revert\" parameter specifies if the job should auto-revert to the\n    # last stable job on deployment failure. A job is marked as stable if all the\n    # allocations as part of its deployment were marked healthy.\n    auto_revert       = false\n\n    # The \"canary\" parameter specifies that changes to the job that would result\n    # in destructive updates should create the specified number of canaries\n    # without stopping any previous allocations. Once the operator determines the\n    # canaries are healthy, they can be promoted which unblocks a rolling update\n    # of the remaining allocations at a rate of \"max_parallel\".\n    #\n    # Further, setting \"canary\" equal to the count of the task group allows\n    # blue/green deployments. When the job is updated, a full set of the new\n    # version is deployed and upon promotion the old version is stopped.\n    canary            = 0\n  }\n\n  # The reschedule stanza specifies the group's rescheduling strategy. If\n  # specified at the job level, the configuration will apply to all groups\n  # within the job. If the reschedule stanza is present on both the job and the\n  # group, they are merged with the group stanza taking the highest precedence\n  # and then the job.\n  reschedule {\n    delay             = \"30s\"\n    delay_function    = \"constant\"\n    unlimited         = true\n  }\n\n  # The \"group\" stanza defines a series of tasks that should be co-located on\n  # the same Nomad client. Any task within a group will be placed on the same\n  # client.\n  #\n  # For more information and examples on the \"group\" stanza, please see\n  # the online documentation at:\n  #\n  #     https://www.nomadproject.io/docs/job-specification/group.html\n  #\n  group \"prod-group1-nginx\" {\n    # The \"count\" parameter specifies the number of the task groups that should\n    # be running under this group. This value must be non-negative and defaults\n    # to 1.\n    count = 1\n\n    # https://www.nomadproject.io/docs/job-specification/volume\n    \n    volume \"prod-volume1-nginx\" {\n      type      = \"host\"\n      read_only = false\n      source    = \"prod-volume-data1-1\"\n    }\n    \n\n    # The restart stanza configures a tasks's behavior on task failure. Restarts\n    # happen on the client that is running the task.\n    #\n    # https://www.nomadproject.io/docs/job-specification/restart\n    #\n    restart {\n      interval  = \"30m\"\n      attempts  = 40\n      delay     = \"15s\"\n      mode      = \"delay\"\n    }\n\n    # The \"task\" stanza creates an individual unit of work, such as a Docker\n    # container, web application, or batch processing.\n    #\n    # For more information and examples on the \"task\" stanza, please see\n    # the online documentation at:\n    #\n    #     https://www.nomadproject.io/docs/job-specification/task.html\n    #\n    task \"prod-task1-nginx\" {\n      # The \"driver\" parameter specifies the task driver that should be used to\n      # run the task.\n      driver = \"docker\"\n\n      # The \"config\" stanza specifies the driver configuration, which is passed\n      # directly to the driver to start the task. The details of configurations\n      # are specific to each driver, so please see specific driver\n      # documentation for more information.\n      config {\n        image        = \"nginx:stable\"\n        port_map {\n          https      = 443\n        }\n        privileged   = false\n        volumes      = [\n          \"/etc/ssl/certs/docs.nginx.service.consul.crt:/etc/ssl/certs/docs.nginx.service.consul.crt\",\n          \"/etc/ssl/private/docs.nginx.service.consul.key:/etc/ssl/private/docs.nginx.service.consul.key\",\n          \"/etc/ssl/certs/logs.nginx.service.consul.crt:/etc/ssl/certs/logs.nginx.service.consul.crt\",\n          \"/etc/ssl/private/logs.nginx.service.consul.key:/etc/ssl/private/logs.nginx.service.consul.key\",\n          \"custom/upstream.conf:/etc/nginx/conf.d/upstream.conf\",\n          \"custom/logs.conf:/etc/nginx/conf.d/logs.conf\",\n          \"custom/docs.conf:/etc/nginx/conf.d/docs.conf\"\n        ]\n      }\n\n      # The \"template\" stanza instructs Nomad to manage a template, such as\n      # a configuration file or script. This template can optionally pull data\n      # from Consul or Vault to populate runtime configuration data.\n      #\n      # For more information and examples on the \"template\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/template.html\n      #\n      template {\n        data = \u003c\u003cEOH\n          upstream storage {\n            {{ range service \"storage\" }}\n              server {{ .Address }}:{{ .Port }};\n            {{ end }}\n          }\n        EOH\n        destination = \"custom/upstream.conf\"\n      }\n      template {\n        data = \u003c\u003cEOH\n          server {\n            listen 443 ssl default_server;\n            server_name logs.nginx.service.consul;\n            keepalive_timeout 70;\n            ssl_session_cache shared:SSL:10m;\n            ssl_session_timeout 10m;\n            ssl_protocols TLSv1.2;\n            ssl_prefer_server_ciphers on;\n            ssl_ciphers \"ECDHE-ECDSA-AES256-GCM-SHA384:ECDHE-RSA-AES256-GCM-SHA384:ECDHE-ECDSA-CHACHA20-POLY1305:ECDHE-RSA-CHACHA20-POLY1305:ECDHE-ECDSA-AES256-SHA384:ECDHE-RSA-AES256-SHA384\";\n            ssl_certificate /etc/ssl/certs/logs.nginx.service.consul.crt;\n            ssl_certificate_key /etc/ssl/private/logs.nginx.service.consul.key;\n            location / {\n              chunked_transfer_encoding off;\n              proxy_connect_timeout 300;\n              proxy_http_version 1.1;\n              proxy_set_header Host $host:$server_port;\n              proxy_set_header Connection \"\";\n              proxy_pass http://storage/logs.fd.io/;\n              server_name_in_redirect off;\n            }\n            location ~ (.*html.gz)$ {\n              add_header Content-Encoding gzip;\n              add_header Content-Type text/html;\n              chunked_transfer_encoding off;\n              proxy_connect_timeout 300;\n              proxy_http_version 1.1;\n              proxy_set_header Host $host:$server_port;\n              proxy_set_header Connection \"\";\n              proxy_pass http://storage/logs.fd.io/$1;\n              server_name_in_redirect off;\n            }\n            location ~ (.*txt.gz|.*log.gz)$ {\n              add_header Content-Encoding gzip;\n              add_header Content-Type text/plain;\n              chunked_transfer_encoding off;\n              proxy_connect_timeout 300;\n              proxy_http_version 1.1;\n              proxy_set_header Host $host:$server_port;\n              proxy_set_header Connection \"\";\n              proxy_pass http://storage/logs.fd.io/$1;\n              server_name_in_redirect off;\n            }\n            location ~ (.*xml.gz)$ {\n              add_header Content-Encoding gzip;\n              add_header Content-Type application/xml;\n              chunked_transfer_encoding off;\n              proxy_connect_timeout 300;\n              proxy_http_version 1.1;\n              proxy_set_header Host $host:$server_port;\n              proxy_set_header Connection \"\";\n              proxy_pass http://storage/logs.fd.io/$1;\n              server_name_in_redirect off;\n            }\n        }\n        EOH\n        destination = \"custom/logs.conf\"\n      }\n      template {\n        data = \u003c\u003cEOH\n          server {\n            listen 443 ssl;\n            server_name docs.nginx.service.consul;\n            keepalive_timeout 70;\n            ssl_session_cache shared:SSL:10m;\n            ssl_session_timeout 10m;\n            ssl_protocols TLSv1.2;\n            ssl_prefer_server_ciphers on;\n            ssl_ciphers \"ECDHE-ECDSA-AES256-GCM-SHA384:ECDHE-RSA-AES256-GCM-SHA384:ECDHE-ECDSA-CHACHA20-POLY1305:ECDHE-RSA-CHACHA20-POLY1305:ECDHE-ECDSA-AES256-SHA384:ECDHE-RSA-AES256-SHA384\";\n            ssl_certificate /etc/ssl/certs/docs.nginx.service.consul.crt;\n            ssl_certificate_key /etc/ssl/private/docs.nginx.service.consul.key;\n            location / {\n              chunked_transfer_encoding off;\n              proxy_connect_timeout 300;\n              proxy_http_version 1.1;\n              proxy_set_header Host $host:$server_port;\n              proxy_set_header Connection \"\";\n              proxy_pass http://storage/docs.fd.io/;\n              server_name_in_redirect off;\n            }\n          }\n        EOH\n        destination = \"custom/docs.conf\"\n      }\n\n      # The service stanza instructs Nomad to register a service with Consul.\n      #\n      # For more information and examples on the \"task\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/service.html\n      #\n      service {\n        name       = \"nginx\"\n        port       = \"https\"\n        tags       = [ \"docs\", \"logs\" ]\n      }\n\n      # The \"resources\" stanza describes the requirements a task needs to\n      # execute. Resource requirements include memory, network, cpu, and more.\n      # This ensures the task will execute on a machine that contains enough\n      # resource capacity.\n      #\n      # For more information and examples on the \"resources\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/resources.html\n      #\n      resources {\n        cpu        = 2000\n        memory     = 4096\n        network {\n          mode     = \"bridge\"\n          port \"https\" {\n            static = 443\n          }\n        }\n      }\n    }\n  }\n}",
-            "template": "job \"${job_name}\" {\n  # The \"region\" parameter specifies the region in which to execute the job.\n  # If omitted, this inherits the default region name of \"global\".\n  # region = \"global\"\n  #\n  # The \"datacenters\" parameter specifies the list of datacenters which should\n  # be considered when placing this task. This must be provided.\n  datacenters = \"${datacenters}\"\n\n  # The \"type\" parameter controls the type of job, which impacts the scheduler's\n  # decision on placement. This configuration is optional and defaults to\n  # \"service\". For a full list of job types and their differences, please see\n  # the online documentation.\n  #\n  # For more information, please see the online documentation at:\n  #\n  #     https://www.nomadproject.io/docs/jobspec/schedulers.html\n  #\n  type = \"service\"\n\n  update {\n    # The \"max_parallel\" parameter specifies the maximum number of updates to\n    # perform in parallel. In this case, this specifies to update a single task\n    # at a time.\n    max_parallel      = 0\n\n    # The \"min_healthy_time\" parameter specifies the minimum time the allocation\n    # must be in the healthy state before it is marked as healthy and unblocks\n    # further allocations from being updated.\n    min_healthy_time  = \"10s\"\n\n    # The \"healthy_deadline\" parameter specifies the deadline in which the\n    # allocation must be marked as healthy after which the allocation is\n    # automatically transitioned to unhealthy. Transitioning to unhealthy will\n    # fail the deployment and potentially roll back the job if \"auto_revert\" is\n    # set to true.\n    healthy_deadline  = \"3m\"\n\n    # The \"progress_deadline\" parameter specifies the deadline in which an\n    # allocation must be marked as healthy. The deadline begins when the first\n    # allocation for the deployment is created and is reset whenever an allocation\n    # as part of the deployment transitions to a healthy state. If no allocation\n    # transitions to the healthy state before the progress deadline, the\n    # deployment is marked as failed.\n    progress_deadline = \"10m\"\n\n    # The \"auto_revert\" parameter specifies if the job should auto-revert to the\n    # last stable job on deployment failure. A job is marked as stable if all the\n    # allocations as part of its deployment were marked healthy.\n    auto_revert       = false\n\n    # The \"canary\" parameter specifies that changes to the job that would result\n    # in destructive updates should create the specified number of canaries\n    # without stopping any previous allocations. Once the operator determines the\n    # canaries are healthy, they can be promoted which unblocks a rolling update\n    # of the remaining allocations at a rate of \"max_parallel\".\n    #\n    # Further, setting \"canary\" equal to the count of the task group allows\n    # blue/green deployments. When the job is updated, a full set of the new\n    # version is deployed and upon promotion the old version is stopped.\n    canary            = 0\n  }\n\n  # The reschedule stanza specifies the group's rescheduling strategy. If\n  # specified at the job level, the configuration will apply to all groups\n  # within the job. If the reschedule stanza is present on both the job and the\n  # group, they are merged with the group stanza taking the highest precedence\n  # and then the job.\n  reschedule {\n    delay             = \"30s\"\n    delay_function    = \"constant\"\n    unlimited         = true\n  }\n\n  # The \"group\" stanza defines a series of tasks that should be co-located on\n  # the same Nomad client. Any task within a group will be placed on the same\n  # client.\n  #\n  # For more information and examples on the \"group\" stanza, please see\n  # the online documentation at:\n  #\n  #     https://www.nomadproject.io/docs/job-specification/group.html\n  #\n  group \"prod-group1-nginx\" {\n    # The \"count\" parameter specifies the number of the task groups that should\n    # be running under this group. This value must be non-negative and defaults\n    # to 1.\n    count = 1\n\n    # https://www.nomadproject.io/docs/job-specification/volume\n    %{ if use_host_volume }\n    volume \"prod-volume1-nginx\" {\n      type      = \"host\"\n      read_only = false\n      source    = \"${host_volume}\"\n    }\n    %{ endif }\n\n    # The restart stanza configures a tasks's behavior on task failure. Restarts\n    # happen on the client that is running the task.\n    #\n    # https://www.nomadproject.io/docs/job-specification/restart\n    #\n    restart {\n      interval  = \"30m\"\n      attempts  = 40\n      delay     = \"15s\"\n      mode      = \"delay\"\n    }\n\n    # The \"task\" stanza creates an individual unit of work, such as a Docker\n    # container, web application, or batch processing.\n    #\n    # For more information and examples on the \"task\" stanza, please see\n    # the online documentation at:\n    #\n    #     https://www.nomadproject.io/docs/job-specification/task.html\n    #\n    task \"prod-task1-nginx\" {\n      # The \"driver\" parameter specifies the task driver that should be used to\n      # run the task.\n      driver = \"docker\"\n\n      # The \"config\" stanza specifies the driver configuration, which is passed\n      # directly to the driver to start the task. The details of configurations\n      # are specific to each driver, so please see specific driver\n      # documentation for more information.\n      config {\n        image        = \"nginx:stable\"\n        port_map {\n          https      = 443\n        }\n        privileged   = false\n        volumes      = [\n          \"/etc/ssl/certs/docs.nginx.service.consul.crt:/etc/ssl/certs/docs.nginx.service.consul.crt\",\n          \"/etc/ssl/private/docs.nginx.service.consul.key:/etc/ssl/private/docs.nginx.service.consul.key\",\n          \"/etc/ssl/certs/logs.nginx.service.consul.crt:/etc/ssl/certs/logs.nginx.service.consul.crt\",\n          \"/etc/ssl/private/logs.nginx.service.consul.key:/etc/ssl/private/logs.nginx.service.consul.key\",\n          \"custom/upstream.conf:/etc/nginx/conf.d/upstream.conf\",\n          \"custom/logs.conf:/etc/nginx/conf.d/logs.conf\",\n          \"custom/docs.conf:/etc/nginx/conf.d/docs.conf\"\n        ]\n      }\n\n      # The \"template\" stanza instructs Nomad to manage a template, such as\n      # a configuration file or script. This template can optionally pull data\n      # from Consul or Vault to populate runtime configuration data.\n      #\n      # For more information and examples on the \"template\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/template.html\n      #\n      template {\n        data = \u003c\u003cEOH\n          upstream storage {\n            {{ range service \"storage\" }}\n              server {{ .Address }}:{{ .Port }};\n            {{ end }}\n          }\n        EOH\n        destination = \"custom/upstream.conf\"\n      }\n      template {\n        data = \u003c\u003cEOH\n          server {\n            listen 443 ssl default_server;\n            server_name logs.nginx.service.consul;\n            keepalive_timeout 70;\n            ssl_session_cache shared:SSL:10m;\n            ssl_session_timeout 10m;\n            ssl_protocols TLSv1.2;\n            ssl_prefer_server_ciphers on;\n            ssl_ciphers \"ECDHE-ECDSA-AES256-GCM-SHA384:ECDHE-RSA-AES256-GCM-SHA384:ECDHE-ECDSA-CHACHA20-POLY1305:ECDHE-RSA-CHACHA20-POLY1305:ECDHE-ECDSA-AES256-SHA384:ECDHE-RSA-AES256-SHA384\";\n            ssl_certificate /etc/ssl/certs/logs.nginx.service.consul.crt;\n            ssl_certificate_key /etc/ssl/private/logs.nginx.service.consul.key;\n            location / {\n              chunked_transfer_encoding off;\n              proxy_connect_timeout 300;\n              proxy_http_version 1.1;\n              proxy_set_header Host $host:$server_port;\n              proxy_set_header Connection \"\";\n              proxy_pass http://storage/logs.fd.io/;\n              server_name_in_redirect off;\n            }\n            location ~ (.*html.gz)$ {\n              add_header Content-Encoding gzip;\n              add_header Content-Type text/html;\n              chunked_transfer_encoding off;\n              proxy_connect_timeout 300;\n              proxy_http_version 1.1;\n              proxy_set_header Host $host:$server_port;\n              proxy_set_header Connection \"\";\n              proxy_pass http://storage/logs.fd.io/$1;\n              server_name_in_redirect off;\n            }\n            location ~ (.*txt.gz|.*log.gz)$ {\n              add_header Content-Encoding gzip;\n              add_header Content-Type text/plain;\n              chunked_transfer_encoding off;\n              proxy_connect_timeout 300;\n              proxy_http_version 1.1;\n              proxy_set_header Host $host:$server_port;\n              proxy_set_header Connection \"\";\n              proxy_pass http://storage/logs.fd.io/$1;\n              server_name_in_redirect off;\n            }\n            location ~ (.*xml.gz)$ {\n              add_header Content-Encoding gzip;\n              add_header Content-Type application/xml;\n              chunked_transfer_encoding off;\n              proxy_connect_timeout 300;\n              proxy_http_version 1.1;\n              proxy_set_header Host $host:$server_port;\n              proxy_set_header Connection \"\";\n              proxy_pass http://storage/logs.fd.io/$1;\n              server_name_in_redirect off;\n            }\n        }\n        EOH\n        destination = \"custom/logs.conf\"\n      }\n      template {\n        data = \u003c\u003cEOH\n          server {\n            listen 443 ssl;\n            server_name docs.nginx.service.consul;\n            keepalive_timeout 70;\n            ssl_session_cache shared:SSL:10m;\n            ssl_session_timeout 10m;\n            ssl_protocols TLSv1.2;\n            ssl_prefer_server_ciphers on;\n            ssl_ciphers \"ECDHE-ECDSA-AES256-GCM-SHA384:ECDHE-RSA-AES256-GCM-SHA384:ECDHE-ECDSA-CHACHA20-POLY1305:ECDHE-RSA-CHACHA20-POLY1305:ECDHE-ECDSA-AES256-SHA384:ECDHE-RSA-AES256-SHA384\";\n            ssl_certificate /etc/ssl/certs/docs.nginx.service.consul.crt;\n            ssl_certificate_key /etc/ssl/private/docs.nginx.service.consul.key;\n            location / {\n              chunked_transfer_encoding off;\n              proxy_connect_timeout 300;\n              proxy_http_version 1.1;\n              proxy_set_header Host $host:$server_port;\n              proxy_set_header Connection \"\";\n              proxy_pass http://storage/docs.fd.io/;\n              server_name_in_redirect off;\n            }\n          }\n        EOH\n        destination = \"custom/docs.conf\"\n      }\n\n      # The service stanza instructs Nomad to register a service with Consul.\n      #\n      # For more information and examples on the \"task\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/service.html\n      #\n      service {\n        name       = \"nginx\"\n        port       = \"https\"\n        tags       = [ \"docs\", \"logs\" ]\n      }\n\n      # The \"resources\" stanza describes the requirements a task needs to\n      # execute. Resource requirements include memory, network, cpu, and more.\n      # This ensures the task will execute on a machine that contains enough\n      # resource capacity.\n      #\n      # For more information and examples on the \"resources\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/resources.html\n      #\n      resources {\n        cpu        = 2000\n        memory     = 4096\n        network {\n          mode     = \"bridge\"\n          port \"https\" {\n            static = 443\n          }\n        }\n      }\n    }\n  }\n}",
+            "id": "6406c7bfb6f177869e124475f94fada7f69c2e6631c6943a6a00a167fd19a925",
+            "rendered": "job \"prod-nginx\" {\n  # The \"region\" parameter specifies the region in which to execute the job.\n  # If omitted, this inherits the default region name of \"global\".\n  # region = \"global\"\n  #\n  # The \"datacenters\" parameter specifies the list of datacenters which should\n  # be considered when placing this task. This must be provided.\n  datacenters = \"yul1\"\n\n  # The \"type\" parameter controls the type of job, which impacts the scheduler's\n  # decision on placement. This configuration is optional and defaults to\n  # \"service\". For a full list of job types and their differences, please see\n  # the online documentation.\n  #\n  # For more information, please see the online documentation at:\n  #\n  #     https://www.nomadproject.io/docs/jobspec/schedulers.html\n  #\n  type = \"service\"\n\n  update {\n    # The \"max_parallel\" parameter specifies the maximum number of updates to\n    # perform in parallel. In this case, this specifies to update a single task\n    # at a time.\n    max_parallel      = 0\n\n    # The \"min_healthy_time\" parameter specifies the minimum time the allocation\n    # must be in the healthy state before it is marked as healthy and unblocks\n    # further allocations from being updated.\n    min_healthy_time  = \"10s\"\n\n    # The \"healthy_deadline\" parameter specifies the deadline in which the\n    # allocation must be marked as healthy after which the allocation is\n    # automatically transitioned to unhealthy. Transitioning to unhealthy will\n    # fail the deployment and potentially roll back the job if \"auto_revert\" is\n    # set to true.\n    healthy_deadline  = \"3m\"\n\n    # The \"progress_deadline\" parameter specifies the deadline in which an\n    # allocation must be marked as healthy. The deadline begins when the first\n    # allocation for the deployment is created and is reset whenever an allocation\n    # as part of the deployment transitions to a healthy state. If no allocation\n    # transitions to the healthy state before the progress deadline, the\n    # deployment is marked as failed.\n    progress_deadline = \"10m\"\n\n    # The \"auto_revert\" parameter specifies if the job should auto-revert to the\n    # last stable job on deployment failure. A job is marked as stable if all the\n    # allocations as part of its deployment were marked healthy.\n    auto_revert       = false\n\n    # The \"canary\" parameter specifies that changes to the job that would result\n    # in destructive updates should create the specified number of canaries\n    # without stopping any previous allocations. Once the operator determines the\n    # canaries are healthy, they can be promoted which unblocks a rolling update\n    # of the remaining allocations at a rate of \"max_parallel\".\n    #\n    # Further, setting \"canary\" equal to the count of the task group allows\n    # blue/green deployments. When the job is updated, a full set of the new\n    # version is deployed and upon promotion the old version is stopped.\n    canary            = 0\n  }\n\n  # The reschedule stanza specifies the group's rescheduling strategy. If\n  # specified at the job level, the configuration will apply to all groups\n  # within the job. If the reschedule stanza is present on both the job and the\n  # group, they are merged with the group stanza taking the highest precedence\n  # and then the job.\n  reschedule {\n    delay             = \"30s\"\n    delay_function    = \"constant\"\n    unlimited         = true\n  }\n\n  # The \"group\" stanza defines a series of tasks that should be co-located on\n  # the same Nomad client. Any task within a group will be placed on the same\n  # client.\n  #\n  # For more information and examples on the \"group\" stanza, please see\n  # the online documentation at:\n  #\n  #     https://www.nomadproject.io/docs/job-specification/group.html\n  #\n  group \"prod-group1-nginx\" {\n    # The \"count\" parameter specifies the number of the task groups that should\n    # be running under this group. This value must be non-negative and defaults\n    # to 1.\n    count             = 1\n\n    # https://www.nomadproject.io/docs/job-specification/volume\n    \n    volume \"prod-volume1-nginx\" {\n      type            = \"host\"\n      read_only       = false\n      source          = \"prod-volume-data1-1\"\n    }\n    \n\n    # The restart stanza configures a tasks's behavior on task failure. Restarts\n    # happen on the client that is running the task.\n    #\n    # https://www.nomadproject.io/docs/job-specification/restart\n    #\n    restart {\n      interval        = \"30m\"\n      attempts        = 40\n      delay           = \"15s\"\n      mode            = \"delay\"\n    }\n\n    # The constraint allows restricting the set of eligible nodes. Constraints\n    # may filter on attributes or client metadata.\n    #\n    # For more information and examples on the \"volume\" stanza, please see\n    # the online documentation at:\n    #\n    #     https://www.nomadproject.io/docs/job-specification/constraint\n    #\n    constraint {\n      attribute       = \"${attr.cpu.arch}\"\n      operator        = \"!=\"\n      value           = \"arm64\"\n    }\n\n    constraint {\n      attribute      = \"${node.class}\"\n      value          = \"builder\"\n    }\n\n    # The \"task\" stanza creates an individual unit of work, such as a Docker\n    # container, web application, or batch processing.\n    #\n    # For more information and examples on the \"task\" stanza, please see\n    # the online documentation at:\n    #\n    #     https://www.nomadproject.io/docs/job-specification/task.html\n    #\n    task \"prod-task1-nginx\" {\n      # The \"driver\" parameter specifies the task driver that should be used to\n      # run the task.\n      driver          = \"docker\"\n\n      # The \"config\" stanza specifies the driver configuration, which is passed\n      # directly to the driver to start the task. The details of configurations\n      # are specific to each driver, so please see specific driver\n      # documentation for more information.\n      config {\n        image         = \"nginx:stable\"\n        port_map {\n          https       = 443\n        }\n        privileged    = false\n        volumes       = [\n          \"/etc/ssl/certs/logs.nginx.service.consul.crt:/etc/ssl/certs/logs.nginx.service.consul.crt\",\n          \"/etc/ssl/private/logs.nginx.service.consul.key:/etc/ssl/private/logs.nginx.service.consul.key\",\n          \"custom/upstream.conf:/etc/nginx/conf.d/upstream.conf\",\n          \"custom/server_logs.conf:/etc/nginx/conf.d/server_logs.conf\"\n        ]\n      }\n\n      # The \"template\" stanza instructs Nomad to manage a template, such as\n      # a configuration file or script. This template can optionally pull data\n      # from Consul or Vault to populate runtime configuration data.\n      #\n      # For more information and examples on the \"template\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/template.html\n      #\n      template {\n        data = \u003c\u003cEOH\n          upstream storage {\n            {{ range service \"storage\" }}\n              server {{ .Address }}:{{ .Port }};\n            {{ end }}\n          }\n        EOH\n        destination = \"custom/upstream.conf\"\n      }\n      template {\n        data = \u003c\u003cEOH\n          server {\n            listen 443 ssl default_server;\n            server_name logs.nginx.service.consul;\n\n            ssl_certificate /etc/ssl/certs/logs.nginx.service.consul.crt;\n            ssl_certificate_key /etc/ssl/private/logs.nginx.service.consul.key;\n            ssl_protocols TLSv1.2;\n            ssl_prefer_server_ciphers on;\n            ssl_ciphers \"ECDHE-ECDSA-AES256-GCM-SHA384:ECDHE-RSA-AES256-GCM-SHA384:ECDHE-ECDSA-CHACHA20-POLY1305:ECDHE-RSA-CHACHA20-POLY1305:ECDHE-ECDSA-AES256-SHA384:ECDHE-RSA-AES256-SHA384\";\n            ssl_session_timeout 10m;\n            ssl_session_cache shared:SSL:10m;\n            ssl_session_tickets off;\n            ssl_stapling on;\n            ssl_stapling_verify on;\n\n            fastcgi_hide_header X-Powered-By;\n\n            client_max_body_size 0;\n            client_header_timeout 60;\n            client_body_timeout 86400;\n            fastcgi_read_timeout 86400;\n            proxy_connect_timeout 60;\n            proxy_read_timeout 86400;\n            proxy_send_timeout 86400;\n            send_timeout 86400;\n\n            keepalive_timeout 70;\n            location / {\n              chunked_transfer_encoding off;\n              proxy_connect_timeout 300;\n              proxy_http_version 1.1;\n              proxy_set_header Host $host:$server_port;\n              proxy_set_header Connection \"\";\n              proxy_pass http://storage/logs.fd.io/;\n              server_name_in_redirect off;\n            }\n            location ~ (.*html.gz)$ {\n              add_header Content-Encoding gzip;\n              add_header Content-Type text/html;\n              chunked_transfer_encoding off;\n              proxy_connect_timeout 300;\n              proxy_http_version 1.1;\n              proxy_set_header Host $host:$server_port;\n              proxy_set_header Connection \"\";\n              proxy_pass http://storage/logs.fd.io/$1;\n              server_name_in_redirect off;\n            }\n            location ~ (.*txt.gz|.*log.gz)$ {\n              add_header Content-Encoding gzip;\n              add_header Content-Type text/plain;\n              chunked_transfer_encoding off;\n              proxy_connect_timeout 300;\n              proxy_http_version 1.1;\n              proxy_set_header Host $host:$server_port;\n              proxy_set_header Connection \"\";\n              proxy_pass http://storage/logs.fd.io/$1;\n              server_name_in_redirect off;\n            }\n            location ~ (.*xml.gz)$ {\n              add_header Content-Encoding gzip;\n              add_header Content-Type application/xml;\n              chunked_transfer_encoding off;\n              proxy_connect_timeout 300;\n              proxy_http_version 1.1;\n              proxy_set_header Host $host:$server_port;\n              proxy_set_header Connection \"\";\n              proxy_pass http://storage/logs.fd.io/$1;\n              server_name_in_redirect off;\n            }\n        }\n        EOH\n        destination = \"custom/logs.conf\"\n      }\n\n      # The service stanza instructs Nomad to register a service with Consul.\n      #\n      # For more information and examples on the \"task\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/service.html\n      #\n      service {\n        name       = \"nginx\"\n        port       = \"https\"\n        tags       = [ \"logs\" ]\n      }\n\n      # The \"resources\" stanza describes the requirements a task needs to\n      # execute. Resource requirements include memory, network, cpu, and more.\n      # This ensures the task will execute on a machine that contains enough\n      # resource capacity.\n      #\n      # For more information and examples on the \"resources\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/resources.html\n      #\n      resources {\n        cpu        = 2000\n        memory     = 4096\n        network {\n          mode     = \"bridge\"\n          port \"https\" {\n            static = 443\n          }\n        }\n      }\n    }\n  }\n}",
+            "template": "job \"${job_name}\" {\n  # The \"region\" parameter specifies the region in which to execute the job.\n  # If omitted, this inherits the default region name of \"global\".\n  # region = \"global\"\n  #\n  # The \"datacenters\" parameter specifies the list of datacenters which should\n  # be considered when placing this task. This must be provided.\n  datacenters = \"${datacenters}\"\n\n  # The \"type\" parameter controls the type of job, which impacts the scheduler's\n  # decision on placement. This configuration is optional and defaults to\n  # \"service\". For a full list of job types and their differences, please see\n  # the online documentation.\n  #\n  # For more information, please see the online documentation at:\n  #\n  #     https://www.nomadproject.io/docs/jobspec/schedulers.html\n  #\n  type = \"service\"\n\n  update {\n    # The \"max_parallel\" parameter specifies the maximum number of updates to\n    # perform in parallel. In this case, this specifies to update a single task\n    # at a time.\n    max_parallel      = 0\n\n    # The \"min_healthy_time\" parameter specifies the minimum time the allocation\n    # must be in the healthy state before it is marked as healthy and unblocks\n    # further allocations from being updated.\n    min_healthy_time  = \"10s\"\n\n    # The \"healthy_deadline\" parameter specifies the deadline in which the\n    # allocation must be marked as healthy after which the allocation is\n    # automatically transitioned to unhealthy. Transitioning to unhealthy will\n    # fail the deployment and potentially roll back the job if \"auto_revert\" is\n    # set to true.\n    healthy_deadline  = \"3m\"\n\n    # The \"progress_deadline\" parameter specifies the deadline in which an\n    # allocation must be marked as healthy. The deadline begins when the first\n    # allocation for the deployment is created and is reset whenever an allocation\n    # as part of the deployment transitions to a healthy state. If no allocation\n    # transitions to the healthy state before the progress deadline, the\n    # deployment is marked as failed.\n    progress_deadline = \"10m\"\n\n    # The \"auto_revert\" parameter specifies if the job should auto-revert to the\n    # last stable job on deployment failure. A job is marked as stable if all the\n    # allocations as part of its deployment were marked healthy.\n    auto_revert       = false\n\n    # The \"canary\" parameter specifies that changes to the job that would result\n    # in destructive updates should create the specified number of canaries\n    # without stopping any previous allocations. Once the operator determines the\n    # canaries are healthy, they can be promoted which unblocks a rolling update\n    # of the remaining allocations at a rate of \"max_parallel\".\n    #\n    # Further, setting \"canary\" equal to the count of the task group allows\n    # blue/green deployments. When the job is updated, a full set of the new\n    # version is deployed and upon promotion the old version is stopped.\n    canary            = 0\n  }\n\n  # The reschedule stanza specifies the group's rescheduling strategy. If\n  # specified at the job level, the configuration will apply to all groups\n  # within the job. If the reschedule stanza is present on both the job and the\n  # group, they are merged with the group stanza taking the highest precedence\n  # and then the job.\n  reschedule {\n    delay             = \"30s\"\n    delay_function    = \"constant\"\n    unlimited         = true\n  }\n\n  # The \"group\" stanza defines a series of tasks that should be co-located on\n  # the same Nomad client. Any task within a group will be placed on the same\n  # client.\n  #\n  # For more information and examples on the \"group\" stanza, please see\n  # the online documentation at:\n  #\n  #     https://www.nomadproject.io/docs/job-specification/group.html\n  #\n  group \"prod-group1-nginx\" {\n    # The \"count\" parameter specifies the number of the task groups that should\n    # be running under this group. This value must be non-negative and defaults\n    # to 1.\n    count             = 1\n\n    # https://www.nomadproject.io/docs/job-specification/volume\n    %{ if use_host_volume }\n    volume \"prod-volume1-nginx\" {\n      type            = \"host\"\n      read_only       = false\n      source          = \"${host_volume}\"\n    }\n    %{ endif }\n\n    # The restart stanza configures a tasks's behavior on task failure. Restarts\n    # happen on the client that is running the task.\n    #\n    # https://www.nomadproject.io/docs/job-specification/restart\n    #\n    restart {\n      interval        = \"30m\"\n      attempts        = 40\n      delay           = \"15s\"\n      mode            = \"delay\"\n    }\n\n    # The constraint allows restricting the set of eligible nodes. Constraints\n    # may filter on attributes or client metadata.\n    #\n    # For more information and examples on the \"volume\" stanza, please see\n    # the online documentation at:\n    #\n    #     https://www.nomadproject.io/docs/job-specification/constraint\n    #\n    constraint {\n      attribute       = \"$${attr.cpu.arch}\"\n      operator        = \"!=\"\n      value           = \"arm64\"\n    }\n\n    constraint {\n      attribute      = \"$${node.class}\"\n      value          = \"builder\"\n    }\n\n    # The \"task\" stanza creates an individual unit of work, such as a Docker\n    # container, web application, or batch processing.\n    #\n    # For more information and examples on the \"task\" stanza, please see\n    # the online documentation at:\n    #\n    #     https://www.nomadproject.io/docs/job-specification/task.html\n    #\n    task \"prod-task1-nginx\" {\n      # The \"driver\" parameter specifies the task driver that should be used to\n      # run the task.\n      driver          = \"docker\"\n\n      # The \"config\" stanza specifies the driver configuration, which is passed\n      # directly to the driver to start the task. The details of configurations\n      # are specific to each driver, so please see specific driver\n      # documentation for more information.\n      config {\n        image         = \"nginx:stable\"\n        port_map {\n          https       = 443\n        }\n        privileged    = false\n        volumes       = [\n          \"/etc/ssl/certs/logs.nginx.service.consul.crt:/etc/ssl/certs/logs.nginx.service.consul.crt\",\n          \"/etc/ssl/private/logs.nginx.service.consul.key:/etc/ssl/private/logs.nginx.service.consul.key\",\n          \"custom/upstream.conf:/etc/nginx/conf.d/upstream.conf\",\n          \"custom/server_logs.conf:/etc/nginx/conf.d/server_logs.conf\"\n        ]\n      }\n\n      # The \"template\" stanza instructs Nomad to manage a template, such as\n      # a configuration file or script. This template can optionally pull data\n      # from Consul or Vault to populate runtime configuration data.\n      #\n      # For more information and examples on the \"template\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/template.html\n      #\n      template {\n        data = \u003c\u003cEOH\n          upstream storage {\n            {{ range service \"storage\" }}\n              server {{ .Address }}:{{ .Port }};\n            {{ end }}\n          }\n        EOH\n        destination = \"custom/upstream.conf\"\n      }\n      template {\n        data = \u003c\u003cEOH\n          server {\n            listen 443 ssl default_server;\n            server_name logs.nginx.service.consul;\n\n            ssl_certificate /etc/ssl/certs/logs.nginx.service.consul.crt;\n            ssl_certificate_key /etc/ssl/private/logs.nginx.service.consul.key;\n            ssl_protocols TLSv1.2;\n            ssl_prefer_server_ciphers on;\n            ssl_ciphers \"ECDHE-ECDSA-AES256-GCM-SHA384:ECDHE-RSA-AES256-GCM-SHA384:ECDHE-ECDSA-CHACHA20-POLY1305:ECDHE-RSA-CHACHA20-POLY1305:ECDHE-ECDSA-AES256-SHA384:ECDHE-RSA-AES256-SHA384\";\n            ssl_session_timeout 10m;\n            ssl_session_cache shared:SSL:10m;\n            ssl_session_tickets off;\n            ssl_stapling on;\n            ssl_stapling_verify on;\n\n            fastcgi_hide_header X-Powered-By;\n\n            client_max_body_size 0;\n            client_header_timeout 60;\n            client_body_timeout 86400;\n            fastcgi_read_timeout 86400;\n            proxy_connect_timeout 60;\n            proxy_read_timeout 86400;\n            proxy_send_timeout 86400;\n            send_timeout 86400;\n\n            keepalive_timeout 70;\n            location / {\n              chunked_transfer_encoding off;\n              proxy_connect_timeout 300;\n              proxy_http_version 1.1;\n              proxy_set_header Host $host:$server_port;\n              proxy_set_header Connection \"\";\n              proxy_pass http://storage/logs.fd.io/;\n              server_name_in_redirect off;\n            }\n            location ~ (.*html.gz)$ {\n              add_header Content-Encoding gzip;\n              add_header Content-Type text/html;\n              chunked_transfer_encoding off;\n              proxy_connect_timeout 300;\n              proxy_http_version 1.1;\n              proxy_set_header Host $host:$server_port;\n              proxy_set_header Connection \"\";\n              proxy_pass http://storage/logs.fd.io/$1;\n              server_name_in_redirect off;\n            }\n            location ~ (.*txt.gz|.*log.gz)$ {\n              add_header Content-Encoding gzip;\n              add_header Content-Type text/plain;\n              chunked_transfer_encoding off;\n              proxy_connect_timeout 300;\n              proxy_http_version 1.1;\n              proxy_set_header Host $host:$server_port;\n              proxy_set_header Connection \"\";\n              proxy_pass http://storage/logs.fd.io/$1;\n              server_name_in_redirect off;\n            }\n            location ~ (.*xml.gz)$ {\n              add_header Content-Encoding gzip;\n              add_header Content-Type application/xml;\n              chunked_transfer_encoding off;\n              proxy_connect_timeout 300;\n              proxy_http_version 1.1;\n              proxy_set_header Host $host:$server_port;\n              proxy_set_header Connection \"\";\n              proxy_pass http://storage/logs.fd.io/$1;\n              server_name_in_redirect off;\n            }\n        }\n        EOH\n        destination = \"custom/logs.conf\"\n      }\n\n      # The service stanza instructs Nomad to register a service with Consul.\n      #\n      # For more information and examples on the \"task\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/service.html\n      #\n      service {\n        name       = \"nginx\"\n        port       = \"https\"\n        tags       = [ \"logs\" ]\n      }\n\n      # The \"resources\" stanza describes the requirements a task needs to\n      # execute. Resource requirements include memory, network, cpu, and more.\n      # This ensures the task will execute on a machine that contains enough\n      # resource capacity.\n      #\n      # For more information and examples on the \"resources\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/resources.html\n      #\n      resources {\n        cpu        = 2000\n        memory     = 4096\n        network {\n          mode     = \"bridge\"\n          port \"https\" {\n            static = 443\n          }\n        }\n      }\n    }\n  }\n}",
             "vars": {
               "datacenters": "yul1",
               "host_volume": "prod-volume-data1-1",
@@ -367,7 +369,8 @@
           "schema_version": 0,
           "attributes": {
             "allocation_ids": [
-              "8a81e41d-911d-e083-9bcd-b5b3c70b33fa"
+              "5f0b5208-cb84-507d-18d0-d294925c13e0",
+              "9a5e3312-8802-e842-1eb0-0cc01a4d4575"
             ],
             "datacenters": [
               "yul1"
@@ -378,9 +381,9 @@
             "deregister_on_id_change": true,
             "detach": false,
             "id": "prod-nginx",
-            "jobspec": "job \"prod-nginx\" {\n  # The \"region\" parameter specifies the region in which to execute the job.\n  # If omitted, this inherits the default region name of \"global\".\n  # region = \"global\"\n  #\n  # The \"datacenters\" parameter specifies the list of datacenters which should\n  # be considered when placing this task. This must be provided.\n  datacenters = \"yul1\"\n\n  # The \"type\" parameter controls the type of job, which impacts the scheduler's\n  # decision on placement. This configuration is optional and defaults to\n  # \"service\". For a full list of job types and their differences, please see\n  # the online documentation.\n  #\n  # For more information, please see the online documentation at:\n  #\n  #     https://www.nomadproject.io/docs/jobspec/schedulers.html\n  #\n  type = \"service\"\n\n  update {\n    # The \"max_parallel\" parameter specifies the maximum number of updates to\n    # perform in parallel. In this case, this specifies to update a single task\n    # at a time.\n    max_parallel      = 0\n\n    # The \"min_healthy_time\" parameter specifies the minimum time the allocation\n    # must be in the healthy state before it is marked as healthy and unblocks\n    # further allocations from being updated.\n    min_healthy_time  = \"10s\"\n\n    # The \"healthy_deadline\" parameter specifies the deadline in which the\n    # allocation must be marked as healthy after which the allocation is\n    # automatically transitioned to unhealthy. Transitioning to unhealthy will\n    # fail the deployment and potentially roll back the job if \"auto_revert\" is\n    # set to true.\n    healthy_deadline  = \"3m\"\n\n    # The \"progress_deadline\" parameter specifies the deadline in which an\n    # allocation must be marked as healthy. The deadline begins when the first\n    # allocation for the deployment is created and is reset whenever an allocation\n    # as part of the deployment transitions to a healthy state. If no allocation\n    # transitions to the healthy state before the progress deadline, the\n    # deployment is marked as failed.\n    progress_deadline = \"10m\"\n\n    # The \"auto_revert\" parameter specifies if the job should auto-revert to the\n    # last stable job on deployment failure. A job is marked as stable if all the\n    # allocations as part of its deployment were marked healthy.\n    auto_revert       = false\n\n    # The \"canary\" parameter specifies that changes to the job that would result\n    # in destructive updates should create the specified number of canaries\n    # without stopping any previous allocations. Once the operator determines the\n    # canaries are healthy, they can be promoted which unblocks a rolling update\n    # of the remaining allocations at a rate of \"max_parallel\".\n    #\n    # Further, setting \"canary\" equal to the count of the task group allows\n    # blue/green deployments. When the job is updated, a full set of the new\n    # version is deployed and upon promotion the old version is stopped.\n    canary            = 0\n  }\n\n  # The reschedule stanza specifies the group's rescheduling strategy. If\n  # specified at the job level, the configuration will apply to all groups\n  # within the job. If the reschedule stanza is present on both the job and the\n  # group, they are merged with the group stanza taking the highest precedence\n  # and then the job.\n  reschedule {\n    delay             = \"30s\"\n    delay_function    = \"constant\"\n    unlimited         = true\n  }\n\n  # The \"group\" stanza defines a series of tasks that should be co-located on\n  # the same Nomad client. Any task within a group will be placed on the same\n  # client.\n  #\n  # For more information and examples on the \"group\" stanza, please see\n  # the online documentation at:\n  #\n  #     https://www.nomadproject.io/docs/job-specification/group.html\n  #\n  group \"prod-group1-nginx\" {\n    # The \"count\" parameter specifies the number of the task groups that should\n    # be running under this group. This value must be non-negative and defaults\n    # to 1.\n    count = 1\n\n    # https://www.nomadproject.io/docs/job-specification/volume\n    \n    volume \"prod-volume1-nginx\" {\n      type      = \"host\"\n      read_only = false\n      source    = \"prod-volume-data1-1\"\n    }\n    \n\n    # The restart stanza configures a tasks's behavior on task failure. Restarts\n    # happen on the client that is running the task.\n    #\n    # https://www.nomadproject.io/docs/job-specification/restart\n    #\n    restart {\n      interval  = \"30m\"\n      attempts  = 40\n      delay     = \"15s\"\n      mode      = \"delay\"\n    }\n\n    # The \"task\" stanza creates an individual unit of work, such as a Docker\n    # container, web application, or batch processing.\n    #\n    # For more information and examples on the \"task\" stanza, please see\n    # the online documentation at:\n    #\n    #     https://www.nomadproject.io/docs/job-specification/task.html\n    #\n    task \"prod-task1-nginx\" {\n      # The \"driver\" parameter specifies the task driver that should be used to\n      # run the task.\n      driver = \"docker\"\n\n      # The \"config\" stanza specifies the driver configuration, which is passed\n      # directly to the driver to start the task. The details of configurations\n      # are specific to each driver, so please see specific driver\n      # documentation for more information.\n      config {\n        image        = \"nginx:stable\"\n        port_map {\n          https      = 443\n        }\n        privileged   = false\n        volumes      = [\n          \"/etc/ssl/certs/docs.nginx.service.consul.crt:/etc/ssl/certs/docs.nginx.service.consul.crt\",\n          \"/etc/ssl/private/docs.nginx.service.consul.key:/etc/ssl/private/docs.nginx.service.consul.key\",\n          \"/etc/ssl/certs/logs.nginx.service.consul.crt:/etc/ssl/certs/logs.nginx.service.consul.crt\",\n          \"/etc/ssl/private/logs.nginx.service.consul.key:/etc/ssl/private/logs.nginx.service.consul.key\",\n          \"custom/upstream.conf:/etc/nginx/conf.d/upstream.conf\",\n          \"custom/logs.conf:/etc/nginx/conf.d/logs.conf\",\n          \"custom/docs.conf:/etc/nginx/conf.d/docs.conf\"\n        ]\n      }\n\n      # The \"template\" stanza instructs Nomad to manage a template, such as\n      # a configuration file or script. This template can optionally pull data\n      # from Consul or Vault to populate runtime configuration data.\n      #\n      # For more information and examples on the \"template\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/template.html\n      #\n      template {\n        data = \u003c\u003cEOH\n          upstream storage {\n            {{ range service \"storage\" }}\n              server {{ .Address }}:{{ .Port }};\n            {{ end }}\n          }\n        EOH\n        destination = \"custom/upstream.conf\"\n      }\n      template {\n        data = \u003c\u003cEOH\n          server {\n            listen 443 ssl default_server;\n            server_name logs.nginx.service.consul;\n            keepalive_timeout 70;\n            ssl_session_cache shared:SSL:10m;\n            ssl_session_timeout 10m;\n            ssl_protocols TLSv1.2;\n            ssl_prefer_server_ciphers on;\n            ssl_ciphers \"ECDHE-ECDSA-AES256-GCM-SHA384:ECDHE-RSA-AES256-GCM-SHA384:ECDHE-ECDSA-CHACHA20-POLY1305:ECDHE-RSA-CHACHA20-POLY1305:ECDHE-ECDSA-AES256-SHA384:ECDHE-RSA-AES256-SHA384\";\n            ssl_certificate /etc/ssl/certs/logs.nginx.service.consul.crt;\n            ssl_certificate_key /etc/ssl/private/logs.nginx.service.consul.key;\n            location / {\n              chunked_transfer_encoding off;\n              proxy_connect_timeout 300;\n              proxy_http_version 1.1;\n              proxy_set_header Host $host:$server_port;\n              proxy_set_header Connection \"\";\n              proxy_pass http://storage/logs.fd.io/;\n              server_name_in_redirect off;\n            }\n            location ~ (.*html.gz)$ {\n              add_header Content-Encoding gzip;\n              add_header Content-Type text/html;\n              chunked_transfer_encoding off;\n              proxy_connect_timeout 300;\n              proxy_http_version 1.1;\n              proxy_set_header Host $host:$server_port;\n              proxy_set_header Connection \"\";\n              proxy_pass http://storage/logs.fd.io/$1;\n              server_name_in_redirect off;\n            }\n            location ~ (.*txt.gz|.*log.gz)$ {\n              add_header Content-Encoding gzip;\n              add_header Content-Type text/plain;\n              chunked_transfer_encoding off;\n              proxy_connect_timeout 300;\n              proxy_http_version 1.1;\n              proxy_set_header Host $host:$server_port;\n              proxy_set_header Connection \"\";\n              proxy_pass http://storage/logs.fd.io/$1;\n              server_name_in_redirect off;\n            }\n            location ~ (.*xml.gz)$ {\n              add_header Content-Encoding gzip;\n              add_header Content-Type application/xml;\n              chunked_transfer_encoding off;\n              proxy_connect_timeout 300;\n              proxy_http_version 1.1;\n              proxy_set_header Host $host:$server_port;\n              proxy_set_header Connection \"\";\n              proxy_pass http://storage/logs.fd.io/$1;\n              server_name_in_redirect off;\n            }\n        }\n        EOH\n        destination = \"custom/logs.conf\"\n      }\n      template {\n        data = \u003c\u003cEOH\n          server {\n            listen 443 ssl;\n            server_name docs.nginx.service.consul;\n            keepalive_timeout 70;\n            ssl_session_cache shared:SSL:10m;\n            ssl_session_timeout 10m;\n            ssl_protocols TLSv1.2;\n            ssl_prefer_server_ciphers on;\n            ssl_ciphers \"ECDHE-ECDSA-AES256-GCM-SHA384:ECDHE-RSA-AES256-GCM-SHA384:ECDHE-ECDSA-CHACHA20-POLY1305:ECDHE-RSA-CHACHA20-POLY1305:ECDHE-ECDSA-AES256-SHA384:ECDHE-RSA-AES256-SHA384\";\n            ssl_certificate /etc/ssl/certs/docs.nginx.service.consul.crt;\n            ssl_certificate_key /etc/ssl/private/docs.nginx.service.consul.key;\n            location / {\n              chunked_transfer_encoding off;\n              proxy_connect_timeout 300;\n              proxy_http_version 1.1;\n              proxy_set_header Host $host:$server_port;\n              proxy_set_header Connection \"\";\n              proxy_pass http://storage/docs.fd.io/;\n              server_name_in_redirect off;\n            }\n          }\n        EOH\n        destination = \"custom/docs.conf\"\n      }\n\n      # The service stanza instructs Nomad to register a service with Consul.\n      #\n      # For more information and examples on the \"task\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/service.html\n      #\n      service {\n        name       = \"nginx\"\n        port       = \"https\"\n        tags       = [ \"docs\", \"logs\" ]\n      }\n\n      # The \"resources\" stanza describes the requirements a task needs to\n      # execute. Resource requirements include memory, network, cpu, and more.\n      # This ensures the task will execute on a machine that contains enough\n      # resource capacity.\n      #\n      # For more information and examples on the \"resources\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/resources.html\n      #\n      resources {\n        cpu        = 2000\n        memory     = 4096\n        network {\n          mode     = \"bridge\"\n          port \"https\" {\n            static = 443\n          }\n        }\n      }\n    }\n  }\n}",
+            "jobspec": "job \"prod-nginx\" {\n  # The \"region\" parameter specifies the region in which to execute the job.\n  # If omitted, this inherits the default region name of \"global\".\n  # region = \"global\"\n  #\n  # The \"datacenters\" parameter specifies the list of datacenters which should\n  # be considered when placing this task. This must be provided.\n  datacenters = \"yul1\"\n\n  # The \"type\" parameter controls the type of job, which impacts the scheduler's\n  # decision on placement. This configuration is optional and defaults to\n  # \"service\". For a full list of job types and their differences, please see\n  # the online documentation.\n  #\n  # For more information, please see the online documentation at:\n  #\n  #     https://www.nomadproject.io/docs/jobspec/schedulers.html\n  #\n  type = \"service\"\n\n  update {\n    # The \"max_parallel\" parameter specifies the maximum number of updates to\n    # perform in parallel. In this case, this specifies to update a single task\n    # at a time.\n    max_parallel      = 0\n\n    # The \"min_healthy_time\" parameter specifies the minimum time the allocation\n    # must be in the healthy state before it is marked as healthy and unblocks\n    # further allocations from being updated.\n    min_healthy_time  = \"10s\"\n\n    # The \"healthy_deadline\" parameter specifies the deadline in which the\n    # allocation must be marked as healthy after which the allocation is\n    # automatically transitioned to unhealthy. Transitioning to unhealthy will\n    # fail the deployment and potentially roll back the job if \"auto_revert\" is\n    # set to true.\n    healthy_deadline  = \"3m\"\n\n    # The \"progress_deadline\" parameter specifies the deadline in which an\n    # allocation must be marked as healthy. The deadline begins when the first\n    # allocation for the deployment is created and is reset whenever an allocation\n    # as part of the deployment transitions to a healthy state. If no allocation\n    # transitions to the healthy state before the progress deadline, the\n    # deployment is marked as failed.\n    progress_deadline = \"10m\"\n\n    # The \"auto_revert\" parameter specifies if the job should auto-revert to the\n    # last stable job on deployment failure. A job is marked as stable if all the\n    # allocations as part of its deployment were marked healthy.\n    auto_revert       = false\n\n    # The \"canary\" parameter specifies that changes to the job that would result\n    # in destructive updates should create the specified number of canaries\n    # without stopping any previous allocations. Once the operator determines the\n    # canaries are healthy, they can be promoted which unblocks a rolling update\n    # of the remaining allocations at a rate of \"max_parallel\".\n    #\n    # Further, setting \"canary\" equal to the count of the task group allows\n    # blue/green deployments. When the job is updated, a full set of the new\n    # version is deployed and upon promotion the old version is stopped.\n    canary            = 0\n  }\n\n  # The reschedule stanza specifies the group's rescheduling strategy. If\n  # specified at the job level, the configuration will apply to all groups\n  # within the job. If the reschedule stanza is present on both the job and the\n  # group, they are merged with the group stanza taking the highest precedence\n  # and then the job.\n  reschedule {\n    delay             = \"30s\"\n    delay_function    = \"constant\"\n    unlimited         = true\n  }\n\n  # The \"group\" stanza defines a series of tasks that should be co-located on\n  # the same Nomad client. Any task within a group will be placed on the same\n  # client.\n  #\n  # For more information and examples on the \"group\" stanza, please see\n  # the online documentation at:\n  #\n  #     https://www.nomadproject.io/docs/job-specification/group.html\n  #\n  group \"prod-group1-nginx\" {\n    # The \"count\" parameter specifies the number of the task groups that should\n    # be running under this group. This value must be non-negative and defaults\n    # to 1.\n    count             = 1\n\n    # https://www.nomadproject.io/docs/job-specification/volume\n    \n    volume \"prod-volume1-nginx\" {\n      type            = \"host\"\n      read_only       = false\n      source          = \"prod-volume-data1-1\"\n    }\n    \n\n    # The restart stanza configures a tasks's behavior on task failure. Restarts\n    # happen on the client that is running the task.\n    #\n    # https://www.nomadproject.io/docs/job-specification/restart\n    #\n    restart {\n      interval        = \"30m\"\n      attempts        = 40\n      delay           = \"15s\"\n      mode            = \"delay\"\n    }\n\n    # The constraint allows restricting the set of eligible nodes. Constraints\n    # may filter on attributes or client metadata.\n    #\n    # For more information and examples on the \"volume\" stanza, please see\n    # the online documentation at:\n    #\n    #     https://www.nomadproject.io/docs/job-specification/constraint\n    #\n    constraint {\n      attribute       = \"${attr.cpu.arch}\"\n      operator        = \"!=\"\n      value           = \"arm64\"\n    }\n\n    constraint {\n      attribute      = \"${node.class}\"\n      value          = \"builder\"\n    }\n\n    # The \"task\" stanza creates an individual unit of work, such as a Docker\n    # container, web application, or batch processing.\n    #\n    # For more information and examples on the \"task\" stanza, please see\n    # the online documentation at:\n    #\n    #     https://www.nomadproject.io/docs/job-specification/task.html\n    #\n    task \"prod-task1-nginx\" {\n      # The \"driver\" parameter specifies the task driver that should be used to\n      # run the task.\n      driver          = \"docker\"\n\n      # The \"config\" stanza specifies the driver configuration, which is passed\n      # directly to the driver to start the task. The details of configurations\n      # are specific to each driver, so please see specific driver\n      # documentation for more information.\n      config {\n        image         = \"nginx:stable\"\n        port_map {\n          https       = 443\n        }\n        privileged    = false\n        volumes       = [\n          \"/etc/ssl/certs/logs.nginx.service.consul.crt:/etc/ssl/certs/logs.nginx.service.consul.crt\",\n          \"/etc/ssl/private/logs.nginx.service.consul.key:/etc/ssl/private/logs.nginx.service.consul.key\",\n          \"custom/upstream.conf:/etc/nginx/conf.d/upstream.conf\",\n          \"custom/server_logs.conf:/etc/nginx/conf.d/server_logs.conf\"\n        ]\n      }\n\n      # The \"template\" stanza instructs Nomad to manage a template, such as\n      # a configuration file or script. This template can optionally pull data\n      # from Consul or Vault to populate runtime configuration data.\n      #\n      # For more information and examples on the \"template\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/template.html\n      #\n      template {\n        data = \u003c\u003cEOH\n          upstream storage {\n            {{ range service \"storage\" }}\n              server {{ .Address }}:{{ .Port }};\n            {{ end }}\n          }\n        EOH\n        destination = \"custom/upstream.conf\"\n      }\n      template {\n        data = \u003c\u003cEOH\n          server {\n            listen 443 ssl default_server;\n            server_name logs.nginx.service.consul;\n\n            ssl_certificate /etc/ssl/certs/logs.nginx.service.consul.crt;\n            ssl_certificate_key /etc/ssl/private/logs.nginx.service.consul.key;\n            ssl_protocols TLSv1.2;\n            ssl_prefer_server_ciphers on;\n            ssl_ciphers \"ECDHE-ECDSA-AES256-GCM-SHA384:ECDHE-RSA-AES256-GCM-SHA384:ECDHE-ECDSA-CHACHA20-POLY1305:ECDHE-RSA-CHACHA20-POLY1305:ECDHE-ECDSA-AES256-SHA384:ECDHE-RSA-AES256-SHA384\";\n            ssl_session_timeout 10m;\n            ssl_session_cache shared:SSL:10m;\n            ssl_session_tickets off;\n            ssl_stapling on;\n            ssl_stapling_verify on;\n\n            fastcgi_hide_header X-Powered-By;\n\n            client_max_body_size 0;\n            client_header_timeout 60;\n            client_body_timeout 86400;\n            fastcgi_read_timeout 86400;\n            proxy_connect_timeout 60;\n            proxy_read_timeout 86400;\n            proxy_send_timeout 86400;\n            send_timeout 86400;\n\n            keepalive_timeout 70;\n            location / {\n              chunked_transfer_encoding off;\n              proxy_connect_timeout 300;\n              proxy_http_version 1.1;\n              proxy_set_header Host $host:$server_port;\n              proxy_set_header Connection \"\";\n              proxy_pass http://storage/logs.fd.io/;\n              server_name_in_redirect off;\n            }\n            location ~ (.*html.gz)$ {\n              add_header Content-Encoding gzip;\n              add_header Content-Type text/html;\n              chunked_transfer_encoding off;\n              proxy_connect_timeout 300;\n              proxy_http_version 1.1;\n              proxy_set_header Host $host:$server_port;\n              proxy_set_header Connection \"\";\n              proxy_pass http://storage/logs.fd.io/$1;\n              server_name_in_redirect off;\n            }\n            location ~ (.*txt.gz|.*log.gz)$ {\n              add_header Content-Encoding gzip;\n              add_header Content-Type text/plain;\n              chunked_transfer_encoding off;\n              proxy_connect_timeout 300;\n              proxy_http_version 1.1;\n              proxy_set_header Host $host:$server_port;\n              proxy_set_header Connection \"\";\n              proxy_pass http://storage/logs.fd.io/$1;\n              server_name_in_redirect off;\n            }\n            location ~ (.*xml.gz)$ {\n              add_header Content-Encoding gzip;\n              add_header Content-Type application/xml;\n              chunked_transfer_encoding off;\n              proxy_connect_timeout 300;\n              proxy_http_version 1.1;\n              proxy_set_header Host $host:$server_port;\n              proxy_set_header Connection \"\";\n              proxy_pass http://storage/logs.fd.io/$1;\n              server_name_in_redirect off;\n            }\n        }\n        EOH\n        destination = \"custom/logs.conf\"\n      }\n\n      # The service stanza instructs Nomad to register a service with Consul.\n      #\n      # For more information and examples on the \"task\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/service.html\n      #\n      service {\n        name       = \"nginx\"\n        port       = \"https\"\n        tags       = [ \"logs\" ]\n      }\n\n      # The \"resources\" stanza describes the requirements a task needs to\n      # execute. Resource requirements include memory, network, cpu, and more.\n      # This ensures the task will execute on a machine that contains enough\n      # resource capacity.\n      #\n      # For more information and examples on the \"resources\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/resources.html\n      #\n      resources {\n        cpu        = 2000\n        memory     = 4096\n        network {\n          mode     = \"bridge\"\n          port \"https\" {\n            static = 443\n          }\n        }\n      }\n    }\n  }\n}",
             "json": null,
-            "modify_index": "8993958",
+            "modify_index": "9138746",
             "name": "prod-nginx",
             "namespace": "default",
             "policy_override": null,
@@ -430,9 +433,9 @@
           "schema_version": 0,
           "attributes": {
             "filename": null,
-            "id": "170256de3b14e7562d5d4b196864b5c0ad562cf124c5866d85bd81a3f35bcc27",
-            "rendered": "job \"prod-prometheus\" {\n  # The \"region\" parameter specifies the region in which to execute the job.\n  # If omitted, this inherits the default region name of \"global\".\n  # region = \"global\"\n  #\n  # The \"datacenters\" parameter specifies the list of datacenters which should\n  # be considered when placing this task. This must be provided.\n  datacenters         = \"yul1\"\n\n  # The \"type\" parameter controls the type of job, which impacts the scheduler's\n  # decision on placement. This configuration is optional and defaults to\n  # \"service\". For a full list of job types and their differences, please see\n  # the online documentation.\n  #\n  # For more information, please see the online documentation at:\n  #\n  #     https://www.nomadproject.io/docs/jobspec/schedulers\n  #\n  type                = \"service\"\n\n  update {\n    # The \"max_parallel\" parameter specifies the maximum number of updates to\n    # perform in parallel. In this case, this specifies to update a single task\n    # at a time.\n    max_parallel      = 1\n\n    health_check      = \"checks\"\n\n    # The \"min_healthy_time\" parameter specifies the minimum time the allocation\n    # must be in the healthy state before it is marked as healthy and unblocks\n    # further allocations from being updated.\n    min_healthy_time  = \"10s\"\n\n    # The \"healthy_deadline\" parameter specifies the deadline in which the\n    # allocation must be marked as healthy after which the allocation is\n    # automatically transitioned to unhealthy. Transitioning to unhealthy will\n    # fail the deployment and potentially roll back the job if \"auto_revert\" is\n    # set to true.\n    healthy_deadline  = \"3m\"\n\n    # The \"progress_deadline\" parameter specifies the deadline in which an\n    # allocation must be marked as healthy. The deadline begins when the first\n    # allocation for the deployment is created and is reset whenever an allocation\n    # as part of the deployment transitions to a healthy state. If no allocation\n    # transitions to the healthy state before the progress deadline, the\n    # deployment is marked as failed.\n    progress_deadline = \"10m\"\n\n\n    # The \"canary\" parameter specifies that changes to the job that would result\n    # in destructive updates should create the specified number of canaries\n    # without stopping any previous allocations. Once the operator determines the\n    # canaries are healthy, they can be promoted which unblocks a rolling update\n    # of the remaining allocations at a rate of \"max_parallel\".\n    #\n    # Further, setting \"canary\" equal to the count of the task group allows\n    # blue/green deployments. When the job is updated, a full set of the new\n    # version is deployed and upon promotion the old version is stopped.\n    canary            = 1\n\n    # Specifies if the job should auto-promote to the canary version when all\n    # canaries become healthy during a deployment. Defaults to false which means\n    # canaries must be manually updated with the nomad deployment promote\n    # command.\n    auto_promote      = true\n\n    # The \"auto_revert\" parameter specifies if the job should auto-revert to the\n    # last stable job on deployment failure. A job is marked as stable if all the\n    # allocations as part of its deployment were marked healthy.\n    auto_revert       = true\n\n  }\n\n  # The reschedule stanza specifies the group's rescheduling strategy. If\n  # specified at the job level, the configuration will apply to all groups\n  # within the job. If the reschedule stanza is present on both the job and the\n  # group, they are merged with the group stanza taking the highest precedence\n  # and then the job.\n  reschedule {\n    delay             = \"30s\"\n    delay_function    = \"constant\"\n    unlimited         = true\n  }\n\n  # The \"group\" stanza defines a series of tasks that should be co-located on\n  # the same Nomad client. Any task within a group will be placed on the same\n  # client.\n  #\n  # For more information and examples on the \"group\" stanza, please see\n  # the online documentation at:\n  #\n  #     https://www.nomadproject.io/docs/job-specification/group\n  #\n  group \"prod-group1-prometheus\" {\n    # The \"count\" parameter specifies the number of the task groups that should\n    # be running under this group. This value must be non-negative and defaults\n    # to 1.\n    count               = 4\n\n    # The restart stanza configures a tasks's behavior on task failure. Restarts\n    # happen on the client that is running the task.\n    #\n    # https://www.nomadproject.io/docs/job-specification/restart\n    #\n    restart {\n      interval  = \"30m\"\n      attempts  = 40\n      delay     = \"15s\"\n      mode      = \"delay\"\n    }\n\n    # The volume stanza allows the group to specify that it requires a given\n    # volume from the cluster.\n    #\n    # For more information and examples on the \"volume\" stanza, please see\n    # the online documentation at:\n    #\n    #     https://www.nomadproject.io/docs/job-specification/volume\n    #\n    \n    volume \"prod-volume1-prometheus\" {\n      type              = \"host\"\n      read_only         = false\n      source            = \"prod-volume-data1-1\"\n    }\n    \n\n    # The constraint allows restricting the set of eligible nodes. Constraints\n    # may filter on attributes or client metadata.\n    #\n    # For more information and examples on the \"volume\" stanza, please see\n    # the online documentation at:\n    #\n    #     https://www.nomadproject.io/docs/job-specification/constraint\n    #\n    constraint {\n      attribute         = \"${attr.cpu.arch}\"\n      operator          = \"!=\"\n      value             = \"arm64\"\n    }\n\n    # The \"task\" stanza creates an individual unit of work, such as a Docker\n    # container, web application, or batch processing.\n    #\n    # For more information and examples on the \"task\" stanza, please see\n    # the online documentation at:\n    #\n    #     https://www.nomadproject.io/docs/job-specification/task\n    #\n    task \"prod-task1-prometheus\" {\n      # The \"driver\" parameter specifies the task driver that should be used to\n      # run the task.\n      driver            = \"exec\"\n\n      \n      volume_mount {\n        volume          = \"prod-volume1-prometheus\"\n        destination     = \"/data/\"\n        read_only       = false\n      }\n      \n\n      \n\n      # The \"config\" stanza specifies the driver configuration, which is passed\n      # directly to the driver to start the task. The details of configurations\n      # are specific to each driver, so please see specific driver\n      # documentation for more information.\n      config {\n        command         = \"local/prometheus-2.28.1.linux-amd64/prometheus\"\n        args            = [\n          \"--config.file=secrets/prometheus.yml\",\n          \"--storage.tsdb.path=/data/prometheus/\",\n          \"--storage.tsdb.retention.time=7d\"\n        ]\n      }\n\n      # The artifact stanza instructs Nomad to fetch and unpack a remote resource,\n      # such as a file, tarball, or binary. Nomad downloads artifacts using the\n      # popular go-getter library, which permits downloading artifacts from a\n      # variety of locations using a URL as the input source.\n      #\n      # For more information and examples on the \"artifact\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/artifact\n      #\n      artifact {\n        source          = \"https://github.com/prometheus/prometheus/releases/download/v2.28.1/prometheus-2.28.1.linux-amd64.tar.gz\"\n      }\n\n      # The \"template\" stanza instructs Nomad to manage a template, such as\n      # a configuration file or script. This template can optionally pull data\n      # from Consul or Vault to populate runtime configuration data.\n      #\n      # For more information and examples on the \"template\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/template\n      #\n      template {\n        change_mode     = \"noop\"\n        change_signal   = \"SIGINT\"\n        destination     = \"secrets/alerts.yml\"\n        left_delimiter  = \"{{{\"\n        right_delimiter = \"}}}\"\n        data            = \u003c\u003cEOH\n---\ngroups:\n- name: \"Jenkins Job Health Exporter\"\n  rules:\n  - alert: JenkinsJobHealthExporterFailures\n    expr: jenkins_job_failure{id=~\".*\"} \u003e jenkins_job_success{id=~\".*\"}\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Jenkins Job Health detected high failure rate on jenkins jobs.\"\n      description: \"Job: {{ $labels.id }}\"\n  - alert: JenkinsJobHealthExporterUnstable\n    expr: jenkins_job_unstable{id=~\".*\"} \u003e jenkins_job_success{id=~\".*\"}\n    for: 0m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Jenkins Job Health detected high unstable rate on jenkins jobs.\"\n      description: \"Job: {{ $labels.id }}\"\n- name: \"Consul\"\n  rules:\n  - alert: ConsulServiceHealthcheckFailed\n    expr: consul_catalog_service_node_healthy == 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Consul service healthcheck failed (instance {{ $labels.instance }}).\"\n      description: \"Service: `{{ $labels.service_name }}` Healthcheck: `{{ $labels.service_id }}`.\"\n  - alert: ConsulMissingMasterNode\n    expr: consul_raft_peers \u003c 3\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Consul missing master node (instance {{ $labels.instance }}).\"\n      description: \"Numbers of consul raft peers should be 3, in order to preserve quorum.\"\n  - alert: ConsulAgentUnhealthy\n    expr: consul_health_node_status{status=\"critical\"} == 1\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Consul agent unhealthy (instance {{ $labels.instance }}).\"\n      description: \"A Consul agent is down.\"\n- name: \"Hosts\"\n  rules:\n  - alert: NodeDown\n    expr: up == 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Prometheus target missing (instance {{ $labels.instance }}).\"\n      description: \"A Prometheus target has disappeared. An exporter might be crashed.\"\n  - alert: HostOutOfMemory\n    expr: node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes * 100 \u003c 10\n    for: 2m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host out of memory (instance {{ $labels.instance }}).\"\n      description: \"Node memory is filling up (\u003c 10% left).\"\n  - alert: HostOomKillDetected\n    expr: increase(node_vmstat_oom_kill[1m]) \u003e 0\n    for: 0m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host OOM kill detected (instance {{ $labels.instance }}).\"\n      description: \"OOM kill detected.\"\n  - alert: HostMemoryUnderMemoryPressure\n    expr: rate(node_vmstat_pgmajfault[1m]) \u003e 1000\n    for: 2m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host memory under memory pressure (instance {{ $labels.instance }}).\"\n      description: \"The node is under heavy memory pressure. High rate of major page faults.\"\n  - alert: HostOutOfDiskSpace\n    expr: (node_filesystem_avail_bytes * 100) / node_filesystem_size_bytes \u003c 10 and ON (instance, device, mountpoint) node_filesystem_readonly == 0\n    for: 2m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host out of disk space (instance {{ $labels.instance }}).\"\n      description: \"Disk is almost full (\u003c 10% left).\"\n  - alert: HostRaidDiskFailure\n    expr: node_md_disks{state=\"failed\"} \u003e 0\n    for: 2m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host RAID disk failure (instance {{ $labels.instance }}).\"\n      description: \"At least one device in RAID array on {{ $labels.instance }} failed. Array {{ $labels.md_device }} needs attention and possibly a disk swap.\"\n  - alert: HostConntrackLimit\n    expr: node_nf_conntrack_entries / node_nf_conntrack_entries_limit \u003e 0.8\n    for: 5m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host conntrack limit (instance {{ $labels.instance }}).\"\n      description: \"The number of conntrack is approching limit.\"\n  - alert: HostNetworkInterfaceSaturated\n    expr: (rate(node_network_receive_bytes_total{device!~\"^tap.*\"}[1m]) + rate(node_network_transmit_bytes_total{device!~\"^tap.*\"}[1m])) / node_network_speed_bytes{device!~\"^tap.*\"} \u003e 0.8\n    for: 1m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host Network Interface Saturated (instance {{ $labels.instance }}).\"\n      description: \"The network interface {{ $labels.interface }} on {{ $labels.instance }} is getting overloaded.\"\n  - alert: HostSystemdServiceCrashed\n    expr: node_systemd_unit_state{state=\"failed\"} == 1\n    for: 0m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host SystemD service crashed (instance {{ $labels.instance }}).\"\n      description: \"SystemD service crashed.\"\n  - alert: HostEdacCorrectableErrorsDetected\n    expr: increase(node_edac_correctable_errors_total[1m]) \u003e 0\n    for: 0m\n    labels:\n      severity: info\n    annotations:\n      summary: \"Host EDAC Correctable Errors detected (instance {{ $labels.instance }}).\"\n      description: '{{ $labels.instance }} has had {{ printf \"%.0f\" $value }} correctable memory errors reported by EDAC in the last 5 minutes.'\n  - alert: HostEdacUncorrectableErrorsDetected\n    expr: node_edac_uncorrectable_errors_total \u003e 0\n    for: 0m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host EDAC Uncorrectable Errors detected (instance {{ $labels.instance }}).\"\n      description: '{{ $labels.instance }} has had {{ printf \"%.0f\" $value }} uncorrectable memory errors reported by EDAC in the last 5 minutes.'\n- name: \"Min.io\"\n  rules:\n  - alert: MinioDiskOffline\n    expr: minio_offline_disks \u003e 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Minio disk offline (instance {{ $labels.instance }})\"\n      description: \"Minio disk is offline.\"\n  - alert: MinioStorageSpaceExhausted\n    expr: minio_disk_storage_free_bytes / 1024 / 1024 / 1024 \u003c 10\n    for: 2m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Minio storage space exhausted (instance {{ $labels.instance }}).\"\n      description: \"Minio storage space is low (\u003c 10 GB).\"\n- name: \"Prometheus\"\n  rules:\n  - alert: PrometheusConfigurationReloadFailure\n    expr: prometheus_config_last_reload_successful != 1\n    for: 0m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Prometheus configuration reload failure (instance {{ $labels.instance }}).\"\n      description: \"Prometheus configuration reload error.\"\n  - alert: PrometheusTooManyRestarts\n    expr: changes(process_start_time_seconds{job=~\"prometheus|pushgateway|alertmanager\"}[15m]) \u003e 2\n    for: 0m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Prometheus too many restarts (instance {{ $labels.instance }}).\"\n      description: \"Prometheus has restarted more than twice in the last 15 minutes. It might be crashlooping.\"\n  - alert: PrometheusAlertmanagerConfigurationReloadFailure\n    expr: alertmanager_config_last_reload_successful != 1\n    for: 0m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Prometheus AlertManager configuration reload failure (instance {{ $labels.instance }}).\"\n      description: \"AlertManager configuration reload error.\"\n  - alert: PrometheusRuleEvaluationFailures\n    expr: increase(prometheus_rule_evaluation_failures_total[3m]) \u003e 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Prometheus rule evaluation failures (instance {{ $labels.instance }}).\"\n      description: \"Prometheus encountered {{ $value }} rule evaluation failures, leading to potentially ignored alerts.\"\n  - alert: PrometheusTargetScrapingSlow\n    expr: prometheus_target_interval_length_seconds{quantile=\"0.9\"} \u003e 60\n    for: 5m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Prometheus target scraping slow (instance {{ $labels.instance }}).\"\n      description: \"Prometheus is scraping exporters slowly.\"\n  - alert: PrometheusTsdbCompactionsFailed\n    expr: increase(prometheus_tsdb_compactions_failed_total[1m]) \u003e 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Prometheus TSDB compactions failed (instance {{ $labels.instance }}).\"\n      description: \"Prometheus encountered {{ $value }} TSDB compactions failures.\"\n  - alert: PrometheusTsdbHeadTruncationsFailed\n    expr: increase(prometheus_tsdb_head_truncations_failed_total[1m]) \u003e 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Prometheus TSDB head truncations failed (instance {{ $labels.instance }}).\"\n      description: \"Prometheus encountered {{ $value }} TSDB head truncation failures.\"\n  - alert: PrometheusTsdbWalCorruptions\n    expr: increase(prometheus_tsdb_wal_corruptions_total[1m]) \u003e 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Prometheus TSDB WAL corruptions (instance {{ $labels.instance }}).\"\n      description: \"Prometheus encountered {{ $value }} TSDB WAL corruptions.\"\n  - alert: PrometheusTsdbWalTruncationsFailed\n    expr: increase(prometheus_tsdb_wal_truncations_failed_total[1m]) \u003e 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Prometheus TSDB WAL truncations failed (instance {{ $labels.instance }}).\"\n      description: \"Prometheus encountered {{ $value }} TSDB WAL truncation failures.\"\nEOH\n      }\n\n      template {\n        change_mode     = \"noop\"\n        change_signal   = \"SIGINT\"\n        destination     = \"secrets/prometheus.yml\"\n        data            = \u003c\u003cEOH\n---\nglobal:\n  scrape_interval:     5s\n  scrape_timeout:      5s\n  evaluation_interval: 5s\n\nalerting:\n  alertmanagers:\n  - consul_sd_configs:\n    - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n      services: [ 'alertmanager' ]\n\nrule_files:\n  - 'alerts.yml'\n\nscrape_configs:\n\n  - job_name: 'Nomad Cluster'\n    consul_sd_configs:\n    - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n      services: [ 'nomad-client', 'nomad' ]\n    relabel_configs:\n    - source_labels: [__meta_consul_tags]\n      regex: '(.*)http(.*)'\n      action: keep\n    metrics_path: /v1/metrics\n    params:\n      format: [ 'prometheus' ]\n\n  - job_name: 'Consul Cluster'\n    static_configs:\n      - targets: [ '10.30.51.22:8500' ]\n      - targets: [ '10.30.51.24:8500' ]\n      - targets: [ '10.30.51.25:8500' ]\n      - targets: [ '10.30.51.26:8500' ]\n      - targets: [ '10.30.51.28:8500' ]\n      - targets: [ '10.30.51.29:8500' ]\n      - targets: [ '10.30.51.30:8500' ]\n      - targets: [ '10.30.51.39:8500' ]\n      - targets: [ '10.30.51.40:8500' ]\n      - targets: [ '10.30.51.50:8500' ]\n      - targets: [ '10.30.51.51:8500' ]\n      - targets: [ '10.30.51.65:8500' ]\n      - targets: [ '10.30.51.66:8500' ]\n      - targets: [ '10.30.51.67:8500' ]\n      - targets: [ '10.30.51.68:8500' ]\n      - targets: [ '10.30.51.70:8500' ]\n      - targets: [ '10.30.51.71:8500' ]\n      - targets: [ '10.32.8.14:8500' ]\n      - targets: [ '10.32.8.15:8500' ]\n      - targets: [ '10.32.8.16:8500' ]\n      - targets: [ '10.32.8.17:8500' ]\n    metrics_path: /v1/agent/metrics\n    params:\n      format: [ 'prometheus' ]\n\n  - job_name: 'Blackbox Exporter (icmp)'\n    static_configs:\n      - targets: [ 'gerrit.fd.io' ]\n      - targets: [ 'jenkins.fd.io' ]\n      - targets: [ '10.32.8.17' ]\n    params:\n      module: [ 'icmp_v4' ]\n    relabel_configs:\n      - source_labels: [__address__]\n        target_label: __param_target\n      - source_labels: [__param_target]\n        target_label: instance\n      - target_label: __address__\n        replacement: localhost:9115\n    metrics_path: /probe\n\n  - job_name: 'Blackbox Exporter (http)'\n    static_configs:\n      - targets: [ 'gerrit.fd.io' ]\n      - targets: [ 'jenkins.fd.io' ]\n    params:\n      module: [ 'http_2xx' ]\n    relabel_configs:\n      - source_labels: [__address__]\n        target_label: __param_target\n      - source_labels: [__param_target]\n        target_label: instance\n      - target_label: __address__\n        replacement: localhost:9115\n    metrics_path: /probe\n\n  - job_name: 'Jenkins Job Health Exporter'\n    static_configs:\n      - targets: [ '10.30.51.22:9186' ]\n    metric_relabel_configs:\n      - source_labels: [ __name__ ]\n        regex: '^(vpp.*|csit.*)_(success|failure|total|unstable|reqtime_ms)$'\n        action: replace\n        replacement: '$1'\n        target_label: id\n      - source_labels: [ __name__ ]\n        regex: '^(vpp.*|csit.*)_(success|failure|total|unstable|reqtime_ms)$'\n        replacement: 'jenkins_job_$2'\n        target_label: __name__\n\n  - job_name: 'Node Exporter'\n    static_configs:\n      - targets: [ '10.30.51.22:9100' ]\n      - targets: [ '10.30.51.24:9100' ]\n      - targets: [ '10.30.51.25:9100' ]\n      - targets: [ '10.30.51.26:9100' ]\n      - targets: [ '10.30.51.28:9100' ]\n      - targets: [ '10.30.51.29:9100' ]\n      - targets: [ '10.30.51.30:9100' ]\n      - targets: [ '10.30.51.39:9100' ]\n      - targets: [ '10.30.51.40:9100' ]\n      - targets: [ '10.30.51.50:9100' ]\n      - targets: [ '10.30.51.51:9100' ]\n      - targets: [ '10.30.51.65:9100' ]\n      - targets: [ '10.30.51.66:9100' ]\n      - targets: [ '10.30.51.67:9100' ]\n      - targets: [ '10.30.51.68:9100' ]\n      - targets: [ '10.30.51.70:9100' ]\n      - targets: [ '10.30.51.71:9100' ]\n      - targets: [ '10.32.8.14:9100' ]\n      - targets: [ '10.32.8.15:9100' ]\n      - targets: [ '10.32.8.16:9100' ]\n      - targets: [ '10.32.8.17:9100' ]\n\n  - job_name: 'Alertmanager'\n    consul_sd_configs:\n    - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n      services: [ 'alertmanager' ]\n\n  - job_name: 'Grafana'\n    consul_sd_configs:\n    - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n      services: [ 'grafana' ]\n\n  - job_name: 'Prometheus'\n    consul_sd_configs:\n    - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n      services: [ 'prometheus' ]\n\n  - job_name: 'Minio'\n    bearer_token: eyJhbGciOiJIUzUxMiIsInR5cCI6IkpXVCJ9.eyJleHAiOjQ3NjQ1ODEzMzcsImlzcyI6InByb21ldGhldXMiLCJzdWIiOiJtaW5pbyJ9.oeTw3EIaiFmlDikrHXWiWXMH2vxLfDLkfjEC7G2N3M_keH_xyA_l2ofLLNYtopa_3GCEZnxLQdPuFZrmgpkDWg\n    consul_sd_configs:\n    - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n      services: [ 'storage' ]\n    metrics_path: /minio/prometheus/metrics\nEOH\n      }\n\n      # The service stanza instructs Nomad to register a service with Consul.\n      #\n      # For more information and examples on the \"task\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/service\n      #\n      service {\n        name            = \"prometheus\"\n        port            = \"prometheus\"\n        tags            = [ \"prometheus${NOMAD_ALLOC_INDEX}\" ]\n        check {\n          name          = \"Prometheus Check Live\"\n          type          = \"http\"\n          path          = \"/-/healthy\"\n          interval      = \"10s\"\n          timeout       = \"2s\"\n        }\n      }\n\n      # The \"resources\" stanza describes the requirements a task needs to\n      # execute. Resource requirements include memory, network, cpu, and more.\n      # This ensures the task will execute on a machine that contains enough\n      # resource capacity.\n      #\n      # For more information and examples on the \"resources\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/resources\n      #\n      resources {\n        cpu             = 2000\n        memory          = 8192\n        # The network stanza specifies the networking requirements for the task\n        # group, including the network mode and port allocations. When scheduling\n        # jobs in Nomad they are provisioned across your fleet of machines along\n        # with other jobs and services. Because you don't know in advance what host\n        # your job will be provisioned on, Nomad will provide your tasks with\n        # network configuration when they start up.\n        #\n        # For more information and examples on the \"template\" stanza, please see\n        # the online documentation at:\n        #\n        #     https://www.nomadproject.io/docs/job-specification/network\n        #\n        network {\n          port \"prometheus\" {\n            static      = 9090\n          }\n        }\n      }\n    }\n  }\n}",
-            "template": "job \"${job_name}\" {\n  # The \"region\" parameter specifies the region in which to execute the job.\n  # If omitted, this inherits the default region name of \"global\".\n  # region = \"global\"\n  #\n  # The \"datacenters\" parameter specifies the list of datacenters which should\n  # be considered when placing this task. This must be provided.\n  datacenters         = \"${datacenters}\"\n\n  # The \"type\" parameter controls the type of job, which impacts the scheduler's\n  # decision on placement. This configuration is optional and defaults to\n  # \"service\". For a full list of job types and their differences, please see\n  # the online documentation.\n  #\n  # For more information, please see the online documentation at:\n  #\n  #     https://www.nomadproject.io/docs/jobspec/schedulers\n  #\n  type                = \"service\"\n\n  update {\n    # The \"max_parallel\" parameter specifies the maximum number of updates to\n    # perform in parallel. In this case, this specifies to update a single task\n    # at a time.\n    max_parallel      = 1\n\n    health_check      = \"checks\"\n\n    # The \"min_healthy_time\" parameter specifies the minimum time the allocation\n    # must be in the healthy state before it is marked as healthy and unblocks\n    # further allocations from being updated.\n    min_healthy_time  = \"10s\"\n\n    # The \"healthy_deadline\" parameter specifies the deadline in which the\n    # allocation must be marked as healthy after which the allocation is\n    # automatically transitioned to unhealthy. Transitioning to unhealthy will\n    # fail the deployment and potentially roll back the job if \"auto_revert\" is\n    # set to true.\n    healthy_deadline  = \"3m\"\n\n    # The \"progress_deadline\" parameter specifies the deadline in which an\n    # allocation must be marked as healthy. The deadline begins when the first\n    # allocation for the deployment is created and is reset whenever an allocation\n    # as part of the deployment transitions to a healthy state. If no allocation\n    # transitions to the healthy state before the progress deadline, the\n    # deployment is marked as failed.\n    progress_deadline = \"10m\"\n\n%{ if use_canary }\n    # The \"canary\" parameter specifies that changes to the job that would result\n    # in destructive updates should create the specified number of canaries\n    # without stopping any previous allocations. Once the operator determines the\n    # canaries are healthy, they can be promoted which unblocks a rolling update\n    # of the remaining allocations at a rate of \"max_parallel\".\n    #\n    # Further, setting \"canary\" equal to the count of the task group allows\n    # blue/green deployments. When the job is updated, a full set of the new\n    # version is deployed and upon promotion the old version is stopped.\n    canary            = 1\n\n    # Specifies if the job should auto-promote to the canary version when all\n    # canaries become healthy during a deployment. Defaults to false which means\n    # canaries must be manually updated with the nomad deployment promote\n    # command.\n    auto_promote      = true\n\n    # The \"auto_revert\" parameter specifies if the job should auto-revert to the\n    # last stable job on deployment failure. A job is marked as stable if all the\n    # allocations as part of its deployment were marked healthy.\n    auto_revert       = true\n%{ endif }\n  }\n\n  # The reschedule stanza specifies the group's rescheduling strategy. If\n  # specified at the job level, the configuration will apply to all groups\n  # within the job. If the reschedule stanza is present on both the job and the\n  # group, they are merged with the group stanza taking the highest precedence\n  # and then the job.\n  reschedule {\n    delay             = \"30s\"\n    delay_function    = \"constant\"\n    unlimited         = true\n  }\n\n  # The \"group\" stanza defines a series of tasks that should be co-located on\n  # the same Nomad client. Any task within a group will be placed on the same\n  # client.\n  #\n  # For more information and examples on the \"group\" stanza, please see\n  # the online documentation at:\n  #\n  #     https://www.nomadproject.io/docs/job-specification/group\n  #\n  group \"prod-group1-${service_name}\" {\n    # The \"count\" parameter specifies the number of the task groups that should\n    # be running under this group. This value must be non-negative and defaults\n    # to 1.\n    count               = ${group_count}\n\n    # The restart stanza configures a tasks's behavior on task failure. Restarts\n    # happen on the client that is running the task.\n    #\n    # https://www.nomadproject.io/docs/job-specification/restart\n    #\n    restart {\n      interval  = \"30m\"\n      attempts  = 40\n      delay     = \"15s\"\n      mode      = \"delay\"\n    }\n\n    # The volume stanza allows the group to specify that it requires a given\n    # volume from the cluster.\n    #\n    # For more information and examples on the \"volume\" stanza, please see\n    # the online documentation at:\n    #\n    #     https://www.nomadproject.io/docs/job-specification/volume\n    #\n    %{ if use_host_volume }\n    volume \"prod-volume1-${service_name}\" {\n      type              = \"host\"\n      read_only         = false\n      source            = \"${host_volume}\"\n    }\n    %{ endif }\n\n    # The constraint allows restricting the set of eligible nodes. Constraints\n    # may filter on attributes or client metadata.\n    #\n    # For more information and examples on the \"volume\" stanza, please see\n    # the online documentation at:\n    #\n    #     https://www.nomadproject.io/docs/job-specification/constraint\n    #\n    constraint {\n      attribute         = \"$${attr.cpu.arch}\"\n      operator          = \"!=\"\n      value             = \"arm64\"\n    }\n\n    # The \"task\" stanza creates an individual unit of work, such as a Docker\n    # container, web application, or batch processing.\n    #\n    # For more information and examples on the \"task\" stanza, please see\n    # the online documentation at:\n    #\n    #     https://www.nomadproject.io/docs/job-specification/task\n    #\n    task \"prod-task1-${service_name}\" {\n      # The \"driver\" parameter specifies the task driver that should be used to\n      # run the task.\n      driver            = \"exec\"\n\n      %{ if use_host_volume }\n      volume_mount {\n        volume          = \"prod-volume1-${service_name}\"\n        destination     = \"${data_dir}\"\n        read_only       = false\n      }\n      %{ endif }\n\n      %{ if use_vault_provider }\n      vault {\n        policies        = \"${vault_kv_policy_name}\"\n      }\n      %{ endif }\n\n      # The \"config\" stanza specifies the driver configuration, which is passed\n      # directly to the driver to start the task. The details of configurations\n      # are specific to each driver, so please see specific driver\n      # documentation for more information.\n      config {\n        command         = \"local/prometheus-${version}.linux-amd64/prometheus\"\n        args            = [\n          \"--config.file=secrets/prometheus.yml\",\n          \"--storage.tsdb.path=${data_dir}prometheus/\",\n          \"--storage.tsdb.retention.time=7d\"\n        ]\n      }\n\n      # The artifact stanza instructs Nomad to fetch and unpack a remote resource,\n      # such as a file, tarball, or binary. Nomad downloads artifacts using the\n      # popular go-getter library, which permits downloading artifacts from a\n      # variety of locations using a URL as the input source.\n      #\n      # For more information and examples on the \"artifact\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/artifact\n      #\n      artifact {\n        source          = \"${url}\"\n      }\n\n      # The \"template\" stanza instructs Nomad to manage a template, such as\n      # a configuration file or script. This template can optionally pull data\n      # from Consul or Vault to populate runtime configuration data.\n      #\n      # For more information and examples on the \"template\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/template\n      #\n      template {\n        change_mode     = \"noop\"\n        change_signal   = \"SIGINT\"\n        destination     = \"secrets/alerts.yml\"\n        left_delimiter  = \"{{{\"\n        right_delimiter = \"}}}\"\n        data            = \u003c\u003cEOH\n---\ngroups:\n- name: \"Jenkins Job Health Exporter\"\n  rules:\n  - alert: JenkinsJobHealthExporterFailures\n    expr: jenkins_job_failure{id=~\".*\"} \u003e jenkins_job_success{id=~\".*\"}\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Jenkins Job Health detected high failure rate on jenkins jobs.\"\n      description: \"Job: {{ $labels.id }}\"\n  - alert: JenkinsJobHealthExporterUnstable\n    expr: jenkins_job_unstable{id=~\".*\"} \u003e jenkins_job_success{id=~\".*\"}\n    for: 0m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Jenkins Job Health detected high unstable rate on jenkins jobs.\"\n      description: \"Job: {{ $labels.id }}\"\n- name: \"Consul\"\n  rules:\n  - alert: ConsulServiceHealthcheckFailed\n    expr: consul_catalog_service_node_healthy == 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Consul service healthcheck failed (instance {{ $labels.instance }}).\"\n      description: \"Service: `{{ $labels.service_name }}` Healthcheck: `{{ $labels.service_id }}`.\"\n  - alert: ConsulMissingMasterNode\n    expr: consul_raft_peers \u003c 3\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Consul missing master node (instance {{ $labels.instance }}).\"\n      description: \"Numbers of consul raft peers should be 3, in order to preserve quorum.\"\n  - alert: ConsulAgentUnhealthy\n    expr: consul_health_node_status{status=\"critical\"} == 1\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Consul agent unhealthy (instance {{ $labels.instance }}).\"\n      description: \"A Consul agent is down.\"\n- name: \"Hosts\"\n  rules:\n  - alert: NodeDown\n    expr: up == 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Prometheus target missing (instance {{ $labels.instance }}).\"\n      description: \"A Prometheus target has disappeared. An exporter might be crashed.\"\n  - alert: HostOutOfMemory\n    expr: node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes * 100 \u003c 10\n    for: 2m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host out of memory (instance {{ $labels.instance }}).\"\n      description: \"Node memory is filling up (\u003c 10% left).\"\n  - alert: HostOomKillDetected\n    expr: increase(node_vmstat_oom_kill[1m]) \u003e 0\n    for: 0m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host OOM kill detected (instance {{ $labels.instance }}).\"\n      description: \"OOM kill detected.\"\n  - alert: HostMemoryUnderMemoryPressure\n    expr: rate(node_vmstat_pgmajfault[1m]) \u003e 1000\n    for: 2m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host memory under memory pressure (instance {{ $labels.instance }}).\"\n      description: \"The node is under heavy memory pressure. High rate of major page faults.\"\n  - alert: HostOutOfDiskSpace\n    expr: (node_filesystem_avail_bytes * 100) / node_filesystem_size_bytes \u003c 10 and ON (instance, device, mountpoint) node_filesystem_readonly == 0\n    for: 2m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host out of disk space (instance {{ $labels.instance }}).\"\n      description: \"Disk is almost full (\u003c 10% left).\"\n  - alert: HostRaidDiskFailure\n    expr: node_md_disks{state=\"failed\"} \u003e 0\n    for: 2m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host RAID disk failure (instance {{ $labels.instance }}).\"\n      description: \"At least one device in RAID array on {{ $labels.instance }} failed. Array {{ $labels.md_device }} needs attention and possibly a disk swap.\"\n  - alert: HostConntrackLimit\n    expr: node_nf_conntrack_entries / node_nf_conntrack_entries_limit \u003e 0.8\n    for: 5m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host conntrack limit (instance {{ $labels.instance }}).\"\n      description: \"The number of conntrack is approching limit.\"\n  - alert: HostNetworkInterfaceSaturated\n    expr: (rate(node_network_receive_bytes_total{device!~\"^tap.*\"}[1m]) + rate(node_network_transmit_bytes_total{device!~\"^tap.*\"}[1m])) / node_network_speed_bytes{device!~\"^tap.*\"} \u003e 0.8\n    for: 1m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host Network Interface Saturated (instance {{ $labels.instance }}).\"\n      description: \"The network interface {{ $labels.interface }} on {{ $labels.instance }} is getting overloaded.\"\n  - alert: HostSystemdServiceCrashed\n    expr: node_systemd_unit_state{state=\"failed\"} == 1\n    for: 0m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host SystemD service crashed (instance {{ $labels.instance }}).\"\n      description: \"SystemD service crashed.\"\n  - alert: HostEdacCorrectableErrorsDetected\n    expr: increase(node_edac_correctable_errors_total[1m]) \u003e 0\n    for: 0m\n    labels:\n      severity: info\n    annotations:\n      summary: \"Host EDAC Correctable Errors detected (instance {{ $labels.instance }}).\"\n      description: '{{ $labels.instance }} has had {{ printf \"%.0f\" $value }} correctable memory errors reported by EDAC in the last 5 minutes.'\n  - alert: HostEdacUncorrectableErrorsDetected\n    expr: node_edac_uncorrectable_errors_total \u003e 0\n    for: 0m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host EDAC Uncorrectable Errors detected (instance {{ $labels.instance }}).\"\n      description: '{{ $labels.instance }} has had {{ printf \"%.0f\" $value }} uncorrectable memory errors reported by EDAC in the last 5 minutes.'\n- name: \"Min.io\"\n  rules:\n  - alert: MinioDiskOffline\n    expr: minio_offline_disks \u003e 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Minio disk offline (instance {{ $labels.instance }})\"\n      description: \"Minio disk is offline.\"\n  - alert: MinioStorageSpaceExhausted\n    expr: minio_disk_storage_free_bytes / 1024 / 1024 / 1024 \u003c 10\n    for: 2m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Minio storage space exhausted (instance {{ $labels.instance }}).\"\n      description: \"Minio storage space is low (\u003c 10 GB).\"\n- name: \"Prometheus\"\n  rules:\n  - alert: PrometheusConfigurationReloadFailure\n    expr: prometheus_config_last_reload_successful != 1\n    for: 0m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Prometheus configuration reload failure (instance {{ $labels.instance }}).\"\n      description: \"Prometheus configuration reload error.\"\n  - alert: PrometheusTooManyRestarts\n    expr: changes(process_start_time_seconds{job=~\"prometheus|pushgateway|alertmanager\"}[15m]) \u003e 2\n    for: 0m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Prometheus too many restarts (instance {{ $labels.instance }}).\"\n      description: \"Prometheus has restarted more than twice in the last 15 minutes. It might be crashlooping.\"\n  - alert: PrometheusAlertmanagerConfigurationReloadFailure\n    expr: alertmanager_config_last_reload_successful != 1\n    for: 0m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Prometheus AlertManager configuration reload failure (instance {{ $labels.instance }}).\"\n      description: \"AlertManager configuration reload error.\"\n  - alert: PrometheusRuleEvaluationFailures\n    expr: increase(prometheus_rule_evaluation_failures_total[3m]) \u003e 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Prometheus rule evaluation failures (instance {{ $labels.instance }}).\"\n      description: \"Prometheus encountered {{ $value }} rule evaluation failures, leading to potentially ignored alerts.\"\n  - alert: PrometheusTargetScrapingSlow\n    expr: prometheus_target_interval_length_seconds{quantile=\"0.9\"} \u003e 60\n    for: 5m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Prometheus target scraping slow (instance {{ $labels.instance }}).\"\n      description: \"Prometheus is scraping exporters slowly.\"\n  - alert: PrometheusTsdbCompactionsFailed\n    expr: increase(prometheus_tsdb_compactions_failed_total[1m]) \u003e 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Prometheus TSDB compactions failed (instance {{ $labels.instance }}).\"\n      description: \"Prometheus encountered {{ $value }} TSDB compactions failures.\"\n  - alert: PrometheusTsdbHeadTruncationsFailed\n    expr: increase(prometheus_tsdb_head_truncations_failed_total[1m]) \u003e 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Prometheus TSDB head truncations failed (instance {{ $labels.instance }}).\"\n      description: \"Prometheus encountered {{ $value }} TSDB head truncation failures.\"\n  - alert: PrometheusTsdbWalCorruptions\n    expr: increase(prometheus_tsdb_wal_corruptions_total[1m]) \u003e 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Prometheus TSDB WAL corruptions (instance {{ $labels.instance }}).\"\n      description: \"Prometheus encountered {{ $value }} TSDB WAL corruptions.\"\n  - alert: PrometheusTsdbWalTruncationsFailed\n    expr: increase(prometheus_tsdb_wal_truncations_failed_total[1m]) \u003e 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Prometheus TSDB WAL truncations failed (instance {{ $labels.instance }}).\"\n      description: \"Prometheus encountered {{ $value }} TSDB WAL truncation failures.\"\nEOH\n      }\n\n      template {\n        change_mode     = \"noop\"\n        change_signal   = \"SIGINT\"\n        destination     = \"secrets/prometheus.yml\"\n        data            = \u003c\u003cEOH\n---\nglobal:\n  scrape_interval:     5s\n  scrape_timeout:      5s\n  evaluation_interval: 5s\n\nalerting:\n  alertmanagers:\n  - consul_sd_configs:\n    - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n      services: [ 'alertmanager' ]\n\nrule_files:\n  - 'alerts.yml'\n\nscrape_configs:\n\n  - job_name: 'Nomad Cluster'\n    consul_sd_configs:\n    - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n      services: [ 'nomad-client', 'nomad' ]\n    relabel_configs:\n    - source_labels: [__meta_consul_tags]\n      regex: '(.*)http(.*)'\n      action: keep\n    metrics_path: /v1/metrics\n    params:\n      format: [ 'prometheus' ]\n\n  - job_name: 'Consul Cluster'\n    static_configs:\n      - targets: [ '10.30.51.22:8500' ]\n      - targets: [ '10.30.51.24:8500' ]\n      - targets: [ '10.30.51.25:8500' ]\n      - targets: [ '10.30.51.26:8500' ]\n      - targets: [ '10.30.51.28:8500' ]\n      - targets: [ '10.30.51.29:8500' ]\n      - targets: [ '10.30.51.30:8500' ]\n      - targets: [ '10.30.51.39:8500' ]\n      - targets: [ '10.30.51.40:8500' ]\n      - targets: [ '10.30.51.50:8500' ]\n      - targets: [ '10.30.51.51:8500' ]\n      - targets: [ '10.30.51.65:8500' ]\n      - targets: [ '10.30.51.66:8500' ]\n      - targets: [ '10.30.51.67:8500' ]\n      - targets: [ '10.30.51.68:8500' ]\n      - targets: [ '10.30.51.70:8500' ]\n      - targets: [ '10.30.51.71:8500' ]\n      - targets: [ '10.32.8.14:8500' ]\n      - targets: [ '10.32.8.15:8500' ]\n      - targets: [ '10.32.8.16:8500' ]\n      - targets: [ '10.32.8.17:8500' ]\n    metrics_path: /v1/agent/metrics\n    params:\n      format: [ 'prometheus' ]\n\n  - job_name: 'Blackbox Exporter (icmp)'\n    static_configs:\n      - targets: [ 'gerrit.fd.io' ]\n      - targets: [ 'jenkins.fd.io' ]\n      - targets: [ '10.32.8.17' ]\n    params:\n      module: [ 'icmp_v4' ]\n    relabel_configs:\n      - source_labels: [__address__]\n        target_label: __param_target\n      - source_labels: [__param_target]\n        target_label: instance\n      - target_label: __address__\n        replacement: localhost:9115\n    metrics_path: /probe\n\n  - job_name: 'Blackbox Exporter (http)'\n    static_configs:\n      - targets: [ 'gerrit.fd.io' ]\n      - targets: [ 'jenkins.fd.io' ]\n    params:\n      module: [ 'http_2xx' ]\n    relabel_configs:\n      - source_labels: [__address__]\n        target_label: __param_target\n      - source_labels: [__param_target]\n        target_label: instance\n      - target_label: __address__\n        replacement: localhost:9115\n    metrics_path: /probe\n\n  - job_name: 'Jenkins Job Health Exporter'\n    static_configs:\n      - targets: [ '10.30.51.22:9186' ]\n    metric_relabel_configs:\n      - source_labels: [ __name__ ]\n        regex: '^(vpp.*|csit.*)_(success|failure|total|unstable|reqtime_ms)$'\n        action: replace\n        replacement: '$1'\n        target_label: id\n      - source_labels: [ __name__ ]\n        regex: '^(vpp.*|csit.*)_(success|failure|total|unstable|reqtime_ms)$'\n        replacement: 'jenkins_job_$2'\n        target_label: __name__\n\n  - job_name: 'Node Exporter'\n    static_configs:\n      - targets: [ '10.30.51.22:9100' ]\n      - targets: [ '10.30.51.24:9100' ]\n      - targets: [ '10.30.51.25:9100' ]\n      - targets: [ '10.30.51.26:9100' ]\n      - targets: [ '10.30.51.28:9100' ]\n      - targets: [ '10.30.51.29:9100' ]\n      - targets: [ '10.30.51.30:9100' ]\n      - targets: [ '10.30.51.39:9100' ]\n      - targets: [ '10.30.51.40:9100' ]\n      - targets: [ '10.30.51.50:9100' ]\n      - targets: [ '10.30.51.51:9100' ]\n      - targets: [ '10.30.51.65:9100' ]\n      - targets: [ '10.30.51.66:9100' ]\n      - targets: [ '10.30.51.67:9100' ]\n      - targets: [ '10.30.51.68:9100' ]\n      - targets: [ '10.30.51.70:9100' ]\n      - targets: [ '10.30.51.71:9100' ]\n      - targets: [ '10.32.8.14:9100' ]\n      - targets: [ '10.32.8.15:9100' ]\n      - targets: [ '10.32.8.16:9100' ]\n      - targets: [ '10.32.8.17:9100' ]\n\n  - job_name: 'Alertmanager'\n    consul_sd_configs:\n    - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n      services: [ 'alertmanager' ]\n\n  - job_name: 'Grafana'\n    consul_sd_configs:\n    - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n      services: [ 'grafana' ]\n\n  - job_name: 'Prometheus'\n    consul_sd_configs:\n    - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n      services: [ 'prometheus' ]\n\n  - job_name: 'Minio'\n    bearer_token: eyJhbGciOiJIUzUxMiIsInR5cCI6IkpXVCJ9.eyJleHAiOjQ3NjQ1ODEzMzcsImlzcyI6InByb21ldGhldXMiLCJzdWIiOiJtaW5pbyJ9.oeTw3EIaiFmlDikrHXWiWXMH2vxLfDLkfjEC7G2N3M_keH_xyA_l2ofLLNYtopa_3GCEZnxLQdPuFZrmgpkDWg\n    consul_sd_configs:\n    - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n      services: [ 'storage' ]\n    metrics_path: /minio/prometheus/metrics\nEOH\n      }\n\n      # The service stanza instructs Nomad to register a service with Consul.\n      #\n      # For more information and examples on the \"task\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/service\n      #\n      service {\n        name            = \"${service_name}\"\n        port            = \"${service_name}\"\n        tags            = [ \"${service_name}$${NOMAD_ALLOC_INDEX}\" ]\n        check {\n          name          = \"Prometheus Check Live\"\n          type          = \"http\"\n          path          = \"/-/healthy\"\n          interval      = \"10s\"\n          timeout       = \"2s\"\n        }\n      }\n\n      # The \"resources\" stanza describes the requirements a task needs to\n      # execute. Resource requirements include memory, network, cpu, and more.\n      # This ensures the task will execute on a machine that contains enough\n      # resource capacity.\n      #\n      # For more information and examples on the \"resources\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/resources\n      #\n      resources {\n        cpu             = ${cpu}\n        memory          = ${mem}\n        # The network stanza specifies the networking requirements for the task\n        # group, including the network mode and port allocations. When scheduling\n        # jobs in Nomad they are provisioned across your fleet of machines along\n        # with other jobs and services. Because you don't know in advance what host\n        # your job will be provisioned on, Nomad will provide your tasks with\n        # network configuration when they start up.\n        #\n        # For more information and examples on the \"template\" stanza, please see\n        # the online documentation at:\n        #\n        #     https://www.nomadproject.io/docs/job-specification/network\n        #\n        network {\n          port \"${service_name}\" {\n            static      = ${port}\n          }\n        }\n      }\n    }\n  }\n}",
+            "id": "2cfc207e58bdcd266ac342e51f9e5a442c595ddad94d04462ca1ad78ea24cf61",
+            "rendered": "job \"prod-prometheus\" {\n  # The \"region\" parameter specifies the region in which to execute the job.\n  # If omitted, this inherits the default region name of \"global\".\n  # region = \"global\"\n  #\n  # The \"datacenters\" parameter specifies the list of datacenters which should\n  # be considered when placing this task. This must be provided.\n  datacenters         = \"yul1\"\n\n  # The \"type\" parameter controls the type of job, which impacts the scheduler's\n  # decision on placement. This configuration is optional and defaults to\n  # \"service\". For a full list of job types and their differences, please see\n  # the online documentation.\n  #\n  # For more information, please see the online documentation at:\n  #\n  #     https://www.nomadproject.io/docs/jobspec/schedulers\n  #\n  type                = \"service\"\n\n  update {\n    # The \"max_parallel\" parameter specifies the maximum number of updates to\n    # perform in parallel. In this case, this specifies to update a single task\n    # at a time.\n    max_parallel      = 1\n\n    health_check      = \"checks\"\n\n    # The \"min_healthy_time\" parameter specifies the minimum time the allocation\n    # must be in the healthy state before it is marked as healthy and unblocks\n    # further allocations from being updated.\n    min_healthy_time  = \"10s\"\n\n    # The \"healthy_deadline\" parameter specifies the deadline in which the\n    # allocation must be marked as healthy after which the allocation is\n    # automatically transitioned to unhealthy. Transitioning to unhealthy will\n    # fail the deployment and potentially roll back the job if \"auto_revert\" is\n    # set to true.\n    healthy_deadline  = \"3m\"\n\n    # The \"progress_deadline\" parameter specifies the deadline in which an\n    # allocation must be marked as healthy. The deadline begins when the first\n    # allocation for the deployment is created and is reset whenever an allocation\n    # as part of the deployment transitions to a healthy state. If no allocation\n    # transitions to the healthy state before the progress deadline, the\n    # deployment is marked as failed.\n    progress_deadline = \"10m\"\n\n\n    # The \"canary\" parameter specifies that changes to the job that would result\n    # in destructive updates should create the specified number of canaries\n    # without stopping any previous allocations. Once the operator determines the\n    # canaries are healthy, they can be promoted which unblocks a rolling update\n    # of the remaining allocations at a rate of \"max_parallel\".\n    #\n    # Further, setting \"canary\" equal to the count of the task group allows\n    # blue/green deployments. When the job is updated, a full set of the new\n    # version is deployed and upon promotion the old version is stopped.\n    canary            = 1\n\n    # Specifies if the job should auto-promote to the canary version when all\n    # canaries become healthy during a deployment. Defaults to false which means\n    # canaries must be manually updated with the nomad deployment promote\n    # command.\n    auto_promote      = true\n\n    # The \"auto_revert\" parameter specifies if the job should auto-revert to the\n    # last stable job on deployment failure. A job is marked as stable if all the\n    # allocations as part of its deployment were marked healthy.\n    auto_revert       = true\n\n  }\n\n  # The reschedule stanza specifies the group's rescheduling strategy. If\n  # specified at the job level, the configuration will apply to all groups\n  # within the job. If the reschedule stanza is present on both the job and the\n  # group, they are merged with the group stanza taking the highest precedence\n  # and then the job.\n  reschedule {\n    delay             = \"30s\"\n    delay_function    = \"constant\"\n    unlimited         = true\n  }\n\n  # The \"group\" stanza defines a series of tasks that should be co-located on\n  # the same Nomad client. Any task within a group will be placed on the same\n  # client.\n  #\n  # For more information and examples on the \"group\" stanza, please see\n  # the online documentation at:\n  #\n  #     https://www.nomadproject.io/docs/job-specification/group\n  #\n  group \"prod-group1-prometheus\" {\n    # The \"count\" parameter specifies the number of the task groups that should\n    # be running under this group. This value must be non-negative and defaults\n    # to 1.\n    count               = 4\n\n    # The restart stanza configures a tasks's behavior on task failure. Restarts\n    # happen on the client that is running the task.\n    #\n    # https://www.nomadproject.io/docs/job-specification/restart\n    #\n    restart {\n      interval  = \"30m\"\n      attempts  = 40\n      delay     = \"15s\"\n      mode      = \"delay\"\n    }\n\n    # The volume stanza allows the group to specify that it requires a given\n    # volume from the cluster.\n    #\n    # For more information and examples on the \"volume\" stanza, please see\n    # the online documentation at:\n    #\n    #     https://www.nomadproject.io/docs/job-specification/volume\n    #\n    \n    volume \"prod-volume1-prometheus\" {\n      type              = \"host\"\n      read_only         = false\n      source            = \"prod-volume-data1-1\"\n    }\n    \n\n    # The constraint allows restricting the set of eligible nodes. Constraints\n    # may filter on attributes or client metadata.\n    #\n    # For more information and examples on the \"volume\" stanza, please see\n    # the online documentation at:\n    #\n    #     https://www.nomadproject.io/docs/job-specification/constraint\n    #\n    constraint {\n      attribute         = \"${attr.cpu.arch}\"\n      operator          = \"!=\"\n      value             = \"arm64\"\n    }\n\n    constraint {\n      attribute      = \"${node.class}\"\n      value          = \"builder\"\n    }\n\n    # The \"task\" stanza creates an individual unit of work, such as a Docker\n    # container, web application, or batch processing.\n    #\n    # For more information and examples on the \"task\" stanza, please see\n    # the online documentation at:\n    #\n    #     https://www.nomadproject.io/docs/job-specification/task\n    #\n    task \"prod-task1-prometheus\" {\n      # The \"driver\" parameter specifies the task driver that should be used to\n      # run the task.\n      driver            = \"exec\"\n\n      \n      volume_mount {\n        volume          = \"prod-volume1-prometheus\"\n        destination     = \"/data/\"\n        read_only       = false\n      }\n      \n\n      \n\n      # The \"config\" stanza specifies the driver configuration, which is passed\n      # directly to the driver to start the task. The details of configurations\n      # are specific to each driver, so please see specific driver\n      # documentation for more information.\n      config {\n        command         = \"local/prometheus-2.28.1.linux-amd64/prometheus\"\n        args            = [\n          \"--config.file=secrets/prometheus.yml\",\n          \"--storage.tsdb.path=/data/prometheus/\",\n          \"--storage.tsdb.retention.time=7d\"\n        ]\n      }\n\n      # The artifact stanza instructs Nomad to fetch and unpack a remote resource,\n      # such as a file, tarball, or binary. Nomad downloads artifacts using the\n      # popular go-getter library, which permits downloading artifacts from a\n      # variety of locations using a URL as the input source.\n      #\n      # For more information and examples on the \"artifact\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/artifact\n      #\n      artifact {\n        source          = \"https://github.com/prometheus/prometheus/releases/download/v2.28.1/prometheus-2.28.1.linux-amd64.tar.gz\"\n      }\n\n      # The \"template\" stanza instructs Nomad to manage a template, such as\n      # a configuration file or script. This template can optionally pull data\n      # from Consul or Vault to populate runtime configuration data.\n      #\n      # For more information and examples on the \"template\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/template\n      #\n      template {\n        change_mode     = \"noop\"\n        change_signal   = \"SIGINT\"\n        destination     = \"secrets/alerts.yml\"\n        left_delimiter  = \"{{{\"\n        right_delimiter = \"}}}\"\n        data            = \u003c\u003cEOH\n---\ngroups:\n- name: \"Jenkins Job Health Exporter\"\n  rules:\n  - alert: JenkinsJobHealthExporterFailures\n    expr: jenkins_job_failure{id=~\".*\"} \u003e jenkins_job_success{id=~\".*\"}\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Jenkins Job Health detected high failure rate on jenkins jobs.\"\n      description: \"Job: {{ $labels.id }}\"\n  - alert: JenkinsJobHealthExporterUnstable\n    expr: jenkins_job_unstable{id=~\".*\"} \u003e jenkins_job_success{id=~\".*\"}\n    for: 0m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Jenkins Job Health detected high unstable rate on jenkins jobs.\"\n      description: \"Job: {{ $labels.id }}\"\n- name: \"Consul\"\n  rules:\n  - alert: ConsulServiceHealthcheckFailed\n    expr: consul_catalog_service_node_healthy == 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Consul service healthcheck failed (instance {{ $labels.instance }}).\"\n      description: \"Service: `{{ $labels.service_name }}` Healthcheck: `{{ $labels.service_id }}`.\"\n  - alert: ConsulMissingMasterNode\n    expr: consul_raft_peers \u003c 3\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Consul missing master node (instance {{ $labels.instance }}).\"\n      description: \"Numbers of consul raft peers should be 3, in order to preserve quorum.\"\n  - alert: ConsulAgentUnhealthy\n    expr: consul_health_node_status{status=\"critical\"} == 1\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Consul agent unhealthy (instance {{ $labels.instance }}).\"\n      description: \"A Consul agent is down.\"\n- name: \"Hosts\"\n  rules:\n  - alert: NodeDown\n    expr: up == 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Prometheus target missing (instance {{ $labels.instance }}).\"\n      description: \"A Prometheus target has disappeared. An exporter might be crashed.\"\n  - alert: HostOutOfMemory\n    expr: node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes * 100 \u003c 10\n    for: 2m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host out of memory (instance {{ $labels.instance }}).\"\n      description: \"Node memory is filling up (\u003c 10% left).\"\n  - alert: HostOomKillDetected\n    expr: increase(node_vmstat_oom_kill[1m]) \u003e 0\n    for: 0m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host OOM kill detected (instance {{ $labels.instance }}).\"\n      description: \"OOM kill detected.\"\n  - alert: HostMemoryUnderMemoryPressure\n    expr: rate(node_vmstat_pgmajfault[1m]) \u003e 1000\n    for: 2m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host memory under memory pressure (instance {{ $labels.instance }}).\"\n      description: \"The node is under heavy memory pressure. High rate of major page faults.\"\n  - alert: HostOutOfDiskSpace\n    expr: (node_filesystem_avail_bytes * 100) / node_filesystem_size_bytes \u003c 10 and ON (instance, device, mountpoint) node_filesystem_readonly == 0\n    for: 2m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host out of disk space (instance {{ $labels.instance }}).\"\n      description: \"Disk is almost full (\u003c 10% left).\"\n  - alert: HostRaidDiskFailure\n    expr: node_md_disks{state=\"failed\"} \u003e 0\n    for: 2m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host RAID disk failure (instance {{ $labels.instance }}).\"\n      description: \"At least one device in RAID array on {{ $labels.instance }} failed. Array {{ $labels.md_device }} needs attention and possibly a disk swap.\"\n  - alert: HostConntrackLimit\n    expr: node_nf_conntrack_entries / node_nf_conntrack_entries_limit \u003e 0.8\n    for: 5m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host conntrack limit (instance {{ $labels.instance }}).\"\n      description: \"The number of conntrack is approching limit.\"\n  - alert: HostNetworkInterfaceSaturated\n    expr: (rate(node_network_receive_bytes_total{device!~\"^tap.*\"}[1m]) + rate(node_network_transmit_bytes_total{device!~\"^tap.*\"}[1m])) / node_network_speed_bytes{device!~\"^tap.*\"} \u003e 0.8\n    for: 1m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host Network Interface Saturated (instance {{ $labels.instance }}).\"\n      description: \"The network interface {{ $labels.interface }} on {{ $labels.instance }} is getting overloaded.\"\n  - alert: HostSystemdServiceCrashed\n    expr: node_systemd_unit_state{state=\"failed\"} == 1\n    for: 0m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host SystemD service crashed (instance {{ $labels.instance }}).\"\n      description: \"SystemD service crashed.\"\n  - alert: HostEdacCorrectableErrorsDetected\n    expr: increase(node_edac_correctable_errors_total[1m]) \u003e 0\n    for: 0m\n    labels:\n      severity: info\n    annotations:\n      summary: \"Host EDAC Correctable Errors detected (instance {{ $labels.instance }}).\"\n      description: '{{ $labels.instance }} has had {{ printf \"%.0f\" $value }} correctable memory errors reported by EDAC in the last 5 minutes.'\n  - alert: HostEdacUncorrectableErrorsDetected\n    expr: node_edac_uncorrectable_errors_total \u003e 0\n    for: 0m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host EDAC Uncorrectable Errors detected (instance {{ $labels.instance }}).\"\n      description: '{{ $labels.instance }} has had {{ printf \"%.0f\" $value }} uncorrectable memory errors reported by EDAC in the last 5 minutes.'\n- name: \"Min.io\"\n  rules:\n  - alert: MinioDiskOffline\n    expr: minio_offline_disks \u003e 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Minio disk offline (instance {{ $labels.instance }})\"\n      description: \"Minio disk is offline.\"\n  - alert: MinioStorageSpaceExhausted\n    expr: minio_disk_storage_free_bytes / 1024 / 1024 / 1024 \u003c 10\n    for: 2m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Minio storage space exhausted (instance {{ $labels.instance }}).\"\n      description: \"Minio storage space is low (\u003c 10 GB).\"\n- name: \"Prometheus\"\n  rules:\n  - alert: PrometheusConfigurationReloadFailure\n    expr: prometheus_config_last_reload_successful != 1\n    for: 0m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Prometheus configuration reload failure (instance {{ $labels.instance }}).\"\n      description: \"Prometheus configuration reload error.\"\n  - alert: PrometheusTooManyRestarts\n    expr: changes(process_start_time_seconds{job=~\"prometheus|pushgateway|alertmanager\"}[15m]) \u003e 2\n    for: 0m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Prometheus too many restarts (instance {{ $labels.instance }}).\"\n      description: \"Prometheus has restarted more than twice in the last 15 minutes. It might be crashlooping.\"\n  - alert: PrometheusAlertmanagerConfigurationReloadFailure\n    expr: alertmanager_config_last_reload_successful != 1\n    for: 0m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Prometheus AlertManager configuration reload failure (instance {{ $labels.instance }}).\"\n      description: \"AlertManager configuration reload error.\"\n  - alert: PrometheusRuleEvaluationFailures\n    expr: increase(prometheus_rule_evaluation_failures_total[3m]) \u003e 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Prometheus rule evaluation failures (instance {{ $labels.instance }}).\"\n      description: \"Prometheus encountered {{ $value }} rule evaluation failures, leading to potentially ignored alerts.\"\n  - alert: PrometheusTargetScrapingSlow\n    expr: prometheus_target_interval_length_seconds{quantile=\"0.9\"} \u003e 60\n    for: 5m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Prometheus target scraping slow (instance {{ $labels.instance }}).\"\n      description: \"Prometheus is scraping exporters slowly.\"\n  - alert: PrometheusTsdbCompactionsFailed\n    expr: increase(prometheus_tsdb_compactions_failed_total[1m]) \u003e 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Prometheus TSDB compactions failed (instance {{ $labels.instance }}).\"\n      description: \"Prometheus encountered {{ $value }} TSDB compactions failures.\"\n  - alert: PrometheusTsdbHeadTruncationsFailed\n    expr: increase(prometheus_tsdb_head_truncations_failed_total[1m]) \u003e 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Prometheus TSDB head truncations failed (instance {{ $labels.instance }}).\"\n      description: \"Prometheus encountered {{ $value }} TSDB head truncation failures.\"\n  - alert: PrometheusTsdbWalCorruptions\n    expr: increase(prometheus_tsdb_wal_corruptions_total[1m]) \u003e 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Prometheus TSDB WAL corruptions (instance {{ $labels.instance }}).\"\n      description: \"Prometheus encountered {{ $value }} TSDB WAL corruptions.\"\n  - alert: PrometheusTsdbWalTruncationsFailed\n    expr: increase(prometheus_tsdb_wal_truncations_failed_total[1m]) \u003e 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Prometheus TSDB WAL truncations failed (instance {{ $labels.instance }}).\"\n      description: \"Prometheus encountered {{ $value }} TSDB WAL truncation failures.\"\nEOH\n      }\n\n      template {\n        change_mode     = \"noop\"\n        change_signal   = \"SIGINT\"\n        destination     = \"secrets/prometheus.yml\"\n        data            = \u003c\u003cEOH\n---\nglobal:\n  scrape_interval:     5s\n  scrape_timeout:      5s\n  evaluation_interval: 5s\n\nalerting:\n  alertmanagers:\n  - consul_sd_configs:\n    - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n      services: [ 'alertmanager' ]\n\nrule_files:\n  - 'alerts.yml'\n\nscrape_configs:\n\n  - job_name: 'Nomad Cluster'\n    consul_sd_configs:\n    - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n      services: [ 'nomad-client', 'nomad' ]\n    relabel_configs:\n    - source_labels: [__meta_consul_tags]\n      regex: '(.*)http(.*)'\n      action: keep\n    metrics_path: /v1/metrics\n    params:\n      format: [ 'prometheus' ]\n\n  - job_name: 'Consul Cluster'\n    static_configs:\n      - targets: [ '10.30.51.22:8500' ]\n      - targets: [ '10.30.51.24:8500' ]\n      - targets: [ '10.30.51.25:8500' ]\n      - targets: [ '10.30.51.26:8500' ]\n      - targets: [ '10.30.51.28:8500' ]\n      - targets: [ '10.30.51.29:8500' ]\n      - targets: [ '10.30.51.30:8500' ]\n      - targets: [ '10.30.51.39:8500' ]\n      - targets: [ '10.30.51.40:8500' ]\n      - targets: [ '10.30.51.50:8500' ]\n      - targets: [ '10.30.51.51:8500' ]\n      - targets: [ '10.30.51.65:8500' ]\n      - targets: [ '10.30.51.66:8500' ]\n      - targets: [ '10.30.51.67:8500' ]\n      - targets: [ '10.30.51.68:8500' ]\n      - targets: [ '10.30.51.70:8500' ]\n      - targets: [ '10.30.51.71:8500' ]\n      - targets: [ '10.32.8.14:8500' ]\n      - targets: [ '10.32.8.15:8500' ]\n      - targets: [ '10.32.8.16:8500' ]\n      - targets: [ '10.32.8.17:8500' ]\n    metrics_path: /v1/agent/metrics\n    params:\n      format: [ 'prometheus' ]\n\n  - job_name: 'Blackbox Exporter (icmp)'\n    static_configs:\n      - targets: [ 'gerrit.fd.io' ]\n      - targets: [ 'jenkins.fd.io' ]\n      - targets: [ '10.32.8.17' ]\n    params:\n      module: [ 'icmp_v4' ]\n    relabel_configs:\n      - source_labels: [__address__]\n        target_label: __param_target\n      - source_labels: [__param_target]\n        target_label: instance\n      - target_label: __address__\n        replacement: localhost:9115\n    metrics_path: /probe\n\n  - job_name: 'Blackbox Exporter (http)'\n    static_configs:\n      - targets: [ 'gerrit.fd.io' ]\n      - targets: [ 'jenkins.fd.io' ]\n    params:\n      module: [ 'http_2xx' ]\n    relabel_configs:\n      - source_labels: [__address__]\n        target_label: __param_target\n      - source_labels: [__param_target]\n        target_label: instance\n      - target_label: __address__\n        replacement: localhost:9115\n    metrics_path: /probe\n\n  - job_name: 'Jenkins Job Health Exporter'\n    static_configs:\n      - targets: [ '10.30.51.22:9186' ]\n    metric_relabel_configs:\n      - source_labels: [ __name__ ]\n        regex: '^(vpp.*|csit.*)_(success|failure|total|unstable|reqtime_ms)$'\n        action: replace\n        replacement: '$1'\n        target_label: id\n      - source_labels: [ __name__ ]\n        regex: '^(vpp.*|csit.*)_(success|failure|total|unstable|reqtime_ms)$'\n        replacement: 'jenkins_job_$2'\n        target_label: __name__\n\n  - job_name: 'Node Exporter'\n    static_configs:\n      - targets: [ '10.30.51.22:9100' ]\n      - targets: [ '10.30.51.24:9100' ]\n      - targets: [ '10.30.51.25:9100' ]\n      - targets: [ '10.30.51.26:9100' ]\n      - targets: [ '10.30.51.28:9100' ]\n      - targets: [ '10.30.51.29:9100' ]\n      - targets: [ '10.30.51.30:9100' ]\n      - targets: [ '10.30.51.39:9100' ]\n      - targets: [ '10.30.51.40:9100' ]\n      - targets: [ '10.30.51.50:9100' ]\n      - targets: [ '10.30.51.51:9100' ]\n      - targets: [ '10.30.51.65:9100' ]\n      - targets: [ '10.30.51.66:9100' ]\n      - targets: [ '10.30.51.67:9100' ]\n      - targets: [ '10.30.51.68:9100' ]\n      - targets: [ '10.30.51.70:9100' ]\n      - targets: [ '10.30.51.71:9100' ]\n      - targets: [ '10.32.8.14:9100' ]\n      - targets: [ '10.32.8.15:9100' ]\n      - targets: [ '10.32.8.16:9100' ]\n      - targets: [ '10.32.8.17:9100' ]\n\n  - job_name: 'Alertmanager'\n    consul_sd_configs:\n    - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n      services: [ 'alertmanager' ]\n\n  - job_name: 'Grafana'\n    consul_sd_configs:\n    - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n      services: [ 'grafana' ]\n\n  - job_name: 'Prometheus'\n    consul_sd_configs:\n    - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n      services: [ 'prometheus' ]\n\n  - job_name: 'Minio'\n    bearer_token: eyJhbGciOiJIUzUxMiIsInR5cCI6IkpXVCJ9.eyJleHAiOjQ3NjQ1ODEzMzcsImlzcyI6InByb21ldGhldXMiLCJzdWIiOiJtaW5pbyJ9.oeTw3EIaiFmlDikrHXWiWXMH2vxLfDLkfjEC7G2N3M_keH_xyA_l2ofLLNYtopa_3GCEZnxLQdPuFZrmgpkDWg\n    consul_sd_configs:\n    - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n      services: [ 'storage' ]\n    metrics_path: /minio/prometheus/metrics\nEOH\n      }\n\n      # The service stanza instructs Nomad to register a service with Consul.\n      #\n      # For more information and examples on the \"task\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/service\n      #\n      service {\n        name            = \"prometheus\"\n        port            = \"prometheus\"\n        tags            = [ \"prometheus${NOMAD_ALLOC_INDEX}\" ]\n        check {\n          name          = \"Prometheus Check Live\"\n          type          = \"http\"\n          path          = \"/-/healthy\"\n          interval      = \"10s\"\n          timeout       = \"2s\"\n        }\n      }\n\n      # The \"resources\" stanza describes the requirements a task needs to\n      # execute. Resource requirements include memory, network, cpu, and more.\n      # This ensures the task will execute on a machine that contains enough\n      # resource capacity.\n      #\n      # For more information and examples on the \"resources\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/resources\n      #\n      resources {\n        cpu             = 2000\n        memory          = 8192\n        # The network stanza specifies the networking requirements for the task\n        # group, including the network mode and port allocations. When scheduling\n        # jobs in Nomad they are provisioned across your fleet of machines along\n        # with other jobs and services. Because you don't know in advance what host\n        # your job will be provisioned on, Nomad will provide your tasks with\n        # network configuration when they start up.\n        #\n        # For more information and examples on the \"template\" stanza, please see\n        # the online documentation at:\n        #\n        #     https://www.nomadproject.io/docs/job-specification/network\n        #\n        network {\n          port \"prometheus\" {\n            static      = 9090\n          }\n        }\n      }\n    }\n  }\n}",
+            "template": "job \"${job_name}\" {\n  # The \"region\" parameter specifies the region in which to execute the job.\n  # If omitted, this inherits the default region name of \"global\".\n  # region = \"global\"\n  #\n  # The \"datacenters\" parameter specifies the list of datacenters which should\n  # be considered when placing this task. This must be provided.\n  datacenters         = \"${datacenters}\"\n\n  # The \"type\" parameter controls the type of job, which impacts the scheduler's\n  # decision on placement. This configuration is optional and defaults to\n  # \"service\". For a full list of job types and their differences, please see\n  # the online documentation.\n  #\n  # For more information, please see the online documentation at:\n  #\n  #     https://www.nomadproject.io/docs/jobspec/schedulers\n  #\n  type                = \"service\"\n\n  update {\n    # The \"max_parallel\" parameter specifies the maximum number of updates to\n    # perform in parallel. In this case, this specifies to update a single task\n    # at a time.\n    max_parallel      = 1\n\n    health_check      = \"checks\"\n\n    # The \"min_healthy_time\" parameter specifies the minimum time the allocation\n    # must be in the healthy state before it is marked as healthy and unblocks\n    # further allocations from being updated.\n    min_healthy_time  = \"10s\"\n\n    # The \"healthy_deadline\" parameter specifies the deadline in which the\n    # allocation must be marked as healthy after which the allocation is\n    # automatically transitioned to unhealthy. Transitioning to unhealthy will\n    # fail the deployment and potentially roll back the job if \"auto_revert\" is\n    # set to true.\n    healthy_deadline  = \"3m\"\n\n    # The \"progress_deadline\" parameter specifies the deadline in which an\n    # allocation must be marked as healthy. The deadline begins when the first\n    # allocation for the deployment is created and is reset whenever an allocation\n    # as part of the deployment transitions to a healthy state. If no allocation\n    # transitions to the healthy state before the progress deadline, the\n    # deployment is marked as failed.\n    progress_deadline = \"10m\"\n\n%{ if use_canary }\n    # The \"canary\" parameter specifies that changes to the job that would result\n    # in destructive updates should create the specified number of canaries\n    # without stopping any previous allocations. Once the operator determines the\n    # canaries are healthy, they can be promoted which unblocks a rolling update\n    # of the remaining allocations at a rate of \"max_parallel\".\n    #\n    # Further, setting \"canary\" equal to the count of the task group allows\n    # blue/green deployments. When the job is updated, a full set of the new\n    # version is deployed and upon promotion the old version is stopped.\n    canary            = 1\n\n    # Specifies if the job should auto-promote to the canary version when all\n    # canaries become healthy during a deployment. Defaults to false which means\n    # canaries must be manually updated with the nomad deployment promote\n    # command.\n    auto_promote      = true\n\n    # The \"auto_revert\" parameter specifies if the job should auto-revert to the\n    # last stable job on deployment failure. A job is marked as stable if all the\n    # allocations as part of its deployment were marked healthy.\n    auto_revert       = true\n%{ endif }\n  }\n\n  # The reschedule stanza specifies the group's rescheduling strategy. If\n  # specified at the job level, the configuration will apply to all groups\n  # within the job. If the reschedule stanza is present on both the job and the\n  # group, they are merged with the group stanza taking the highest precedence\n  # and then the job.\n  reschedule {\n    delay             = \"30s\"\n    delay_function    = \"constant\"\n    unlimited         = true\n  }\n\n  # The \"group\" stanza defines a series of tasks that should be co-located on\n  # the same Nomad client. Any task within a group will be placed on the same\n  # client.\n  #\n  # For more information and examples on the \"group\" stanza, please see\n  # the online documentation at:\n  #\n  #     https://www.nomadproject.io/docs/job-specification/group\n  #\n  group \"prod-group1-${service_name}\" {\n    # The \"count\" parameter specifies the number of the task groups that should\n    # be running under this group. This value must be non-negative and defaults\n    # to 1.\n    count               = ${group_count}\n\n    # The restart stanza configures a tasks's behavior on task failure. Restarts\n    # happen on the client that is running the task.\n    #\n    # https://www.nomadproject.io/docs/job-specification/restart\n    #\n    restart {\n      interval  = \"30m\"\n      attempts  = 40\n      delay     = \"15s\"\n      mode      = \"delay\"\n    }\n\n    # The volume stanza allows the group to specify that it requires a given\n    # volume from the cluster.\n    #\n    # For more information and examples on the \"volume\" stanza, please see\n    # the online documentation at:\n    #\n    #     https://www.nomadproject.io/docs/job-specification/volume\n    #\n    %{ if use_host_volume }\n    volume \"prod-volume1-${service_name}\" {\n      type              = \"host\"\n      read_only         = false\n      source            = \"${host_volume}\"\n    }\n    %{ endif }\n\n    # The constraint allows restricting the set of eligible nodes. Constraints\n    # may filter on attributes or client metadata.\n    #\n    # For more information and examples on the \"volume\" stanza, please see\n    # the online documentation at:\n    #\n    #     https://www.nomadproject.io/docs/job-specification/constraint\n    #\n    constraint {\n      attribute         = \"$${attr.cpu.arch}\"\n      operator          = \"!=\"\n      value             = \"arm64\"\n    }\n\n    constraint {\n      attribute      = \"$${node.class}\"\n      value          = \"builder\"\n    }\n\n    # The \"task\" stanza creates an individual unit of work, such as a Docker\n    # container, web application, or batch processing.\n    #\n    # For more information and examples on the \"task\" stanza, please see\n    # the online documentation at:\n    #\n    #     https://www.nomadproject.io/docs/job-specification/task\n    #\n    task \"prod-task1-${service_name}\" {\n      # The \"driver\" parameter specifies the task driver that should be used to\n      # run the task.\n      driver            = \"exec\"\n\n      %{ if use_host_volume }\n      volume_mount {\n        volume          = \"prod-volume1-${service_name}\"\n        destination     = \"${data_dir}\"\n        read_only       = false\n      }\n      %{ endif }\n\n      %{ if use_vault_provider }\n      vault {\n        policies        = \"${vault_kv_policy_name}\"\n      }\n      %{ endif }\n\n      # The \"config\" stanza specifies the driver configuration, which is passed\n      # directly to the driver to start the task. The details of configurations\n      # are specific to each driver, so please see specific driver\n      # documentation for more information.\n      config {\n        command         = \"local/prometheus-${version}.linux-amd64/prometheus\"\n        args            = [\n          \"--config.file=secrets/prometheus.yml\",\n          \"--storage.tsdb.path=${data_dir}prometheus/\",\n          \"--storage.tsdb.retention.time=7d\"\n        ]\n      }\n\n      # The artifact stanza instructs Nomad to fetch and unpack a remote resource,\n      # such as a file, tarball, or binary. Nomad downloads artifacts using the\n      # popular go-getter library, which permits downloading artifacts from a\n      # variety of locations using a URL as the input source.\n      #\n      # For more information and examples on the \"artifact\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/artifact\n      #\n      artifact {\n        source          = \"${url}\"\n      }\n\n      # The \"template\" stanza instructs Nomad to manage a template, such as\n      # a configuration file or script. This template can optionally pull data\n      # from Consul or Vault to populate runtime configuration data.\n      #\n      # For more information and examples on the \"template\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/template\n      #\n      template {\n        change_mode     = \"noop\"\n        change_signal   = \"SIGINT\"\n        destination     = \"secrets/alerts.yml\"\n        left_delimiter  = \"{{{\"\n        right_delimiter = \"}}}\"\n        data            = \u003c\u003cEOH\n---\ngroups:\n- name: \"Jenkins Job Health Exporter\"\n  rules:\n  - alert: JenkinsJobHealthExporterFailures\n    expr: jenkins_job_failure{id=~\".*\"} \u003e jenkins_job_success{id=~\".*\"}\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Jenkins Job Health detected high failure rate on jenkins jobs.\"\n      description: \"Job: {{ $labels.id }}\"\n  - alert: JenkinsJobHealthExporterUnstable\n    expr: jenkins_job_unstable{id=~\".*\"} \u003e jenkins_job_success{id=~\".*\"}\n    for: 0m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Jenkins Job Health detected high unstable rate on jenkins jobs.\"\n      description: \"Job: {{ $labels.id }}\"\n- name: \"Consul\"\n  rules:\n  - alert: ConsulServiceHealthcheckFailed\n    expr: consul_catalog_service_node_healthy == 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Consul service healthcheck failed (instance {{ $labels.instance }}).\"\n      description: \"Service: `{{ $labels.service_name }}` Healthcheck: `{{ $labels.service_id }}`.\"\n  - alert: ConsulMissingMasterNode\n    expr: consul_raft_peers \u003c 3\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Consul missing master node (instance {{ $labels.instance }}).\"\n      description: \"Numbers of consul raft peers should be 3, in order to preserve quorum.\"\n  - alert: ConsulAgentUnhealthy\n    expr: consul_health_node_status{status=\"critical\"} == 1\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Consul agent unhealthy (instance {{ $labels.instance }}).\"\n      description: \"A Consul agent is down.\"\n- name: \"Hosts\"\n  rules:\n  - alert: NodeDown\n    expr: up == 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Prometheus target missing (instance {{ $labels.instance }}).\"\n      description: \"A Prometheus target has disappeared. An exporter might be crashed.\"\n  - alert: HostOutOfMemory\n    expr: node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes * 100 \u003c 10\n    for: 2m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host out of memory (instance {{ $labels.instance }}).\"\n      description: \"Node memory is filling up (\u003c 10% left).\"\n  - alert: HostOomKillDetected\n    expr: increase(node_vmstat_oom_kill[1m]) \u003e 0\n    for: 0m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host OOM kill detected (instance {{ $labels.instance }}).\"\n      description: \"OOM kill detected.\"\n  - alert: HostMemoryUnderMemoryPressure\n    expr: rate(node_vmstat_pgmajfault[1m]) \u003e 1000\n    for: 2m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host memory under memory pressure (instance {{ $labels.instance }}).\"\n      description: \"The node is under heavy memory pressure. High rate of major page faults.\"\n  - alert: HostOutOfDiskSpace\n    expr: (node_filesystem_avail_bytes * 100) / node_filesystem_size_bytes \u003c 10 and ON (instance, device, mountpoint) node_filesystem_readonly == 0\n    for: 2m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host out of disk space (instance {{ $labels.instance }}).\"\n      description: \"Disk is almost full (\u003c 10% left).\"\n  - alert: HostRaidDiskFailure\n    expr: node_md_disks{state=\"failed\"} \u003e 0\n    for: 2m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host RAID disk failure (instance {{ $labels.instance }}).\"\n      description: \"At least one device in RAID array on {{ $labels.instance }} failed. Array {{ $labels.md_device }} needs attention and possibly a disk swap.\"\n  - alert: HostConntrackLimit\n    expr: node_nf_conntrack_entries / node_nf_conntrack_entries_limit \u003e 0.8\n    for: 5m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host conntrack limit (instance {{ $labels.instance }}).\"\n      description: \"The number of conntrack is approching limit.\"\n  - alert: HostNetworkInterfaceSaturated\n    expr: (rate(node_network_receive_bytes_total{device!~\"^tap.*\"}[1m]) + rate(node_network_transmit_bytes_total{device!~\"^tap.*\"}[1m])) / node_network_speed_bytes{device!~\"^tap.*\"} \u003e 0.8\n    for: 1m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host Network Interface Saturated (instance {{ $labels.instance }}).\"\n      description: \"The network interface {{ $labels.interface }} on {{ $labels.instance }} is getting overloaded.\"\n  - alert: HostSystemdServiceCrashed\n    expr: node_systemd_unit_state{state=\"failed\"} == 1\n    for: 0m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host SystemD service crashed (instance {{ $labels.instance }}).\"\n      description: \"SystemD service crashed.\"\n  - alert: HostEdacCorrectableErrorsDetected\n    expr: increase(node_edac_correctable_errors_total[1m]) \u003e 0\n    for: 0m\n    labels:\n      severity: info\n    annotations:\n      summary: \"Host EDAC Correctable Errors detected (instance {{ $labels.instance }}).\"\n      description: '{{ $labels.instance }} has had {{ printf \"%.0f\" $value }} correctable memory errors reported by EDAC in the last 5 minutes.'\n  - alert: HostEdacUncorrectableErrorsDetected\n    expr: node_edac_uncorrectable_errors_total \u003e 0\n    for: 0m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host EDAC Uncorrectable Errors detected (instance {{ $labels.instance }}).\"\n      description: '{{ $labels.instance }} has had {{ printf \"%.0f\" $value }} uncorrectable memory errors reported by EDAC in the last 5 minutes.'\n- name: \"Min.io\"\n  rules:\n  - alert: MinioDiskOffline\n    expr: minio_offline_disks \u003e 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Minio disk offline (instance {{ $labels.instance }})\"\n      description: \"Minio disk is offline.\"\n  - alert: MinioStorageSpaceExhausted\n    expr: minio_disk_storage_free_bytes / 1024 / 1024 / 1024 \u003c 10\n    for: 2m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Minio storage space exhausted (instance {{ $labels.instance }}).\"\n      description: \"Minio storage space is low (\u003c 10 GB).\"\n- name: \"Prometheus\"\n  rules:\n  - alert: PrometheusConfigurationReloadFailure\n    expr: prometheus_config_last_reload_successful != 1\n    for: 0m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Prometheus configuration reload failure (instance {{ $labels.instance }}).\"\n      description: \"Prometheus configuration reload error.\"\n  - alert: PrometheusTooManyRestarts\n    expr: changes(process_start_time_seconds{job=~\"prometheus|pushgateway|alertmanager\"}[15m]) \u003e 2\n    for: 0m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Prometheus too many restarts (instance {{ $labels.instance }}).\"\n      description: \"Prometheus has restarted more than twice in the last 15 minutes. It might be crashlooping.\"\n  - alert: PrometheusAlertmanagerConfigurationReloadFailure\n    expr: alertmanager_config_last_reload_successful != 1\n    for: 0m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Prometheus AlertManager configuration reload failure (instance {{ $labels.instance }}).\"\n      description: \"AlertManager configuration reload error.\"\n  - alert: PrometheusRuleEvaluationFailures\n    expr: increase(prometheus_rule_evaluation_failures_total[3m]) \u003e 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Prometheus rule evaluation failures (instance {{ $labels.instance }}).\"\n      description: \"Prometheus encountered {{ $value }} rule evaluation failures, leading to potentially ignored alerts.\"\n  - alert: PrometheusTargetScrapingSlow\n    expr: prometheus_target_interval_length_seconds{quantile=\"0.9\"} \u003e 60\n    for: 5m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Prometheus target scraping slow (instance {{ $labels.instance }}).\"\n      description: \"Prometheus is scraping exporters slowly.\"\n  - alert: PrometheusTsdbCompactionsFailed\n    expr: increase(prometheus_tsdb_compactions_failed_total[1m]) \u003e 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Prometheus TSDB compactions failed (instance {{ $labels.instance }}).\"\n      description: \"Prometheus encountered {{ $value }} TSDB compactions failures.\"\n  - alert: PrometheusTsdbHeadTruncationsFailed\n    expr: increase(prometheus_tsdb_head_truncations_failed_total[1m]) \u003e 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Prometheus TSDB head truncations failed (instance {{ $labels.instance }}).\"\n      description: \"Prometheus encountered {{ $value }} TSDB head truncation failures.\"\n  - alert: PrometheusTsdbWalCorruptions\n    expr: increase(prometheus_tsdb_wal_corruptions_total[1m]) \u003e 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Prometheus TSDB WAL corruptions (instance {{ $labels.instance }}).\"\n      description: \"Prometheus encountered {{ $value }} TSDB WAL corruptions.\"\n  - alert: PrometheusTsdbWalTruncationsFailed\n    expr: increase(prometheus_tsdb_wal_truncations_failed_total[1m]) \u003e 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Prometheus TSDB WAL truncations failed (instance {{ $labels.instance }}).\"\n      description: \"Prometheus encountered {{ $value }} TSDB WAL truncation failures.\"\nEOH\n      }\n\n      template {\n        change_mode     = \"noop\"\n        change_signal   = \"SIGINT\"\n        destination     = \"secrets/prometheus.yml\"\n        data            = \u003c\u003cEOH\n---\nglobal:\n  scrape_interval:     5s\n  scrape_timeout:      5s\n  evaluation_interval: 5s\n\nalerting:\n  alertmanagers:\n  - consul_sd_configs:\n    - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n      services: [ 'alertmanager' ]\n\nrule_files:\n  - 'alerts.yml'\n\nscrape_configs:\n\n  - job_name: 'Nomad Cluster'\n    consul_sd_configs:\n    - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n      services: [ 'nomad-client', 'nomad' ]\n    relabel_configs:\n    - source_labels: [__meta_consul_tags]\n      regex: '(.*)http(.*)'\n      action: keep\n    metrics_path: /v1/metrics\n    params:\n      format: [ 'prometheus' ]\n\n  - job_name: 'Consul Cluster'\n    static_configs:\n      - targets: [ '10.30.51.22:8500' ]\n      - targets: [ '10.30.51.24:8500' ]\n      - targets: [ '10.30.51.25:8500' ]\n      - targets: [ '10.30.51.26:8500' ]\n      - targets: [ '10.30.51.28:8500' ]\n      - targets: [ '10.30.51.29:8500' ]\n      - targets: [ '10.30.51.30:8500' ]\n      - targets: [ '10.30.51.39:8500' ]\n      - targets: [ '10.30.51.40:8500' ]\n      - targets: [ '10.30.51.50:8500' ]\n      - targets: [ '10.30.51.51:8500' ]\n      - targets: [ '10.30.51.65:8500' ]\n      - targets: [ '10.30.51.66:8500' ]\n      - targets: [ '10.30.51.67:8500' ]\n      - targets: [ '10.30.51.68:8500' ]\n      - targets: [ '10.30.51.70:8500' ]\n      - targets: [ '10.30.51.71:8500' ]\n      - targets: [ '10.32.8.14:8500' ]\n      - targets: [ '10.32.8.15:8500' ]\n      - targets: [ '10.32.8.16:8500' ]\n      - targets: [ '10.32.8.17:8500' ]\n    metrics_path: /v1/agent/metrics\n    params:\n      format: [ 'prometheus' ]\n\n  - job_name: 'Blackbox Exporter (icmp)'\n    static_configs:\n      - targets: [ 'gerrit.fd.io' ]\n      - targets: [ 'jenkins.fd.io' ]\n      - targets: [ '10.32.8.17' ]\n    params:\n      module: [ 'icmp_v4' ]\n    relabel_configs:\n      - source_labels: [__address__]\n        target_label: __param_target\n      - source_labels: [__param_target]\n        target_label: instance\n      - target_label: __address__\n        replacement: localhost:9115\n    metrics_path: /probe\n\n  - job_name: 'Blackbox Exporter (http)'\n    static_configs:\n      - targets: [ 'gerrit.fd.io' ]\n      - targets: [ 'jenkins.fd.io' ]\n    params:\n      module: [ 'http_2xx' ]\n    relabel_configs:\n      - source_labels: [__address__]\n        target_label: __param_target\n      - source_labels: [__param_target]\n        target_label: instance\n      - target_label: __address__\n        replacement: localhost:9115\n    metrics_path: /probe\n\n  - job_name: 'Jenkins Job Health Exporter'\n    static_configs:\n      - targets: [ '10.30.51.22:9186' ]\n    metric_relabel_configs:\n      - source_labels: [ __name__ ]\n        regex: '^(vpp.*|csit.*)_(success|failure|total|unstable|reqtime_ms)$'\n        action: replace\n        replacement: '$1'\n        target_label: id\n      - source_labels: [ __name__ ]\n        regex: '^(vpp.*|csit.*)_(success|failure|total|unstable|reqtime_ms)$'\n        replacement: 'jenkins_job_$2'\n        target_label: __name__\n\n  - job_name: 'Node Exporter'\n    static_configs:\n      - targets: [ '10.30.51.22:9100' ]\n      - targets: [ '10.30.51.24:9100' ]\n      - targets: [ '10.30.51.25:9100' ]\n      - targets: [ '10.30.51.26:9100' ]\n      - targets: [ '10.30.51.28:9100' ]\n      - targets: [ '10.30.51.29:9100' ]\n      - targets: [ '10.30.51.30:9100' ]\n      - targets: [ '10.30.51.39:9100' ]\n      - targets: [ '10.30.51.40:9100' ]\n      - targets: [ '10.30.51.50:9100' ]\n      - targets: [ '10.30.51.51:9100' ]\n      - targets: [ '10.30.51.65:9100' ]\n      - targets: [ '10.30.51.66:9100' ]\n      - targets: [ '10.30.51.67:9100' ]\n      - targets: [ '10.30.51.68:9100' ]\n      - targets: [ '10.30.51.70:9100' ]\n      - targets: [ '10.30.51.71:9100' ]\n      - targets: [ '10.32.8.14:9100' ]\n      - targets: [ '10.32.8.15:9100' ]\n      - targets: [ '10.32.8.16:9100' ]\n      - targets: [ '10.32.8.17:9100' ]\n\n  - job_name: 'Alertmanager'\n    consul_sd_configs:\n    - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n      services: [ 'alertmanager' ]\n\n  - job_name: 'Grafana'\n    consul_sd_configs:\n    - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n      services: [ 'grafana' ]\n\n  - job_name: 'Prometheus'\n    consul_sd_configs:\n    - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n      services: [ 'prometheus' ]\n\n  - job_name: 'Minio'\n    bearer_token: eyJhbGciOiJIUzUxMiIsInR5cCI6IkpXVCJ9.eyJleHAiOjQ3NjQ1ODEzMzcsImlzcyI6InByb21ldGhldXMiLCJzdWIiOiJtaW5pbyJ9.oeTw3EIaiFmlDikrHXWiWXMH2vxLfDLkfjEC7G2N3M_keH_xyA_l2ofLLNYtopa_3GCEZnxLQdPuFZrmgpkDWg\n    consul_sd_configs:\n    - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n      services: [ 'storage' ]\n    metrics_path: /minio/prometheus/metrics\nEOH\n      }\n\n      # The service stanza instructs Nomad to register a service with Consul.\n      #\n      # For more information and examples on the \"task\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/service\n      #\n      service {\n        name            = \"${service_name}\"\n        port            = \"${service_name}\"\n        tags            = [ \"${service_name}$${NOMAD_ALLOC_INDEX}\" ]\n        check {\n          name          = \"Prometheus Check Live\"\n          type          = \"http\"\n          path          = \"/-/healthy\"\n          interval      = \"10s\"\n          timeout       = \"2s\"\n        }\n      }\n\n      # The \"resources\" stanza describes the requirements a task needs to\n      # execute. Resource requirements include memory, network, cpu, and more.\n      # This ensures the task will execute on a machine that contains enough\n      # resource capacity.\n      #\n      # For more information and examples on the \"resources\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/resources\n      #\n      resources {\n        cpu             = ${cpu}\n        memory          = ${mem}\n        # The network stanza specifies the networking requirements for the task\n        # group, including the network mode and port allocations. When scheduling\n        # jobs in Nomad they are provisioned across your fleet of machines along\n        # with other jobs and services. Because you don't know in advance what host\n        # your job will be provisioned on, Nomad will provide your tasks with\n        # network configuration when they start up.\n        #\n        # For more information and examples on the \"template\" stanza, please see\n        # the online documentation at:\n        #\n        #     https://www.nomadproject.io/docs/job-specification/network\n        #\n        network {\n          port \"${service_name}\" {\n            static      = ${port}\n          }\n        }\n      }\n    }\n  }\n}",
             "vars": {
               "cpu": "2000",
               "data_dir": "/data/",
@@ -465,27 +468,25 @@
           "schema_version": 0,
           "attributes": {
             "allocation_ids": [
-              "9b7311cc-95ba-fead-8c92-91148f48d218",
-              "5564fb46-6a89-1e92-7bcd-7f5fa55c42e8",
-              "519e4ea1-f088-069c-3bc2-eb6de1b36b9e",
-              "6f144324-2ee0-c1fd-0f71-c07cc1fda099",
-              "6776d9ca-70ba-129f-05a9-ca6fccdb6289",
-              "0fb06047-62e0-48e4-e352-63b4602407f2",
-              "ddb72c78-1f3f-2d1e-0157-7b7bb05aaa4a",
-              "67dfb1da-36a3-e442-5c66-8d6340f579c3"
+              "655f7aa1-199f-4241-9ff0-37620b2f3f10",
+              "f80ed1f8-7783-6b17-0ed0-db3ab7786dbf",
+              "0df91982-632b-a2dd-5149-d81cd93235f6",
+              "277d7a3b-c31a-e4eb-a8fe-d97377fb4d9c",
+              "6d8dc89f-788d-1229-5558-0e56398eb6f0",
+              "b9f0d581-0093-d4e0-a502-9f15475b7b93"
             ],
             "datacenters": [
               "yul1"
             ],
-            "deployment_id": "88fd2d42-3b5a-8e1e-3047-7a4f93417fd3",
+            "deployment_id": "c5203cd1-b38b-44ca-21d0-4b1638ad382a",
             "deployment_status": "successful",
             "deregister_on_destroy": true,
             "deregister_on_id_change": true,
             "detach": false,
             "id": "prod-prometheus",
-            "jobspec": "job \"prod-prometheus\" {\n  # The \"region\" parameter specifies the region in which to execute the job.\n  # If omitted, this inherits the default region name of \"global\".\n  # region = \"global\"\n  #\n  # The \"datacenters\" parameter specifies the list of datacenters which should\n  # be considered when placing this task. This must be provided.\n  datacenters         = \"yul1\"\n\n  # The \"type\" parameter controls the type of job, which impacts the scheduler's\n  # decision on placement. This configuration is optional and defaults to\n  # \"service\". For a full list of job types and their differences, please see\n  # the online documentation.\n  #\n  # For more information, please see the online documentation at:\n  #\n  #     https://www.nomadproject.io/docs/jobspec/schedulers\n  #\n  type                = \"service\"\n\n  update {\n    # The \"max_parallel\" parameter specifies the maximum number of updates to\n    # perform in parallel. In this case, this specifies to update a single task\n    # at a time.\n    max_parallel      = 1\n\n    health_check      = \"checks\"\n\n    # The \"min_healthy_time\" parameter specifies the minimum time the allocation\n    # must be in the healthy state before it is marked as healthy and unblocks\n    # further allocations from being updated.\n    min_healthy_time  = \"10s\"\n\n    # The \"healthy_deadline\" parameter specifies the deadline in which the\n    # allocation must be marked as healthy after which the allocation is\n    # automatically transitioned to unhealthy. Transitioning to unhealthy will\n    # fail the deployment and potentially roll back the job if \"auto_revert\" is\n    # set to true.\n    healthy_deadline  = \"3m\"\n\n    # The \"progress_deadline\" parameter specifies the deadline in which an\n    # allocation must be marked as healthy. The deadline begins when the first\n    # allocation for the deployment is created and is reset whenever an allocation\n    # as part of the deployment transitions to a healthy state. If no allocation\n    # transitions to the healthy state before the progress deadline, the\n    # deployment is marked as failed.\n    progress_deadline = \"10m\"\n\n\n    # The \"canary\" parameter specifies that changes to the job that would result\n    # in destructive updates should create the specified number of canaries\n    # without stopping any previous allocations. Once the operator determines the\n    # canaries are healthy, they can be promoted which unblocks a rolling update\n    # of the remaining allocations at a rate of \"max_parallel\".\n    #\n    # Further, setting \"canary\" equal to the count of the task group allows\n    # blue/green deployments. When the job is updated, a full set of the new\n    # version is deployed and upon promotion the old version is stopped.\n    canary            = 1\n\n    # Specifies if the job should auto-promote to the canary version when all\n    # canaries become healthy during a deployment. Defaults to false which means\n    # canaries must be manually updated with the nomad deployment promote\n    # command.\n    auto_promote      = true\n\n    # The \"auto_revert\" parameter specifies if the job should auto-revert to the\n    # last stable job on deployment failure. A job is marked as stable if all the\n    # allocations as part of its deployment were marked healthy.\n    auto_revert       = true\n\n  }\n\n  # The reschedule stanza specifies the group's rescheduling strategy. If\n  # specified at the job level, the configuration will apply to all groups\n  # within the job. If the reschedule stanza is present on both the job and the\n  # group, they are merged with the group stanza taking the highest precedence\n  # and then the job.\n  reschedule {\n    delay             = \"30s\"\n    delay_function    = \"constant\"\n    unlimited         = true\n  }\n\n  # The \"group\" stanza defines a series of tasks that should be co-located on\n  # the same Nomad client. Any task within a group will be placed on the same\n  # client.\n  #\n  # For more information and examples on the \"group\" stanza, please see\n  # the online documentation at:\n  #\n  #     https://www.nomadproject.io/docs/job-specification/group\n  #\n  group \"prod-group1-prometheus\" {\n    # The \"count\" parameter specifies the number of the task groups that should\n    # be running under this group. This value must be non-negative and defaults\n    # to 1.\n    count               = 4\n\n    # The restart stanza configures a tasks's behavior on task failure. Restarts\n    # happen on the client that is running the task.\n    #\n    # https://www.nomadproject.io/docs/job-specification/restart\n    #\n    restart {\n      interval  = \"30m\"\n      attempts  = 40\n      delay     = \"15s\"\n      mode      = \"delay\"\n    }\n\n    # The volume stanza allows the group to specify that it requires a given\n    # volume from the cluster.\n    #\n    # For more information and examples on the \"volume\" stanza, please see\n    # the online documentation at:\n    #\n    #     https://www.nomadproject.io/docs/job-specification/volume\n    #\n    \n    volume \"prod-volume1-prometheus\" {\n      type              = \"host\"\n      read_only         = false\n      source            = \"prod-volume-data1-1\"\n    }\n    \n\n    # The constraint allows restricting the set of eligible nodes. Constraints\n    # may filter on attributes or client metadata.\n    #\n    # For more information and examples on the \"volume\" stanza, please see\n    # the online documentation at:\n    #\n    #     https://www.nomadproject.io/docs/job-specification/constraint\n    #\n    constraint {\n      attribute         = \"${attr.cpu.arch}\"\n      operator          = \"!=\"\n      value             = \"arm64\"\n    }\n\n    # The \"task\" stanza creates an individual unit of work, such as a Docker\n    # container, web application, or batch processing.\n    #\n    # For more information and examples on the \"task\" stanza, please see\n    # the online documentation at:\n    #\n    #     https://www.nomadproject.io/docs/job-specification/task\n    #\n    task \"prod-task1-prometheus\" {\n      # The \"driver\" parameter specifies the task driver that should be used to\n      # run the task.\n      driver            = \"exec\"\n\n      \n      volume_mount {\n        volume          = \"prod-volume1-prometheus\"\n        destination     = \"/data/\"\n        read_only       = false\n      }\n      \n\n      \n\n      # The \"config\" stanza specifies the driver configuration, which is passed\n      # directly to the driver to start the task. The details of configurations\n      # are specific to each driver, so please see specific driver\n      # documentation for more information.\n      config {\n        command         = \"local/prometheus-2.28.1.linux-amd64/prometheus\"\n        args            = [\n          \"--config.file=secrets/prometheus.yml\",\n          \"--storage.tsdb.path=/data/prometheus/\",\n          \"--storage.tsdb.retention.time=7d\"\n        ]\n      }\n\n      # The artifact stanza instructs Nomad to fetch and unpack a remote resource,\n      # such as a file, tarball, or binary. Nomad downloads artifacts using the\n      # popular go-getter library, which permits downloading artifacts from a\n      # variety of locations using a URL as the input source.\n      #\n      # For more information and examples on the \"artifact\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/artifact\n      #\n      artifact {\n        source          = \"https://github.com/prometheus/prometheus/releases/download/v2.28.1/prometheus-2.28.1.linux-amd64.tar.gz\"\n      }\n\n      # The \"template\" stanza instructs Nomad to manage a template, such as\n      # a configuration file or script. This template can optionally pull data\n      # from Consul or Vault to populate runtime configuration data.\n      #\n      # For more information and examples on the \"template\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/template\n      #\n      template {\n        change_mode     = \"noop\"\n        change_signal   = \"SIGINT\"\n        destination     = \"secrets/alerts.yml\"\n        left_delimiter  = \"{{{\"\n        right_delimiter = \"}}}\"\n        data            = \u003c\u003cEOH\n---\ngroups:\n- name: \"Jenkins Job Health Exporter\"\n  rules:\n  - alert: JenkinsJobHealthExporterFailures\n    expr: jenkins_job_failure{id=~\".*\"} \u003e jenkins_job_success{id=~\".*\"}\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Jenkins Job Health detected high failure rate on jenkins jobs.\"\n      description: \"Job: {{ $labels.id }}\"\n  - alert: JenkinsJobHealthExporterUnstable\n    expr: jenkins_job_unstable{id=~\".*\"} \u003e jenkins_job_success{id=~\".*\"}\n    for: 0m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Jenkins Job Health detected high unstable rate on jenkins jobs.\"\n      description: \"Job: {{ $labels.id }}\"\n- name: \"Consul\"\n  rules:\n  - alert: ConsulServiceHealthcheckFailed\n    expr: consul_catalog_service_node_healthy == 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Consul service healthcheck failed (instance {{ $labels.instance }}).\"\n      description: \"Service: `{{ $labels.service_name }}` Healthcheck: `{{ $labels.service_id }}`.\"\n  - alert: ConsulMissingMasterNode\n    expr: consul_raft_peers \u003c 3\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Consul missing master node (instance {{ $labels.instance }}).\"\n      description: \"Numbers of consul raft peers should be 3, in order to preserve quorum.\"\n  - alert: ConsulAgentUnhealthy\n    expr: consul_health_node_status{status=\"critical\"} == 1\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Consul agent unhealthy (instance {{ $labels.instance }}).\"\n      description: \"A Consul agent is down.\"\n- name: \"Hosts\"\n  rules:\n  - alert: NodeDown\n    expr: up == 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Prometheus target missing (instance {{ $labels.instance }}).\"\n      description: \"A Prometheus target has disappeared. An exporter might be crashed.\"\n  - alert: HostOutOfMemory\n    expr: node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes * 100 \u003c 10\n    for: 2m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host out of memory (instance {{ $labels.instance }}).\"\n      description: \"Node memory is filling up (\u003c 10% left).\"\n  - alert: HostOomKillDetected\n    expr: increase(node_vmstat_oom_kill[1m]) \u003e 0\n    for: 0m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host OOM kill detected (instance {{ $labels.instance }}).\"\n      description: \"OOM kill detected.\"\n  - alert: HostMemoryUnderMemoryPressure\n    expr: rate(node_vmstat_pgmajfault[1m]) \u003e 1000\n    for: 2m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host memory under memory pressure (instance {{ $labels.instance }}).\"\n      description: \"The node is under heavy memory pressure. High rate of major page faults.\"\n  - alert: HostOutOfDiskSpace\n    expr: (node_filesystem_avail_bytes * 100) / node_filesystem_size_bytes \u003c 10 and ON (instance, device, mountpoint) node_filesystem_readonly == 0\n    for: 2m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host out of disk space (instance {{ $labels.instance }}).\"\n      description: \"Disk is almost full (\u003c 10% left).\"\n  - alert: HostRaidDiskFailure\n    expr: node_md_disks{state=\"failed\"} \u003e 0\n    for: 2m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host RAID disk failure (instance {{ $labels.instance }}).\"\n      description: \"At least one device in RAID array on {{ $labels.instance }} failed. Array {{ $labels.md_device }} needs attention and possibly a disk swap.\"\n  - alert: HostConntrackLimit\n    expr: node_nf_conntrack_entries / node_nf_conntrack_entries_limit \u003e 0.8\n    for: 5m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host conntrack limit (instance {{ $labels.instance }}).\"\n      description: \"The number of conntrack is approching limit.\"\n  - alert: HostNetworkInterfaceSaturated\n    expr: (rate(node_network_receive_bytes_total{device!~\"^tap.*\"}[1m]) + rate(node_network_transmit_bytes_total{device!~\"^tap.*\"}[1m])) / node_network_speed_bytes{device!~\"^tap.*\"} \u003e 0.8\n    for: 1m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host Network Interface Saturated (instance {{ $labels.instance }}).\"\n      description: \"The network interface {{ $labels.interface }} on {{ $labels.instance }} is getting overloaded.\"\n  - alert: HostSystemdServiceCrashed\n    expr: node_systemd_unit_state{state=\"failed\"} == 1\n    for: 0m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host SystemD service crashed (instance {{ $labels.instance }}).\"\n      description: \"SystemD service crashed.\"\n  - alert: HostEdacCorrectableErrorsDetected\n    expr: increase(node_edac_correctable_errors_total[1m]) \u003e 0\n    for: 0m\n    labels:\n      severity: info\n    annotations:\n      summary: \"Host EDAC Correctable Errors detected (instance {{ $labels.instance }}).\"\n      description: '{{ $labels.instance }} has had {{ printf \"%.0f\" $value }} correctable memory errors reported by EDAC in the last 5 minutes.'\n  - alert: HostEdacUncorrectableErrorsDetected\n    expr: node_edac_uncorrectable_errors_total \u003e 0\n    for: 0m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host EDAC Uncorrectable Errors detected (instance {{ $labels.instance }}).\"\n      description: '{{ $labels.instance }} has had {{ printf \"%.0f\" $value }} uncorrectable memory errors reported by EDAC in the last 5 minutes.'\n- name: \"Min.io\"\n  rules:\n  - alert: MinioDiskOffline\n    expr: minio_offline_disks \u003e 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Minio disk offline (instance {{ $labels.instance }})\"\n      description: \"Minio disk is offline.\"\n  - alert: MinioStorageSpaceExhausted\n    expr: minio_disk_storage_free_bytes / 1024 / 1024 / 1024 \u003c 10\n    for: 2m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Minio storage space exhausted (instance {{ $labels.instance }}).\"\n      description: \"Minio storage space is low (\u003c 10 GB).\"\n- name: \"Prometheus\"\n  rules:\n  - alert: PrometheusConfigurationReloadFailure\n    expr: prometheus_config_last_reload_successful != 1\n    for: 0m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Prometheus configuration reload failure (instance {{ $labels.instance }}).\"\n      description: \"Prometheus configuration reload error.\"\n  - alert: PrometheusTooManyRestarts\n    expr: changes(process_start_time_seconds{job=~\"prometheus|pushgateway|alertmanager\"}[15m]) \u003e 2\n    for: 0m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Prometheus too many restarts (instance {{ $labels.instance }}).\"\n      description: \"Prometheus has restarted more than twice in the last 15 minutes. It might be crashlooping.\"\n  - alert: PrometheusAlertmanagerConfigurationReloadFailure\n    expr: alertmanager_config_last_reload_successful != 1\n    for: 0m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Prometheus AlertManager configuration reload failure (instance {{ $labels.instance }}).\"\n      description: \"AlertManager configuration reload error.\"\n  - alert: PrometheusRuleEvaluationFailures\n    expr: increase(prometheus_rule_evaluation_failures_total[3m]) \u003e 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Prometheus rule evaluation failures (instance {{ $labels.instance }}).\"\n      description: \"Prometheus encountered {{ $value }} rule evaluation failures, leading to potentially ignored alerts.\"\n  - alert: PrometheusTargetScrapingSlow\n    expr: prometheus_target_interval_length_seconds{quantile=\"0.9\"} \u003e 60\n    for: 5m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Prometheus target scraping slow (instance {{ $labels.instance }}).\"\n      description: \"Prometheus is scraping exporters slowly.\"\n  - alert: PrometheusTsdbCompactionsFailed\n    expr: increase(prometheus_tsdb_compactions_failed_total[1m]) \u003e 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Prometheus TSDB compactions failed (instance {{ $labels.instance }}).\"\n      description: \"Prometheus encountered {{ $value }} TSDB compactions failures.\"\n  - alert: PrometheusTsdbHeadTruncationsFailed\n    expr: increase(prometheus_tsdb_head_truncations_failed_total[1m]) \u003e 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Prometheus TSDB head truncations failed (instance {{ $labels.instance }}).\"\n      description: \"Prometheus encountered {{ $value }} TSDB head truncation failures.\"\n  - alert: PrometheusTsdbWalCorruptions\n    expr: increase(prometheus_tsdb_wal_corruptions_total[1m]) \u003e 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Prometheus TSDB WAL corruptions (instance {{ $labels.instance }}).\"\n      description: \"Prometheus encountered {{ $value }} TSDB WAL corruptions.\"\n  - alert: PrometheusTsdbWalTruncationsFailed\n    expr: increase(prometheus_tsdb_wal_truncations_failed_total[1m]) \u003e 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Prometheus TSDB WAL truncations failed (instance {{ $labels.instance }}).\"\n      description: \"Prometheus encountered {{ $value }} TSDB WAL truncation failures.\"\nEOH\n      }\n\n      template {\n        change_mode     = \"noop\"\n        change_signal   = \"SIGINT\"\n        destination     = \"secrets/prometheus.yml\"\n        data            = \u003c\u003cEOH\n---\nglobal:\n  scrape_interval:     5s\n  scrape_timeout:      5s\n  evaluation_interval: 5s\n\nalerting:\n  alertmanagers:\n  - consul_sd_configs:\n    - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n      services: [ 'alertmanager' ]\n\nrule_files:\n  - 'alerts.yml'\n\nscrape_configs:\n\n  - job_name: 'Nomad Cluster'\n    consul_sd_configs:\n    - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n      services: [ 'nomad-client', 'nomad' ]\n    relabel_configs:\n    - source_labels: [__meta_consul_tags]\n      regex: '(.*)http(.*)'\n      action: keep\n    metrics_path: /v1/metrics\n    params:\n      format: [ 'prometheus' ]\n\n  - job_name: 'Consul Cluster'\n    static_configs:\n      - targets: [ '10.30.51.22:8500' ]\n      - targets: [ '10.30.51.24:8500' ]\n      - targets: [ '10.30.51.25:8500' ]\n      - targets: [ '10.30.51.26:8500' ]\n      - targets: [ '10.30.51.28:8500' ]\n      - targets: [ '10.30.51.29:8500' ]\n      - targets: [ '10.30.51.30:8500' ]\n      - targets: [ '10.30.51.39:8500' ]\n      - targets: [ '10.30.51.40:8500' ]\n      - targets: [ '10.30.51.50:8500' ]\n      - targets: [ '10.30.51.51:8500' ]\n      - targets: [ '10.30.51.65:8500' ]\n      - targets: [ '10.30.51.66:8500' ]\n      - targets: [ '10.30.51.67:8500' ]\n      - targets: [ '10.30.51.68:8500' ]\n      - targets: [ '10.30.51.70:8500' ]\n      - targets: [ '10.30.51.71:8500' ]\n      - targets: [ '10.32.8.14:8500' ]\n      - targets: [ '10.32.8.15:8500' ]\n      - targets: [ '10.32.8.16:8500' ]\n      - targets: [ '10.32.8.17:8500' ]\n    metrics_path: /v1/agent/metrics\n    params:\n      format: [ 'prometheus' ]\n\n  - job_name: 'Blackbox Exporter (icmp)'\n    static_configs:\n      - targets: [ 'gerrit.fd.io' ]\n      - targets: [ 'jenkins.fd.io' ]\n      - targets: [ '10.32.8.17' ]\n    params:\n      module: [ 'icmp_v4' ]\n    relabel_configs:\n      - source_labels: [__address__]\n        target_label: __param_target\n      - source_labels: [__param_target]\n        target_label: instance\n      - target_label: __address__\n        replacement: localhost:9115\n    metrics_path: /probe\n\n  - job_name: 'Blackbox Exporter (http)'\n    static_configs:\n      - targets: [ 'gerrit.fd.io' ]\n      - targets: [ 'jenkins.fd.io' ]\n    params:\n      module: [ 'http_2xx' ]\n    relabel_configs:\n      - source_labels: [__address__]\n        target_label: __param_target\n      - source_labels: [__param_target]\n        target_label: instance\n      - target_label: __address__\n        replacement: localhost:9115\n    metrics_path: /probe\n\n  - job_name: 'Jenkins Job Health Exporter'\n    static_configs:\n      - targets: [ '10.30.51.22:9186' ]\n    metric_relabel_configs:\n      - source_labels: [ __name__ ]\n        regex: '^(vpp.*|csit.*)_(success|failure|total|unstable|reqtime_ms)$'\n        action: replace\n        replacement: '$1'\n        target_label: id\n      - source_labels: [ __name__ ]\n        regex: '^(vpp.*|csit.*)_(success|failure|total|unstable|reqtime_ms)$'\n        replacement: 'jenkins_job_$2'\n        target_label: __name__\n\n  - job_name: 'Node Exporter'\n    static_configs:\n      - targets: [ '10.30.51.22:9100' ]\n      - targets: [ '10.30.51.24:9100' ]\n      - targets: [ '10.30.51.25:9100' ]\n      - targets: [ '10.30.51.26:9100' ]\n      - targets: [ '10.30.51.28:9100' ]\n      - targets: [ '10.30.51.29:9100' ]\n      - targets: [ '10.30.51.30:9100' ]\n      - targets: [ '10.30.51.39:9100' ]\n      - targets: [ '10.30.51.40:9100' ]\n      - targets: [ '10.30.51.50:9100' ]\n      - targets: [ '10.30.51.51:9100' ]\n      - targets: [ '10.30.51.65:9100' ]\n      - targets: [ '10.30.51.66:9100' ]\n      - targets: [ '10.30.51.67:9100' ]\n      - targets: [ '10.30.51.68:9100' ]\n      - targets: [ '10.30.51.70:9100' ]\n      - targets: [ '10.30.51.71:9100' ]\n      - targets: [ '10.32.8.14:9100' ]\n      - targets: [ '10.32.8.15:9100' ]\n      - targets: [ '10.32.8.16:9100' ]\n      - targets: [ '10.32.8.17:9100' ]\n\n  - job_name: 'Alertmanager'\n    consul_sd_configs:\n    - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n      services: [ 'alertmanager' ]\n\n  - job_name: 'Grafana'\n    consul_sd_configs:\n    - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n      services: [ 'grafana' ]\n\n  - job_name: 'Prometheus'\n    consul_sd_configs:\n    - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n      services: [ 'prometheus' ]\n\n  - job_name: 'Minio'\n    bearer_token: eyJhbGciOiJIUzUxMiIsInR5cCI6IkpXVCJ9.eyJleHAiOjQ3NjQ1ODEzMzcsImlzcyI6InByb21ldGhldXMiLCJzdWIiOiJtaW5pbyJ9.oeTw3EIaiFmlDikrHXWiWXMH2vxLfDLkfjEC7G2N3M_keH_xyA_l2ofLLNYtopa_3GCEZnxLQdPuFZrmgpkDWg\n    consul_sd_configs:\n    - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n      services: [ 'storage' ]\n    metrics_path: /minio/prometheus/metrics\nEOH\n      }\n\n      # The service stanza instructs Nomad to register a service with Consul.\n      #\n      # For more information and examples on the \"task\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/service\n      #\n      service {\n        name            = \"prometheus\"\n        port            = \"prometheus\"\n        tags            = [ \"prometheus${NOMAD_ALLOC_INDEX}\" ]\n        check {\n          name          = \"Prometheus Check Live\"\n          type          = \"http\"\n          path          = \"/-/healthy\"\n          interval      = \"10s\"\n          timeout       = \"2s\"\n        }\n      }\n\n      # The \"resources\" stanza describes the requirements a task needs to\n      # execute. Resource requirements include memory, network, cpu, and more.\n      # This ensures the task will execute on a machine that contains enough\n      # resource capacity.\n      #\n      # For more information and examples on the \"resources\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/resources\n      #\n      resources {\n        cpu             = 2000\n        memory          = 8192\n        # The network stanza specifies the networking requirements for the task\n        # group, including the network mode and port allocations. When scheduling\n        # jobs in Nomad they are provisioned across your fleet of machines along\n        # with other jobs and services. Because you don't know in advance what host\n        # your job will be provisioned on, Nomad will provide your tasks with\n        # network configuration when they start up.\n        #\n        # For more information and examples on the \"template\" stanza, please see\n        # the online documentation at:\n        #\n        #     https://www.nomadproject.io/docs/job-specification/network\n        #\n        network {\n          port \"prometheus\" {\n            static      = 9090\n          }\n        }\n      }\n    }\n  }\n}",
+            "jobspec": "job \"prod-prometheus\" {\n  # The \"region\" parameter specifies the region in which to execute the job.\n  # If omitted, this inherits the default region name of \"global\".\n  # region = \"global\"\n  #\n  # The \"datacenters\" parameter specifies the list of datacenters which should\n  # be considered when placing this task. This must be provided.\n  datacenters         = \"yul1\"\n\n  # The \"type\" parameter controls the type of job, which impacts the scheduler's\n  # decision on placement. This configuration is optional and defaults to\n  # \"service\". For a full list of job types and their differences, please see\n  # the online documentation.\n  #\n  # For more information, please see the online documentation at:\n  #\n  #     https://www.nomadproject.io/docs/jobspec/schedulers\n  #\n  type                = \"service\"\n\n  update {\n    # The \"max_parallel\" parameter specifies the maximum number of updates to\n    # perform in parallel. In this case, this specifies to update a single task\n    # at a time.\n    max_parallel      = 1\n\n    health_check      = \"checks\"\n\n    # The \"min_healthy_time\" parameter specifies the minimum time the allocation\n    # must be in the healthy state before it is marked as healthy and unblocks\n    # further allocations from being updated.\n    min_healthy_time  = \"10s\"\n\n    # The \"healthy_deadline\" parameter specifies the deadline in which the\n    # allocation must be marked as healthy after which the allocation is\n    # automatically transitioned to unhealthy. Transitioning to unhealthy will\n    # fail the deployment and potentially roll back the job if \"auto_revert\" is\n    # set to true.\n    healthy_deadline  = \"3m\"\n\n    # The \"progress_deadline\" parameter specifies the deadline in which an\n    # allocation must be marked as healthy. The deadline begins when the first\n    # allocation for the deployment is created and is reset whenever an allocation\n    # as part of the deployment transitions to a healthy state. If no allocation\n    # transitions to the healthy state before the progress deadline, the\n    # deployment is marked as failed.\n    progress_deadline = \"10m\"\n\n\n    # The \"canary\" parameter specifies that changes to the job that would result\n    # in destructive updates should create the specified number of canaries\n    # without stopping any previous allocations. Once the operator determines the\n    # canaries are healthy, they can be promoted which unblocks a rolling update\n    # of the remaining allocations at a rate of \"max_parallel\".\n    #\n    # Further, setting \"canary\" equal to the count of the task group allows\n    # blue/green deployments. When the job is updated, a full set of the new\n    # version is deployed and upon promotion the old version is stopped.\n    canary            = 1\n\n    # Specifies if the job should auto-promote to the canary version when all\n    # canaries become healthy during a deployment. Defaults to false which means\n    # canaries must be manually updated with the nomad deployment promote\n    # command.\n    auto_promote      = true\n\n    # The \"auto_revert\" parameter specifies if the job should auto-revert to the\n    # last stable job on deployment failure. A job is marked as stable if all the\n    # allocations as part of its deployment were marked healthy.\n    auto_revert       = true\n\n  }\n\n  # The reschedule stanza specifies the group's rescheduling strategy. If\n  # specified at the job level, the configuration will apply to all groups\n  # within the job. If the reschedule stanza is present on both the job and the\n  # group, they are merged with the group stanza taking the highest precedence\n  # and then the job.\n  reschedule {\n    delay             = \"30s\"\n    delay_function    = \"constant\"\n    unlimited         = true\n  }\n\n  # The \"group\" stanza defines a series of tasks that should be co-located on\n  # the same Nomad client. Any task within a group will be placed on the same\n  # client.\n  #\n  # For more information and examples on the \"group\" stanza, please see\n  # the online documentation at:\n  #\n  #     https://www.nomadproject.io/docs/job-specification/group\n  #\n  group \"prod-group1-prometheus\" {\n    # The \"count\" parameter specifies the number of the task groups that should\n    # be running under this group. This value must be non-negative and defaults\n    # to 1.\n    count               = 4\n\n    # The restart stanza configures a tasks's behavior on task failure. Restarts\n    # happen on the client that is running the task.\n    #\n    # https://www.nomadproject.io/docs/job-specification/restart\n    #\n    restart {\n      interval  = \"30m\"\n      attempts  = 40\n      delay     = \"15s\"\n      mode      = \"delay\"\n    }\n\n    # The volume stanza allows the group to specify that it requires a given\n    # volume from the cluster.\n    #\n    # For more information and examples on the \"volume\" stanza, please see\n    # the online documentation at:\n    #\n    #     https://www.nomadproject.io/docs/job-specification/volume\n    #\n    \n    volume \"prod-volume1-prometheus\" {\n      type              = \"host\"\n      read_only         = false\n      source            = \"prod-volume-data1-1\"\n    }\n    \n\n    # The constraint allows restricting the set of eligible nodes. Constraints\n    # may filter on attributes or client metadata.\n    #\n    # For more information and examples on the \"volume\" stanza, please see\n    # the online documentation at:\n    #\n    #     https://www.nomadproject.io/docs/job-specification/constraint\n    #\n    constraint {\n      attribute         = \"${attr.cpu.arch}\"\n      operator          = \"!=\"\n      value             = \"arm64\"\n    }\n\n    constraint {\n      attribute      = \"${node.class}\"\n      value          = \"builder\"\n    }\n\n    # The \"task\" stanza creates an individual unit of work, such as a Docker\n    # container, web application, or batch processing.\n    #\n    # For more information and examples on the \"task\" stanza, please see\n    # the online documentation at:\n    #\n    #     https://www.nomadproject.io/docs/job-specification/task\n    #\n    task \"prod-task1-prometheus\" {\n      # The \"driver\" parameter specifies the task driver that should be used to\n      # run the task.\n      driver            = \"exec\"\n\n      \n      volume_mount {\n        volume          = \"prod-volume1-prometheus\"\n        destination     = \"/data/\"\n        read_only       = false\n      }\n      \n\n      \n\n      # The \"config\" stanza specifies the driver configuration, which is passed\n      # directly to the driver to start the task. The details of configurations\n      # are specific to each driver, so please see specific driver\n      # documentation for more information.\n      config {\n        command         = \"local/prometheus-2.28.1.linux-amd64/prometheus\"\n        args            = [\n          \"--config.file=secrets/prometheus.yml\",\n          \"--storage.tsdb.path=/data/prometheus/\",\n          \"--storage.tsdb.retention.time=7d\"\n        ]\n      }\n\n      # The artifact stanza instructs Nomad to fetch and unpack a remote resource,\n      # such as a file, tarball, or binary. Nomad downloads artifacts using the\n      # popular go-getter library, which permits downloading artifacts from a\n      # variety of locations using a URL as the input source.\n      #\n      # For more information and examples on the \"artifact\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/artifact\n      #\n      artifact {\n        source          = \"https://github.com/prometheus/prometheus/releases/download/v2.28.1/prometheus-2.28.1.linux-amd64.tar.gz\"\n      }\n\n      # The \"template\" stanza instructs Nomad to manage a template, such as\n      # a configuration file or script. This template can optionally pull data\n      # from Consul or Vault to populate runtime configuration data.\n      #\n      # For more information and examples on the \"template\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/template\n      #\n      template {\n        change_mode     = \"noop\"\n        change_signal   = \"SIGINT\"\n        destination     = \"secrets/alerts.yml\"\n        left_delimiter  = \"{{{\"\n        right_delimiter = \"}}}\"\n        data            = \u003c\u003cEOH\n---\ngroups:\n- name: \"Jenkins Job Health Exporter\"\n  rules:\n  - alert: JenkinsJobHealthExporterFailures\n    expr: jenkins_job_failure{id=~\".*\"} \u003e jenkins_job_success{id=~\".*\"}\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Jenkins Job Health detected high failure rate on jenkins jobs.\"\n      description: \"Job: {{ $labels.id }}\"\n  - alert: JenkinsJobHealthExporterUnstable\n    expr: jenkins_job_unstable{id=~\".*\"} \u003e jenkins_job_success{id=~\".*\"}\n    for: 0m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Jenkins Job Health detected high unstable rate on jenkins jobs.\"\n      description: \"Job: {{ $labels.id }}\"\n- name: \"Consul\"\n  rules:\n  - alert: ConsulServiceHealthcheckFailed\n    expr: consul_catalog_service_node_healthy == 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Consul service healthcheck failed (instance {{ $labels.instance }}).\"\n      description: \"Service: `{{ $labels.service_name }}` Healthcheck: `{{ $labels.service_id }}`.\"\n  - alert: ConsulMissingMasterNode\n    expr: consul_raft_peers \u003c 3\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Consul missing master node (instance {{ $labels.instance }}).\"\n      description: \"Numbers of consul raft peers should be 3, in order to preserve quorum.\"\n  - alert: ConsulAgentUnhealthy\n    expr: consul_health_node_status{status=\"critical\"} == 1\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Consul agent unhealthy (instance {{ $labels.instance }}).\"\n      description: \"A Consul agent is down.\"\n- name: \"Hosts\"\n  rules:\n  - alert: NodeDown\n    expr: up == 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Prometheus target missing (instance {{ $labels.instance }}).\"\n      description: \"A Prometheus target has disappeared. An exporter might be crashed.\"\n  - alert: HostOutOfMemory\n    expr: node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes * 100 \u003c 10\n    for: 2m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host out of memory (instance {{ $labels.instance }}).\"\n      description: \"Node memory is filling up (\u003c 10% left).\"\n  - alert: HostOomKillDetected\n    expr: increase(node_vmstat_oom_kill[1m]) \u003e 0\n    for: 0m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host OOM kill detected (instance {{ $labels.instance }}).\"\n      description: \"OOM kill detected.\"\n  - alert: HostMemoryUnderMemoryPressure\n    expr: rate(node_vmstat_pgmajfault[1m]) \u003e 1000\n    for: 2m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host memory under memory pressure (instance {{ $labels.instance }}).\"\n      description: \"The node is under heavy memory pressure. High rate of major page faults.\"\n  - alert: HostOutOfDiskSpace\n    expr: (node_filesystem_avail_bytes * 100) / node_filesystem_size_bytes \u003c 10 and ON (instance, device, mountpoint) node_filesystem_readonly == 0\n    for: 2m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host out of disk space (instance {{ $labels.instance }}).\"\n      description: \"Disk is almost full (\u003c 10% left).\"\n  - alert: HostRaidDiskFailure\n    expr: node_md_disks{state=\"failed\"} \u003e 0\n    for: 2m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host RAID disk failure (instance {{ $labels.instance }}).\"\n      description: \"At least one device in RAID array on {{ $labels.instance }} failed. Array {{ $labels.md_device }} needs attention and possibly a disk swap.\"\n  - alert: HostConntrackLimit\n    expr: node_nf_conntrack_entries / node_nf_conntrack_entries_limit \u003e 0.8\n    for: 5m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host conntrack limit (instance {{ $labels.instance }}).\"\n      description: \"The number of conntrack is approching limit.\"\n  - alert: HostNetworkInterfaceSaturated\n    expr: (rate(node_network_receive_bytes_total{device!~\"^tap.*\"}[1m]) + rate(node_network_transmit_bytes_total{device!~\"^tap.*\"}[1m])) / node_network_speed_bytes{device!~\"^tap.*\"} \u003e 0.8\n    for: 1m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host Network Interface Saturated (instance {{ $labels.instance }}).\"\n      description: \"The network interface {{ $labels.interface }} on {{ $labels.instance }} is getting overloaded.\"\n  - alert: HostSystemdServiceCrashed\n    expr: node_systemd_unit_state{state=\"failed\"} == 1\n    for: 0m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host SystemD service crashed (instance {{ $labels.instance }}).\"\n      description: \"SystemD service crashed.\"\n  - alert: HostEdacCorrectableErrorsDetected\n    expr: increase(node_edac_correctable_errors_total[1m]) \u003e 0\n    for: 0m\n    labels:\n      severity: info\n    annotations:\n      summary: \"Host EDAC Correctable Errors detected (instance {{ $labels.instance }}).\"\n      description: '{{ $labels.instance }} has had {{ printf \"%.0f\" $value }} correctable memory errors reported by EDAC in the last 5 minutes.'\n  - alert: HostEdacUncorrectableErrorsDetected\n    expr: node_edac_uncorrectable_errors_total \u003e 0\n    for: 0m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host EDAC Uncorrectable Errors detected (instance {{ $labels.instance }}).\"\n      description: '{{ $labels.instance }} has had {{ printf \"%.0f\" $value }} uncorrectable memory errors reported by EDAC in the last 5 minutes.'\n- name: \"Min.io\"\n  rules:\n  - alert: MinioDiskOffline\n    expr: minio_offline_disks \u003e 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Minio disk offline (instance {{ $labels.instance }})\"\n      description: \"Minio disk is offline.\"\n  - alert: MinioStorageSpaceExhausted\n    expr: minio_disk_storage_free_bytes / 1024 / 1024 / 1024 \u003c 10\n    for: 2m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Minio storage space exhausted (instance {{ $labels.instance }}).\"\n      description: \"Minio storage space is low (\u003c 10 GB).\"\n- name: \"Prometheus\"\n  rules:\n  - alert: PrometheusConfigurationReloadFailure\n    expr: prometheus_config_last_reload_successful != 1\n    for: 0m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Prometheus configuration reload failure (instance {{ $labels.instance }}).\"\n      description: \"Prometheus configuration reload error.\"\n  - alert: PrometheusTooManyRestarts\n    expr: changes(process_start_time_seconds{job=~\"prometheus|pushgateway|alertmanager\"}[15m]) \u003e 2\n    for: 0m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Prometheus too many restarts (instance {{ $labels.instance }}).\"\n      description: \"Prometheus has restarted more than twice in the last 15 minutes. It might be crashlooping.\"\n  - alert: PrometheusAlertmanagerConfigurationReloadFailure\n    expr: alertmanager_config_last_reload_successful != 1\n    for: 0m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Prometheus AlertManager configuration reload failure (instance {{ $labels.instance }}).\"\n      description: \"AlertManager configuration reload error.\"\n  - alert: PrometheusRuleEvaluationFailures\n    expr: increase(prometheus_rule_evaluation_failures_total[3m]) \u003e 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Prometheus rule evaluation failures (instance {{ $labels.instance }}).\"\n      description: \"Prometheus encountered {{ $value }} rule evaluation failures, leading to potentially ignored alerts.\"\n  - alert: PrometheusTargetScrapingSlow\n    expr: prometheus_target_interval_length_seconds{quantile=\"0.9\"} \u003e 60\n    for: 5m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Prometheus target scraping slow (instance {{ $labels.instance }}).\"\n      description: \"Prometheus is scraping exporters slowly.\"\n  - alert: PrometheusTsdbCompactionsFailed\n    expr: increase(prometheus_tsdb_compactions_failed_total[1m]) \u003e 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Prometheus TSDB compactions failed (instance {{ $labels.instance }}).\"\n      description: \"Prometheus encountered {{ $value }} TSDB compactions failures.\"\n  - alert: PrometheusTsdbHeadTruncationsFailed\n    expr: increase(prometheus_tsdb_head_truncations_failed_total[1m]) \u003e 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Prometheus TSDB head truncations failed (instance {{ $labels.instance }}).\"\n      description: \"Prometheus encountered {{ $value }} TSDB head truncation failures.\"\n  - alert: PrometheusTsdbWalCorruptions\n    expr: increase(prometheus_tsdb_wal_corruptions_total[1m]) \u003e 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Prometheus TSDB WAL corruptions (instance {{ $labels.instance }}).\"\n      description: \"Prometheus encountered {{ $value }} TSDB WAL corruptions.\"\n  - alert: PrometheusTsdbWalTruncationsFailed\n    expr: increase(prometheus_tsdb_wal_truncations_failed_total[1m]) \u003e 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Prometheus TSDB WAL truncations failed (instance {{ $labels.instance }}).\"\n      description: \"Prometheus encountered {{ $value }} TSDB WAL truncation failures.\"\nEOH\n      }\n\n      template {\n        change_mode     = \"noop\"\n        change_signal   = \"SIGINT\"\n        destination     = \"secrets/prometheus.yml\"\n        data            = \u003c\u003cEOH\n---\nglobal:\n  scrape_interval:     5s\n  scrape_timeout:      5s\n  evaluation_interval: 5s\n\nalerting:\n  alertmanagers:\n  - consul_sd_configs:\n    - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n      services: [ 'alertmanager' ]\n\nrule_files:\n  - 'alerts.yml'\n\nscrape_configs:\n\n  - job_name: 'Nomad Cluster'\n    consul_sd_configs:\n    - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n      services: [ 'nomad-client', 'nomad' ]\n    relabel_configs:\n    - source_labels: [__meta_consul_tags]\n      regex: '(.*)http(.*)'\n      action: keep\n    metrics_path: /v1/metrics\n    params:\n      format: [ 'prometheus' ]\n\n  - job_name: 'Consul Cluster'\n    static_configs:\n      - targets: [ '10.30.51.22:8500' ]\n      - targets: [ '10.30.51.24:8500' ]\n      - targets: [ '10.30.51.25:8500' ]\n      - targets: [ '10.30.51.26:8500' ]\n      - targets: [ '10.30.51.28:8500' ]\n      - targets: [ '10.30.51.29:8500' ]\n      - targets: [ '10.30.51.30:8500' ]\n      - targets: [ '10.30.51.39:8500' ]\n      - targets: [ '10.30.51.40:8500' ]\n      - targets: [ '10.30.51.50:8500' ]\n      - targets: [ '10.30.51.51:8500' ]\n      - targets: [ '10.30.51.65:8500' ]\n      - targets: [ '10.30.51.66:8500' ]\n      - targets: [ '10.30.51.67:8500' ]\n      - targets: [ '10.30.51.68:8500' ]\n      - targets: [ '10.30.51.70:8500' ]\n      - targets: [ '10.30.51.71:8500' ]\n      - targets: [ '10.32.8.14:8500' ]\n      - targets: [ '10.32.8.15:8500' ]\n      - targets: [ '10.32.8.16:8500' ]\n      - targets: [ '10.32.8.17:8500' ]\n    metrics_path: /v1/agent/metrics\n    params:\n      format: [ 'prometheus' ]\n\n  - job_name: 'Blackbox Exporter (icmp)'\n    static_configs:\n      - targets: [ 'gerrit.fd.io' ]\n      - targets: [ 'jenkins.fd.io' ]\n      - targets: [ '10.32.8.17' ]\n    params:\n      module: [ 'icmp_v4' ]\n    relabel_configs:\n      - source_labels: [__address__]\n        target_label: __param_target\n      - source_labels: [__param_target]\n        target_label: instance\n      - target_label: __address__\n        replacement: localhost:9115\n    metrics_path: /probe\n\n  - job_name: 'Blackbox Exporter (http)'\n    static_configs:\n      - targets: [ 'gerrit.fd.io' ]\n      - targets: [ 'jenkins.fd.io' ]\n    params:\n      module: [ 'http_2xx' ]\n    relabel_configs:\n      - source_labels: [__address__]\n        target_label: __param_target\n      - source_labels: [__param_target]\n        target_label: instance\n      - target_label: __address__\n        replacement: localhost:9115\n    metrics_path: /probe\n\n  - job_name: 'Jenkins Job Health Exporter'\n    static_configs:\n      - targets: [ '10.30.51.22:9186' ]\n    metric_relabel_configs:\n      - source_labels: [ __name__ ]\n        regex: '^(vpp.*|csit.*)_(success|failure|total|unstable|reqtime_ms)$'\n        action: replace\n        replacement: '$1'\n        target_label: id\n      - source_labels: [ __name__ ]\n        regex: '^(vpp.*|csit.*)_(success|failure|total|unstable|reqtime_ms)$'\n        replacement: 'jenkins_job_$2'\n        target_label: __name__\n\n  - job_name: 'Node Exporter'\n    static_configs:\n      - targets: [ '10.30.51.22:9100' ]\n      - targets: [ '10.30.51.24:9100' ]\n      - targets: [ '10.30.51.25:9100' ]\n      - targets: [ '10.30.51.26:9100' ]\n      - targets: [ '10.30.51.28:9100' ]\n      - targets: [ '10.30.51.29:9100' ]\n      - targets: [ '10.30.51.30:9100' ]\n      - targets: [ '10.30.51.39:9100' ]\n      - targets: [ '10.30.51.40:9100' ]\n      - targets: [ '10.30.51.50:9100' ]\n      - targets: [ '10.30.51.51:9100' ]\n      - targets: [ '10.30.51.65:9100' ]\n      - targets: [ '10.30.51.66:9100' ]\n      - targets: [ '10.30.51.67:9100' ]\n      - targets: [ '10.30.51.68:9100' ]\n      - targets: [ '10.30.51.70:9100' ]\n      - targets: [ '10.30.51.71:9100' ]\n      - targets: [ '10.32.8.14:9100' ]\n      - targets: [ '10.32.8.15:9100' ]\n      - targets: [ '10.32.8.16:9100' ]\n      - targets: [ '10.32.8.17:9100' ]\n\n  - job_name: 'Alertmanager'\n    consul_sd_configs:\n    - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n      services: [ 'alertmanager' ]\n\n  - job_name: 'Grafana'\n    consul_sd_configs:\n    - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n      services: [ 'grafana' ]\n\n  - job_name: 'Prometheus'\n    consul_sd_configs:\n    - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n      services: [ 'prometheus' ]\n\n  - job_name: 'Minio'\n    bearer_token: eyJhbGciOiJIUzUxMiIsInR5cCI6IkpXVCJ9.eyJleHAiOjQ3NjQ1ODEzMzcsImlzcyI6InByb21ldGhldXMiLCJzdWIiOiJtaW5pbyJ9.oeTw3EIaiFmlDikrHXWiWXMH2vxLfDLkfjEC7G2N3M_keH_xyA_l2ofLLNYtopa_3GCEZnxLQdPuFZrmgpkDWg\n    consul_sd_configs:\n    - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n      services: [ 'storage' ]\n    metrics_path: /minio/prometheus/metrics\nEOH\n      }\n\n      # The service stanza instructs Nomad to register a service with Consul.\n      #\n      # For more information and examples on the \"task\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/service\n      #\n      service {\n        name            = \"prometheus\"\n        port            = \"prometheus\"\n        tags            = [ \"prometheus${NOMAD_ALLOC_INDEX}\" ]\n        check {\n          name          = \"Prometheus Check Live\"\n          type          = \"http\"\n          path          = \"/-/healthy\"\n          interval      = \"10s\"\n          timeout       = \"2s\"\n        }\n      }\n\n      # The \"resources\" stanza describes the requirements a task needs to\n      # execute. Resource requirements include memory, network, cpu, and more.\n      # This ensures the task will execute on a machine that contains enough\n      # resource capacity.\n      #\n      # For more information and examples on the \"resources\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/resources\n      #\n      resources {\n        cpu             = 2000\n        memory          = 8192\n        # The network stanza specifies the networking requirements for the task\n        # group, including the network mode and port allocations. When scheduling\n        # jobs in Nomad they are provisioned across your fleet of machines along\n        # with other jobs and services. Because you don't know in advance what host\n        # your job will be provisioned on, Nomad will provide your tasks with\n        # network configuration when they start up.\n        #\n        # For more information and examples on the \"template\" stanza, please see\n        # the online documentation at:\n        #\n        #     https://www.nomadproject.io/docs/job-specification/network\n        #\n        network {\n          port \"prometheus\" {\n            static      = 9090\n          }\n        }\n      }\n    }\n  }\n}",
             "json": null,
-            "modify_index": "8995654",
+            "modify_index": "9138750",
             "name": "prod-prometheus",
             "namespace": "default",
             "policy_override": null,
@@ -568,12 +569,7 @@
         {
           "schema_version": 0,
           "attributes": {
-            "allocation_ids": [
-              "0c5c6e61-f8e5-bc82-0de9-5ac202d3600c",
-              "f9058e31-91d4-4cde-cef8-25ce59f2f4b6",
-              "d89ab9c0-4c2c-8430-f7ea-b609fc8285ac",
-              "055428eb-e662-5e07-14f1-afc32a2a491f"
-            ],
+            "allocation_ids": [],
             "datacenters": [
               "yul1"
             ],
diff --git a/fdio.infra.terraform/1n_nmd/terraform.tfstate.backup b/fdio.infra.terraform/1n_nmd/terraform.tfstate.backup
index 5c3f0aeb41..5397697870 100644
--- a/fdio.infra.terraform/1n_nmd/terraform.tfstate.backup
+++ b/fdio.infra.terraform/1n_nmd/terraform.tfstate.backup
@@ -1,7 +1,7 @@
 {
   "version": 4,
-  "terraform_version": "1.0.2",
-  "serial": 1184,
+  "terraform_version": "1.0.4",
+  "serial": 1187,
   "lineage": "e4e7f30a-652d-7a31-e31c-5e3a3388c9b9",
   "outputs": {},
   "resources": [
@@ -430,9 +430,9 @@
           "schema_version": 0,
           "attributes": {
             "filename": null,
-            "id": "ead2225fbdf17b54946cfd825a5b21205f7d98c776601d1a822a025b0cee042a",
-            "rendered": "job \"prod-prometheus\" {\n  # The \"region\" parameter specifies the region in which to execute the job.\n  # If omitted, this inherits the default region name of \"global\".\n  # region = \"global\"\n  #\n  # The \"datacenters\" parameter specifies the list of datacenters which should\n  # be considered when placing this task. This must be provided.\n  datacenters         = \"yul1\"\n\n  # The \"type\" parameter controls the type of job, which impacts the scheduler's\n  # decision on placement. This configuration is optional and defaults to\n  # \"service\". For a full list of job types and their differences, please see\n  # the online documentation.\n  #\n  # For more information, please see the online documentation at:\n  #\n  #     https://www.nomadproject.io/docs/jobspec/schedulers\n  #\n  type                = \"service\"\n\n  update {\n    # The \"max_parallel\" parameter specifies the maximum number of updates to\n    # perform in parallel. In this case, this specifies to update a single task\n    # at a time.\n    max_parallel      = 1\n\n    health_check      = \"checks\"\n\n    # The \"min_healthy_time\" parameter specifies the minimum time the allocation\n    # must be in the healthy state before it is marked as healthy and unblocks\n    # further allocations from being updated.\n    min_healthy_time  = \"10s\"\n\n    # The \"healthy_deadline\" parameter specifies the deadline in which the\n    # allocation must be marked as healthy after which the allocation is\n    # automatically transitioned to unhealthy. Transitioning to unhealthy will\n    # fail the deployment and potentially roll back the job if \"auto_revert\" is\n    # set to true.\n    healthy_deadline  = \"3m\"\n\n    # The \"progress_deadline\" parameter specifies the deadline in which an\n    # allocation must be marked as healthy. The deadline begins when the first\n    # allocation for the deployment is created and is reset whenever an allocation\n    # as part of the deployment transitions to a healthy state. If no allocation\n    # transitions to the healthy state before the progress deadline, the\n    # deployment is marked as failed.\n    progress_deadline = \"10m\"\n\n\n    # The \"canary\" parameter specifies that changes to the job that would result\n    # in destructive updates should create the specified number of canaries\n    # without stopping any previous allocations. Once the operator determines the\n    # canaries are healthy, they can be promoted which unblocks a rolling update\n    # of the remaining allocations at a rate of \"max_parallel\".\n    #\n    # Further, setting \"canary\" equal to the count of the task group allows\n    # blue/green deployments. When the job is updated, a full set of the new\n    # version is deployed and upon promotion the old version is stopped.\n    canary            = 1\n\n    # Specifies if the job should auto-promote to the canary version when all\n    # canaries become healthy during a deployment. Defaults to false which means\n    # canaries must be manually updated with the nomad deployment promote\n    # command.\n    auto_promote      = true\n\n    # The \"auto_revert\" parameter specifies if the job should auto-revert to the\n    # last stable job on deployment failure. A job is marked as stable if all the\n    # allocations as part of its deployment were marked healthy.\n    auto_revert       = true\n\n  }\n\n  # The reschedule stanza specifies the group's rescheduling strategy. If\n  # specified at the job level, the configuration will apply to all groups\n  # within the job. If the reschedule stanza is present on both the job and the\n  # group, they are merged with the group stanza taking the highest precedence\n  # and then the job.\n  reschedule {\n    delay             = \"30s\"\n    delay_function    = \"constant\"\n    unlimited         = true\n  }\n\n  # The \"group\" stanza defines a series of tasks that should be co-located on\n  # the same Nomad client. Any task within a group will be placed on the same\n  # client.\n  #\n  # For more information and examples on the \"group\" stanza, please see\n  # the online documentation at:\n  #\n  #     https://www.nomadproject.io/docs/job-specification/group\n  #\n  group \"prod-group1-prometheus\" {\n    # The \"count\" parameter specifies the number of the task groups that should\n    # be running under this group. This value must be non-negative and defaults\n    # to 1.\n    count               = 4\n\n    # The restart stanza configures a tasks's behavior on task failure. Restarts\n    # happen on the client that is running the task.\n    #\n    # https://www.nomadproject.io/docs/job-specification/restart\n    #\n    restart {\n      interval  = \"30m\"\n      attempts  = 40\n      delay     = \"15s\"\n      mode      = \"delay\"\n    }\n\n    # The volume stanza allows the group to specify that it requires a given\n    # volume from the cluster.\n    #\n    # For more information and examples on the \"volume\" stanza, please see\n    # the online documentation at:\n    #\n    #     https://www.nomadproject.io/docs/job-specification/volume\n    #\n    \n    volume \"prod-volume1-prometheus\" {\n      type              = \"host\"\n      read_only         = false\n      source            = \"prod-volume-data1-1\"\n    }\n    \n\n    # The constraint allows restricting the set of eligible nodes. Constraints\n    # may filter on attributes or client metadata.\n    #\n    # For more information and examples on the \"volume\" stanza, please see\n    # the online documentation at:\n    #\n    #     https://www.nomadproject.io/docs/job-specification/constraint\n    #\n    constraint {\n      attribute         = \"${attr.cpu.arch}\"\n      operator          = \"!=\"\n      value             = \"arm64\"\n    }\n\n    # The \"task\" stanza creates an individual unit of work, such as a Docker\n    # container, web application, or batch processing.\n    #\n    # For more information and examples on the \"task\" stanza, please see\n    # the online documentation at:\n    #\n    #     https://www.nomadproject.io/docs/job-specification/task\n    #\n    task \"prod-task1-prometheus\" {\n      # The \"driver\" parameter specifies the task driver that should be used to\n      # run the task.\n      driver            = \"exec\"\n\n      \n      volume_mount {\n        volume          = \"prod-volume1-prometheus\"\n        destination     = \"/data/\"\n        read_only       = false\n      }\n      \n\n      \n\n      # The \"config\" stanza specifies the driver configuration, which is passed\n      # directly to the driver to start the task. The details of configurations\n      # are specific to each driver, so please see specific driver\n      # documentation for more information.\n      config {\n        command         = \"local/prometheus-2.28.1.linux-amd64/prometheus\"\n        args            = [\n          \"--config.file=secrets/prometheus.yml\",\n          \"--storage.tsdb.path=/data/prometheus/\",\n          \"--storage.tsdb.retention.time=7d\"\n        ]\n      }\n\n      # The artifact stanza instructs Nomad to fetch and unpack a remote resource,\n      # such as a file, tarball, or binary. Nomad downloads artifacts using the\n      # popular go-getter library, which permits downloading artifacts from a\n      # variety of locations using a URL as the input source.\n      #\n      # For more information and examples on the \"artifact\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/artifact\n      #\n      artifact {\n        source          = \"https://github.com/prometheus/prometheus/releases/download/v2.28.1/prometheus-2.28.1.linux-amd64.tar.gz\"\n      }\n\n      # The \"template\" stanza instructs Nomad to manage a template, such as\n      # a configuration file or script. This template can optionally pull data\n      # from Consul or Vault to populate runtime configuration data.\n      #\n      # For more information and examples on the \"template\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/template\n      #\n      template {\n        change_mode     = \"noop\"\n        change_signal   = \"SIGINT\"\n        destination     = \"secrets/alerts.yml\"\n        left_delimiter  = \"{{{\"\n        right_delimiter = \"}}}\"\n        data            = \u003c\u003cEOH\n---\ngroups:\n- name: \"Jenkins Job Health Exporter\"\n  rules:\n  - alert: JenkinsJobHealthExporterFailures\n    expr: jenkins_job_failure{id=~\".*\"} \u003e jenkins_job_success{id=~\".*\"}\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Jenkins Job Health detected high failure rate on jenkins jobs.\"\n      description: \"Job: {{ $labels.id }}\"\n  - alert: JenkinsJobHealthExporterUnstable\n    expr: jenkins_job_unstable{id=~\".*\"} \u003e jenkins_job_success{id=~\".*\"}\n    for: 0m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Jenkins Job Health detected high unstable rate on jenkins jobs.\"\n      description: \"Job: {{ $labels.id }}\"\n- name: \"Consul\"\n  rules:\n  - alert: ConsulServiceHealthcheckFailed\n    expr: consul_catalog_service_node_healthy == 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Consul service healthcheck failed (instance {{ $labels.instance }}).\"\n      description: \"Service: `{{ $labels.service_name }}` Healthcheck: `{{ $labels.service_id }}`.\"\n  - alert: ConsulMissingMasterNode\n    expr: consul_raft_peers \u003c 3\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Consul missing master node (instance {{ $labels.instance }}).\"\n      description: \"Numbers of consul raft peers should be 3, in order to preserve quorum.\"\n  - alert: ConsulAgentUnhealthy\n    expr: consul_health_node_status{status=\"critical\"} == 1\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Consul agent unhealthy (instance {{ $labels.instance }}).\"\n      description: \"A Consul agent is down.\"\n- name: \"Hosts\"\n  rules:\n  - alert: NodeDown\n    expr: up == 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Prometheus target missing (instance {{ $labels.instance }}).\"\n      description: \"A Prometheus target has disappeared. An exporter might be crashed.\"\n  - alert: HostOutOfMemory\n    expr: node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes * 100 \u003c 10\n    for: 2m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host out of memory (instance {{ $labels.instance }}).\"\n      description: \"Node memory is filling up (\u003c 10% left).\"\n  - alert: HostOomKillDetected\n    expr: increase(node_vmstat_oom_kill[1m]) \u003e 0\n    for: 0m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host OOM kill detected (instance {{ $labels.instance }}).\"\n      description: \"OOM kill detected.\"\n  - alert: HostMemoryUnderMemoryPressure\n    expr: rate(node_vmstat_pgmajfault[1m]) \u003e 1000\n    for: 2m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host memory under memory pressure (instance {{ $labels.instance }}).\"\n      description: \"The node is under heavy memory pressure. High rate of major page faults.\"\n  - alert: HostOutOfDiskSpace\n    expr: (node_filesystem_avail_bytes * 100) / node_filesystem_size_bytes \u003c 10 and ON (instance, device, mountpoint) node_filesystem_readonly == 0\n    for: 2m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host out of disk space (instance {{ $labels.instance }}).\"\n      description: \"Disk is almost full (\u003c 10% left).\"\n  - alert: HostRaidDiskFailure\n    expr: node_md_disks{state=\"failed\"} \u003e 0\n    for: 2m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host RAID disk failure (instance {{ $labels.instance }}).\"\n      description: \"At least one device in RAID array on {{ $labels.instance }} failed. Array {{ $labels.md_device }} needs attention and possibly a disk swap.\"\n  - alert: HostConntrackLimit\n    expr: node_nf_conntrack_entries / node_nf_conntrack_entries_limit \u003e 0.8\n    for: 5m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host conntrack limit (instance {{ $labels.instance }}).\"\n      description: \"The number of conntrack is approching limit.\"\n  - alert: HostNetworkInterfaceSaturated\n    expr: (rate(node_network_receive_bytes_total{device!~\"^tap.*\"}[1m]) + rate(node_network_transmit_bytes_total{device!~\"^tap.*\"}[1m])) / node_network_speed_bytes{device!~\"^tap.*\"} \u003e 0.8\n    for: 1m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host Network Interface Saturated (instance {{ $labels.instance }}).\"\n      description: \"The network interface {{ $labels.interface }} on {{ $labels.instance }} is getting overloaded.\"\n  - alert: HostSystemdServiceCrashed\n    expr: node_systemd_unit_state{state=\"failed\"} == 1\n    for: 0m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host SystemD service crashed (instance {{ $labels.instance }}).\"\n      description: \"SystemD service crashed.\"\n  - alert: HostEdacCorrectableErrorsDetected\n    expr: increase(node_edac_correctable_errors_total[1m]) \u003e 0\n    for: 0m\n    labels:\n      severity: info\n    annotations:\n      summary: \"Host EDAC Correctable Errors detected (instance {{ $labels.instance }}).\"\n      description: '{{ $labels.instance }} has had {{ printf \"%.0f\" $value }} correctable memory errors reported by EDAC in the last 5 minutes.'\n  - alert: HostEdacUncorrectableErrorsDetected\n    expr: node_edac_uncorrectable_errors_total \u003e 0\n    for: 0m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host EDAC Uncorrectable Errors detected (instance {{ $labels.instance }}).\"\n      description: '{{ $labels.instance }} has had {{ printf \"%.0f\" $value }} uncorrectable memory errors reported by EDAC in the last 5 minutes.'\n- name: \"Min.io\"\n  rules:\n  - alert: MinioDiskOffline\n    expr: minio_offline_disks \u003e 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Minio disk offline (instance {{ $labels.instance }})\"\n      description: \"Minio disk is offline.\"\n  - alert: MinioStorageSpaceExhausted\n    expr: minio_disk_storage_free_bytes / 1024 / 1024 / 1024 \u003c 10\n    for: 2m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Minio storage space exhausted (instance {{ $labels.instance }}).\"\n      description: \"Minio storage space is low (\u003c 10 GB).\"\n- name: \"Prometheus\"\n  rules:\n  - alert: PrometheusConfigurationReloadFailure\n    expr: prometheus_config_last_reload_successful != 1\n    for: 0m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Prometheus configuration reload failure (instance {{ $labels.instance }}).\"\n      description: \"Prometheus configuration reload error.\"\n  - alert: PrometheusTooManyRestarts\n    expr: changes(process_start_time_seconds{job=~\"prometheus|pushgateway|alertmanager\"}[15m]) \u003e 2\n    for: 0m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Prometheus too many restarts (instance {{ $labels.instance }}).\"\n      description: \"Prometheus has restarted more than twice in the last 15 minutes. It might be crashlooping.\"\n  - alert: PrometheusAlertmanagerConfigurationReloadFailure\n    expr: alertmanager_config_last_reload_successful != 1\n    for: 0m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Prometheus AlertManager configuration reload failure (instance {{ $labels.instance }}).\"\n      description: \"AlertManager configuration reload error.\"\n  - alert: PrometheusRuleEvaluationFailures\n    expr: increase(prometheus_rule_evaluation_failures_total[3m]) \u003e 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Prometheus rule evaluation failures (instance {{ $labels.instance }}).\"\n      description: \"Prometheus encountered {{ $value }} rule evaluation failures, leading to potentially ignored alerts.\"\n  - alert: PrometheusTargetScrapingSlow\n    expr: prometheus_target_interval_length_seconds{quantile=\"0.9\"} \u003e 60\n    for: 5m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Prometheus target scraping slow (instance {{ $labels.instance }}).\"\n      description: \"Prometheus is scraping exporters slowly.\"\n  - alert: PrometheusTsdbCompactionsFailed\n    expr: increase(prometheus_tsdb_compactions_failed_total[1m]) \u003e 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Prometheus TSDB compactions failed (instance {{ $labels.instance }}).\"\n      description: \"Prometheus encountered {{ $value }} TSDB compactions failures.\"\n  - alert: PrometheusTsdbHeadTruncationsFailed\n    expr: increase(prometheus_tsdb_head_truncations_failed_total[1m]) \u003e 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Prometheus TSDB head truncations failed (instance {{ $labels.instance }}).\"\n      description: \"Prometheus encountered {{ $value }} TSDB head truncation failures.\"\n  - alert: PrometheusTsdbWalCorruptions\n    expr: increase(prometheus_tsdb_wal_corruptions_total[1m]) \u003e 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Prometheus TSDB WAL corruptions (instance {{ $labels.instance }}).\"\n      description: \"Prometheus encountered {{ $value }} TSDB WAL corruptions.\"\n  - alert: PrometheusTsdbWalTruncationsFailed\n    expr: increase(prometheus_tsdb_wal_truncations_failed_total[1m]) \u003e 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Prometheus TSDB WAL truncations failed (instance {{ $labels.instance }}).\"\n      description: \"Prometheus encountered {{ $value }} TSDB WAL truncation failures.\"\nEOH\n      }\n\n      template {\n        change_mode     = \"noop\"\n        change_signal   = \"SIGINT\"\n        destination     = \"secrets/prometheus.yml\"\n        data            = \u003c\u003cEOH\n---\nglobal:\n  scrape_interval:     5s\n  scrape_timeout:      5s\n  evaluation_interval: 5s\n\nalerting:\n  alertmanagers:\n  - consul_sd_configs:\n    - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n      services: [ 'alertmanager' ]\n\nrule_files:\n  - 'alerts.yml'\n\nscrape_configs:\n\n  - job_name: 'Nomad Cluster'\n    consul_sd_configs:\n    - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n      services: [ 'nomad-client', 'nomad' ]\n    relabel_configs:\n    - source_labels: [__meta_consul_tags]\n      regex: '(.*)http(.*)'\n      action: keep\n    metrics_path: /v1/metrics\n    params:\n      format: [ 'prometheus' ]\n\n  - job_name: 'Consul Cluster'\n    static_configs:\n      - targets: [ '10.30.51.22:8500' ]\n      - targets: [ '10.30.51.24:8500' ]\n      - targets: [ '10.30.51.25:8500' ]\n      - targets: [ '10.30.51.26:8500' ]\n      - targets: [ '10.30.51.28:8500' ]\n      - targets: [ '10.30.51.29:8500' ]\n      - targets: [ '10.30.51.30:8500' ]\n      - targets: [ '10.30.51.39:8500' ]\n      - targets: [ '10.30.51.40:8500' ]\n      - targets: [ '10.30.51.50:8500' ]\n      - targets: [ '10.30.51.51:8500' ]\n      - targets: [ '10.30.51.65:8500' ]\n      - targets: [ '10.30.51.66:8500' ]\n      - targets: [ '10.30.51.67:8500' ]\n      - targets: [ '10.30.51.68:8500' ]\n      - targets: [ '10.30.51.70:8500' ]\n      - targets: [ '10.30.51.71:8500' ]\n      - targets: [ '10.32.8.14:8500' ]\n      - targets: [ '10.32.8.15:8500' ]\n      - targets: [ '10.32.8.16:8500' ]\n      - targets: [ '10.32.8.17:8500' ]\n    metrics_path: /v1/agent/metrics\n    params:\n      format: [ 'prometheus' ]\n\n  - job_name: 'Blackbox Exporter (icmp)'\n    static_configs:\n      - targets: [ 'gerrit.fd.io' ]\n      - targets: [ 'jenkins.fd.io' ]\n      - targets: [ '10.32.8.17' ]\n    params:\n      module: [ 'icmp_v4' ]\n    relabel_configs:\n      - source_labels: [__address__]\n        target_label: __param_target\n      - source_labels: [__param_target]\n        target_label: instance\n      - target_label: __address__\n        replacement: localhost:9115\n    metrics_path: /probe\n\n  - job_name: 'Blackbox Exporter (http)'\n    static_configs:\n      - targets: [ 'gerrit.fd.io' ]\n      - targets: [ 'jenkins.fd.io' ]\n    params:\n      module: [ 'http_2xx' ]\n    relabel_configs:\n      - source_labels: [__address__]\n        target_label: __param_target\n      - source_labels: [__param_target]\n        target_label: instance\n      - target_label: __address__\n        replacement: localhost:9115\n    metrics_path: /probe\n\n  - job_name: 'Jenkins Job Health Exporter'\n    static_configs:\n      - targets: [ 10.30.51.22:9186' ]\n    metric_relabel_configs:\n      - source_labels: [ __name__ ]\n        regex: '^(vpp.*|csit.*)_(success|failure|total|unstable|reqtime_ms)$'\n        action: replace\n        replacement: '$1'\n        target_label: id\n      - source_labels: [ __name__ ]\n        regex: '^(vpp.*|csit.*)_(success|failure|total|unstable|reqtime_ms)$'\n        replacement: 'jenkins_job_$2'\n        target_label: __name__\n\n  - job_name: 'Node Exporter'\n    static_configs:\n      - targets: [ '10.30.51.22:9100' ]\n      - targets: [ '10.30.51.24:9100' ]\n      - targets: [ '10.30.51.25:9100' ]\n      - targets: [ '10.30.51.26:9100' ]\n      - targets: [ '10.30.51.28:9100' ]\n      - targets: [ '10.30.51.29:9100' ]\n      - targets: [ '10.30.51.30:9100' ]\n      - targets: [ '10.30.51.39:9100' ]\n      - targets: [ '10.30.51.40:9100' ]\n      - targets: [ '10.30.51.50:9100' ]\n      - targets: [ '10.30.51.51:9100' ]\n      - targets: [ '10.30.51.65:9100' ]\n      - targets: [ '10.30.51.66:9100' ]\n      - targets: [ '10.30.51.67:9100' ]\n      - targets: [ '10.30.51.68:9100' ]\n      - targets: [ '10.30.51.70:9100' ]\n      - targets: [ '10.30.51.71:9100' ]\n      - targets: [ '10.32.8.14:9100' ]\n      - targets: [ '10.32.8.15:9100' ]\n      - targets: [ '10.32.8.16:9100' ]\n      - targets: [ '10.32.8.17:9100' ]\n\n  - job_name: 'Alertmanager'\n    consul_sd_configs:\n    - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n      services: [ 'alertmanager' ]\n\n  - job_name: 'Grafana'\n    consul_sd_configs:\n    - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n      services: [ 'grafana' ]\n\n  - job_name: 'Prometheus'\n    consul_sd_configs:\n    - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n      services: [ 'prometheus' ]\n\n  - job_name: 'Minio'\n    bearer_token: eyJhbGciOiJIUzUxMiIsInR5cCI6IkpXVCJ9.eyJleHAiOjQ3NjQ1ODEzMzcsImlzcyI6InByb21ldGhldXMiLCJzdWIiOiJtaW5pbyJ9.oeTw3EIaiFmlDikrHXWiWXMH2vxLfDLkfjEC7G2N3M_keH_xyA_l2ofLLNYtopa_3GCEZnxLQdPuFZrmgpkDWg\n    consul_sd_configs:\n    - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n      services: [ 'storage' ]\n    metrics_path: /minio/prometheus/metrics\nEOH\n      }\n\n      # The service stanza instructs Nomad to register a service with Consul.\n      #\n      # For more information and examples on the \"task\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/service\n      #\n      service {\n        name            = \"prometheus\"\n        port            = \"prometheus\"\n        tags            = [ \"prometheus${NOMAD_ALLOC_INDEX}\" ]\n        check {\n          name          = \"Prometheus Check Live\"\n          type          = \"http\"\n          path          = \"/-/healthy\"\n          interval      = \"10s\"\n          timeout       = \"2s\"\n        }\n      }\n\n      # The \"resources\" stanza describes the requirements a task needs to\n      # execute. Resource requirements include memory, network, cpu, and more.\n      # This ensures the task will execute on a machine that contains enough\n      # resource capacity.\n      #\n      # For more information and examples on the \"resources\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/resources\n      #\n      resources {\n        cpu             = 2000\n        memory          = 8192\n        # The network stanza specifies the networking requirements for the task\n        # group, including the network mode and port allocations. When scheduling\n        # jobs in Nomad they are provisioned across your fleet of machines along\n        # with other jobs and services. Because you don't know in advance what host\n        # your job will be provisioned on, Nomad will provide your tasks with\n        # network configuration when they start up.\n        #\n        # For more information and examples on the \"template\" stanza, please see\n        # the online documentation at:\n        #\n        #     https://www.nomadproject.io/docs/job-specification/network\n        #\n        network {\n          port \"prometheus\" {\n            static      = 9090\n          }\n        }\n      }\n    }\n  }\n}",
-            "template": "job \"${job_name}\" {\n  # The \"region\" parameter specifies the region in which to execute the job.\n  # If omitted, this inherits the default region name of \"global\".\n  # region = \"global\"\n  #\n  # The \"datacenters\" parameter specifies the list of datacenters which should\n  # be considered when placing this task. This must be provided.\n  datacenters         = \"${datacenters}\"\n\n  # The \"type\" parameter controls the type of job, which impacts the scheduler's\n  # decision on placement. This configuration is optional and defaults to\n  # \"service\". For a full list of job types and their differences, please see\n  # the online documentation.\n  #\n  # For more information, please see the online documentation at:\n  #\n  #     https://www.nomadproject.io/docs/jobspec/schedulers\n  #\n  type                = \"service\"\n\n  update {\n    # The \"max_parallel\" parameter specifies the maximum number of updates to\n    # perform in parallel. In this case, this specifies to update a single task\n    # at a time.\n    max_parallel      = 1\n\n    health_check      = \"checks\"\n\n    # The \"min_healthy_time\" parameter specifies the minimum time the allocation\n    # must be in the healthy state before it is marked as healthy and unblocks\n    # further allocations from being updated.\n    min_healthy_time  = \"10s\"\n\n    # The \"healthy_deadline\" parameter specifies the deadline in which the\n    # allocation must be marked as healthy after which the allocation is\n    # automatically transitioned to unhealthy. Transitioning to unhealthy will\n    # fail the deployment and potentially roll back the job if \"auto_revert\" is\n    # set to true.\n    healthy_deadline  = \"3m\"\n\n    # The \"progress_deadline\" parameter specifies the deadline in which an\n    # allocation must be marked as healthy. The deadline begins when the first\n    # allocation for the deployment is created and is reset whenever an allocation\n    # as part of the deployment transitions to a healthy state. If no allocation\n    # transitions to the healthy state before the progress deadline, the\n    # deployment is marked as failed.\n    progress_deadline = \"10m\"\n\n%{ if use_canary }\n    # The \"canary\" parameter specifies that changes to the job that would result\n    # in destructive updates should create the specified number of canaries\n    # without stopping any previous allocations. Once the operator determines the\n    # canaries are healthy, they can be promoted which unblocks a rolling update\n    # of the remaining allocations at a rate of \"max_parallel\".\n    #\n    # Further, setting \"canary\" equal to the count of the task group allows\n    # blue/green deployments. When the job is updated, a full set of the new\n    # version is deployed and upon promotion the old version is stopped.\n    canary            = 1\n\n    # Specifies if the job should auto-promote to the canary version when all\n    # canaries become healthy during a deployment. Defaults to false which means\n    # canaries must be manually updated with the nomad deployment promote\n    # command.\n    auto_promote      = true\n\n    # The \"auto_revert\" parameter specifies if the job should auto-revert to the\n    # last stable job on deployment failure. A job is marked as stable if all the\n    # allocations as part of its deployment were marked healthy.\n    auto_revert       = true\n%{ endif }\n  }\n\n  # The reschedule stanza specifies the group's rescheduling strategy. If\n  # specified at the job level, the configuration will apply to all groups\n  # within the job. If the reschedule stanza is present on both the job and the\n  # group, they are merged with the group stanza taking the highest precedence\n  # and then the job.\n  reschedule {\n    delay             = \"30s\"\n    delay_function    = \"constant\"\n    unlimited         = true\n  }\n\n  # The \"group\" stanza defines a series of tasks that should be co-located on\n  # the same Nomad client. Any task within a group will be placed on the same\n  # client.\n  #\n  # For more information and examples on the \"group\" stanza, please see\n  # the online documentation at:\n  #\n  #     https://www.nomadproject.io/docs/job-specification/group\n  #\n  group \"prod-group1-${service_name}\" {\n    # The \"count\" parameter specifies the number of the task groups that should\n    # be running under this group. This value must be non-negative and defaults\n    # to 1.\n    count               = ${group_count}\n\n    # The restart stanza configures a tasks's behavior on task failure. Restarts\n    # happen on the client that is running the task.\n    #\n    # https://www.nomadproject.io/docs/job-specification/restart\n    #\n    restart {\n      interval  = \"30m\"\n      attempts  = 40\n      delay     = \"15s\"\n      mode      = \"delay\"\n    }\n\n    # The volume stanza allows the group to specify that it requires a given\n    # volume from the cluster.\n    #\n    # For more information and examples on the \"volume\" stanza, please see\n    # the online documentation at:\n    #\n    #     https://www.nomadproject.io/docs/job-specification/volume\n    #\n    %{ if use_host_volume }\n    volume \"prod-volume1-${service_name}\" {\n      type              = \"host\"\n      read_only         = false\n      source            = \"${host_volume}\"\n    }\n    %{ endif }\n\n    # The constraint allows restricting the set of eligible nodes. Constraints\n    # may filter on attributes or client metadata.\n    #\n    # For more information and examples on the \"volume\" stanza, please see\n    # the online documentation at:\n    #\n    #     https://www.nomadproject.io/docs/job-specification/constraint\n    #\n    constraint {\n      attribute         = \"$${attr.cpu.arch}\"\n      operator          = \"!=\"\n      value             = \"arm64\"\n    }\n\n    # The \"task\" stanza creates an individual unit of work, such as a Docker\n    # container, web application, or batch processing.\n    #\n    # For more information and examples on the \"task\" stanza, please see\n    # the online documentation at:\n    #\n    #     https://www.nomadproject.io/docs/job-specification/task\n    #\n    task \"prod-task1-${service_name}\" {\n      # The \"driver\" parameter specifies the task driver that should be used to\n      # run the task.\n      driver            = \"exec\"\n\n      %{ if use_host_volume }\n      volume_mount {\n        volume          = \"prod-volume1-${service_name}\"\n        destination     = \"${data_dir}\"\n        read_only       = false\n      }\n      %{ endif }\n\n      %{ if use_vault_provider }\n      vault {\n        policies        = \"${vault_kv_policy_name}\"\n      }\n      %{ endif }\n\n      # The \"config\" stanza specifies the driver configuration, which is passed\n      # directly to the driver to start the task. The details of configurations\n      # are specific to each driver, so please see specific driver\n      # documentation for more information.\n      config {\n        command         = \"local/prometheus-${version}.linux-amd64/prometheus\"\n        args            = [\n          \"--config.file=secrets/prometheus.yml\",\n          \"--storage.tsdb.path=${data_dir}prometheus/\",\n          \"--storage.tsdb.retention.time=7d\"\n        ]\n      }\n\n      # The artifact stanza instructs Nomad to fetch and unpack a remote resource,\n      # such as a file, tarball, or binary. Nomad downloads artifacts using the\n      # popular go-getter library, which permits downloading artifacts from a\n      # variety of locations using a URL as the input source.\n      #\n      # For more information and examples on the \"artifact\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/artifact\n      #\n      artifact {\n        source          = \"${url}\"\n      }\n\n      # The \"template\" stanza instructs Nomad to manage a template, such as\n      # a configuration file or script. This template can optionally pull data\n      # from Consul or Vault to populate runtime configuration data.\n      #\n      # For more information and examples on the \"template\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/template\n      #\n      template {\n        change_mode     = \"noop\"\n        change_signal   = \"SIGINT\"\n        destination     = \"secrets/alerts.yml\"\n        left_delimiter  = \"{{{\"\n        right_delimiter = \"}}}\"\n        data            = \u003c\u003cEOH\n---\ngroups:\n- name: \"Jenkins Job Health Exporter\"\n  rules:\n  - alert: JenkinsJobHealthExporterFailures\n    expr: jenkins_job_failure{id=~\".*\"} \u003e jenkins_job_success{id=~\".*\"}\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Jenkins Job Health detected high failure rate on jenkins jobs.\"\n      description: \"Job: {{ $labels.id }}\"\n  - alert: JenkinsJobHealthExporterUnstable\n    expr: jenkins_job_unstable{id=~\".*\"} \u003e jenkins_job_success{id=~\".*\"}\n    for: 0m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Jenkins Job Health detected high unstable rate on jenkins jobs.\"\n      description: \"Job: {{ $labels.id }}\"\n- name: \"Consul\"\n  rules:\n  - alert: ConsulServiceHealthcheckFailed\n    expr: consul_catalog_service_node_healthy == 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Consul service healthcheck failed (instance {{ $labels.instance }}).\"\n      description: \"Service: `{{ $labels.service_name }}` Healthcheck: `{{ $labels.service_id }}`.\"\n  - alert: ConsulMissingMasterNode\n    expr: consul_raft_peers \u003c 3\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Consul missing master node (instance {{ $labels.instance }}).\"\n      description: \"Numbers of consul raft peers should be 3, in order to preserve quorum.\"\n  - alert: ConsulAgentUnhealthy\n    expr: consul_health_node_status{status=\"critical\"} == 1\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Consul agent unhealthy (instance {{ $labels.instance }}).\"\n      description: \"A Consul agent is down.\"\n- name: \"Hosts\"\n  rules:\n  - alert: NodeDown\n    expr: up == 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Prometheus target missing (instance {{ $labels.instance }}).\"\n      description: \"A Prometheus target has disappeared. An exporter might be crashed.\"\n  - alert: HostOutOfMemory\n    expr: node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes * 100 \u003c 10\n    for: 2m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host out of memory (instance {{ $labels.instance }}).\"\n      description: \"Node memory is filling up (\u003c 10% left).\"\n  - alert: HostOomKillDetected\n    expr: increase(node_vmstat_oom_kill[1m]) \u003e 0\n    for: 0m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host OOM kill detected (instance {{ $labels.instance }}).\"\n      description: \"OOM kill detected.\"\n  - alert: HostMemoryUnderMemoryPressure\n    expr: rate(node_vmstat_pgmajfault[1m]) \u003e 1000\n    for: 2m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host memory under memory pressure (instance {{ $labels.instance }}).\"\n      description: \"The node is under heavy memory pressure. High rate of major page faults.\"\n  - alert: HostOutOfDiskSpace\n    expr: (node_filesystem_avail_bytes * 100) / node_filesystem_size_bytes \u003c 10 and ON (instance, device, mountpoint) node_filesystem_readonly == 0\n    for: 2m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host out of disk space (instance {{ $labels.instance }}).\"\n      description: \"Disk is almost full (\u003c 10% left).\"\n  - alert: HostRaidDiskFailure\n    expr: node_md_disks{state=\"failed\"} \u003e 0\n    for: 2m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host RAID disk failure (instance {{ $labels.instance }}).\"\n      description: \"At least one device in RAID array on {{ $labels.instance }} failed. Array {{ $labels.md_device }} needs attention and possibly a disk swap.\"\n  - alert: HostConntrackLimit\n    expr: node_nf_conntrack_entries / node_nf_conntrack_entries_limit \u003e 0.8\n    for: 5m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host conntrack limit (instance {{ $labels.instance }}).\"\n      description: \"The number of conntrack is approching limit.\"\n  - alert: HostNetworkInterfaceSaturated\n    expr: (rate(node_network_receive_bytes_total{device!~\"^tap.*\"}[1m]) + rate(node_network_transmit_bytes_total{device!~\"^tap.*\"}[1m])) / node_network_speed_bytes{device!~\"^tap.*\"} \u003e 0.8\n    for: 1m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host Network Interface Saturated (instance {{ $labels.instance }}).\"\n      description: \"The network interface {{ $labels.interface }} on {{ $labels.instance }} is getting overloaded.\"\n  - alert: HostSystemdServiceCrashed\n    expr: node_systemd_unit_state{state=\"failed\"} == 1\n    for: 0m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host SystemD service crashed (instance {{ $labels.instance }}).\"\n      description: \"SystemD service crashed.\"\n  - alert: HostEdacCorrectableErrorsDetected\n    expr: increase(node_edac_correctable_errors_total[1m]) \u003e 0\n    for: 0m\n    labels:\n      severity: info\n    annotations:\n      summary: \"Host EDAC Correctable Errors detected (instance {{ $labels.instance }}).\"\n      description: '{{ $labels.instance }} has had {{ printf \"%.0f\" $value }} correctable memory errors reported by EDAC in the last 5 minutes.'\n  - alert: HostEdacUncorrectableErrorsDetected\n    expr: node_edac_uncorrectable_errors_total \u003e 0\n    for: 0m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host EDAC Uncorrectable Errors detected (instance {{ $labels.instance }}).\"\n      description: '{{ $labels.instance }} has had {{ printf \"%.0f\" $value }} uncorrectable memory errors reported by EDAC in the last 5 minutes.'\n- name: \"Min.io\"\n  rules:\n  - alert: MinioDiskOffline\n    expr: minio_offline_disks \u003e 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Minio disk offline (instance {{ $labels.instance }})\"\n      description: \"Minio disk is offline.\"\n  - alert: MinioStorageSpaceExhausted\n    expr: minio_disk_storage_free_bytes / 1024 / 1024 / 1024 \u003c 10\n    for: 2m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Minio storage space exhausted (instance {{ $labels.instance }}).\"\n      description: \"Minio storage space is low (\u003c 10 GB).\"\n- name: \"Prometheus\"\n  rules:\n  - alert: PrometheusConfigurationReloadFailure\n    expr: prometheus_config_last_reload_successful != 1\n    for: 0m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Prometheus configuration reload failure (instance {{ $labels.instance }}).\"\n      description: \"Prometheus configuration reload error.\"\n  - alert: PrometheusTooManyRestarts\n    expr: changes(process_start_time_seconds{job=~\"prometheus|pushgateway|alertmanager\"}[15m]) \u003e 2\n    for: 0m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Prometheus too many restarts (instance {{ $labels.instance }}).\"\n      description: \"Prometheus has restarted more than twice in the last 15 minutes. It might be crashlooping.\"\n  - alert: PrometheusAlertmanagerConfigurationReloadFailure\n    expr: alertmanager_config_last_reload_successful != 1\n    for: 0m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Prometheus AlertManager configuration reload failure (instance {{ $labels.instance }}).\"\n      description: \"AlertManager configuration reload error.\"\n  - alert: PrometheusRuleEvaluationFailures\n    expr: increase(prometheus_rule_evaluation_failures_total[3m]) \u003e 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Prometheus rule evaluation failures (instance {{ $labels.instance }}).\"\n      description: \"Prometheus encountered {{ $value }} rule evaluation failures, leading to potentially ignored alerts.\"\n  - alert: PrometheusTargetScrapingSlow\n    expr: prometheus_target_interval_length_seconds{quantile=\"0.9\"} \u003e 60\n    for: 5m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Prometheus target scraping slow (instance {{ $labels.instance }}).\"\n      description: \"Prometheus is scraping exporters slowly.\"\n  - alert: PrometheusTsdbCompactionsFailed\n    expr: increase(prometheus_tsdb_compactions_failed_total[1m]) \u003e 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Prometheus TSDB compactions failed (instance {{ $labels.instance }}).\"\n      description: \"Prometheus encountered {{ $value }} TSDB compactions failures.\"\n  - alert: PrometheusTsdbHeadTruncationsFailed\n    expr: increase(prometheus_tsdb_head_truncations_failed_total[1m]) \u003e 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Prometheus TSDB head truncations failed (instance {{ $labels.instance }}).\"\n      description: \"Prometheus encountered {{ $value }} TSDB head truncation failures.\"\n  - alert: PrometheusTsdbWalCorruptions\n    expr: increase(prometheus_tsdb_wal_corruptions_total[1m]) \u003e 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Prometheus TSDB WAL corruptions (instance {{ $labels.instance }}).\"\n      description: \"Prometheus encountered {{ $value }} TSDB WAL corruptions.\"\n  - alert: PrometheusTsdbWalTruncationsFailed\n    expr: increase(prometheus_tsdb_wal_truncations_failed_total[1m]) \u003e 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Prometheus TSDB WAL truncations failed (instance {{ $labels.instance }}).\"\n      description: \"Prometheus encountered {{ $value }} TSDB WAL truncation failures.\"\nEOH\n      }\n\n      template {\n        change_mode     = \"noop\"\n        change_signal   = \"SIGINT\"\n        destination     = \"secrets/prometheus.yml\"\n        data            = \u003c\u003cEOH\n---\nglobal:\n  scrape_interval:     5s\n  scrape_timeout:      5s\n  evaluation_interval: 5s\n\nalerting:\n  alertmanagers:\n  - consul_sd_configs:\n    - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n      services: [ 'alertmanager' ]\n\nrule_files:\n  - 'alerts.yml'\n\nscrape_configs:\n\n  - job_name: 'Nomad Cluster'\n    consul_sd_configs:\n    - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n      services: [ 'nomad-client', 'nomad' ]\n    relabel_configs:\n    - source_labels: [__meta_consul_tags]\n      regex: '(.*)http(.*)'\n      action: keep\n    metrics_path: /v1/metrics\n    params:\n      format: [ 'prometheus' ]\n\n  - job_name: 'Consul Cluster'\n    static_configs:\n      - targets: [ '10.30.51.22:8500' ]\n      - targets: [ '10.30.51.24:8500' ]\n      - targets: [ '10.30.51.25:8500' ]\n      - targets: [ '10.30.51.26:8500' ]\n      - targets: [ '10.30.51.28:8500' ]\n      - targets: [ '10.30.51.29:8500' ]\n      - targets: [ '10.30.51.30:8500' ]\n      - targets: [ '10.30.51.39:8500' ]\n      - targets: [ '10.30.51.40:8500' ]\n      - targets: [ '10.30.51.50:8500' ]\n      - targets: [ '10.30.51.51:8500' ]\n      - targets: [ '10.30.51.65:8500' ]\n      - targets: [ '10.30.51.66:8500' ]\n      - targets: [ '10.30.51.67:8500' ]\n      - targets: [ '10.30.51.68:8500' ]\n      - targets: [ '10.30.51.70:8500' ]\n      - targets: [ '10.30.51.71:8500' ]\n      - targets: [ '10.32.8.14:8500' ]\n      - targets: [ '10.32.8.15:8500' ]\n      - targets: [ '10.32.8.16:8500' ]\n      - targets: [ '10.32.8.17:8500' ]\n    metrics_path: /v1/agent/metrics\n    params:\n      format: [ 'prometheus' ]\n\n  - job_name: 'Blackbox Exporter (icmp)'\n    static_configs:\n      - targets: [ 'gerrit.fd.io' ]\n      - targets: [ 'jenkins.fd.io' ]\n      - targets: [ '10.32.8.17' ]\n    params:\n      module: [ 'icmp_v4' ]\n    relabel_configs:\n      - source_labels: [__address__]\n        target_label: __param_target\n      - source_labels: [__param_target]\n        target_label: instance\n      - target_label: __address__\n        replacement: localhost:9115\n    metrics_path: /probe\n\n  - job_name: 'Blackbox Exporter (http)'\n    static_configs:\n      - targets: [ 'gerrit.fd.io' ]\n      - targets: [ 'jenkins.fd.io' ]\n    params:\n      module: [ 'http_2xx' ]\n    relabel_configs:\n      - source_labels: [__address__]\n        target_label: __param_target\n      - source_labels: [__param_target]\n        target_label: instance\n      - target_label: __address__\n        replacement: localhost:9115\n    metrics_path: /probe\n\n  - job_name: 'Jenkins Job Health Exporter'\n    static_configs:\n      - targets: [ 10.30.51.22:9186' ]\n    metric_relabel_configs:\n      - source_labels: [ __name__ ]\n        regex: '^(vpp.*|csit.*)_(success|failure|total|unstable|reqtime_ms)$'\n        action: replace\n        replacement: '$1'\n        target_label: id\n      - source_labels: [ __name__ ]\n        regex: '^(vpp.*|csit.*)_(success|failure|total|unstable|reqtime_ms)$'\n        replacement: 'jenkins_job_$2'\n        target_label: __name__\n\n  - job_name: 'Node Exporter'\n    static_configs:\n      - targets: [ '10.30.51.22:9100' ]\n      - targets: [ '10.30.51.24:9100' ]\n      - targets: [ '10.30.51.25:9100' ]\n      - targets: [ '10.30.51.26:9100' ]\n      - targets: [ '10.30.51.28:9100' ]\n      - targets: [ '10.30.51.29:9100' ]\n      - targets: [ '10.30.51.30:9100' ]\n      - targets: [ '10.30.51.39:9100' ]\n      - targets: [ '10.30.51.40:9100' ]\n      - targets: [ '10.30.51.50:9100' ]\n      - targets: [ '10.30.51.51:9100' ]\n      - targets: [ '10.30.51.65:9100' ]\n      - targets: [ '10.30.51.66:9100' ]\n      - targets: [ '10.30.51.67:9100' ]\n      - targets: [ '10.30.51.68:9100' ]\n      - targets: [ '10.30.51.70:9100' ]\n      - targets: [ '10.30.51.71:9100' ]\n      - targets: [ '10.32.8.14:9100' ]\n      - targets: [ '10.32.8.15:9100' ]\n      - targets: [ '10.32.8.16:9100' ]\n      - targets: [ '10.32.8.17:9100' ]\n\n  - job_name: 'Alertmanager'\n    consul_sd_configs:\n    - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n      services: [ 'alertmanager' ]\n\n  - job_name: 'Grafana'\n    consul_sd_configs:\n    - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n      services: [ 'grafana' ]\n\n  - job_name: 'Prometheus'\n    consul_sd_configs:\n    - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n      services: [ 'prometheus' ]\n\n  - job_name: 'Minio'\n    bearer_token: eyJhbGciOiJIUzUxMiIsInR5cCI6IkpXVCJ9.eyJleHAiOjQ3NjQ1ODEzMzcsImlzcyI6InByb21ldGhldXMiLCJzdWIiOiJtaW5pbyJ9.oeTw3EIaiFmlDikrHXWiWXMH2vxLfDLkfjEC7G2N3M_keH_xyA_l2ofLLNYtopa_3GCEZnxLQdPuFZrmgpkDWg\n    consul_sd_configs:\n    - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n      services: [ 'storage' ]\n    metrics_path: /minio/prometheus/metrics\nEOH\n      }\n\n      # The service stanza instructs Nomad to register a service with Consul.\n      #\n      # For more information and examples on the \"task\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/service\n      #\n      service {\n        name            = \"${service_name}\"\n        port            = \"${service_name}\"\n        tags            = [ \"${service_name}$${NOMAD_ALLOC_INDEX}\" ]\n        check {\n          name          = \"Prometheus Check Live\"\n          type          = \"http\"\n          path          = \"/-/healthy\"\n          interval      = \"10s\"\n          timeout       = \"2s\"\n        }\n      }\n\n      # The \"resources\" stanza describes the requirements a task needs to\n      # execute. Resource requirements include memory, network, cpu, and more.\n      # This ensures the task will execute on a machine that contains enough\n      # resource capacity.\n      #\n      # For more information and examples on the \"resources\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/resources\n      #\n      resources {\n        cpu             = ${cpu}\n        memory          = ${mem}\n        # The network stanza specifies the networking requirements for the task\n        # group, including the network mode and port allocations. When scheduling\n        # jobs in Nomad they are provisioned across your fleet of machines along\n        # with other jobs and services. Because you don't know in advance what host\n        # your job will be provisioned on, Nomad will provide your tasks with\n        # network configuration when they start up.\n        #\n        # For more information and examples on the \"template\" stanza, please see\n        # the online documentation at:\n        #\n        #     https://www.nomadproject.io/docs/job-specification/network\n        #\n        network {\n          port \"${service_name}\" {\n            static      = ${port}\n          }\n        }\n      }\n    }\n  }\n}",
+            "id": "170256de3b14e7562d5d4b196864b5c0ad562cf124c5866d85bd81a3f35bcc27",
+            "rendered": "job \"prod-prometheus\" {\n  # The \"region\" parameter specifies the region in which to execute the job.\n  # If omitted, this inherits the default region name of \"global\".\n  # region = \"global\"\n  #\n  # The \"datacenters\" parameter specifies the list of datacenters which should\n  # be considered when placing this task. This must be provided.\n  datacenters         = \"yul1\"\n\n  # The \"type\" parameter controls the type of job, which impacts the scheduler's\n  # decision on placement. This configuration is optional and defaults to\n  # \"service\". For a full list of job types and their differences, please see\n  # the online documentation.\n  #\n  # For more information, please see the online documentation at:\n  #\n  #     https://www.nomadproject.io/docs/jobspec/schedulers\n  #\n  type                = \"service\"\n\n  update {\n    # The \"max_parallel\" parameter specifies the maximum number of updates to\n    # perform in parallel. In this case, this specifies to update a single task\n    # at a time.\n    max_parallel      = 1\n\n    health_check      = \"checks\"\n\n    # The \"min_healthy_time\" parameter specifies the minimum time the allocation\n    # must be in the healthy state before it is marked as healthy and unblocks\n    # further allocations from being updated.\n    min_healthy_time  = \"10s\"\n\n    # The \"healthy_deadline\" parameter specifies the deadline in which the\n    # allocation must be marked as healthy after which the allocation is\n    # automatically transitioned to unhealthy. Transitioning to unhealthy will\n    # fail the deployment and potentially roll back the job if \"auto_revert\" is\n    # set to true.\n    healthy_deadline  = \"3m\"\n\n    # The \"progress_deadline\" parameter specifies the deadline in which an\n    # allocation must be marked as healthy. The deadline begins when the first\n    # allocation for the deployment is created and is reset whenever an allocation\n    # as part of the deployment transitions to a healthy state. If no allocation\n    # transitions to the healthy state before the progress deadline, the\n    # deployment is marked as failed.\n    progress_deadline = \"10m\"\n\n\n    # The \"canary\" parameter specifies that changes to the job that would result\n    # in destructive updates should create the specified number of canaries\n    # without stopping any previous allocations. Once the operator determines the\n    # canaries are healthy, they can be promoted which unblocks a rolling update\n    # of the remaining allocations at a rate of \"max_parallel\".\n    #\n    # Further, setting \"canary\" equal to the count of the task group allows\n    # blue/green deployments. When the job is updated, a full set of the new\n    # version is deployed and upon promotion the old version is stopped.\n    canary            = 1\n\n    # Specifies if the job should auto-promote to the canary version when all\n    # canaries become healthy during a deployment. Defaults to false which means\n    # canaries must be manually updated with the nomad deployment promote\n    # command.\n    auto_promote      = true\n\n    # The \"auto_revert\" parameter specifies if the job should auto-revert to the\n    # last stable job on deployment failure. A job is marked as stable if all the\n    # allocations as part of its deployment were marked healthy.\n    auto_revert       = true\n\n  }\n\n  # The reschedule stanza specifies the group's rescheduling strategy. If\n  # specified at the job level, the configuration will apply to all groups\n  # within the job. If the reschedule stanza is present on both the job and the\n  # group, they are merged with the group stanza taking the highest precedence\n  # and then the job.\n  reschedule {\n    delay             = \"30s\"\n    delay_function    = \"constant\"\n    unlimited         = true\n  }\n\n  # The \"group\" stanza defines a series of tasks that should be co-located on\n  # the same Nomad client. Any task within a group will be placed on the same\n  # client.\n  #\n  # For more information and examples on the \"group\" stanza, please see\n  # the online documentation at:\n  #\n  #     https://www.nomadproject.io/docs/job-specification/group\n  #\n  group \"prod-group1-prometheus\" {\n    # The \"count\" parameter specifies the number of the task groups that should\n    # be running under this group. This value must be non-negative and defaults\n    # to 1.\n    count               = 4\n\n    # The restart stanza configures a tasks's behavior on task failure. Restarts\n    # happen on the client that is running the task.\n    #\n    # https://www.nomadproject.io/docs/job-specification/restart\n    #\n    restart {\n      interval  = \"30m\"\n      attempts  = 40\n      delay     = \"15s\"\n      mode      = \"delay\"\n    }\n\n    # The volume stanza allows the group to specify that it requires a given\n    # volume from the cluster.\n    #\n    # For more information and examples on the \"volume\" stanza, please see\n    # the online documentation at:\n    #\n    #     https://www.nomadproject.io/docs/job-specification/volume\n    #\n    \n    volume \"prod-volume1-prometheus\" {\n      type              = \"host\"\n      read_only         = false\n      source            = \"prod-volume-data1-1\"\n    }\n    \n\n    # The constraint allows restricting the set of eligible nodes. Constraints\n    # may filter on attributes or client metadata.\n    #\n    # For more information and examples on the \"volume\" stanza, please see\n    # the online documentation at:\n    #\n    #     https://www.nomadproject.io/docs/job-specification/constraint\n    #\n    constraint {\n      attribute         = \"${attr.cpu.arch}\"\n      operator          = \"!=\"\n      value             = \"arm64\"\n    }\n\n    # The \"task\" stanza creates an individual unit of work, such as a Docker\n    # container, web application, or batch processing.\n    #\n    # For more information and examples on the \"task\" stanza, please see\n    # the online documentation at:\n    #\n    #     https://www.nomadproject.io/docs/job-specification/task\n    #\n    task \"prod-task1-prometheus\" {\n      # The \"driver\" parameter specifies the task driver that should be used to\n      # run the task.\n      driver            = \"exec\"\n\n      \n      volume_mount {\n        volume          = \"prod-volume1-prometheus\"\n        destination     = \"/data/\"\n        read_only       = false\n      }\n      \n\n      \n\n      # The \"config\" stanza specifies the driver configuration, which is passed\n      # directly to the driver to start the task. The details of configurations\n      # are specific to each driver, so please see specific driver\n      # documentation for more information.\n      config {\n        command         = \"local/prometheus-2.28.1.linux-amd64/prometheus\"\n        args            = [\n          \"--config.file=secrets/prometheus.yml\",\n          \"--storage.tsdb.path=/data/prometheus/\",\n          \"--storage.tsdb.retention.time=7d\"\n        ]\n      }\n\n      # The artifact stanza instructs Nomad to fetch and unpack a remote resource,\n      # such as a file, tarball, or binary. Nomad downloads artifacts using the\n      # popular go-getter library, which permits downloading artifacts from a\n      # variety of locations using a URL as the input source.\n      #\n      # For more information and examples on the \"artifact\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/artifact\n      #\n      artifact {\n        source          = \"https://github.com/prometheus/prometheus/releases/download/v2.28.1/prometheus-2.28.1.linux-amd64.tar.gz\"\n      }\n\n      # The \"template\" stanza instructs Nomad to manage a template, such as\n      # a configuration file or script. This template can optionally pull data\n      # from Consul or Vault to populate runtime configuration data.\n      #\n      # For more information and examples on the \"template\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/template\n      #\n      template {\n        change_mode     = \"noop\"\n        change_signal   = \"SIGINT\"\n        destination     = \"secrets/alerts.yml\"\n        left_delimiter  = \"{{{\"\n        right_delimiter = \"}}}\"\n        data            = \u003c\u003cEOH\n---\ngroups:\n- name: \"Jenkins Job Health Exporter\"\n  rules:\n  - alert: JenkinsJobHealthExporterFailures\n    expr: jenkins_job_failure{id=~\".*\"} \u003e jenkins_job_success{id=~\".*\"}\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Jenkins Job Health detected high failure rate on jenkins jobs.\"\n      description: \"Job: {{ $labels.id }}\"\n  - alert: JenkinsJobHealthExporterUnstable\n    expr: jenkins_job_unstable{id=~\".*\"} \u003e jenkins_job_success{id=~\".*\"}\n    for: 0m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Jenkins Job Health detected high unstable rate on jenkins jobs.\"\n      description: \"Job: {{ $labels.id }}\"\n- name: \"Consul\"\n  rules:\n  - alert: ConsulServiceHealthcheckFailed\n    expr: consul_catalog_service_node_healthy == 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Consul service healthcheck failed (instance {{ $labels.instance }}).\"\n      description: \"Service: `{{ $labels.service_name }}` Healthcheck: `{{ $labels.service_id }}`.\"\n  - alert: ConsulMissingMasterNode\n    expr: consul_raft_peers \u003c 3\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Consul missing master node (instance {{ $labels.instance }}).\"\n      description: \"Numbers of consul raft peers should be 3, in order to preserve quorum.\"\n  - alert: ConsulAgentUnhealthy\n    expr: consul_health_node_status{status=\"critical\"} == 1\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Consul agent unhealthy (instance {{ $labels.instance }}).\"\n      description: \"A Consul agent is down.\"\n- name: \"Hosts\"\n  rules:\n  - alert: NodeDown\n    expr: up == 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Prometheus target missing (instance {{ $labels.instance }}).\"\n      description: \"A Prometheus target has disappeared. An exporter might be crashed.\"\n  - alert: HostOutOfMemory\n    expr: node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes * 100 \u003c 10\n    for: 2m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host out of memory (instance {{ $labels.instance }}).\"\n      description: \"Node memory is filling up (\u003c 10% left).\"\n  - alert: HostOomKillDetected\n    expr: increase(node_vmstat_oom_kill[1m]) \u003e 0\n    for: 0m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host OOM kill detected (instance {{ $labels.instance }}).\"\n      description: \"OOM kill detected.\"\n  - alert: HostMemoryUnderMemoryPressure\n    expr: rate(node_vmstat_pgmajfault[1m]) \u003e 1000\n    for: 2m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host memory under memory pressure (instance {{ $labels.instance }}).\"\n      description: \"The node is under heavy memory pressure. High rate of major page faults.\"\n  - alert: HostOutOfDiskSpace\n    expr: (node_filesystem_avail_bytes * 100) / node_filesystem_size_bytes \u003c 10 and ON (instance, device, mountpoint) node_filesystem_readonly == 0\n    for: 2m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host out of disk space (instance {{ $labels.instance }}).\"\n      description: \"Disk is almost full (\u003c 10% left).\"\n  - alert: HostRaidDiskFailure\n    expr: node_md_disks{state=\"failed\"} \u003e 0\n    for: 2m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host RAID disk failure (instance {{ $labels.instance }}).\"\n      description: \"At least one device in RAID array on {{ $labels.instance }} failed. Array {{ $labels.md_device }} needs attention and possibly a disk swap.\"\n  - alert: HostConntrackLimit\n    expr: node_nf_conntrack_entries / node_nf_conntrack_entries_limit \u003e 0.8\n    for: 5m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host conntrack limit (instance {{ $labels.instance }}).\"\n      description: \"The number of conntrack is approching limit.\"\n  - alert: HostNetworkInterfaceSaturated\n    expr: (rate(node_network_receive_bytes_total{device!~\"^tap.*\"}[1m]) + rate(node_network_transmit_bytes_total{device!~\"^tap.*\"}[1m])) / node_network_speed_bytes{device!~\"^tap.*\"} \u003e 0.8\n    for: 1m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host Network Interface Saturated (instance {{ $labels.instance }}).\"\n      description: \"The network interface {{ $labels.interface }} on {{ $labels.instance }} is getting overloaded.\"\n  - alert: HostSystemdServiceCrashed\n    expr: node_systemd_unit_state{state=\"failed\"} == 1\n    for: 0m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host SystemD service crashed (instance {{ $labels.instance }}).\"\n      description: \"SystemD service crashed.\"\n  - alert: HostEdacCorrectableErrorsDetected\n    expr: increase(node_edac_correctable_errors_total[1m]) \u003e 0\n    for: 0m\n    labels:\n      severity: info\n    annotations:\n      summary: \"Host EDAC Correctable Errors detected (instance {{ $labels.instance }}).\"\n      description: '{{ $labels.instance }} has had {{ printf \"%.0f\" $value }} correctable memory errors reported by EDAC in the last 5 minutes.'\n  - alert: HostEdacUncorrectableErrorsDetected\n    expr: node_edac_uncorrectable_errors_total \u003e 0\n    for: 0m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host EDAC Uncorrectable Errors detected (instance {{ $labels.instance }}).\"\n      description: '{{ $labels.instance }} has had {{ printf \"%.0f\" $value }} uncorrectable memory errors reported by EDAC in the last 5 minutes.'\n- name: \"Min.io\"\n  rules:\n  - alert: MinioDiskOffline\n    expr: minio_offline_disks \u003e 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Minio disk offline (instance {{ $labels.instance }})\"\n      description: \"Minio disk is offline.\"\n  - alert: MinioStorageSpaceExhausted\n    expr: minio_disk_storage_free_bytes / 1024 / 1024 / 1024 \u003c 10\n    for: 2m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Minio storage space exhausted (instance {{ $labels.instance }}).\"\n      description: \"Minio storage space is low (\u003c 10 GB).\"\n- name: \"Prometheus\"\n  rules:\n  - alert: PrometheusConfigurationReloadFailure\n    expr: prometheus_config_last_reload_successful != 1\n    for: 0m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Prometheus configuration reload failure (instance {{ $labels.instance }}).\"\n      description: \"Prometheus configuration reload error.\"\n  - alert: PrometheusTooManyRestarts\n    expr: changes(process_start_time_seconds{job=~\"prometheus|pushgateway|alertmanager\"}[15m]) \u003e 2\n    for: 0m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Prometheus too many restarts (instance {{ $labels.instance }}).\"\n      description: \"Prometheus has restarted more than twice in the last 15 minutes. It might be crashlooping.\"\n  - alert: PrometheusAlertmanagerConfigurationReloadFailure\n    expr: alertmanager_config_last_reload_successful != 1\n    for: 0m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Prometheus AlertManager configuration reload failure (instance {{ $labels.instance }}).\"\n      description: \"AlertManager configuration reload error.\"\n  - alert: PrometheusRuleEvaluationFailures\n    expr: increase(prometheus_rule_evaluation_failures_total[3m]) \u003e 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Prometheus rule evaluation failures (instance {{ $labels.instance }}).\"\n      description: \"Prometheus encountered {{ $value }} rule evaluation failures, leading to potentially ignored alerts.\"\n  - alert: PrometheusTargetScrapingSlow\n    expr: prometheus_target_interval_length_seconds{quantile=\"0.9\"} \u003e 60\n    for: 5m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Prometheus target scraping slow (instance {{ $labels.instance }}).\"\n      description: \"Prometheus is scraping exporters slowly.\"\n  - alert: PrometheusTsdbCompactionsFailed\n    expr: increase(prometheus_tsdb_compactions_failed_total[1m]) \u003e 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Prometheus TSDB compactions failed (instance {{ $labels.instance }}).\"\n      description: \"Prometheus encountered {{ $value }} TSDB compactions failures.\"\n  - alert: PrometheusTsdbHeadTruncationsFailed\n    expr: increase(prometheus_tsdb_head_truncations_failed_total[1m]) \u003e 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Prometheus TSDB head truncations failed (instance {{ $labels.instance }}).\"\n      description: \"Prometheus encountered {{ $value }} TSDB head truncation failures.\"\n  - alert: PrometheusTsdbWalCorruptions\n    expr: increase(prometheus_tsdb_wal_corruptions_total[1m]) \u003e 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Prometheus TSDB WAL corruptions (instance {{ $labels.instance }}).\"\n      description: \"Prometheus encountered {{ $value }} TSDB WAL corruptions.\"\n  - alert: PrometheusTsdbWalTruncationsFailed\n    expr: increase(prometheus_tsdb_wal_truncations_failed_total[1m]) \u003e 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Prometheus TSDB WAL truncations failed (instance {{ $labels.instance }}).\"\n      description: \"Prometheus encountered {{ $value }} TSDB WAL truncation failures.\"\nEOH\n      }\n\n      template {\n        change_mode     = \"noop\"\n        change_signal   = \"SIGINT\"\n        destination     = \"secrets/prometheus.yml\"\n        data            = \u003c\u003cEOH\n---\nglobal:\n  scrape_interval:     5s\n  scrape_timeout:      5s\n  evaluation_interval: 5s\n\nalerting:\n  alertmanagers:\n  - consul_sd_configs:\n    - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n      services: [ 'alertmanager' ]\n\nrule_files:\n  - 'alerts.yml'\n\nscrape_configs:\n\n  - job_name: 'Nomad Cluster'\n    consul_sd_configs:\n    - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n      services: [ 'nomad-client', 'nomad' ]\n    relabel_configs:\n    - source_labels: [__meta_consul_tags]\n      regex: '(.*)http(.*)'\n      action: keep\n    metrics_path: /v1/metrics\n    params:\n      format: [ 'prometheus' ]\n\n  - job_name: 'Consul Cluster'\n    static_configs:\n      - targets: [ '10.30.51.22:8500' ]\n      - targets: [ '10.30.51.24:8500' ]\n      - targets: [ '10.30.51.25:8500' ]\n      - targets: [ '10.30.51.26:8500' ]\n      - targets: [ '10.30.51.28:8500' ]\n      - targets: [ '10.30.51.29:8500' ]\n      - targets: [ '10.30.51.30:8500' ]\n      - targets: [ '10.30.51.39:8500' ]\n      - targets: [ '10.30.51.40:8500' ]\n      - targets: [ '10.30.51.50:8500' ]\n      - targets: [ '10.30.51.51:8500' ]\n      - targets: [ '10.30.51.65:8500' ]\n      - targets: [ '10.30.51.66:8500' ]\n      - targets: [ '10.30.51.67:8500' ]\n      - targets: [ '10.30.51.68:8500' ]\n      - targets: [ '10.30.51.70:8500' ]\n      - targets: [ '10.30.51.71:8500' ]\n      - targets: [ '10.32.8.14:8500' ]\n      - targets: [ '10.32.8.15:8500' ]\n      - targets: [ '10.32.8.16:8500' ]\n      - targets: [ '10.32.8.17:8500' ]\n    metrics_path: /v1/agent/metrics\n    params:\n      format: [ 'prometheus' ]\n\n  - job_name: 'Blackbox Exporter (icmp)'\n    static_configs:\n      - targets: [ 'gerrit.fd.io' ]\n      - targets: [ 'jenkins.fd.io' ]\n      - targets: [ '10.32.8.17' ]\n    params:\n      module: [ 'icmp_v4' ]\n    relabel_configs:\n      - source_labels: [__address__]\n        target_label: __param_target\n      - source_labels: [__param_target]\n        target_label: instance\n      - target_label: __address__\n        replacement: localhost:9115\n    metrics_path: /probe\n\n  - job_name: 'Blackbox Exporter (http)'\n    static_configs:\n      - targets: [ 'gerrit.fd.io' ]\n      - targets: [ 'jenkins.fd.io' ]\n    params:\n      module: [ 'http_2xx' ]\n    relabel_configs:\n      - source_labels: [__address__]\n        target_label: __param_target\n      - source_labels: [__param_target]\n        target_label: instance\n      - target_label: __address__\n        replacement: localhost:9115\n    metrics_path: /probe\n\n  - job_name: 'Jenkins Job Health Exporter'\n    static_configs:\n      - targets: [ '10.30.51.22:9186' ]\n    metric_relabel_configs:\n      - source_labels: [ __name__ ]\n        regex: '^(vpp.*|csit.*)_(success|failure|total|unstable|reqtime_ms)$'\n        action: replace\n        replacement: '$1'\n        target_label: id\n      - source_labels: [ __name__ ]\n        regex: '^(vpp.*|csit.*)_(success|failure|total|unstable|reqtime_ms)$'\n        replacement: 'jenkins_job_$2'\n        target_label: __name__\n\n  - job_name: 'Node Exporter'\n    static_configs:\n      - targets: [ '10.30.51.22:9100' ]\n      - targets: [ '10.30.51.24:9100' ]\n      - targets: [ '10.30.51.25:9100' ]\n      - targets: [ '10.30.51.26:9100' ]\n      - targets: [ '10.30.51.28:9100' ]\n      - targets: [ '10.30.51.29:9100' ]\n      - targets: [ '10.30.51.30:9100' ]\n      - targets: [ '10.30.51.39:9100' ]\n      - targets: [ '10.30.51.40:9100' ]\n      - targets: [ '10.30.51.50:9100' ]\n      - targets: [ '10.30.51.51:9100' ]\n      - targets: [ '10.30.51.65:9100' ]\n      - targets: [ '10.30.51.66:9100' ]\n      - targets: [ '10.30.51.67:9100' ]\n      - targets: [ '10.30.51.68:9100' ]\n      - targets: [ '10.30.51.70:9100' ]\n      - targets: [ '10.30.51.71:9100' ]\n      - targets: [ '10.32.8.14:9100' ]\n      - targets: [ '10.32.8.15:9100' ]\n      - targets: [ '10.32.8.16:9100' ]\n      - targets: [ '10.32.8.17:9100' ]\n\n  - job_name: 'Alertmanager'\n    consul_sd_configs:\n    - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n      services: [ 'alertmanager' ]\n\n  - job_name: 'Grafana'\n    consul_sd_configs:\n    - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n      services: [ 'grafana' ]\n\n  - job_name: 'Prometheus'\n    consul_sd_configs:\n    - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n      services: [ 'prometheus' ]\n\n  - job_name: 'Minio'\n    bearer_token: eyJhbGciOiJIUzUxMiIsInR5cCI6IkpXVCJ9.eyJleHAiOjQ3NjQ1ODEzMzcsImlzcyI6InByb21ldGhldXMiLCJzdWIiOiJtaW5pbyJ9.oeTw3EIaiFmlDikrHXWiWXMH2vxLfDLkfjEC7G2N3M_keH_xyA_l2ofLLNYtopa_3GCEZnxLQdPuFZrmgpkDWg\n    consul_sd_configs:\n    - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n      services: [ 'storage' ]\n    metrics_path: /minio/prometheus/metrics\nEOH\n      }\n\n      # The service stanza instructs Nomad to register a service with Consul.\n      #\n      # For more information and examples on the \"task\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/service\n      #\n      service {\n        name            = \"prometheus\"\n        port            = \"prometheus\"\n        tags            = [ \"prometheus${NOMAD_ALLOC_INDEX}\" ]\n        check {\n          name          = \"Prometheus Check Live\"\n          type          = \"http\"\n          path          = \"/-/healthy\"\n          interval      = \"10s\"\n          timeout       = \"2s\"\n        }\n      }\n\n      # The \"resources\" stanza describes the requirements a task needs to\n      # execute. Resource requirements include memory, network, cpu, and more.\n      # This ensures the task will execute on a machine that contains enough\n      # resource capacity.\n      #\n      # For more information and examples on the \"resources\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/resources\n      #\n      resources {\n        cpu             = 2000\n        memory          = 8192\n        # The network stanza specifies the networking requirements for the task\n        # group, including the network mode and port allocations. When scheduling\n        # jobs in Nomad they are provisioned across your fleet of machines along\n        # with other jobs and services. Because you don't know in advance what host\n        # your job will be provisioned on, Nomad will provide your tasks with\n        # network configuration when they start up.\n        #\n        # For more information and examples on the \"template\" stanza, please see\n        # the online documentation at:\n        #\n        #     https://www.nomadproject.io/docs/job-specification/network\n        #\n        network {\n          port \"prometheus\" {\n            static      = 9090\n          }\n        }\n      }\n    }\n  }\n}",
+            "template": "job \"${job_name}\" {\n  # The \"region\" parameter specifies the region in which to execute the job.\n  # If omitted, this inherits the default region name of \"global\".\n  # region = \"global\"\n  #\n  # The \"datacenters\" parameter specifies the list of datacenters which should\n  # be considered when placing this task. This must be provided.\n  datacenters         = \"${datacenters}\"\n\n  # The \"type\" parameter controls the type of job, which impacts the scheduler's\n  # decision on placement. This configuration is optional and defaults to\n  # \"service\". For a full list of job types and their differences, please see\n  # the online documentation.\n  #\n  # For more information, please see the online documentation at:\n  #\n  #     https://www.nomadproject.io/docs/jobspec/schedulers\n  #\n  type                = \"service\"\n\n  update {\n    # The \"max_parallel\" parameter specifies the maximum number of updates to\n    # perform in parallel. In this case, this specifies to update a single task\n    # at a time.\n    max_parallel      = 1\n\n    health_check      = \"checks\"\n\n    # The \"min_healthy_time\" parameter specifies the minimum time the allocation\n    # must be in the healthy state before it is marked as healthy and unblocks\n    # further allocations from being updated.\n    min_healthy_time  = \"10s\"\n\n    # The \"healthy_deadline\" parameter specifies the deadline in which the\n    # allocation must be marked as healthy after which the allocation is\n    # automatically transitioned to unhealthy. Transitioning to unhealthy will\n    # fail the deployment and potentially roll back the job if \"auto_revert\" is\n    # set to true.\n    healthy_deadline  = \"3m\"\n\n    # The \"progress_deadline\" parameter specifies the deadline in which an\n    # allocation must be marked as healthy. The deadline begins when the first\n    # allocation for the deployment is created and is reset whenever an allocation\n    # as part of the deployment transitions to a healthy state. If no allocation\n    # transitions to the healthy state before the progress deadline, the\n    # deployment is marked as failed.\n    progress_deadline = \"10m\"\n\n%{ if use_canary }\n    # The \"canary\" parameter specifies that changes to the job that would result\n    # in destructive updates should create the specified number of canaries\n    # without stopping any previous allocations. Once the operator determines the\n    # canaries are healthy, they can be promoted which unblocks a rolling update\n    # of the remaining allocations at a rate of \"max_parallel\".\n    #\n    # Further, setting \"canary\" equal to the count of the task group allows\n    # blue/green deployments. When the job is updated, a full set of the new\n    # version is deployed and upon promotion the old version is stopped.\n    canary            = 1\n\n    # Specifies if the job should auto-promote to the canary version when all\n    # canaries become healthy during a deployment. Defaults to false which means\n    # canaries must be manually updated with the nomad deployment promote\n    # command.\n    auto_promote      = true\n\n    # The \"auto_revert\" parameter specifies if the job should auto-revert to the\n    # last stable job on deployment failure. A job is marked as stable if all the\n    # allocations as part of its deployment were marked healthy.\n    auto_revert       = true\n%{ endif }\n  }\n\n  # The reschedule stanza specifies the group's rescheduling strategy. If\n  # specified at the job level, the configuration will apply to all groups\n  # within the job. If the reschedule stanza is present on both the job and the\n  # group, they are merged with the group stanza taking the highest precedence\n  # and then the job.\n  reschedule {\n    delay             = \"30s\"\n    delay_function    = \"constant\"\n    unlimited         = true\n  }\n\n  # The \"group\" stanza defines a series of tasks that should be co-located on\n  # the same Nomad client. Any task within a group will be placed on the same\n  # client.\n  #\n  # For more information and examples on the \"group\" stanza, please see\n  # the online documentation at:\n  #\n  #     https://www.nomadproject.io/docs/job-specification/group\n  #\n  group \"prod-group1-${service_name}\" {\n    # The \"count\" parameter specifies the number of the task groups that should\n    # be running under this group. This value must be non-negative and defaults\n    # to 1.\n    count               = ${group_count}\n\n    # The restart stanza configures a tasks's behavior on task failure. Restarts\n    # happen on the client that is running the task.\n    #\n    # https://www.nomadproject.io/docs/job-specification/restart\n    #\n    restart {\n      interval  = \"30m\"\n      attempts  = 40\n      delay     = \"15s\"\n      mode      = \"delay\"\n    }\n\n    # The volume stanza allows the group to specify that it requires a given\n    # volume from the cluster.\n    #\n    # For more information and examples on the \"volume\" stanza, please see\n    # the online documentation at:\n    #\n    #     https://www.nomadproject.io/docs/job-specification/volume\n    #\n    %{ if use_host_volume }\n    volume \"prod-volume1-${service_name}\" {\n      type              = \"host\"\n      read_only         = false\n      source            = \"${host_volume}\"\n    }\n    %{ endif }\n\n    # The constraint allows restricting the set of eligible nodes. Constraints\n    # may filter on attributes or client metadata.\n    #\n    # For more information and examples on the \"volume\" stanza, please see\n    # the online documentation at:\n    #\n    #     https://www.nomadproject.io/docs/job-specification/constraint\n    #\n    constraint {\n      attribute         = \"$${attr.cpu.arch}\"\n      operator          = \"!=\"\n      value             = \"arm64\"\n    }\n\n    # The \"task\" stanza creates an individual unit of work, such as a Docker\n    # container, web application, or batch processing.\n    #\n    # For more information and examples on the \"task\" stanza, please see\n    # the online documentation at:\n    #\n    #     https://www.nomadproject.io/docs/job-specification/task\n    #\n    task \"prod-task1-${service_name}\" {\n      # The \"driver\" parameter specifies the task driver that should be used to\n      # run the task.\n      driver            = \"exec\"\n\n      %{ if use_host_volume }\n      volume_mount {\n        volume          = \"prod-volume1-${service_name}\"\n        destination     = \"${data_dir}\"\n        read_only       = false\n      }\n      %{ endif }\n\n      %{ if use_vault_provider }\n      vault {\n        policies        = \"${vault_kv_policy_name}\"\n      }\n      %{ endif }\n\n      # The \"config\" stanza specifies the driver configuration, which is passed\n      # directly to the driver to start the task. The details of configurations\n      # are specific to each driver, so please see specific driver\n      # documentation for more information.\n      config {\n        command         = \"local/prometheus-${version}.linux-amd64/prometheus\"\n        args            = [\n          \"--config.file=secrets/prometheus.yml\",\n          \"--storage.tsdb.path=${data_dir}prometheus/\",\n          \"--storage.tsdb.retention.time=7d\"\n        ]\n      }\n\n      # The artifact stanza instructs Nomad to fetch and unpack a remote resource,\n      # such as a file, tarball, or binary. Nomad downloads artifacts using the\n      # popular go-getter library, which permits downloading artifacts from a\n      # variety of locations using a URL as the input source.\n      #\n      # For more information and examples on the \"artifact\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/artifact\n      #\n      artifact {\n        source          = \"${url}\"\n      }\n\n      # The \"template\" stanza instructs Nomad to manage a template, such as\n      # a configuration file or script. This template can optionally pull data\n      # from Consul or Vault to populate runtime configuration data.\n      #\n      # For more information and examples on the \"template\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/template\n      #\n      template {\n        change_mode     = \"noop\"\n        change_signal   = \"SIGINT\"\n        destination     = \"secrets/alerts.yml\"\n        left_delimiter  = \"{{{\"\n        right_delimiter = \"}}}\"\n        data            = \u003c\u003cEOH\n---\ngroups:\n- name: \"Jenkins Job Health Exporter\"\n  rules:\n  - alert: JenkinsJobHealthExporterFailures\n    expr: jenkins_job_failure{id=~\".*\"} \u003e jenkins_job_success{id=~\".*\"}\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Jenkins Job Health detected high failure rate on jenkins jobs.\"\n      description: \"Job: {{ $labels.id }}\"\n  - alert: JenkinsJobHealthExporterUnstable\n    expr: jenkins_job_unstable{id=~\".*\"} \u003e jenkins_job_success{id=~\".*\"}\n    for: 0m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Jenkins Job Health detected high unstable rate on jenkins jobs.\"\n      description: \"Job: {{ $labels.id }}\"\n- name: \"Consul\"\n  rules:\n  - alert: ConsulServiceHealthcheckFailed\n    expr: consul_catalog_service_node_healthy == 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Consul service healthcheck failed (instance {{ $labels.instance }}).\"\n      description: \"Service: `{{ $labels.service_name }}` Healthcheck: `{{ $labels.service_id }}`.\"\n  - alert: ConsulMissingMasterNode\n    expr: consul_raft_peers \u003c 3\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Consul missing master node (instance {{ $labels.instance }}).\"\n      description: \"Numbers of consul raft peers should be 3, in order to preserve quorum.\"\n  - alert: ConsulAgentUnhealthy\n    expr: consul_health_node_status{status=\"critical\"} == 1\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Consul agent unhealthy (instance {{ $labels.instance }}).\"\n      description: \"A Consul agent is down.\"\n- name: \"Hosts\"\n  rules:\n  - alert: NodeDown\n    expr: up == 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Prometheus target missing (instance {{ $labels.instance }}).\"\n      description: \"A Prometheus target has disappeared. An exporter might be crashed.\"\n  - alert: HostOutOfMemory\n    expr: node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes * 100 \u003c 10\n    for: 2m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host out of memory (instance {{ $labels.instance }}).\"\n      description: \"Node memory is filling up (\u003c 10% left).\"\n  - alert: HostOomKillDetected\n    expr: increase(node_vmstat_oom_kill[1m]) \u003e 0\n    for: 0m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host OOM kill detected (instance {{ $labels.instance }}).\"\n      description: \"OOM kill detected.\"\n  - alert: HostMemoryUnderMemoryPressure\n    expr: rate(node_vmstat_pgmajfault[1m]) \u003e 1000\n    for: 2m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host memory under memory pressure (instance {{ $labels.instance }}).\"\n      description: \"The node is under heavy memory pressure. High rate of major page faults.\"\n  - alert: HostOutOfDiskSpace\n    expr: (node_filesystem_avail_bytes * 100) / node_filesystem_size_bytes \u003c 10 and ON (instance, device, mountpoint) node_filesystem_readonly == 0\n    for: 2m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host out of disk space (instance {{ $labels.instance }}).\"\n      description: \"Disk is almost full (\u003c 10% left).\"\n  - alert: HostRaidDiskFailure\n    expr: node_md_disks{state=\"failed\"} \u003e 0\n    for: 2m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host RAID disk failure (instance {{ $labels.instance }}).\"\n      description: \"At least one device in RAID array on {{ $labels.instance }} failed. Array {{ $labels.md_device }} needs attention and possibly a disk swap.\"\n  - alert: HostConntrackLimit\n    expr: node_nf_conntrack_entries / node_nf_conntrack_entries_limit \u003e 0.8\n    for: 5m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host conntrack limit (instance {{ $labels.instance }}).\"\n      description: \"The number of conntrack is approching limit.\"\n  - alert: HostNetworkInterfaceSaturated\n    expr: (rate(node_network_receive_bytes_total{device!~\"^tap.*\"}[1m]) + rate(node_network_transmit_bytes_total{device!~\"^tap.*\"}[1m])) / node_network_speed_bytes{device!~\"^tap.*\"} \u003e 0.8\n    for: 1m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host Network Interface Saturated (instance {{ $labels.instance }}).\"\n      description: \"The network interface {{ $labels.interface }} on {{ $labels.instance }} is getting overloaded.\"\n  - alert: HostSystemdServiceCrashed\n    expr: node_systemd_unit_state{state=\"failed\"} == 1\n    for: 0m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host SystemD service crashed (instance {{ $labels.instance }}).\"\n      description: \"SystemD service crashed.\"\n  - alert: HostEdacCorrectableErrorsDetected\n    expr: increase(node_edac_correctable_errors_total[1m]) \u003e 0\n    for: 0m\n    labels:\n      severity: info\n    annotations:\n      summary: \"Host EDAC Correctable Errors detected (instance {{ $labels.instance }}).\"\n      description: '{{ $labels.instance }} has had {{ printf \"%.0f\" $value }} correctable memory errors reported by EDAC in the last 5 minutes.'\n  - alert: HostEdacUncorrectableErrorsDetected\n    expr: node_edac_uncorrectable_errors_total \u003e 0\n    for: 0m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host EDAC Uncorrectable Errors detected (instance {{ $labels.instance }}).\"\n      description: '{{ $labels.instance }} has had {{ printf \"%.0f\" $value }} uncorrectable memory errors reported by EDAC in the last 5 minutes.'\n- name: \"Min.io\"\n  rules:\n  - alert: MinioDiskOffline\n    expr: minio_offline_disks \u003e 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Minio disk offline (instance {{ $labels.instance }})\"\n      description: \"Minio disk is offline.\"\n  - alert: MinioStorageSpaceExhausted\n    expr: minio_disk_storage_free_bytes / 1024 / 1024 / 1024 \u003c 10\n    for: 2m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Minio storage space exhausted (instance {{ $labels.instance }}).\"\n      description: \"Minio storage space is low (\u003c 10 GB).\"\n- name: \"Prometheus\"\n  rules:\n  - alert: PrometheusConfigurationReloadFailure\n    expr: prometheus_config_last_reload_successful != 1\n    for: 0m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Prometheus configuration reload failure (instance {{ $labels.instance }}).\"\n      description: \"Prometheus configuration reload error.\"\n  - alert: PrometheusTooManyRestarts\n    expr: changes(process_start_time_seconds{job=~\"prometheus|pushgateway|alertmanager\"}[15m]) \u003e 2\n    for: 0m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Prometheus too many restarts (instance {{ $labels.instance }}).\"\n      description: \"Prometheus has restarted more than twice in the last 15 minutes. It might be crashlooping.\"\n  - alert: PrometheusAlertmanagerConfigurationReloadFailure\n    expr: alertmanager_config_last_reload_successful != 1\n    for: 0m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Prometheus AlertManager configuration reload failure (instance {{ $labels.instance }}).\"\n      description: \"AlertManager configuration reload error.\"\n  - alert: PrometheusRuleEvaluationFailures\n    expr: increase(prometheus_rule_evaluation_failures_total[3m]) \u003e 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Prometheus rule evaluation failures (instance {{ $labels.instance }}).\"\n      description: \"Prometheus encountered {{ $value }} rule evaluation failures, leading to potentially ignored alerts.\"\n  - alert: PrometheusTargetScrapingSlow\n    expr: prometheus_target_interval_length_seconds{quantile=\"0.9\"} \u003e 60\n    for: 5m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Prometheus target scraping slow (instance {{ $labels.instance }}).\"\n      description: \"Prometheus is scraping exporters slowly.\"\n  - alert: PrometheusTsdbCompactionsFailed\n    expr: increase(prometheus_tsdb_compactions_failed_total[1m]) \u003e 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Prometheus TSDB compactions failed (instance {{ $labels.instance }}).\"\n      description: \"Prometheus encountered {{ $value }} TSDB compactions failures.\"\n  - alert: PrometheusTsdbHeadTruncationsFailed\n    expr: increase(prometheus_tsdb_head_truncations_failed_total[1m]) \u003e 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Prometheus TSDB head truncations failed (instance {{ $labels.instance }}).\"\n      description: \"Prometheus encountered {{ $value }} TSDB head truncation failures.\"\n  - alert: PrometheusTsdbWalCorruptions\n    expr: increase(prometheus_tsdb_wal_corruptions_total[1m]) \u003e 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Prometheus TSDB WAL corruptions (instance {{ $labels.instance }}).\"\n      description: \"Prometheus encountered {{ $value }} TSDB WAL corruptions.\"\n  - alert: PrometheusTsdbWalTruncationsFailed\n    expr: increase(prometheus_tsdb_wal_truncations_failed_total[1m]) \u003e 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Prometheus TSDB WAL truncations failed (instance {{ $labels.instance }}).\"\n      description: \"Prometheus encountered {{ $value }} TSDB WAL truncation failures.\"\nEOH\n      }\n\n      template {\n        change_mode     = \"noop\"\n        change_signal   = \"SIGINT\"\n        destination     = \"secrets/prometheus.yml\"\n        data            = \u003c\u003cEOH\n---\nglobal:\n  scrape_interval:     5s\n  scrape_timeout:      5s\n  evaluation_interval: 5s\n\nalerting:\n  alertmanagers:\n  - consul_sd_configs:\n    - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n      services: [ 'alertmanager' ]\n\nrule_files:\n  - 'alerts.yml'\n\nscrape_configs:\n\n  - job_name: 'Nomad Cluster'\n    consul_sd_configs:\n    - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n      services: [ 'nomad-client', 'nomad' ]\n    relabel_configs:\n    - source_labels: [__meta_consul_tags]\n      regex: '(.*)http(.*)'\n      action: keep\n    metrics_path: /v1/metrics\n    params:\n      format: [ 'prometheus' ]\n\n  - job_name: 'Consul Cluster'\n    static_configs:\n      - targets: [ '10.30.51.22:8500' ]\n      - targets: [ '10.30.51.24:8500' ]\n      - targets: [ '10.30.51.25:8500' ]\n      - targets: [ '10.30.51.26:8500' ]\n      - targets: [ '10.30.51.28:8500' ]\n      - targets: [ '10.30.51.29:8500' ]\n      - targets: [ '10.30.51.30:8500' ]\n      - targets: [ '10.30.51.39:8500' ]\n      - targets: [ '10.30.51.40:8500' ]\n      - targets: [ '10.30.51.50:8500' ]\n      - targets: [ '10.30.51.51:8500' ]\n      - targets: [ '10.30.51.65:8500' ]\n      - targets: [ '10.30.51.66:8500' ]\n      - targets: [ '10.30.51.67:8500' ]\n      - targets: [ '10.30.51.68:8500' ]\n      - targets: [ '10.30.51.70:8500' ]\n      - targets: [ '10.30.51.71:8500' ]\n      - targets: [ '10.32.8.14:8500' ]\n      - targets: [ '10.32.8.15:8500' ]\n      - targets: [ '10.32.8.16:8500' ]\n      - targets: [ '10.32.8.17:8500' ]\n    metrics_path: /v1/agent/metrics\n    params:\n      format: [ 'prometheus' ]\n\n  - job_name: 'Blackbox Exporter (icmp)'\n    static_configs:\n      - targets: [ 'gerrit.fd.io' ]\n      - targets: [ 'jenkins.fd.io' ]\n      - targets: [ '10.32.8.17' ]\n    params:\n      module: [ 'icmp_v4' ]\n    relabel_configs:\n      - source_labels: [__address__]\n        target_label: __param_target\n      - source_labels: [__param_target]\n        target_label: instance\n      - target_label: __address__\n        replacement: localhost:9115\n    metrics_path: /probe\n\n  - job_name: 'Blackbox Exporter (http)'\n    static_configs:\n      - targets: [ 'gerrit.fd.io' ]\n      - targets: [ 'jenkins.fd.io' ]\n    params:\n      module: [ 'http_2xx' ]\n    relabel_configs:\n      - source_labels: [__address__]\n        target_label: __param_target\n      - source_labels: [__param_target]\n        target_label: instance\n      - target_label: __address__\n        replacement: localhost:9115\n    metrics_path: /probe\n\n  - job_name: 'Jenkins Job Health Exporter'\n    static_configs:\n      - targets: [ '10.30.51.22:9186' ]\n    metric_relabel_configs:\n      - source_labels: [ __name__ ]\n        regex: '^(vpp.*|csit.*)_(success|failure|total|unstable|reqtime_ms)$'\n        action: replace\n        replacement: '$1'\n        target_label: id\n      - source_labels: [ __name__ ]\n        regex: '^(vpp.*|csit.*)_(success|failure|total|unstable|reqtime_ms)$'\n        replacement: 'jenkins_job_$2'\n        target_label: __name__\n\n  - job_name: 'Node Exporter'\n    static_configs:\n      - targets: [ '10.30.51.22:9100' ]\n      - targets: [ '10.30.51.24:9100' ]\n      - targets: [ '10.30.51.25:9100' ]\n      - targets: [ '10.30.51.26:9100' ]\n      - targets: [ '10.30.51.28:9100' ]\n      - targets: [ '10.30.51.29:9100' ]\n      - targets: [ '10.30.51.30:9100' ]\n      - targets: [ '10.30.51.39:9100' ]\n      - targets: [ '10.30.51.40:9100' ]\n      - targets: [ '10.30.51.50:9100' ]\n      - targets: [ '10.30.51.51:9100' ]\n      - targets: [ '10.30.51.65:9100' ]\n      - targets: [ '10.30.51.66:9100' ]\n      - targets: [ '10.30.51.67:9100' ]\n      - targets: [ '10.30.51.68:9100' ]\n      - targets: [ '10.30.51.70:9100' ]\n      - targets: [ '10.30.51.71:9100' ]\n      - targets: [ '10.32.8.14:9100' ]\n      - targets: [ '10.32.8.15:9100' ]\n      - targets: [ '10.32.8.16:9100' ]\n      - targets: [ '10.32.8.17:9100' ]\n\n  - job_name: 'Alertmanager'\n    consul_sd_configs:\n    - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n      services: [ 'alertmanager' ]\n\n  - job_name: 'Grafana'\n    consul_sd_configs:\n    - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n      services: [ 'grafana' ]\n\n  - job_name: 'Prometheus'\n    consul_sd_configs:\n    - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n      services: [ 'prometheus' ]\n\n  - job_name: 'Minio'\n    bearer_token: eyJhbGciOiJIUzUxMiIsInR5cCI6IkpXVCJ9.eyJleHAiOjQ3NjQ1ODEzMzcsImlzcyI6InByb21ldGhldXMiLCJzdWIiOiJtaW5pbyJ9.oeTw3EIaiFmlDikrHXWiWXMH2vxLfDLkfjEC7G2N3M_keH_xyA_l2ofLLNYtopa_3GCEZnxLQdPuFZrmgpkDWg\n    consul_sd_configs:\n    - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n      services: [ 'storage' ]\n    metrics_path: /minio/prometheus/metrics\nEOH\n      }\n\n      # The service stanza instructs Nomad to register a service with Consul.\n      #\n      # For more information and examples on the \"task\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/service\n      #\n      service {\n        name            = \"${service_name}\"\n        port            = \"${service_name}\"\n        tags            = [ \"${service_name}$${NOMAD_ALLOC_INDEX}\" ]\n        check {\n          name          = \"Prometheus Check Live\"\n          type          = \"http\"\n          path          = \"/-/healthy\"\n          interval      = \"10s\"\n          timeout       = \"2s\"\n        }\n      }\n\n      # The \"resources\" stanza describes the requirements a task needs to\n      # execute. Resource requirements include memory, network, cpu, and more.\n      # This ensures the task will execute on a machine that contains enough\n      # resource capacity.\n      #\n      # For more information and examples on the \"resources\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/resources\n      #\n      resources {\n        cpu             = ${cpu}\n        memory          = ${mem}\n        # The network stanza specifies the networking requirements for the task\n        # group, including the network mode and port allocations. When scheduling\n        # jobs in Nomad they are provisioned across your fleet of machines along\n        # with other jobs and services. Because you don't know in advance what host\n        # your job will be provisioned on, Nomad will provide your tasks with\n        # network configuration when they start up.\n        #\n        # For more information and examples on the \"template\" stanza, please see\n        # the online documentation at:\n        #\n        #     https://www.nomadproject.io/docs/job-specification/network\n        #\n        network {\n          port \"${service_name}\" {\n            static      = ${port}\n          }\n        }\n      }\n    }\n  }\n}",
             "vars": {
               "cpu": "2000",
               "data_dir": "/data/",
@@ -465,6 +465,10 @@
           "schema_version": 0,
           "attributes": {
             "allocation_ids": [
+              "9b7311cc-95ba-fead-8c92-91148f48d218",
+              "5564fb46-6a89-1e92-7bcd-7f5fa55c42e8",
+              "519e4ea1-f088-069c-3bc2-eb6de1b36b9e",
+              "6f144324-2ee0-c1fd-0f71-c07cc1fda099",
               "6776d9ca-70ba-129f-05a9-ca6fccdb6289",
               "0fb06047-62e0-48e4-e352-63b4602407f2",
               "ddb72c78-1f3f-2d1e-0157-7b7bb05aaa4a",
@@ -473,15 +477,15 @@
             "datacenters": [
               "yul1"
             ],
-            "deployment_id": "8196f20a-50e5-c63a-36f5-0b2084c4b02a",
+            "deployment_id": "88fd2d42-3b5a-8e1e-3047-7a4f93417fd3",
             "deployment_status": "successful",
             "deregister_on_destroy": true,
             "deregister_on_id_change": true,
             "detach": false,
             "id": "prod-prometheus",
-            "jobspec": "job \"prod-prometheus\" {\n  # The \"region\" parameter specifies the region in which to execute the job.\n  # If omitted, this inherits the default region name of \"global\".\n  # region = \"global\"\n  #\n  # The \"datacenters\" parameter specifies the list of datacenters which should\n  # be considered when placing this task. This must be provided.\n  datacenters         = \"yul1\"\n\n  # The \"type\" parameter controls the type of job, which impacts the scheduler's\n  # decision on placement. This configuration is optional and defaults to\n  # \"service\". For a full list of job types and their differences, please see\n  # the online documentation.\n  #\n  # For more information, please see the online documentation at:\n  #\n  #     https://www.nomadproject.io/docs/jobspec/schedulers\n  #\n  type                = \"service\"\n\n  update {\n    # The \"max_parallel\" parameter specifies the maximum number of updates to\n    # perform in parallel. In this case, this specifies to update a single task\n    # at a time.\n    max_parallel      = 1\n\n    health_check      = \"checks\"\n\n    # The \"min_healthy_time\" parameter specifies the minimum time the allocation\n    # must be in the healthy state before it is marked as healthy and unblocks\n    # further allocations from being updated.\n    min_healthy_time  = \"10s\"\n\n    # The \"healthy_deadline\" parameter specifies the deadline in which the\n    # allocation must be marked as healthy after which the allocation is\n    # automatically transitioned to unhealthy. Transitioning to unhealthy will\n    # fail the deployment and potentially roll back the job if \"auto_revert\" is\n    # set to true.\n    healthy_deadline  = \"3m\"\n\n    # The \"progress_deadline\" parameter specifies the deadline in which an\n    # allocation must be marked as healthy. The deadline begins when the first\n    # allocation for the deployment is created and is reset whenever an allocation\n    # as part of the deployment transitions to a healthy state. If no allocation\n    # transitions to the healthy state before the progress deadline, the\n    # deployment is marked as failed.\n    progress_deadline = \"10m\"\n\n\n    # The \"canary\" parameter specifies that changes to the job that would result\n    # in destructive updates should create the specified number of canaries\n    # without stopping any previous allocations. Once the operator determines the\n    # canaries are healthy, they can be promoted which unblocks a rolling update\n    # of the remaining allocations at a rate of \"max_parallel\".\n    #\n    # Further, setting \"canary\" equal to the count of the task group allows\n    # blue/green deployments. When the job is updated, a full set of the new\n    # version is deployed and upon promotion the old version is stopped.\n    canary            = 1\n\n    # Specifies if the job should auto-promote to the canary version when all\n    # canaries become healthy during a deployment. Defaults to false which means\n    # canaries must be manually updated with the nomad deployment promote\n    # command.\n    auto_promote      = true\n\n    # The \"auto_revert\" parameter specifies if the job should auto-revert to the\n    # last stable job on deployment failure. A job is marked as stable if all the\n    # allocations as part of its deployment were marked healthy.\n    auto_revert       = true\n\n  }\n\n  # The reschedule stanza specifies the group's rescheduling strategy. If\n  # specified at the job level, the configuration will apply to all groups\n  # within the job. If the reschedule stanza is present on both the job and the\n  # group, they are merged with the group stanza taking the highest precedence\n  # and then the job.\n  reschedule {\n    delay             = \"30s\"\n    delay_function    = \"constant\"\n    unlimited         = true\n  }\n\n  # The \"group\" stanza defines a series of tasks that should be co-located on\n  # the same Nomad client. Any task within a group will be placed on the same\n  # client.\n  #\n  # For more information and examples on the \"group\" stanza, please see\n  # the online documentation at:\n  #\n  #     https://www.nomadproject.io/docs/job-specification/group\n  #\n  group \"prod-group1-prometheus\" {\n    # The \"count\" parameter specifies the number of the task groups that should\n    # be running under this group. This value must be non-negative and defaults\n    # to 1.\n    count               = 4\n\n    # The restart stanza configures a tasks's behavior on task failure. Restarts\n    # happen on the client that is running the task.\n    #\n    # https://www.nomadproject.io/docs/job-specification/restart\n    #\n    restart {\n      interval  = \"30m\"\n      attempts  = 40\n      delay     = \"15s\"\n      mode      = \"delay\"\n    }\n\n    # The volume stanza allows the group to specify that it requires a given\n    # volume from the cluster.\n    #\n    # For more information and examples on the \"volume\" stanza, please see\n    # the online documentation at:\n    #\n    #     https://www.nomadproject.io/docs/job-specification/volume\n    #\n    \n    volume \"prod-volume1-prometheus\" {\n      type              = \"host\"\n      read_only         = false\n      source            = \"prod-volume-data1-1\"\n    }\n    \n\n    # The constraint allows restricting the set of eligible nodes. Constraints\n    # may filter on attributes or client metadata.\n    #\n    # For more information and examples on the \"volume\" stanza, please see\n    # the online documentation at:\n    #\n    #     https://www.nomadproject.io/docs/job-specification/constraint\n    #\n    constraint {\n      attribute         = \"${attr.cpu.arch}\"\n      operator          = \"!=\"\n      value             = \"arm64\"\n    }\n\n    # The \"task\" stanza creates an individual unit of work, such as a Docker\n    # container, web application, or batch processing.\n    #\n    # For more information and examples on the \"task\" stanza, please see\n    # the online documentation at:\n    #\n    #     https://www.nomadproject.io/docs/job-specification/task\n    #\n    task \"prod-task1-prometheus\" {\n      # The \"driver\" parameter specifies the task driver that should be used to\n      # run the task.\n      driver            = \"exec\"\n\n      \n      volume_mount {\n        volume          = \"prod-volume1-prometheus\"\n        destination     = \"/data/\"\n        read_only       = false\n      }\n      \n\n      \n\n      # The \"config\" stanza specifies the driver configuration, which is passed\n      # directly to the driver to start the task. The details of configurations\n      # are specific to each driver, so please see specific driver\n      # documentation for more information.\n      config {\n        command         = \"local/prometheus-2.28.1.linux-amd64/prometheus\"\n        args            = [\n          \"--config.file=secrets/prometheus.yml\",\n          \"--storage.tsdb.path=/data/prometheus/\",\n          \"--storage.tsdb.retention.time=7d\"\n        ]\n      }\n\n      # The artifact stanza instructs Nomad to fetch and unpack a remote resource,\n      # such as a file, tarball, or binary. Nomad downloads artifacts using the\n      # popular go-getter library, which permits downloading artifacts from a\n      # variety of locations using a URL as the input source.\n      #\n      # For more information and examples on the \"artifact\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/artifact\n      #\n      artifact {\n        source          = \"https://github.com/prometheus/prometheus/releases/download/v2.28.1/prometheus-2.28.1.linux-amd64.tar.gz\"\n      }\n\n      # The \"template\" stanza instructs Nomad to manage a template, such as\n      # a configuration file or script. This template can optionally pull data\n      # from Consul or Vault to populate runtime configuration data.\n      #\n      # For more information and examples on the \"template\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/template\n      #\n      template {\n        change_mode     = \"noop\"\n        change_signal   = \"SIGINT\"\n        destination     = \"secrets/alerts.yml\"\n        left_delimiter  = \"{{{\"\n        right_delimiter = \"}}}\"\n        data            = \u003c\u003cEOH\n---\ngroups:\n- name: \"Jenkins Job Health Exporter\"\n  rules:\n  - alert: JenkinsJobHealthExporterFailures\n    expr: jenkins_job_failure{id=~\".*\"} \u003e jenkins_job_success{id=~\".*\"}\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Jenkins Job Health detected high failure rate on jenkins jobs.\"\n      description: \"Job: {{ $labels.id }}\"\n  - alert: JenkinsJobHealthExporterUnstable\n    expr: jenkins_job_unstable{id=~\".*\"} \u003e jenkins_job_success{id=~\".*\"}\n    for: 0m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Jenkins Job Health detected high unstable rate on jenkins jobs.\"\n      description: \"Job: {{ $labels.id }}\"\n- name: \"Consul\"\n  rules:\n  - alert: ConsulServiceHealthcheckFailed\n    expr: consul_catalog_service_node_healthy == 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Consul service healthcheck failed (instance {{ $labels.instance }}).\"\n      description: \"Service: `{{ $labels.service_name }}` Healthcheck: `{{ $labels.service_id }}`.\"\n  - alert: ConsulMissingMasterNode\n    expr: consul_raft_peers \u003c 3\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Consul missing master node (instance {{ $labels.instance }}).\"\n      description: \"Numbers of consul raft peers should be 3, in order to preserve quorum.\"\n  - alert: ConsulAgentUnhealthy\n    expr: consul_health_node_status{status=\"critical\"} == 1\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Consul agent unhealthy (instance {{ $labels.instance }}).\"\n      description: \"A Consul agent is down.\"\n- name: \"Hosts\"\n  rules:\n  - alert: NodeDown\n    expr: up == 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Prometheus target missing (instance {{ $labels.instance }}).\"\n      description: \"A Prometheus target has disappeared. An exporter might be crashed.\"\n  - alert: HostOutOfMemory\n    expr: node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes * 100 \u003c 10\n    for: 2m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host out of memory (instance {{ $labels.instance }}).\"\n      description: \"Node memory is filling up (\u003c 10% left).\"\n  - alert: HostOomKillDetected\n    expr: increase(node_vmstat_oom_kill[1m]) \u003e 0\n    for: 0m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host OOM kill detected (instance {{ $labels.instance }}).\"\n      description: \"OOM kill detected.\"\n  - alert: HostMemoryUnderMemoryPressure\n    expr: rate(node_vmstat_pgmajfault[1m]) \u003e 1000\n    for: 2m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host memory under memory pressure (instance {{ $labels.instance }}).\"\n      description: \"The node is under heavy memory pressure. High rate of major page faults.\"\n  - alert: HostOutOfDiskSpace\n    expr: (node_filesystem_avail_bytes * 100) / node_filesystem_size_bytes \u003c 10 and ON (instance, device, mountpoint) node_filesystem_readonly == 0\n    for: 2m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host out of disk space (instance {{ $labels.instance }}).\"\n      description: \"Disk is almost full (\u003c 10% left).\"\n  - alert: HostRaidDiskFailure\n    expr: node_md_disks{state=\"failed\"} \u003e 0\n    for: 2m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host RAID disk failure (instance {{ $labels.instance }}).\"\n      description: \"At least one device in RAID array on {{ $labels.instance }} failed. Array {{ $labels.md_device }} needs attention and possibly a disk swap.\"\n  - alert: HostConntrackLimit\n    expr: node_nf_conntrack_entries / node_nf_conntrack_entries_limit \u003e 0.8\n    for: 5m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host conntrack limit (instance {{ $labels.instance }}).\"\n      description: \"The number of conntrack is approching limit.\"\n  - alert: HostNetworkInterfaceSaturated\n    expr: (rate(node_network_receive_bytes_total{device!~\"^tap.*\"}[1m]) + rate(node_network_transmit_bytes_total{device!~\"^tap.*\"}[1m])) / node_network_speed_bytes{device!~\"^tap.*\"} \u003e 0.8\n    for: 1m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host Network Interface Saturated (instance {{ $labels.instance }}).\"\n      description: \"The network interface {{ $labels.interface }} on {{ $labels.instance }} is getting overloaded.\"\n  - alert: HostSystemdServiceCrashed\n    expr: node_systemd_unit_state{state=\"failed\"} == 1\n    for: 0m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host SystemD service crashed (instance {{ $labels.instance }}).\"\n      description: \"SystemD service crashed.\"\n  - alert: HostEdacCorrectableErrorsDetected\n    expr: increase(node_edac_correctable_errors_total[1m]) \u003e 0\n    for: 0m\n    labels:\n      severity: info\n    annotations:\n      summary: \"Host EDAC Correctable Errors detected (instance {{ $labels.instance }}).\"\n      description: '{{ $labels.instance }} has had {{ printf \"%.0f\" $value }} correctable memory errors reported by EDAC in the last 5 minutes.'\n  - alert: HostEdacUncorrectableErrorsDetected\n    expr: node_edac_uncorrectable_errors_total \u003e 0\n    for: 0m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host EDAC Uncorrectable Errors detected (instance {{ $labels.instance }}).\"\n      description: '{{ $labels.instance }} has had {{ printf \"%.0f\" $value }} uncorrectable memory errors reported by EDAC in the last 5 minutes.'\n- name: \"Min.io\"\n  rules:\n  - alert: MinioDiskOffline\n    expr: minio_offline_disks \u003e 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Minio disk offline (instance {{ $labels.instance }})\"\n      description: \"Minio disk is offline.\"\n  - alert: MinioStorageSpaceExhausted\n    expr: minio_disk_storage_free_bytes / 1024 / 1024 / 1024 \u003c 10\n    for: 2m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Minio storage space exhausted (instance {{ $labels.instance }}).\"\n      description: \"Minio storage space is low (\u003c 10 GB).\"\n- name: \"Prometheus\"\n  rules:\n  - alert: PrometheusConfigurationReloadFailure\n    expr: prometheus_config_last_reload_successful != 1\n    for: 0m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Prometheus configuration reload failure (instance {{ $labels.instance }}).\"\n      description: \"Prometheus configuration reload error.\"\n  - alert: PrometheusTooManyRestarts\n    expr: changes(process_start_time_seconds{job=~\"prometheus|pushgateway|alertmanager\"}[15m]) \u003e 2\n    for: 0m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Prometheus too many restarts (instance {{ $labels.instance }}).\"\n      description: \"Prometheus has restarted more than twice in the last 15 minutes. It might be crashlooping.\"\n  - alert: PrometheusAlertmanagerConfigurationReloadFailure\n    expr: alertmanager_config_last_reload_successful != 1\n    for: 0m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Prometheus AlertManager configuration reload failure (instance {{ $labels.instance }}).\"\n      description: \"AlertManager configuration reload error.\"\n  - alert: PrometheusRuleEvaluationFailures\n    expr: increase(prometheus_rule_evaluation_failures_total[3m]) \u003e 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Prometheus rule evaluation failures (instance {{ $labels.instance }}).\"\n      description: \"Prometheus encountered {{ $value }} rule evaluation failures, leading to potentially ignored alerts.\"\n  - alert: PrometheusTargetScrapingSlow\n    expr: prometheus_target_interval_length_seconds{quantile=\"0.9\"} \u003e 60\n    for: 5m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Prometheus target scraping slow (instance {{ $labels.instance }}).\"\n      description: \"Prometheus is scraping exporters slowly.\"\n  - alert: PrometheusTsdbCompactionsFailed\n    expr: increase(prometheus_tsdb_compactions_failed_total[1m]) \u003e 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Prometheus TSDB compactions failed (instance {{ $labels.instance }}).\"\n      description: \"Prometheus encountered {{ $value }} TSDB compactions failures.\"\n  - alert: PrometheusTsdbHeadTruncationsFailed\n    expr: increase(prometheus_tsdb_head_truncations_failed_total[1m]) \u003e 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Prometheus TSDB head truncations failed (instance {{ $labels.instance }}).\"\n      description: \"Prometheus encountered {{ $value }} TSDB head truncation failures.\"\n  - alert: PrometheusTsdbWalCorruptions\n    expr: increase(prometheus_tsdb_wal_corruptions_total[1m]) \u003e 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Prometheus TSDB WAL corruptions (instance {{ $labels.instance }}).\"\n      description: \"Prometheus encountered {{ $value }} TSDB WAL corruptions.\"\n  - alert: PrometheusTsdbWalTruncationsFailed\n    expr: increase(prometheus_tsdb_wal_truncations_failed_total[1m]) \u003e 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Prometheus TSDB WAL truncations failed (instance {{ $labels.instance }}).\"\n      description: \"Prometheus encountered {{ $value }} TSDB WAL truncation failures.\"\nEOH\n      }\n\n      template {\n        change_mode     = \"noop\"\n        change_signal   = \"SIGINT\"\n        destination     = \"secrets/prometheus.yml\"\n        data            = \u003c\u003cEOH\n---\nglobal:\n  scrape_interval:     5s\n  scrape_timeout:      5s\n  evaluation_interval: 5s\n\nalerting:\n  alertmanagers:\n  - consul_sd_configs:\n    - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n      services: [ 'alertmanager' ]\n\nrule_files:\n  - 'alerts.yml'\n\nscrape_configs:\n\n  - job_name: 'Nomad Cluster'\n    consul_sd_configs:\n    - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n      services: [ 'nomad-client', 'nomad' ]\n    relabel_configs:\n    - source_labels: [__meta_consul_tags]\n      regex: '(.*)http(.*)'\n      action: keep\n    metrics_path: /v1/metrics\n    params:\n      format: [ 'prometheus' ]\n\n  - job_name: 'Consul Cluster'\n    static_configs:\n      - targets: [ '10.30.51.22:8500' ]\n      - targets: [ '10.30.51.24:8500' ]\n      - targets: [ '10.30.51.25:8500' ]\n      - targets: [ '10.30.51.26:8500' ]\n      - targets: [ '10.30.51.28:8500' ]\n      - targets: [ '10.30.51.29:8500' ]\n      - targets: [ '10.30.51.30:8500' ]\n      - targets: [ '10.30.51.39:8500' ]\n      - targets: [ '10.30.51.40:8500' ]\n      - targets: [ '10.30.51.50:8500' ]\n      - targets: [ '10.30.51.51:8500' ]\n      - targets: [ '10.30.51.65:8500' ]\n      - targets: [ '10.30.51.66:8500' ]\n      - targets: [ '10.30.51.67:8500' ]\n      - targets: [ '10.30.51.68:8500' ]\n      - targets: [ '10.30.51.70:8500' ]\n      - targets: [ '10.30.51.71:8500' ]\n      - targets: [ '10.32.8.14:8500' ]\n      - targets: [ '10.32.8.15:8500' ]\n      - targets: [ '10.32.8.16:8500' ]\n      - targets: [ '10.32.8.17:8500' ]\n    metrics_path: /v1/agent/metrics\n    params:\n      format: [ 'prometheus' ]\n\n  - job_name: 'Blackbox Exporter (icmp)'\n    static_configs:\n      - targets: [ 'gerrit.fd.io' ]\n      - targets: [ 'jenkins.fd.io' ]\n      - targets: [ '10.32.8.17' ]\n    params:\n      module: [ 'icmp_v4' ]\n    relabel_configs:\n      - source_labels: [__address__]\n        target_label: __param_target\n      - source_labels: [__param_target]\n        target_label: instance\n      - target_label: __address__\n        replacement: localhost:9115\n    metrics_path: /probe\n\n  - job_name: 'Blackbox Exporter (http)'\n    static_configs:\n      - targets: [ 'gerrit.fd.io' ]\n      - targets: [ 'jenkins.fd.io' ]\n    params:\n      module: [ 'http_2xx' ]\n    relabel_configs:\n      - source_labels: [__address__]\n        target_label: __param_target\n      - source_labels: [__param_target]\n        target_label: instance\n      - target_label: __address__\n        replacement: localhost:9115\n    metrics_path: /probe\n\n  - job_name: 'Jenkins Job Health Exporter'\n    static_configs:\n      - targets: [ 10.30.51.22:9186' ]\n    metric_relabel_configs:\n      - source_labels: [ __name__ ]\n        regex: '^(vpp.*|csit.*)_(success|failure|total|unstable|reqtime_ms)$'\n        action: replace\n        replacement: '$1'\n        target_label: id\n      - source_labels: [ __name__ ]\n        regex: '^(vpp.*|csit.*)_(success|failure|total|unstable|reqtime_ms)$'\n        replacement: 'jenkins_job_$2'\n        target_label: __name__\n\n  - job_name: 'Node Exporter'\n    static_configs:\n      - targets: [ '10.30.51.22:9100' ]\n      - targets: [ '10.30.51.24:9100' ]\n      - targets: [ '10.30.51.25:9100' ]\n      - targets: [ '10.30.51.26:9100' ]\n      - targets: [ '10.30.51.28:9100' ]\n      - targets: [ '10.30.51.29:9100' ]\n      - targets: [ '10.30.51.30:9100' ]\n      - targets: [ '10.30.51.39:9100' ]\n      - targets: [ '10.30.51.40:9100' ]\n      - targets: [ '10.30.51.50:9100' ]\n      - targets: [ '10.30.51.51:9100' ]\n      - targets: [ '10.30.51.65:9100' ]\n      - targets: [ '10.30.51.66:9100' ]\n      - targets: [ '10.30.51.67:9100' ]\n      - targets: [ '10.30.51.68:9100' ]\n      - targets: [ '10.30.51.70:9100' ]\n      - targets: [ '10.30.51.71:9100' ]\n      - targets: [ '10.32.8.14:9100' ]\n      - targets: [ '10.32.8.15:9100' ]\n      - targets: [ '10.32.8.16:9100' ]\n      - targets: [ '10.32.8.17:9100' ]\n\n  - job_name: 'Alertmanager'\n    consul_sd_configs:\n    - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n      services: [ 'alertmanager' ]\n\n  - job_name: 'Grafana'\n    consul_sd_configs:\n    - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n      services: [ 'grafana' ]\n\n  - job_name: 'Prometheus'\n    consul_sd_configs:\n    - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n      services: [ 'prometheus' ]\n\n  - job_name: 'Minio'\n    bearer_token: eyJhbGciOiJIUzUxMiIsInR5cCI6IkpXVCJ9.eyJleHAiOjQ3NjQ1ODEzMzcsImlzcyI6InByb21ldGhldXMiLCJzdWIiOiJtaW5pbyJ9.oeTw3EIaiFmlDikrHXWiWXMH2vxLfDLkfjEC7G2N3M_keH_xyA_l2ofLLNYtopa_3GCEZnxLQdPuFZrmgpkDWg\n    consul_sd_configs:\n    - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n      services: [ 'storage' ]\n    metrics_path: /minio/prometheus/metrics\nEOH\n      }\n\n      # The service stanza instructs Nomad to register a service with Consul.\n      #\n      # For more information and examples on the \"task\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/service\n      #\n      service {\n        name            = \"prometheus\"\n        port            = \"prometheus\"\n        tags            = [ \"prometheus${NOMAD_ALLOC_INDEX}\" ]\n        check {\n          name          = \"Prometheus Check Live\"\n          type          = \"http\"\n          path          = \"/-/healthy\"\n          interval      = \"10s\"\n          timeout       = \"2s\"\n        }\n      }\n\n      # The \"resources\" stanza describes the requirements a task needs to\n      # execute. Resource requirements include memory, network, cpu, and more.\n      # This ensures the task will execute on a machine that contains enough\n      # resource capacity.\n      #\n      # For more information and examples on the \"resources\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/resources\n      #\n      resources {\n        cpu             = 2000\n        memory          = 8192\n        # The network stanza specifies the networking requirements for the task\n        # group, including the network mode and port allocations. When scheduling\n        # jobs in Nomad they are provisioned across your fleet of machines along\n        # with other jobs and services. Because you don't know in advance what host\n        # your job will be provisioned on, Nomad will provide your tasks with\n        # network configuration when they start up.\n        #\n        # For more information and examples on the \"template\" stanza, please see\n        # the online documentation at:\n        #\n        #     https://www.nomadproject.io/docs/job-specification/network\n        #\n        network {\n          port \"prometheus\" {\n            static      = 9090\n          }\n        }\n      }\n    }\n  }\n}",
+            "jobspec": "job \"prod-prometheus\" {\n  # The \"region\" parameter specifies the region in which to execute the job.\n  # If omitted, this inherits the default region name of \"global\".\n  # region = \"global\"\n  #\n  # The \"datacenters\" parameter specifies the list of datacenters which should\n  # be considered when placing this task. This must be provided.\n  datacenters         = \"yul1\"\n\n  # The \"type\" parameter controls the type of job, which impacts the scheduler's\n  # decision on placement. This configuration is optional and defaults to\n  # \"service\". For a full list of job types and their differences, please see\n  # the online documentation.\n  #\n  # For more information, please see the online documentation at:\n  #\n  #     https://www.nomadproject.io/docs/jobspec/schedulers\n  #\n  type                = \"service\"\n\n  update {\n    # The \"max_parallel\" parameter specifies the maximum number of updates to\n    # perform in parallel. In this case, this specifies to update a single task\n    # at a time.\n    max_parallel      = 1\n\n    health_check      = \"checks\"\n\n    # The \"min_healthy_time\" parameter specifies the minimum time the allocation\n    # must be in the healthy state before it is marked as healthy and unblocks\n    # further allocations from being updated.\n    min_healthy_time  = \"10s\"\n\n    # The \"healthy_deadline\" parameter specifies the deadline in which the\n    # allocation must be marked as healthy after which the allocation is\n    # automatically transitioned to unhealthy. Transitioning to unhealthy will\n    # fail the deployment and potentially roll back the job if \"auto_revert\" is\n    # set to true.\n    healthy_deadline  = \"3m\"\n\n    # The \"progress_deadline\" parameter specifies the deadline in which an\n    # allocation must be marked as healthy. The deadline begins when the first\n    # allocation for the deployment is created and is reset whenever an allocation\n    # as part of the deployment transitions to a healthy state. If no allocation\n    # transitions to the healthy state before the progress deadline, the\n    # deployment is marked as failed.\n    progress_deadline = \"10m\"\n\n\n    # The \"canary\" parameter specifies that changes to the job that would result\n    # in destructive updates should create the specified number of canaries\n    # without stopping any previous allocations. Once the operator determines the\n    # canaries are healthy, they can be promoted which unblocks a rolling update\n    # of the remaining allocations at a rate of \"max_parallel\".\n    #\n    # Further, setting \"canary\" equal to the count of the task group allows\n    # blue/green deployments. When the job is updated, a full set of the new\n    # version is deployed and upon promotion the old version is stopped.\n    canary            = 1\n\n    # Specifies if the job should auto-promote to the canary version when all\n    # canaries become healthy during a deployment. Defaults to false which means\n    # canaries must be manually updated with the nomad deployment promote\n    # command.\n    auto_promote      = true\n\n    # The \"auto_revert\" parameter specifies if the job should auto-revert to the\n    # last stable job on deployment failure. A job is marked as stable if all the\n    # allocations as part of its deployment were marked healthy.\n    auto_revert       = true\n\n  }\n\n  # The reschedule stanza specifies the group's rescheduling strategy. If\n  # specified at the job level, the configuration will apply to all groups\n  # within the job. If the reschedule stanza is present on both the job and the\n  # group, they are merged with the group stanza taking the highest precedence\n  # and then the job.\n  reschedule {\n    delay             = \"30s\"\n    delay_function    = \"constant\"\n    unlimited         = true\n  }\n\n  # The \"group\" stanza defines a series of tasks that should be co-located on\n  # the same Nomad client. Any task within a group will be placed on the same\n  # client.\n  #\n  # For more information and examples on the \"group\" stanza, please see\n  # the online documentation at:\n  #\n  #     https://www.nomadproject.io/docs/job-specification/group\n  #\n  group \"prod-group1-prometheus\" {\n    # The \"count\" parameter specifies the number of the task groups that should\n    # be running under this group. This value must be non-negative and defaults\n    # to 1.\n    count               = 4\n\n    # The restart stanza configures a tasks's behavior on task failure. Restarts\n    # happen on the client that is running the task.\n    #\n    # https://www.nomadproject.io/docs/job-specification/restart\n    #\n    restart {\n      interval  = \"30m\"\n      attempts  = 40\n      delay     = \"15s\"\n      mode      = \"delay\"\n    }\n\n    # The volume stanza allows the group to specify that it requires a given\n    # volume from the cluster.\n    #\n    # For more information and examples on the \"volume\" stanza, please see\n    # the online documentation at:\n    #\n    #     https://www.nomadproject.io/docs/job-specification/volume\n    #\n    \n    volume \"prod-volume1-prometheus\" {\n      type              = \"host\"\n      read_only         = false\n      source            = \"prod-volume-data1-1\"\n    }\n    \n\n    # The constraint allows restricting the set of eligible nodes. Constraints\n    # may filter on attributes or client metadata.\n    #\n    # For more information and examples on the \"volume\" stanza, please see\n    # the online documentation at:\n    #\n    #     https://www.nomadproject.io/docs/job-specification/constraint\n    #\n    constraint {\n      attribute         = \"${attr.cpu.arch}\"\n      operator          = \"!=\"\n      value             = \"arm64\"\n    }\n\n    # The \"task\" stanza creates an individual unit of work, such as a Docker\n    # container, web application, or batch processing.\n    #\n    # For more information and examples on the \"task\" stanza, please see\n    # the online documentation at:\n    #\n    #     https://www.nomadproject.io/docs/job-specification/task\n    #\n    task \"prod-task1-prometheus\" {\n      # The \"driver\" parameter specifies the task driver that should be used to\n      # run the task.\n      driver            = \"exec\"\n\n      \n      volume_mount {\n        volume          = \"prod-volume1-prometheus\"\n        destination     = \"/data/\"\n        read_only       = false\n      }\n      \n\n      \n\n      # The \"config\" stanza specifies the driver configuration, which is passed\n      # directly to the driver to start the task. The details of configurations\n      # are specific to each driver, so please see specific driver\n      # documentation for more information.\n      config {\n        command         = \"local/prometheus-2.28.1.linux-amd64/prometheus\"\n        args            = [\n          \"--config.file=secrets/prometheus.yml\",\n          \"--storage.tsdb.path=/data/prometheus/\",\n          \"--storage.tsdb.retention.time=7d\"\n        ]\n      }\n\n      # The artifact stanza instructs Nomad to fetch and unpack a remote resource,\n      # such as a file, tarball, or binary. Nomad downloads artifacts using the\n      # popular go-getter library, which permits downloading artifacts from a\n      # variety of locations using a URL as the input source.\n      #\n      # For more information and examples on the \"artifact\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/artifact\n      #\n      artifact {\n        source          = \"https://github.com/prometheus/prometheus/releases/download/v2.28.1/prometheus-2.28.1.linux-amd64.tar.gz\"\n      }\n\n      # The \"template\" stanza instructs Nomad to manage a template, such as\n      # a configuration file or script. This template can optionally pull data\n      # from Consul or Vault to populate runtime configuration data.\n      #\n      # For more information and examples on the \"template\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/template\n      #\n      template {\n        change_mode     = \"noop\"\n        change_signal   = \"SIGINT\"\n        destination     = \"secrets/alerts.yml\"\n        left_delimiter  = \"{{{\"\n        right_delimiter = \"}}}\"\n        data            = \u003c\u003cEOH\n---\ngroups:\n- name: \"Jenkins Job Health Exporter\"\n  rules:\n  - alert: JenkinsJobHealthExporterFailures\n    expr: jenkins_job_failure{id=~\".*\"} \u003e jenkins_job_success{id=~\".*\"}\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Jenkins Job Health detected high failure rate on jenkins jobs.\"\n      description: \"Job: {{ $labels.id }}\"\n  - alert: JenkinsJobHealthExporterUnstable\n    expr: jenkins_job_unstable{id=~\".*\"} \u003e jenkins_job_success{id=~\".*\"}\n    for: 0m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Jenkins Job Health detected high unstable rate on jenkins jobs.\"\n      description: \"Job: {{ $labels.id }}\"\n- name: \"Consul\"\n  rules:\n  - alert: ConsulServiceHealthcheckFailed\n    expr: consul_catalog_service_node_healthy == 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Consul service healthcheck failed (instance {{ $labels.instance }}).\"\n      description: \"Service: `{{ $labels.service_name }}` Healthcheck: `{{ $labels.service_id }}`.\"\n  - alert: ConsulMissingMasterNode\n    expr: consul_raft_peers \u003c 3\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Consul missing master node (instance {{ $labels.instance }}).\"\n      description: \"Numbers of consul raft peers should be 3, in order to preserve quorum.\"\n  - alert: ConsulAgentUnhealthy\n    expr: consul_health_node_status{status=\"critical\"} == 1\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Consul agent unhealthy (instance {{ $labels.instance }}).\"\n      description: \"A Consul agent is down.\"\n- name: \"Hosts\"\n  rules:\n  - alert: NodeDown\n    expr: up == 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Prometheus target missing (instance {{ $labels.instance }}).\"\n      description: \"A Prometheus target has disappeared. An exporter might be crashed.\"\n  - alert: HostOutOfMemory\n    expr: node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes * 100 \u003c 10\n    for: 2m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host out of memory (instance {{ $labels.instance }}).\"\n      description: \"Node memory is filling up (\u003c 10% left).\"\n  - alert: HostOomKillDetected\n    expr: increase(node_vmstat_oom_kill[1m]) \u003e 0\n    for: 0m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host OOM kill detected (instance {{ $labels.instance }}).\"\n      description: \"OOM kill detected.\"\n  - alert: HostMemoryUnderMemoryPressure\n    expr: rate(node_vmstat_pgmajfault[1m]) \u003e 1000\n    for: 2m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host memory under memory pressure (instance {{ $labels.instance }}).\"\n      description: \"The node is under heavy memory pressure. High rate of major page faults.\"\n  - alert: HostOutOfDiskSpace\n    expr: (node_filesystem_avail_bytes * 100) / node_filesystem_size_bytes \u003c 10 and ON (instance, device, mountpoint) node_filesystem_readonly == 0\n    for: 2m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host out of disk space (instance {{ $labels.instance }}).\"\n      description: \"Disk is almost full (\u003c 10% left).\"\n  - alert: HostRaidDiskFailure\n    expr: node_md_disks{state=\"failed\"} \u003e 0\n    for: 2m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host RAID disk failure (instance {{ $labels.instance }}).\"\n      description: \"At least one device in RAID array on {{ $labels.instance }} failed. Array {{ $labels.md_device }} needs attention and possibly a disk swap.\"\n  - alert: HostConntrackLimit\n    expr: node_nf_conntrack_entries / node_nf_conntrack_entries_limit \u003e 0.8\n    for: 5m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host conntrack limit (instance {{ $labels.instance }}).\"\n      description: \"The number of conntrack is approching limit.\"\n  - alert: HostNetworkInterfaceSaturated\n    expr: (rate(node_network_receive_bytes_total{device!~\"^tap.*\"}[1m]) + rate(node_network_transmit_bytes_total{device!~\"^tap.*\"}[1m])) / node_network_speed_bytes{device!~\"^tap.*\"} \u003e 0.8\n    for: 1m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host Network Interface Saturated (instance {{ $labels.instance }}).\"\n      description: \"The network interface {{ $labels.interface }} on {{ $labels.instance }} is getting overloaded.\"\n  - alert: HostSystemdServiceCrashed\n    expr: node_systemd_unit_state{state=\"failed\"} == 1\n    for: 0m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host SystemD service crashed (instance {{ $labels.instance }}).\"\n      description: \"SystemD service crashed.\"\n  - alert: HostEdacCorrectableErrorsDetected\n    expr: increase(node_edac_correctable_errors_total[1m]) \u003e 0\n    for: 0m\n    labels:\n      severity: info\n    annotations:\n      summary: \"Host EDAC Correctable Errors detected (instance {{ $labels.instance }}).\"\n      description: '{{ $labels.instance }} has had {{ printf \"%.0f\" $value }} correctable memory errors reported by EDAC in the last 5 minutes.'\n  - alert: HostEdacUncorrectableErrorsDetected\n    expr: node_edac_uncorrectable_errors_total \u003e 0\n    for: 0m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Host EDAC Uncorrectable Errors detected (instance {{ $labels.instance }}).\"\n      description: '{{ $labels.instance }} has had {{ printf \"%.0f\" $value }} uncorrectable memory errors reported by EDAC in the last 5 minutes.'\n- name: \"Min.io\"\n  rules:\n  - alert: MinioDiskOffline\n    expr: minio_offline_disks \u003e 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Minio disk offline (instance {{ $labels.instance }})\"\n      description: \"Minio disk is offline.\"\n  - alert: MinioStorageSpaceExhausted\n    expr: minio_disk_storage_free_bytes / 1024 / 1024 / 1024 \u003c 10\n    for: 2m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Minio storage space exhausted (instance {{ $labels.instance }}).\"\n      description: \"Minio storage space is low (\u003c 10 GB).\"\n- name: \"Prometheus\"\n  rules:\n  - alert: PrometheusConfigurationReloadFailure\n    expr: prometheus_config_last_reload_successful != 1\n    for: 0m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Prometheus configuration reload failure (instance {{ $labels.instance }}).\"\n      description: \"Prometheus configuration reload error.\"\n  - alert: PrometheusTooManyRestarts\n    expr: changes(process_start_time_seconds{job=~\"prometheus|pushgateway|alertmanager\"}[15m]) \u003e 2\n    for: 0m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Prometheus too many restarts (instance {{ $labels.instance }}).\"\n      description: \"Prometheus has restarted more than twice in the last 15 minutes. It might be crashlooping.\"\n  - alert: PrometheusAlertmanagerConfigurationReloadFailure\n    expr: alertmanager_config_last_reload_successful != 1\n    for: 0m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Prometheus AlertManager configuration reload failure (instance {{ $labels.instance }}).\"\n      description: \"AlertManager configuration reload error.\"\n  - alert: PrometheusRuleEvaluationFailures\n    expr: increase(prometheus_rule_evaluation_failures_total[3m]) \u003e 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Prometheus rule evaluation failures (instance {{ $labels.instance }}).\"\n      description: \"Prometheus encountered {{ $value }} rule evaluation failures, leading to potentially ignored alerts.\"\n  - alert: PrometheusTargetScrapingSlow\n    expr: prometheus_target_interval_length_seconds{quantile=\"0.9\"} \u003e 60\n    for: 5m\n    labels:\n      severity: warning\n    annotations:\n      summary: \"Prometheus target scraping slow (instance {{ $labels.instance }}).\"\n      description: \"Prometheus is scraping exporters slowly.\"\n  - alert: PrometheusTsdbCompactionsFailed\n    expr: increase(prometheus_tsdb_compactions_failed_total[1m]) \u003e 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Prometheus TSDB compactions failed (instance {{ $labels.instance }}).\"\n      description: \"Prometheus encountered {{ $value }} TSDB compactions failures.\"\n  - alert: PrometheusTsdbHeadTruncationsFailed\n    expr: increase(prometheus_tsdb_head_truncations_failed_total[1m]) \u003e 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Prometheus TSDB head truncations failed (instance {{ $labels.instance }}).\"\n      description: \"Prometheus encountered {{ $value }} TSDB head truncation failures.\"\n  - alert: PrometheusTsdbWalCorruptions\n    expr: increase(prometheus_tsdb_wal_corruptions_total[1m]) \u003e 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Prometheus TSDB WAL corruptions (instance {{ $labels.instance }}).\"\n      description: \"Prometheus encountered {{ $value }} TSDB WAL corruptions.\"\n  - alert: PrometheusTsdbWalTruncationsFailed\n    expr: increase(prometheus_tsdb_wal_truncations_failed_total[1m]) \u003e 0\n    for: 0m\n    labels:\n      severity: critical\n    annotations:\n      summary: \"Prometheus TSDB WAL truncations failed (instance {{ $labels.instance }}).\"\n      description: \"Prometheus encountered {{ $value }} TSDB WAL truncation failures.\"\nEOH\n      }\n\n      template {\n        change_mode     = \"noop\"\n        change_signal   = \"SIGINT\"\n        destination     = \"secrets/prometheus.yml\"\n        data            = \u003c\u003cEOH\n---\nglobal:\n  scrape_interval:     5s\n  scrape_timeout:      5s\n  evaluation_interval: 5s\n\nalerting:\n  alertmanagers:\n  - consul_sd_configs:\n    - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n      services: [ 'alertmanager' ]\n\nrule_files:\n  - 'alerts.yml'\n\nscrape_configs:\n\n  - job_name: 'Nomad Cluster'\n    consul_sd_configs:\n    - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n      services: [ 'nomad-client', 'nomad' ]\n    relabel_configs:\n    - source_labels: [__meta_consul_tags]\n      regex: '(.*)http(.*)'\n      action: keep\n    metrics_path: /v1/metrics\n    params:\n      format: [ 'prometheus' ]\n\n  - job_name: 'Consul Cluster'\n    static_configs:\n      - targets: [ '10.30.51.22:8500' ]\n      - targets: [ '10.30.51.24:8500' ]\n      - targets: [ '10.30.51.25:8500' ]\n      - targets: [ '10.30.51.26:8500' ]\n      - targets: [ '10.30.51.28:8500' ]\n      - targets: [ '10.30.51.29:8500' ]\n      - targets: [ '10.30.51.30:8500' ]\n      - targets: [ '10.30.51.39:8500' ]\n      - targets: [ '10.30.51.40:8500' ]\n      - targets: [ '10.30.51.50:8500' ]\n      - targets: [ '10.30.51.51:8500' ]\n      - targets: [ '10.30.51.65:8500' ]\n      - targets: [ '10.30.51.66:8500' ]\n      - targets: [ '10.30.51.67:8500' ]\n      - targets: [ '10.30.51.68:8500' ]\n      - targets: [ '10.30.51.70:8500' ]\n      - targets: [ '10.30.51.71:8500' ]\n      - targets: [ '10.32.8.14:8500' ]\n      - targets: [ '10.32.8.15:8500' ]\n      - targets: [ '10.32.8.16:8500' ]\n      - targets: [ '10.32.8.17:8500' ]\n    metrics_path: /v1/agent/metrics\n    params:\n      format: [ 'prometheus' ]\n\n  - job_name: 'Blackbox Exporter (icmp)'\n    static_configs:\n      - targets: [ 'gerrit.fd.io' ]\n      - targets: [ 'jenkins.fd.io' ]\n      - targets: [ '10.32.8.17' ]\n    params:\n      module: [ 'icmp_v4' ]\n    relabel_configs:\n      - source_labels: [__address__]\n        target_label: __param_target\n      - source_labels: [__param_target]\n        target_label: instance\n      - target_label: __address__\n        replacement: localhost:9115\n    metrics_path: /probe\n\n  - job_name: 'Blackbox Exporter (http)'\n    static_configs:\n      - targets: [ 'gerrit.fd.io' ]\n      - targets: [ 'jenkins.fd.io' ]\n    params:\n      module: [ 'http_2xx' ]\n    relabel_configs:\n      - source_labels: [__address__]\n        target_label: __param_target\n      - source_labels: [__param_target]\n        target_label: instance\n      - target_label: __address__\n        replacement: localhost:9115\n    metrics_path: /probe\n\n  - job_name: 'Jenkins Job Health Exporter'\n    static_configs:\n      - targets: [ '10.30.51.22:9186' ]\n    metric_relabel_configs:\n      - source_labels: [ __name__ ]\n        regex: '^(vpp.*|csit.*)_(success|failure|total|unstable|reqtime_ms)$'\n        action: replace\n        replacement: '$1'\n        target_label: id\n      - source_labels: [ __name__ ]\n        regex: '^(vpp.*|csit.*)_(success|failure|total|unstable|reqtime_ms)$'\n        replacement: 'jenkins_job_$2'\n        target_label: __name__\n\n  - job_name: 'Node Exporter'\n    static_configs:\n      - targets: [ '10.30.51.22:9100' ]\n      - targets: [ '10.30.51.24:9100' ]\n      - targets: [ '10.30.51.25:9100' ]\n      - targets: [ '10.30.51.26:9100' ]\n      - targets: [ '10.30.51.28:9100' ]\n      - targets: [ '10.30.51.29:9100' ]\n      - targets: [ '10.30.51.30:9100' ]\n      - targets: [ '10.30.51.39:9100' ]\n      - targets: [ '10.30.51.40:9100' ]\n      - targets: [ '10.30.51.50:9100' ]\n      - targets: [ '10.30.51.51:9100' ]\n      - targets: [ '10.30.51.65:9100' ]\n      - targets: [ '10.30.51.66:9100' ]\n      - targets: [ '10.30.51.67:9100' ]\n      - targets: [ '10.30.51.68:9100' ]\n      - targets: [ '10.30.51.70:9100' ]\n      - targets: [ '10.30.51.71:9100' ]\n      - targets: [ '10.32.8.14:9100' ]\n      - targets: [ '10.32.8.15:9100' ]\n      - targets: [ '10.32.8.16:9100' ]\n      - targets: [ '10.32.8.17:9100' ]\n\n  - job_name: 'Alertmanager'\n    consul_sd_configs:\n    - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n      services: [ 'alertmanager' ]\n\n  - job_name: 'Grafana'\n    consul_sd_configs:\n    - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n      services: [ 'grafana' ]\n\n  - job_name: 'Prometheus'\n    consul_sd_configs:\n    - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n      services: [ 'prometheus' ]\n\n  - job_name: 'Minio'\n    bearer_token: eyJhbGciOiJIUzUxMiIsInR5cCI6IkpXVCJ9.eyJleHAiOjQ3NjQ1ODEzMzcsImlzcyI6InByb21ldGhldXMiLCJzdWIiOiJtaW5pbyJ9.oeTw3EIaiFmlDikrHXWiWXMH2vxLfDLkfjEC7G2N3M_keH_xyA_l2ofLLNYtopa_3GCEZnxLQdPuFZrmgpkDWg\n    consul_sd_configs:\n    - server: '{{ env \"NOMAD_IP_prometheus\" }}:8500'\n      services: [ 'storage' ]\n    metrics_path: /minio/prometheus/metrics\nEOH\n      }\n\n      # The service stanza instructs Nomad to register a service with Consul.\n      #\n      # For more information and examples on the \"task\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/service\n      #\n      service {\n        name            = \"prometheus\"\n        port            = \"prometheus\"\n        tags            = [ \"prometheus${NOMAD_ALLOC_INDEX}\" ]\n        check {\n          name          = \"Prometheus Check Live\"\n          type          = \"http\"\n          path          = \"/-/healthy\"\n          interval      = \"10s\"\n          timeout       = \"2s\"\n        }\n      }\n\n      # The \"resources\" stanza describes the requirements a task needs to\n      # execute. Resource requirements include memory, network, cpu, and more.\n      # This ensures the task will execute on a machine that contains enough\n      # resource capacity.\n      #\n      # For more information and examples on the \"resources\" stanza, please see\n      # the online documentation at:\n      #\n      #     https://www.nomadproject.io/docs/job-specification/resources\n      #\n      resources {\n        cpu             = 2000\n        memory          = 8192\n        # The network stanza specifies the networking requirements for the task\n        # group, including the network mode and port allocations. When scheduling\n        # jobs in Nomad they are provisioned across your fleet of machines along\n        # with other jobs and services. Because you don't know in advance what host\n        # your job will be provisioned on, Nomad will provide your tasks with\n        # network configuration when they start up.\n        #\n        # For more information and examples on the \"template\" stanza, please see\n        # the online documentation at:\n        #\n        #     https://www.nomadproject.io/docs/job-specification/network\n        #\n        network {\n          port \"prometheus\" {\n            static      = 9090\n          }\n        }\n      }\n    }\n  }\n}",
             "json": null,
-            "modify_index": "8995420",
+            "modify_index": "8995654",
             "name": "prod-prometheus",
             "namespace": "default",
             "policy_override": null,
diff --git a/fdio.infra.terraform/1n_nmd/vpp_device/providers.tf b/fdio.infra.terraform/1n_nmd/vpp_device/providers.tf
new file mode 100644
index 0000000000..1399201d21
--- /dev/null
+++ b/fdio.infra.terraform/1n_nmd/vpp_device/providers.tf
@@ -0,0 +1,13 @@
+terraform {
+  required_providers {
+    nomad = {
+      source  = "hashicorp/nomad"
+      version = "~> 1.4.9"
+    }
+    template = {
+      source  = "hashicorp/template"
+      version = "~> 2.1.2"
+    }
+  }
+  required_version = ">= 1.0.3"
+}
diff --git a/fdio.infra.terraform/1n_nmd/vpp_device/versions.tf b/fdio.infra.terraform/1n_nmd/vpp_device/versions.tf
deleted file mode 100644
index 960bd4bba6..0000000000
--- a/fdio.infra.terraform/1n_nmd/vpp_device/versions.tf
+++ /dev/null
@@ -1,13 +0,0 @@
-terraform {
-  required_providers {
-    nomad = {
-      source  = "hashicorp/nomad"
-      version = "~> 1.4.9"
-    }
-    template = {
-      source  = "hashicorp/template"
-      version = "~> 2.1.2"
-    }
-  }
-  required_version = ">= 0.13"
-}