An amalgamation of NATS-related content from multiple Icinga config files

icinga-monitor-nats.conf

# ~~~~~~~~~~~~~~~~~~~~~~~~8< Your Commands File >8~~~~~~~~~~~~~~~~~~~~~~~~

object CheckCommand "nats-server" {
  import "plugin-check-command"
  command = [PluginDir+"/nats", "server", "check", "connection"]

  # If the context has been defined, outside Icinga alas, then that's the best way to just check for some context
  env.NATS_CONTEXT = "$nats_context$"
  env.NATS_URL = "$nats_url$"
  env.NATS_CREDS = "$nats_creds_file$"
  env.NATS_USER = "$nats_user$"
  env.NATS_PASSWORD = "$nats_password$"
  env.NATS_NKEY = "$nats_nkey_file$"
  env.NATS_CERT = "$nats_tls_cert_file$"
  env.NATS_KEY = "$nats_tls_key_file$"
  env.NATS_CA = "$nats_tls_ca_file$"
  env.NATS_TIMEOUT = "$nats_timeout$"  # Go duration, default 5s; this is NOT the NAGIOS warn/critical threshold

  arguments = {
    "--connect-warn" = {
      value = "$nats_connect_warn$"
      description = "Warning threshold to allow for establishing connections"
      # default (2021-06): 500ms
    }
    "--connect-critical" = {
      value = "$nats_connect_critical$"
      description = "Critical threshold to allow for establishing connections"
      # default (2021-06): 1s
    }
    "--rtt-warn" = {
      value = "$nats_rtt_warn$"
      description = "Warning threshold to allow for server RTT"
      # default (2021-06): 500ms
    }
    "--rtt-critical" = {
      value = "$nats_rtt_critical$"
      description = "Critical threshold to allow for server RTT"
      # default (2021-06): 1s
    }
    "--req-warn" = {
      value = "$nats_req_warn$"
      description = "Warning threshold to allow for full round trip test"
      # default (2021-06): 500ms
    }
    "--req-critical" = {
      value = "$nats_req_critical$"
      description = "Critical threshold to allow for full round trip test"
      # default (2021-06): 1s
    }
  }
}

object CheckCommand "nats-jetstream" {
  import "plugin-check-command"
  command = [PluginDir+"/nats", "server", "check", "js"]

  # If the context has been defined, outside Icinga alas, then that's the best way to just check for some context
  env.NATS_CONTEXT = "$nats_context$"
  env.NATS_URL = "$nats_url$"
  env.NATS_CREDS = "$nats_creds_file$"
  env.NATS_USER = "$nats_user$"
  env.NATS_PASSWORD = "$nats_password$"
  env.NATS_NKEY = "$nats_nkey_file$"
  env.NATS_CERT = "$nats_tls_cert_file$"
  env.NATS_KEY = "$nats_tls_key_file$"
  env.NATS_CA = "$nats_tls_ca_file$"
  env.NATS_TIMEOUT = "$nats_timeout$"  # Go duration, default 5s

  arguments = {
    "--js-domain" = {
      value = "$nats_js_domain$"
      description = "JetStream Domain for targetting clusters on the NATS network"
    }
  }
}

# ~~~~~~~~~~~~~~~~~~~~~~~~~8< Your rules file >8~~~~~~~~~~~~~~~~~~~~~~~~~~

apply Service "nats-healthz" {
  import "generic-service"

  assign where host.vars.nats_healthz_https

  check_command = "http"
  vars += {
    http_uri = "/healthz"
    http_port = host.vars.nats_healthz_https
    http_ssl = true
    http_sni = true
    # http_certificate value is days the cert has to still be valid for to avoid "warning"; when comma-separated, second is "critical"
    http_certificate = "10,2"
    # (nothing checks that the cert hostname matches)
    http_expect_body_regex = "\"status\"\\s*:\\s*\"ok\""
  }
}

template Service "nats-server" {
  import "generic-service"
  check_command = "nats-server"
}

template Service "nats-jetstream" {
  import "generic-service"
  check_command = "nats-jetstream"
}

apply Service "nats" {
  import "nats-server"

  assign where host.vars.nats_server == true

  vars.nats_url = host.vars.nats_url ? host.vars.nats_url : "nats://" + host.name
  vars.slack_notifications = "enabled"
}

apply Service "nats-js" {
  import "nats-jetstream"

  assign where host.vars.nats_js_enabled == true

  vars.nats_url = host.vars.nats_url ? host.vars.nats_url : "nats://" + host.name

  vars.slack_notifications = "enabled"
}

# ~~~~~~~~~~~~~~~~~~~~~~~~~8< Your checks file >8~~~~~~~~~~~~~~~~~~~~~~~~~

object Host "nats.lan" {
  import "home-host"
  address = "192.0.2.1"
  vars.nats_server = true
  vars.nats_js_enabled = true
  vars.nats_user = "icinga"
  vars.nats_password = "SSWs!HP07M1V/=u_Aeef7_.V60leHn"   # freshly generated for this gist, could use a canary :)
  vars.nats_healthz_https = 8222
  vars.slack_notifications = "enabled"
}

object HostGroup "nats-clusters" {
  display_name = "NATS Clusters"
}

object ServiceGroup "nats" {
  display_name = "NATS"
  assign where service.check_command == "nats-server"
}

object ServiceGroup "nats-js" {
  display_name = "NATS JetStream"
  assign where service.check_command == "nats-jetstream"
}

# It's good to auto-gen hosts here, so that you build from lists of known servers.

object Host "prod-foo" {
  display_name = "Foo: Production"
  groups = ["nats-clusters"]
  check_command = "dummy"
  vars.dummy_state = 0 //Up
  vars.dummy_text = "Everything OK."
  vars.pt_remote = true
  vars.nats_url = "tls://connect.example.org"
  vars.nats_context = "foo-client1"  # this would be managed outside of Icinga, however you manage contexts
  vars.pt_nats_supercluster = true
}

object HostGroup "foo-clusters-prod" {
  display_name = "Foo NATS Production Clusters"
}

object Host "foo-prod-us-east-2.aws.cloud.foo.example.org" {
  display_name = "Foo-Geo: Production: us-east-2.aws.cloud.foo.example.org"
  groups = ["foo-clusters-prod"]
  check_command = "dummy"
  check_interval = 5m
  retry_interval = 30s
  vars.dummy_state = 0 //Up
  vars.dummy_text = "Everything OK."
  vars.nats_url = "tls://us-east-2.aws.cloud.foo.example.org"
  vars.nats_context = "foo-check1"
}