awesome-prometheus-alerts/dist/rules/nats/nats-exporter.yml

groups:

- name: NatsExporter

  
  rules:

    - alert: NatsHighRoutesCount
      expr: 'gnatsd_varz_routes > 10'
      for: 3m
      labels:
        severity: warning
      annotations:
        summary: Nats high routes count (instance {{ $labels.instance }})
        description: "High number of NATS routes ({{ $value }}) for {{ $labels.instance }}\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

    - alert: NatsHighMemoryUsage
      expr: 'gnatsd_varz_mem > 200 * 1024 * 1024'
      for: 5m
      labels:
        severity: warning
      annotations:
        summary: Nats high memory usage (instance {{ $labels.instance }})
        description: "NATS server memory usage is above 200MB for {{ $labels.instance }}\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

    - alert: NatsSlowConsumers
      expr: 'gnatsd_varz_slow_consumers > 0'
      for: 3m
      labels:
        severity: critical
      annotations:
        summary: Nats slow consumers (instance {{ $labels.instance }})
        description: "There are slow consumers in NATS for {{ $labels.instance }}\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

    - alert: NatsServerDown
      expr: 'absent(up{job="nats"})'
      for: 5m
      labels:
        severity: critical
      annotations:
        summary: Nats server down (instance {{ $labels.instance }})
        description: "NATS server has been down for more than 5 minutes\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

    # gnatsd_varz_cpu is a gauge reporting CPU percentage (0-100 scale).
    - alert: NatsHighCpuUsage
      expr: 'gnatsd_varz_cpu > 80'
      for: 5m
      labels:
        severity: warning
      annotations:
        summary: Nats high CPU usage (instance {{ $labels.instance }})
        description: "NATS server is using more than 80% CPU for the last 5 minutes\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

    - alert: NatsHighNumberOfConnections
      expr: 'gnatsd_connz_num_connections > 1000'
      for: 5m
      labels:
        severity: warning
      annotations:
        summary: Nats high number of connections (instance {{ $labels.instance }})
        description: "NATS server has more than 1000 active connections\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

    - alert: NatsHighJetstreamStoreUsage
      expr: 'gnatsd_varz_jetstream_stats_storage / gnatsd_varz_jetstream_config_max_storage > 0.8 and gnatsd_varz_jetstream_config_max_storage > 0'
      for: 5m
      labels:
        severity: warning
      annotations:
        summary: Nats high JetStream store usage (instance {{ $labels.instance }})
        description: "JetStream store usage is over 80%\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

    - alert: NatsHighJetstreamMemoryUsage
      expr: 'gnatsd_varz_jetstream_stats_memory / gnatsd_varz_jetstream_config_max_memory > 0.8 and gnatsd_varz_jetstream_config_max_memory > 0'
      for: 5m
      labels:
        severity: warning
      annotations:
        summary: Nats high JetStream memory usage (instance {{ $labels.instance }})
        description: "JetStream memory usage is over 80%\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

    - alert: NatsHighNumberOfSubscriptions
      expr: 'gnatsd_connz_subscriptions > 1000'
      for: 5m
      labels:
        severity: warning
      annotations:
        summary: Nats high number of subscriptions (instance {{ $labels.instance }})
        description: "NATS server has more than 1000 active subscriptions\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

    - alert: NatsHighPendingBytes
      expr: 'gnatsd_connz_pending_bytes > 100000'
      for: 5m
      labels:
        severity: warning
      annotations:
        summary: Nats high pending bytes (instance {{ $labels.instance }})
        description: "NATS server has more than 100,000 pending bytes\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

    - alert: NatsTooManyErrors
      expr: 'increase(gnatsd_varz_jetstream_stats_api_errors[5m]) > 0'
      for: 5m
      labels:
        severity: warning
      annotations:
        summary: Nats too many errors (instance {{ $labels.instance }})
        description: "NATS server has encountered errors in the last 5 minutes\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

    - alert: NatsJetstreamAccountsExceeded
      expr: 'sum(gnatsd_varz_jetstream_stats_accounts) > 100'
      for: 5m
      labels:
        severity: warning
      annotations:
        summary: Nats JetStream accounts exceeded (instance {{ $labels.instance }})
        description: "JetStream has more than 100 active accounts\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

    - alert: NatsLeafNodeConnectionIssue
      expr: 'gnatsd_varz_leafnodes == 0'
      for: 5m
      labels:
        severity: warning
      annotations:
        summary: Nats leaf node connection issue (instance {{ $labels.instance }})
        description: "No leaf node connections on {{ $labels.instance }}\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"