alert.rules

groups:
- name: Test Alerts for check_plugin
  rules:
  - alert: Watchdog
    annotations:
      message: |
        This is an alert meant to ensure that the entire alerting pipeline is functional.
        This alert is always firing.
    expr: vector(1)
    labels:
      severity: none
  - alert: PrometheusTargetMissing
    expr: up == 0
    for: 0m
    labels:
      severity: critical
      icingaState: warning
    annotations:
      summary: Prometheus target missing (instance {{ $labels.instance }})
      description: "A Prometheus target has disappeared. An exporter might be crashed.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

  - alert: PrometheusAlertmanagerJobMissing
    expr: absent(up{job="alertmanager"})
    for: 0m
    labels:
      severity: low
      icingaState: warning
    annotations:
      summary: Prometheus AlertManager job missing (instance {{ $labels.instance }})
      description: "A Prometheus AlertManager job has disappeared\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

  - alert: HostOutOfMemory
    expr: node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes * 100 < 10
    for: 2m
    labels:
      severity: warning
    annotations:
      summary: Host out of memory (instance {{ $labels.instance }})
      description: "Node memory is filling up (< 10% left)\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

  - alert: HostHighCpuLoad
    expr: 100 - (avg by(instance) (rate(node_cpu_seconds_total{mode="idle"}[2m])) * 100) > 80
    for: 0m
    labels:
      severity: extreme
    annotations:
      summary: Host high CPU load (instance {{ $labels.instance }})
      description: "CPU load is > 80%\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"