groups:
- name: prometheus
  rules:

  # Alert for any instance that is unreachable for >5 minutes.
  - alert: prometheus/instance-down
    expr: up == 0
    for: 5m
    labels:
      severity: page
    annotations:
      summary: "Instance {{ $labels.instance }} down"
      description: "{{ $labels.instance }} of job {{ $labels.job }} has been down for more than 5 minutes."

  - alert: prometheus/config-failed
    expr: prometheus_config_last_reload_successful == 0
    for: 0m
    labels:
      severity: page
    annotations:
      summary: "Prometheus config reload in pod {{ $labels.kubernetes_pod_name }} has failed"
      description: "Prometheus instance {{ $labels.kubernetes_pod_name }} (`{{ $labels.instance }}`) has failed to reload its config."