alert.rules.yml

groups:
- name: alert.rules
  rules:
  - alert: InstanceDown
    expr: up == 0
    for: 1m
    labels:
      severity: "critical"
    annotations:
      summary: "Endpoint {{ $labels.instance }} down"
      description: "{{ $labels.instance }} of job {{ $labels.job }} has been down for more than 1 minutes."
  
  - alert: HostOutOfMemory
    expr: node_memory_MemAvailable / node_memory_MemTotal * 100 < 25
    for: 5m
    labels:
      severity: warning
    annotations:
      summary: "Host out of memory (instance {{ $labels.instance }})"
      description: "Node memory is filling up (< 25% left)\n  VALUE = {{ $value }}\n  LABELS: {{ $labels }}"


  - alert: HostOutOfDiskSpace
    expr: (node_filesystem_avail{mountpoint="/"}  * 100) / node_filesystem_size{mountpoint="/"} < 50
    for: 1s
    labels:
      severity: warning
    annotations:
      summary: "Host out of disk space (instance {{ $labels.instance }})"
      description: "Disk is almost full (< 50% left)\n  VALUE = {{ $value }}\n  LABELS: {{ $labels }}"


  - alert: HostHighCpuLoad
    expr: (sum by (instance) (irate(node_cpu{job="node_exporter_metrics",mode="idle"}[5m]))) > 80
    for: 5m
    labels:
      severity: warning
    annotations:
      summary: "Host high CPU load (instance {{ $labels.instance }})"
      description: "CPU load is > 80%\n  VALUE = {{ $value }}\n  LABELS: {{ $labels }}"