alert_rules.yml

groups:
- name: targets
  rules:
  - alert: monitor_service_down
    expr: up == 0
    for: 30s
    labels:
      severity: critical
    annotations:
      summary: "Monitor service non-operational"
      description: "Service {{ $labels.job }} is down."

- name: host
  rules:
  - alert: high_memory_load
    expr: (sum(node_memory_MemTotal_bytes) - sum(node_memory_MemFree_bytes + node_memory_Buffers_bytes + node_memory_Cached_bytes) ) / sum(node_memory_MemTotal_bytes) * 100 > 85
    for: 30s
    labels:
      severity: warning
    annotations:
      summary: "Server memory is almost full"
      description: "Docker host memory usage is {{ humanize $value}}%. Reported by instance {{ $labels.instance }} of job {{ $labels.job }}."


- name: host_2
  rules:
  - alert: high_memory_load
    expr: (sum(node_memory_MemTotal_bytes) - sum(node_memory_MemFree_bytes + node_memory_Buffers_bytes + node_memory_Cached_bytes) ) / sum(node_memory_MemTotal_bytes) * 100 > 90
    for: 30s
    labels:
      severity: critical
    annotations:
      summary: "Server memory is almost full"
      description: "Docker host memory usage is {{ humanize $value}}%. Reported by instance {{ $labels.instance }} of job {{ $labels.job }}."