prometheus2 alertmanager rules demo

groups:

• name: targets
  rules:

  • alert: EndpointDown
    expr: probe_success == 0
    for: 10s
    labels:
    severity: "critical"
    annotations:
    summary: "Endpoint {{ $labels.instance }} down"

• name: host-cpu
  rules:

  • alert: high_cpu_load
    expr: node_load1 > 1.5
    for: 30s
    labels:
    severity: warning
    annotations:
    summary: "Server under high load"
    description: "Docker host is under high load, the avg load 1m is at {{ labels.instance }} of job {{ $labels.job }}."

  • 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 labels.instance }} of job {{ $labels.job }}."

  • alert: high_storage_load
    expr: (node_filesystem_size_bytes{fstype="aufs"} - node_filesystem_free_bytes{fstype="aufs"}) / node_filesystem_size_bytes{fstype="aufs"} * 100 > 85
    for: 30s
    labels:
    severity: warning
    annotations:
    summary: "Server storage is almost full"
    description: "Docker host storage usage is {{ humanize labels.instance }} of job {{ $labels.job }}."