groups:

• name: 服务器告警
  rules:
  • alert: 服务器宕机告警
    expr: up == 0
    for: 3m
    annotations:
    summary: "Alerting {{$labels.instance}}宕机！"
    description: "环境{{$labels.job}} 服务器{{$labels.instance}}已宕机！"
  • alert: cpu使用率过高告警
    expr: (100 - (avg(irate(node_cpu_seconds_total{mode="idle"}[5m])) by(instance)* 100))* on(instance) group_left(nodename) (node_uname_info) > 85
    for: 5m
    annotations:
    summary: "Alerting环境{{$labels.job}} {{$labels.instance}}（{{$labels.nodename}}）CPU使用率过高！"
    description: '服务器{{$labels.instance}}（{{$labels.nodename}}）CPU使用率超过85%(目前使用:{{printf "%.2f" $value}}%)'
  • alert: 系统负载过高
    expr: (node_load1/count without (cpu, mode) (node_cpu_seconds_total{mode="system"}))* on(instance) group_left(nodename) (node_uname_info)>4
    for: 3m
    annotations:
    summary: "Alerting环境{{$labels.job}} {{$labels.instance}}（{{$labels.nodename}}）系统负载过高！"
    description: '{{$labels.instance}}（{{$labels.nodename}}）当前负载超标率 {{printf "%.2f" $value}}'
  • alert: 内存不足告警
    expr: (100 - node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes * 100)* on(instance) group_left(nodename) (node_uname_info) > 88
    for: 3m
    annotations:
    summary: "Alerting环境{{$labels.job}} {{$labels.instance}}（{{$labels.nodename}}）内存使用率过高！"
    description: '服务器{{$labels.instance}}（{{$labels.nodename}}）内存使用率超过80%(目前使用:{{printf "%.2f" $value}}%)'
  • alert: 硬盘空间不足告警
    expr: (100-(node_filesystem_free_bytes{fstype=~"ext4|xfs"}/node_filesystem_size_bytes {fstype=~"ext4|xfs"}100) ) on(instance) group_left(nodename) (node_uname_info)> 85
    for: 3m
    annotations:
    summary: "Alerting环境{{$labels.job}} {{$labels.instance}}（{{$labels.nodename}}）硬盘使用率过高！"
    description: '服务器{{$labels.instance}}（{{$labels.nodename}}）硬盘使用率超过80%(目前使用:{{printf "%.2f" $value}}%)'
  • alert: TCP连接数

    expr: node_netstat_Tcp_CurrEstab > 1000

    expr: (node_netstat_Tcp_CurrEstab)* on(instance) group_left(nodename) (node_uname_info) > 1000
    for: 2m
    annotations:
    summary: "Alerting环境{{$labels.job}} {{$labels.instance}} TCP ESTABLISHED连接数过高!"
    description: "{{$labels.instanceJ}} TCP_ESTABLISHED当前连接数{[ $value }"
    groups:
• name: Docker pod
  rules:
  • alert: DockerInstanceDown
    expr: container_last_seen{image!="",id!=""} == 0
    for: 1m
    annotations:
    description: '{{ $value.name }} {{ $labels.nodename }} of job {{ $labels.job }} has been down for more than 5 s.'
    summary: 'Instance {{ $labels.instance }} down'