Prometheus告警规则模板

templet.yml

groups:
- name: 主机状态-监控告警
  rules:
  - alert: 主机状态
    expr: up *on(instance)group_left(nodename)(node_uname_info) == 0
    for: 5m
    labels:
      level: waring
    annotations:
      summary: "{{$labels.instance}}:服务器宕机"
      description: "{{$labels.instance}}({{$labels.nodename}}):服务器延时超过3分钟"
  - alert: 主机cpu使用情况
    expr: 100-avg(irate(node_cpu_seconds_total{mode="idle"}[5m])) by(instance) *100  *on(instance)group_left(nodename)(node_uname_info) > 80
    for: 3m
    labels:
      level: waring
    annotations:
      summary: "{{ $labels.instance }}cpu使用率过高"
      description: "{{ $labels.instance }}({{$labels.nodename}}):cpu使用率超过80%(当前使用率: {{ $value }}%)"
  - alert: 主机内存使用情况
    expr: (node_memory_MemTotal_bytes - (node_memory_MemFree_bytes + node_memory_Buffers_bytes + node_memory_Cached_bytes)) / node_memory_MemTotal_bytes* 100 *on(instance)group_left(nodename)(node_uname_info) > 80
    for: 3m
    labels:
      level: waring
    annotations:
      summary: "{{$labels.instance}}: High Memory usage detected"
      description: "{{$labels.instance}}({{$labels.nodename}}): 内存使用率超过 80% (当前使用率: {{ $value }}%)"
  - alert: 主机磁盘使用情况
    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)  > 80
    for: 3m
    labels:
      level: waring
    annotations:
      summary: "{{ $labels.instance }} 磁盘空间使用率过高！"
      description: "{{ $labels.instance }}({{$labels.nodename}}): 磁盘空间使用大于80%(当前使用率: {{$value}}%)"
  - alert: 磁盘IO性能
    expr: 100-(avg(irate(node_disk_io_time_seconds_total[1m])) by(instance) *100) *on(instance)group_left(nodename)(node_uname_info)   < 60
    for: 3m
    labels:
      level: waring
    annotations:
      summary: "{{ $labels.instance }} 流入磁盘IO使用率过高！"
      description: "{{ $labels.instance }}({{$labels.nodename}}): 流入磁盘IO大于60%(当前使用率: {{$value}}%)"
  - alert: TCP会话
    expr: node_netstat_Tcp_CurrEstab *on(instance)group_left(nodename)(node_uname_info)  > 1000
    for: 3m
    labels:
      level: waring
    annotations:
      summary: "{{ $labels.instance }} TCP_ESTABLISHED过高！"
      description: "{{ $labels.instance }}({{$labels.nodename}}): TCP_ESTABLISHED大于1000%(当前使用率: {{$value}}%)"  
  - alert: inside网络
    expr: ((sum(rate (node_network_receive_bytes_total{device!~'tap.*|veth.*|br.*|docker.*|virbr*|lo*'}[5m])) by (instance)) / 100) *on(instance)group_left(nodename)(node_uname_info)   > 204800
    for: 3m
    labels:
      level: waring
    annotations:
      summary: "{{ $labels.instance }} 流入网络带宽过高！"
      description: "{{ $labels.instance }}({{$labels.nodename}}): 流入网络带宽持续2分钟高于200M(当前使用: {{$value}})"
  - alert: outside网络
    expr: ((sum(rate (node_network_transmit_bytes_total{device!~'tap.*|veth.*|br.*|docker.*|virbr*|lo*'}[5m])) by (instance)) / 100 ) *on(instance)group_left(nodename)(node_uname_info) > 204800
    for: 3m
    labels:
      level: waring
    annotations:
      summary: "{{ $labels.instance }} 流出网络带宽过高！"
      description: "{{ $labels.instance }}({{$labels.nodename}}): 流出网络带宽持续2分钟高于200M(当前使用: {{$value}})"