prometheus linux系統告警規則 實例

#prometheus linux系統告警規則 實例

根據實際情況修改參數

 #rules.linux.yml
groups:
- name: linux
  rules:
  - alert: Node-Down #告警名稱
    expr: up == 0
    for: 1m #持續多久后發送
    labels:
      severity: warning
    annotations: #信息
      summary: "Node has been down"
      description: "has been down "

  - alert: "內存使用率過高"
    expr: round(100- node_memory_MemAvailable_bytes/node_memory_MemTotal_bytes*100) > 80
    for: 1m
    labels:
      severity: warning
    annotations:
      summary: "內存使用率過高"
      description: "當前使用率{{ $value }}%"

  - alert: "CPU使用率過高"
    expr: round(100 - ((avg by (instance,job)(irate(node_cpu_seconds_total{mode="idle",instance!~'bac-.*'}[5m]))) *100)) > 80
    for: 2m
    labels:
      severity: warning
    annotations:
      summary: "CPU使用率過高"
      description: "當前使用率{{ $value }}%"

  - alert: "磁盤使用率過高"
    expr: round(100-100*(node_filesystem_avail_bytes{fstype=~"ext4|xfs"} / node_filesystem_size_bytes{fstype=~"ext4|xfs"})) > 80
    for: 15s
    labels:
      severity: warning
    annotations:
      summary: "磁盤使用率過高"
      description: "當前磁盤{{$labels.mountpoint}} 使用率{{ $value }}%"

  - alert: "分區容量過低"
    expr: round(node_filesystem_avail_bytes{fstype=~"ext4|xfs",instance!~"testnode",mountpoint!~"/boot.*"}/1024/1024/1024) < 10
    for: 15s
    labels:
      severity: warning
    annotations:
      summary: "分區容量過低"
      description: "當前分區{{$labels.mountpoint}} 容量{{ $value }}GB"

  - alert: "網絡流出速率過高"
    expr: round(irate(node_network_receive_bytes_total{instance!~"data.*",device!~'tap.*|veth.*|br.*|docker.*|vir.*|lo.*|vnet.*'}[1m])/1024) > 2048
    for: 1m
    labels:
      severity: warning
    annotations:
      summary: "網絡流出速率過高"
      description: "當前速率{{ $value }}KB/s"