Prometheus 监控之 zookeeper

groups:
- name: zookeeperStatsAlert
  rules:
  - alert: 堆积请求数过大
    expr: avg(zk_outstanding_requests) by (instance) > 10    for: 1m
    labels:      severity: critical
    annotations:
      summary: "Instance {{ $labels.instance }} "
      description: "积请求数过大"
  - alert: 阻塞中的 sync 过多
    expr: avg(zk_pending_syncs) by (instance) > 10
    for: 1m
    labels:
      severity: critical
    annotations:
      summary: "Instance {{ $labels.instance }} "
      description: "塞中的 sync 过多"
  - alert: 平均响应延迟过高
    expr: avg(zk_avg_latency) by (instance) > 10
    for: 1m
    labels:
      severity: critical
    annotations:
      summary: "Instance {{ $labels.instance }} "
      description: ‘平均响应延迟过高‘
  - alert: 打开文件描述符数大于系统设定的大小
    expr: zk_open_file_descriptor_count > zk_max_file_descriptor_count * 0.85
    for: 1m
    labels:
      severity: critical
    annotations:
      summary: "Instance {{ $labels.instance }} "
      description: ‘打开文件描述符数大于系统设定的大小‘
  - alert: zookeeper服务器宕机
    expr: zk_up == 0
    for: 1m
    labels:
      severity: critical
    annotations:
      summary: "Instance {{ $labels.instance }} "
      description: ‘zookeeper服务器宕机‘
  - alert: zk主节点丢失
    expr: absent(zk_server_state{state="leader"})  != 1
    for: 1m
    labels:
      severity: critical
    annotations:
      summary: "Instance {{ $labels.instance }} "
      description: ‘zk主节点丢失‘