普罗米修斯监控对es集群监控常见的监控告警指标

[root@master rules]# cat conf/rules/es.yml groups: - name: es.rules rules: - alert: esclusterwrong expr: es_cluster_status != 0
    for: 5m labels: severity: critical annotations: description: "elasticsearch cluster {{$labels.server}} had primary shared not normal runningworking"

  
  - alert: esDown expr: up{job="elasticsearch"}  == 0
    for: 5m labels: severity: critical annotations: description: "elasticsearch service {{$labels.instance}} down"

  - alert: EsUnassignedTotal expr: es_cluster_shards_number{type="unassigned"}  > 0
    for: 5m labels: severity: critical annotations: description: "elasticsearch cluster {{$labels.server}} had shares lost"
  
  - alert: EsCpuUsed expr: es_os_cpu_percent > 80
    for: 5m labels: severity: warning annotations: description: "elasticsearch in {{$labels.server}}-{{$labels.node}} cpu used is above 80% current {{$value}}%"

  - alert: EsJvmHeapMemUsed expr: es_jvm_mem_heap_used_percent > 75
    for: 10m labels: severity: warnning annotations: description: "elasticsearch node {{$labels.node}} Jvm Heap mem used is above 75% current {{$value}}%"

  - alert: EsDiskUsed expr: ceil((1 - es_fs_path_available_bytes / es_fs_path_total_bytes) * 100 ) > 90
    for: 5m labels: severity: warnning annotations: description: "{{$labels.node}} elasticsearch DiskUsage Used is above 90% current {{$value}}%"


http://www.javashuo.com/article/p-bsbgbnrs-gt.html