prometheus自定义监控项的报警规则

- name: basic-and-important
    rules:
    - alert: NodeCPUUsage
      annotations:
        description: ‘{{ $labels.instance }} CPU usage is above 80% (current value is {{ $value }})‘ 
      expr: 100 - (avg by (instance) (irate(node_cpu_seconds_total{job="node-exporter",mode="idle"}[5m])) * 100) > 80
      for: 10m
      labels:
        severity: critical
      annotations:
        description: ‘{{$labels.instance}} CPU usage is above 80% (current value is {{ $value }})‘
    - alert: NodeMEMUsage
      expr: ((1 - (node_memory_MemAvailable_bytes{job="node-exporter"} / (node_memory_MemTotal_bytes{job="node-exporter"}))) * 100) > 80
      for: 10m
      labels:
        severity: critical
      annotations:
        description: ‘{{$labels.instance}} MEM usage is above 80% (current value is {{ $value }})‘
    - alert: NodeDiskUsage
      expr: (1-(node_filesystem_free_bytes{job="node-exporter",fstype=~"ext4|xfs"} / node_filesystem_size_bytes{job="node-exporter",fstype=~"ext4|xfs"}))*100 > 80
      for: 10m
      labels:
        severity: critical
      annotations:
        description: ‘{{$labels.instance}} Disk usage is above 80% (current value is {{ $value }})‘
    - alert: API response time per min
      expr: increase(http_server_requests_seconds_sum{uri!="/actuator/health"}[1m])/increase(http_server_requests_seconds_count{uri!="/actuator/health"}[1m])>2
      for: 1m 
      labels:
        severity: critical
      annotations:
        description: ‘{{$labels.job}} {{$labels.url}}  response time more than 2s. current value is {{ $value }}‘
    - alert: Count of API request times per min
      expr: increase(http_server_requests_seconds_count{uri!="/actuator/health",uri!="/actuator/prometheus",status!="200"}[1m])>1
      for: 1m
      labels:
        severity: critical
      annotations:
        description: ‘{{$labels.job}} {{$labels.url}}  request error times is {{ $value }} in recent one min‘
  - name: rabbitmq-monitoring
    rules:
    - alert: rabbitmq_queue_messages
      expr: rabbitmq_queue_messages{queue!~".*_DL"} > 10
      for: 5m
      labels:
        severity: critical
      annotations:
        description: ‘queue name:{{$labels.queue}} is blocked. current count is {{ $value }}‘
    - alert: rabbitmq_consumer_error_total
      expr: increase(rabbitmq_consumer_error_total[1m]) > 10
      for: 1m
      labels:
        severity: critical
      annotations:
        description: ‘service name:{{$labels.job}} cannot consume the queues. current count is {{ $value }}‘
    - alert: rabbitmq_connection_recovery_total
      expr: increase(rabbitmq_connection_recovery_total[1m]) > 10
      for: 1m
      labels:
        severity: critical
      annotations:
        description: ‘service name:{{$labels.job}} connection recovery total is {{ $value }}‘