Prometheus常用告警规则rules.yml

Posted 2023-02-23

拓扑

1、服务器告警规则 node_exporter_rules.yml

2、Radis服务告警规则 redis_exporter_rules.yml

3、RabbitMQ服务告警规则 rabbitmq_exporter_rules.yml

4、kafka集群服务告警规则 kafka_exporter_rules.yml

5、域名SSL证书过期监控规则 kafka_exporter_rules.yml

6、Elasticsearch集群告警规则 Elasticsearch_exporter_rules.yml

具体规则如下

1、服务器告警规则 node_exporter_rules.yml

[root@grafana rules]# cat node_exporter_rules.yml 
# 服务器资源告警策略
groups:
- name: 服务器资源监控
  rules:
  - alert: 内存使用率过高
    expr: (node_memory_Buffers_bytes+node_memory_Cached_bytes+node_memory_MemFree_bytes)/node_memory_MemTotal_bytes*100 > 90 
    for: 5m  # 告警持续时间，超过这个时间才会发送给alertmanager
    labels:
      severity: 严重告警
    annotations:
      summary: " $labels.instance  内存使用率过高，请尽快处理！"
      description: " $labels.instance 内存使用率超过90%,当前使用率 $value %."
          
  - alert: 服务器宕机
    expr: up == 0
    for: 3m
    labels:
      severity: 严重告警
    annotations:
      summary: "$labels.instance 服务器宕机，请尽快处理！"
      description: "$labels.instance 服务器延时超过3分钟，当前状态 $value . "
 
  - alert: CPU高负荷
    expr: 100 - (avg by (instance,job)(irate(node_cpu_seconds_totalmode="idle"[5m])) * 100) > 90
    for: 5m
    labels:
      severity: 严重告警
    annotations:
      summary: "$labels.instance CPU使用率过高，请尽快处理！"
      description: "$labels.instance CPU使用大于90%，当前使用率 $value %. "
      
  - alert: 磁盘IO性能
    expr: avg(irate(node_disk_io_time_seconds_total[1m])) by(instance,job)* 100 > 90
    for: 5m
    labels:
      severity: 严重告警
    annotations:
      summary: "$labels.instance 流入磁盘IO使用率过高，请尽快处理！"
      description: "$labels.instance 流入磁盘IO大于90%,当前使用率 $value %."
 
 
  - alert: 网络流入
    expr: ((sum(rate (node_network_receive_bytes_totaldevice!~tap.*|veth.*|br.*|docker.*|virbr*|lo*[5m])) by (instance,job)) / 100) > 102400
    for: 5m
    labels:
      severity: 严重告警
    annotations:
      summary: "$labels.instance 流入网络带宽过高，请尽快处理！"
      description: "$labels.instance 流入网络带宽持续5分钟高于100M. RX带宽使用量$value."
 
  - alert: 网络流出
    expr: ((sum(rate (node_network_transmit_bytes_totaldevice!~tap.*|veth.*|br.*|docker.*|virbr*|lo*[5m])) by (instance,job)) / 100) > 102400
    for: 5m
    labels:
      severity: 严重告警
    annotations:
      summary: "$labels.instance 流出网络带宽过高,请尽快处理！"
      description: "$labels.instance 流出网络带宽持续5分钟高于100M. RX带宽使用量$value."
  
  - alert: TCP连接数
    expr: node_netstat_Tcp_CurrEstab > 10000
    for: 2m
    labels:
      severity: 严重告警
    annotations:
      summary: " TCP_ESTABLISHED过高！"
      description: "$labels.instance TCP_ESTABLISHED大于100%,当前使用率 $value %."
 
  - alert: 磁盘容量
    expr: 100-(node_filesystem_free_bytesfstype=~"ext4|xfs"/node_filesystem_size_bytes fstype=~"ext4|xfs"*100) > 90
    for: 1m
    labels:
      severity: 严重告警
    annotations:
      summary: "$labels.mountpoint 磁盘分区使用率过高，请尽快处理！"
      description: "$labels.instance 磁盘分区使用大于90%，当前使用率 $value %."

2、Radis服务告警规则 redis_exporter_rules.yml

[root@grafana rules]# cat redis_exporter_rules.yml 
# Redis服务监控
groups:
- name: Redis服务监控
  rules:
  - alert: Redis服务停止
    expr: redis_up == 0
    for: 1m
    labels:
      severity: 严重告警
    annotations:
      summary: "  $labels.alias  Redis服务已停止，当前状态 $value "
      description: "$labels.instance:Redis 服务停止运行 "
 
  - alert: Redis连接数超过最大
    expr: redis_connected_clients / redis_config_maxclients * 100 > 80
    for: 1m
    labels:
      severity: 严重告警
    annotations:
      summary: "  $labels.alias "
      description: " $labels.instance:Redis连接数超过最大连接数的80%.当前连接数 $value "

3.RabbitMQ服务告警规则 rabbitmq_exporter_rules.yml

[root@grafana rules]# cat rabbitmq_exporter_rules.yml
# RabbitMQ服务监控
groups:
- name: RabbitMQ服务监控
  rules:
  - alert: RabbitMQ服务停止
    expr: rabbitmq_up ==0
    for: 3m
    labels:
      severity: 严重告警
    annotations:
      description: "$labels.instanceRabbitMQ服务已停止，当前状态 $value "
      summary:  "RabbitMQ服务已停止3分钟，请尽快处理！"
    
  - alert: RabbitMQ内存使用大于2G
    expr: rabbitmq_node_mem_used/1024/1024 > 2048
    for: 3m
    labels:
      severity: 严重告警
    annotations:
      description: " $labels.instance  RabbitMQ内存使占用过高 !"
      value:  $value  MB
      summary:  "RabbitMQ内存使占用大于2G"

4.kafka集群警告

[root@grafana rules]# cat kafka_exporter_rules.yml
# kafka集群服务监控
groups:
- name: kafka服务监控
  rules:
  - alert: kafka消费滞后
    expr: sum(kafka_consumergroup_lagtopic!="sop_free_study_fix-student_wechat_detail") by (consumergroup, topic, job) > 50000
    for: 3m
    labels:
      severity: 严重告警
    annotations:
      summary: "$labels.instance kafka消费滞后($.Labels.consumergroup)"
      description: "$.Labels.topic消费滞后超过5万持续3分钟(当前$value)"
 
  - alert: kafka集群节点减少
    expr: kafka_brokers < 3   #kafka集群节点数3
    for: 3m
    labels:
      severity: 严重告警
    annotations:
      summary: "kafka集群部分节点已停止，请尽快处理！"
      description: "$labels.instance kafka集群节点减少"
 
  - alert: emqx_rule_to_kafka最近五分钟内的每秒平均变化率为0
    expr: sum(rate(kafka_topic_partition_current_offsettopic="emqx_rule_to_kafka"[5m])) by ( instance,topic,job) ==0
    for: 5m
    labels:
      severity: 严重告警
    annotations:
      summary: "$labels.instance emqx_rule_to_kafka未接收到消息"
      description: "$.Labels.topicemqx_rule_to_kafka持续5分钟未接收到消息(当前$value)"

5、域名SSL证书过期监控规则 kafka_exporter_rules.yml

[root@grafana rules]# cat ssl_expiry.yml
groups: 
  - name: SSL证书监测
    rules:
    - alert: 证书还有30天过期
      expr: probe_ssl_earliest_cert_expiry - time() < 86400 * 300
      for: 5m
      labels:
        severity: 重要告警
      annotations:
        summary: "SSL证书即将过期 (instance  $labels.instance )"
        description: "SSL证书即将30天内过期 VALUE =  $value \\n  LABELS:  $labels "
        
    - alert: 证书已过期
      expr: probe_ssl_earliest_cert_expiry - time()  <= 0
      for: 5m
      labels:
        severity: 严重告警
      annotations:
        summary: "SSL证书已经过期 (instance  $labels.instance )"
        description: "SSL证书已经过期\\n  VALUE =  $value \\n  LABELS:  $labels "

6、Elasticsearch集群告警规则 Elasticsearch_exporter_rules.yml

[root@grafana rules]# cat elasticsearch_exporter_rules.yml
groups:
   - name: ElasticSearch服务监控
     rules:
     - alert: ES集群节点减少
       expr: elasticsearch_cluster_health_number_of_nodes < 3  #ES集群节点数3
       for: 5m
       labels:
         severity: 严重告警
       annotations:
         summary: "ES集群节点减少:$.Labels.job"
         description: "ES集群节点数减少:$.Labels.job,(当前:$value)"
    
     - alert: jvm内存使用率告警
       expr: elasticsearch_jvm_memory_used_bytesarea="heap" / elasticsearch_jvm_memory_max_bytesarea="heap"*100 > 90
       for: 5m
       labels:
         severity: 严重告警
       annotations:
         summary: "jvm内存使用率过高:$.Labels.job"
         description: "jvm内存使用率过高:$.Labels.job大于90%,(当前:$value)"