1. - name: IOPS告警
    2.   rules:
    3.   - alert: 系统磁盘读IOPS告警
    4.     expr: irate(node_disk_reads_completed_total{group="linux",device="vda"}[1m]) > 400
    5.     for: 1s
    6.     annotations:
    7.       summary: "{{ $labels.name }}: 系统磁盘读IOPS告警"
    8.       description: "{{ $labels.instance }},系统磁盘读IOPS大于400 当前值为: {{ $value }}"
    9.     labels:
    10.       severity: warning
    12. - name: IO使用率过高
    13.   rules:
    14.   - alert: IO性能
    15.     expr: 100-(avg(irate(node_disk_io_time_seconds_total[1m])) by(instance)* 100) < 60
    16.     for: 1s
    17.     annotations:
    18.       summary: "{{ $labels.name }}: 流入磁盘IO使用率过高！"
    19.       description: "{{ $labels.instance }},流入磁盘IO大于60% 当前值为: {{ $value }}"
    20.     labels:
    21.       severity: warning
    23. - name: 负载使用率告警
    24.   rules:
    25.   - alert: "node_cpu"
    26.     expr: ceil(sum(node_load5 ) by (instance) / count(count(node_cpu_seconds_total) by(cpu,instance)) by (instance)*100) >150
    27.     for: 1s
    28.     annotations:
    29.       summary: "负载使用过高"
    30.       description: "{{$labels.instance}}在5分钟平均负载超过100,当前负载率为{{ printf \"%.0f\" $value }}%"
    31.       value: "{{ $value }}"
    32.     labels:
    33.       severity: warning
    35. - name: TCP会话告警
    36.   rules:
    37.   - alert: TCP会话
    38.     expr: node_netstat_Tcp_CurrEstab > 1000
    39.     for: 1s
    40.     annotations:
    41.       summary: "TCP_ESTABLISHED过高！"
    42.       description: "{{ $labels.instance }},TCP_ESTABLISHED大于1000%(目前使用:{{$value}}%)"
    43.     labels:
    44.       severity: warning
    46. - name: Mysql_High_QPS告警
    47.   rules:
    48.   - alert: Mysql_High_QPS
    49.     expr: rate(mysql_global_status_questions[5m]) > 500 
    50.     for: 2m
    51.     labels:
    52.       severity: warning
    53.     annotations:
    54.       summary: "{{$labels.name}}: Mysql_High_QPS 检测"
    55.       description: "{{$labels.instance}}: Mysql操作速度超过每秒500次 ,(当前值: {{ $value }})"
    57. - name: SQL 线程告警
    58.   rules:
    59.   - alert: SQL thread stopped
    60.     expr: mysql_slave_status_slave_sql_running != 1
    61.     for: 1m
    62.     labels:
    63.       severity: warning
    64.     annotations:
    65.       summary: "Instance {{ $labels.instance }} SQL 线程已停止"
    66.       description: " This is usually because it cannot apply a SQL statement received from the master."
    68. - name: mysql连接数告警
    69.   rules:
    70.   - alert: Mysql_Too_Many_Connections
    71.     expr: rate(mysql_global_status_threads_connected[5m]) > 200
    72.     for: 2m
    73.     labels:
    74.       severity: warning
    75.     annotations:
    76.       summary: "{{$labels.instance}}: 检测到Mysql连接太多"
    77.       description: "{{$labels.instance}}: Mysql Connections is more than 200 per second ,(current value is: {{ $value }})"
    79. - name: ES集群状态告警
    80.   rules: 
    81.   - alert: ES集群状态
    82.     expr: elasticsearch_cluster_health_status{color="green",group="es"} != 1
    83.     for: 1s
    84.     annotations:
    85.       summary: "{{ $labels.name }}:分片异常"
    86.       description: "{{ $labels.instance }},主分片和副本分片异常 (目前使用:{{$value}})"
    87.     labels:
    88.       severity: warning
    90. - name: ES副本告警
    91.   rules: 
    92.   - alert: ES副本分片丢失
    93.     expr: elasticsearch_cluster_health_unassigned_shards{group="es"} != 0
    94.     for: 1s
    95.     annotations:
    96.       summary: "{{ $labels.name }}:ES副本分片丢失"
    97.       description: "{{ $labels.instance }},当前节点正在迁移到其他节点的分片数量，通常为0，集群中有节点新加入或者退出时该值会增加 (目前使用:{{$value}})"
    98.     labels:
    99.       severity: warning
    101. - name: ES CPU使用率告警
    102.   rules: 
    103.   - alert: ES CPU使用率
    104.     expr: elasticsearch_process_cpu_percent{group="es"} > 50
    105.     for: 1s
    106.     annotations:
    107.       summary: "{{ $labels.name }}:ES CPU使用率异常"
    108.       description: "{{ $labels.instance }},ES CPU使用率大于百分之50% (目前使用:{{$value}})"
    109.     labels:
    110.       severity: warning