1. groups:
    2. - name: example
    3.   rules:
    5.   - alert: "实例丢失"
    6.     expr: up{job="node-exporter"} == 0
    7.     for: 1m
    8.     labels:
    9.       severity: page
    10.     annotations:
    11.       summary: "服务器实例 {{ $labels.instance }} 丢失"
    12.       description: "{{ $labels.instance }} 上的任务 {{ $labels.job }} 已经停止了 1 分钟已上了"
    14.   - alert: "磁盘容量小于 5%"
    15.     expr: 100 - ((node_filesystem_avail_bytes{job="node-exporter",mountpoint=~".*",fstype=~"ext4|xfs|ext2|ext3"} * 100) / node_filesystem_size_bytes {job="node-exporter",mountpoint=~".*",fstype=~"ext4|xfs|ext2|ext3"}) > 95
    16.     for: 30s
    17.     annotations:
    18.       summary: "服务器实例 {{ $labels.instance }} 磁盘不足 告警通知"
    19.       description: "{{ $labels.instance }}磁盘 {{ $labels.device }} 资源 已不足 5%, 当前值: {{ $value }}"
    21.   - alert: "内存容量小于 20%"
    22.     expr: ((node_memory_MemTotal_bytes - node_memory_MemFree_bytes - node_memory_Buffers_bytes - node_memory_Cached_bytes) / (node_memory_MemTotal_bytes )) * 100 > 80
    23.     for: 30s
    24.     labels:
    25.       severity: warning
    26.     annotations:
    27.       summary: "服务器实例 {{ $labels.instance }} 内存不足 告警通知"
    28.       description: "{{ $labels.instance }}内存资源已不足 20%,当前值: {{ $value }}"
    30.   - alert: "CPU 平均负载大于 4 个"
    31.     expr: node_load5 > 4
    32.     for: 30s
    33.     annotations:
    34.       sumary: "服务器实例 {{ $labels.instance }} CPU 负载 告警通知"
    35.       description: "{{ $labels.instance }}CPU 平均负载(5 分钟) 已超过 4 ,当前值: {{ $value }}"
    37.   - alert: "磁盘读 I/O 超过 30MB/s"
    38.     expr: irate(node_disk_read_bytes_total{device="sda"}[1m]) > 30000000
    39.     for: 30s
    40.     annotations:
    41.       sumary: "服务器实例 {{ $labels.instance }} I/O 读负载 告警通知"
    42.       description: "{{ $labels.instance }}I/O 每分钟读已超过 30MB/s,当前值: {{ $value }}"
    44.   - alert: "磁盘写 I/O 超过 30MB/s"
    45.     expr: irate(node_disk_written_bytes_total{device="sda"}[1m]) > 30000000
    46.     for: 30s
    47.     annotations:
    48.       sumary: "服务器实例 {{ $labels.instance }} I/O 写负载 告警通知"
    49.       description: "{{ $labels.instance }}I/O 每分钟写已超过 30MB/s,当前值: {{ $value }}"
    51.   - alert: "网卡流出速率大于 10MB/s"
    52.     expr: (irate(node_network_transmit_bytes_total{device!~"lo"}[1m]) / 1000) > 1000000
    53.     for: 30s
    54.     annotations:
    55.       sumary: "服务器实例 {{ $labels.instance }} 网卡流量负载 告警通知"
    56.       description: "{{ $labels.instance }}网卡 {{ $labels.device }} 流量已经超过 10MB/s, 当前值: {{ $value }}"
    58.   - alert: "CPU 使用率大于 90%"
    59.     expr: 100 - ((avg by (instance,job,env)(irate(node_cpu_seconds_total{mode="idle"}[30s]))) *100) > 90
    60.     for: 30s
    61.     annotations:
    62.       sumary: "服务器实例 {{ $labels.instance }} CPU 使用率 告警通知"
    63.       description: "{{ $labels.instance }}CPU 使用率已超过 90%, 当前值: {{ $value }}"