监控-基础指标

Node 是否运行

[root@k8s-node02 rules]# cat node.yml 
groups:
- name: Node_exporter Down
  rules:
  - alert: Node实例已宕机
    expr: up == 0
    for: 10s
    labels:
      user: root
      severity: Warning
    annotations:
      summary: "{{ $labels.job }}"
      address: "{{ $labels.instance }}"
      description: "Node_exporter 客户端在1分钟内连接失败."

CPU 使用率

[root@k8s-node02 rules]# cat cpu.yml 
groups:
- name: CPU
  rules:
  - alert: CPU使用率过高
    expr: 100 - (avg(irate(node_cpu_seconds_total{mode="idle"}[5m])) by (instance) * 100) > 90
    for: 1m
    labels:
      severity: Warning
    annotations:
      summary: "{{ $labels.instance }} CPU使用率过高"
      description: "{{ $labels.instance }}: CPU使用率超过90%，当前使用率({{ $value }})."

MEM使用率

[root@k8s-node02 rules]# cat mem.yml 
groups:
- name: Memory
  rules:
  - alert: 内存使用率过高
    expr: (node_memory_MemTotal_bytes - (node_memory_MemFree_bytes+node_memory_Buffers_bytes+node_memory_Cached_bytes )) / node_memory_MemTotal_bytes * 100 > 80
    for: 1m  #告警持续时间，超过这个时间才会发送给alertmanager
    labels:
      severity: Warning
    annotations:
      summary: "{{ $labels.instance }} 内存使用率过高"
      description: "{{ $labels.instance }}：内存使用率超过80%，当前使用率({{ $value }})."

---

总基础指标

groups:
  - name: node-alert
    rules:
    - alert: NodeDown
      expr: up{job="node"} == 0
      for: 3m
      labels:
        severity: critical
        instance: "{{ $labels.instance }}"
      annotations:
        summary: "instance: {{ $labels.instance }} down"
        description: "Instance: {{ $labels.instance }} 已经宕机 3分钟"
        value: "{{ $value }}"
        
    - alert: NodeCpuHigh
      expr: (1 - avg by (instance) (irate(node_cpu_seconds_total{job="node",mode="idle"}[5m]))) * 100 > 80
      for: 5m
      labels:
        severity: warning
        instance: "{{ $labels.instance }}"
      annotations:
        summary: "instance: {{ $labels.instance }} cpu使用率过高"
        description: "CPU 使用率超过 80%"
        value: "{{ $value }}"

    - alert: NodeCpuIowaitHigh
      expr: avg by (instance) (irate(node_cpu_seconds_total{job="node",mode="iowait"}[5m])) * 100 > 50
      for: 5m
      labels:
        severity: warning
        instance: "{{ $labels.instance }}"
      annotations:
        summary: "instance: {{ $labels.instance }} cpu iowait 使用率过高"
        description: "CPU iowait 使用率超过 50%"
        value: "{{ $value }}"

    - alert: NodeLoad5High
      expr: node_load5 > (count by (instance) (node_cpu_seconds_total{job="node",mode='system'})) * 1.2
      for: 5m
      labels:
        severity: warning
        instance: "{{ $labels.instance }}"
      annotations:
        summary: "instance: {{ $labels.instance }} load(5m) 过高"
        description: "Load(5m) 过高，超出cpu核数 1.2倍"
        value: "{{ $value }}"

    - alert: NodeMemoryHigh
      expr: (1 - node_memory_MemAvailable_bytes{job="node"} / node_memory_MemTotal_bytes{job="node"}) * 100 > 90
      for: 5m
      labels:
        severity: warning
        instance: "{{ $labels.instance }}"
      annotations:
        summary: "instance: {{ $labels.instance }} memory 使用率过高"
        description: "Memory 使用率超过 90%"
        value: "{{ $value }}"

    - alert: NodeDiskRootHigh
      expr: (1 - node_filesystem_avail_bytes{job="node",fstype=~"ext.*|xfs",mountpoint ="/"} / node_filesystem_size_bytes{job="node",fstype=~"ext.*|xfs",mountpoint ="/"}) * 100 > 90
      for: 10m
      labels:
        severity: warning
        instance: "{{ $labels.instance }}"
      annotations:
        summary: "instance: {{ $labels.instance }} disk(/ 分区) 使用率过高"
        description: "Disk(/ 分区) 使用率超过 90%"
        value: "{{ $value }}"

    - alert: NodeDiskBootHigh
      expr: (1 - node_filesystem_avail_bytes{job="node",fstype=~"ext.*|xfs",mountpoint ="/boot"} / node_filesystem_size_bytes{job="node",fstype=~"ext.*|xfs",mountpoint ="/boot"}) * 100 > 80
      for: 10m
      labels:
        severity: warning
        instance: "{{ $labels.instance }}"
      annotations:
        summary: "instance: {{ $labels.instance }} disk(/boot 分区) 使用率过高"
        description: "Disk(/boot 分区) 使用率超过 80%"
        value: "{{ $value }}"

    - alert: NodeDiskReadHigh
      expr: irate(node_disk_read_bytes_total{job="node"}[5m]) > 20 * (1024 ^ 2)
      for: 5m
      labels:
        severity: warning
        instance: "{{ $labels.instance }}"
      annotations:
        summary: "instance: {{ $labels.instance }} disk 读取字节数 速率过高"
        description: "Disk 读取字节数 速率超过 20 MB/s"
        value: "{{ $value }}"

    - alert: NodeDiskWriteHigh
      expr: irate(node_disk_written_bytes_total{job="node"}[5m]) > 20 * (1024 ^ 2)
      for: 5m
      labels:
        severity: warning
        instance: "{{ $labels.instance }}"
      annotations:
        summary: "instance: {{ $labels.instance }} disk 写入字节数 速率过高"
        description: "Disk 写入字节数 速率超过 20 MB/s"
        value: "{{ $value }}"
        
    - alert: NodeDiskReadRateCountHigh
      expr: irate(node_disk_reads_completed_total{job="node"}[5m]) > 3000
      for: 5m
      labels:
        severity: warning
        instance: "{{ $labels.instance }}"
      annotations:
        summary: "instance: {{ $labels.instance }} disk iops 每秒读取速率过高"
        description: "Disk iops 每秒读取速率超过 3000 iops"
        value: "{{ $value }}"

    - alert: NodeDiskWriteRateCountHigh
      expr: irate(node_disk_writes_completed_total{job="node"}[5m]) > 3000
      for: 5m
      labels:
        severity: warning
        instance: "{{ $labels.instance }}"
      annotations:
        summary: "instance: {{ $labels.instance }} disk iops 每秒写入速率过高"
        description: "Disk iops 每秒写入速率超过 3000 iops"
        value: "{{ $value }}"

    - alert: NodeInodeRootUsedPercentHigh
      expr: (1 - node_filesystem_files_free{job="node",fstype=~"ext4|xfs",mountpoint="/"} / node_filesystem_files{job="node",fstype=~"ext4|xfs",mountpoint="/"}) * 100 > 80
      for: 10m
      labels:
        severity: warning
        instance: "{{ $labels.instance }}"
      annotations:
        summary: "instance: {{ $labels.instance }} disk(/ 分区) inode 使用率过高"
        description: "Disk (/ 分区) inode 使用率超过 80%"
        value: "{{ $value }}"

    - alert: NodeInodeBootUsedPercentHigh
      expr: (1 - node_filesystem_files_free{job="node",fstype=~"ext4|xfs",mountpoint="/boot"} / node_filesystem_files{job="node",fstype=~"ext4|xfs",mountpoint="/boot"}) * 100 > 80
      for: 10m
      labels:
        severity: warning
        instance: "{{ $labels.instance }}"
      annotations:
        summary: "instance: {{ $labels.instance }} disk(/boot 分区) inode 使用率过高"
        description: "Disk (/boot 分区) inode 使用率超过 80%"
        value: "{{ $value }}"
        
    - alert: NodeFilefdAllocatedPercentHigh
      expr: node_filefd_allocated{job="node"} / node_filefd_maximum{job="node"} * 100 > 80
      for: 10m
      labels:
        severity: warning
        instance: "{{ $labels.instance }}"
      annotations:
        summary: "instance: {{ $labels.instance }} filefd 打开百分比过高"
        description: "Filefd 打开百分比 超过 80%"
        value: "{{ $value }}"

    - alert: NodeNetworkNetinBitRateHigh
      expr: avg by (instance) (irate(node_network_receive_bytes_total{device=~"eth0|eth1|ens33|ens37"}[1m]) * 8) > 20 * (1024 ^ 2) * 8
      for: 3m
      labels:
        severity: warning
        instance: "{{ $labels.instance }}"
      annotations:
        summary: "instance: {{ $labels.instance }} network 接收比特数 速率过高"
        description: "Network 接收比特数 速率超过 20MB/s"
        value: "{{ $value }}"

    - alert: NodeNetworkNetoutBitRateHigh
      expr: avg by (instance) (irate(node_network_transmit_bytes_total{device=~"eth0|eth1|ens33|ens37"}[1m]) * 8) > 20 * (1024 ^ 2) * 8
      for: 3m
      labels:
        severity: warning
        instance: "{{ $labels.instance }}"
      annotations:
        summary: "instance: {{ $labels.instance }} network 发送比特数 速率过高"
        description: "Network 发送比特数 速率超过 20MB/s"
        value: "{{ $value }}"
        
    - alert: NodeNetworkNetinPacketErrorRateHigh
      expr: avg by (instance) (irate(node_network_receive_errs_total{device=~"eth0|eth1|ens33|ens37"}[1m])) > 15
      for: 3m
      labels:
        severity: warning
        instance: "{{ $labels.instance }}"
      annotations:
        summary: "instance: {{ $labels.instance }} 接收错误包 速率过高"
        description: "Network 接收错误包 速率超过 15个/秒"
        value: "{{ $value }}"

    - alert: NodeNetworkNetoutPacketErrorRateHigh
      expr: avg by (instance) (irate(node_network_transmit_packets_total{device=~"eth0|eth1|ens33|ens37"}[1m])) > 15
      for: 3m
      labels:
        severity: warning
        instance: "{{ $labels.instance }}"
      annotations:
        summary: "instance: {{ $labels.instance }} 发送错误包 速率过高"
        description: "Network 发送错误包 速率超过 15个/秒"
        value: "{{ $value }}"

    - alert: NodeProcessBlockedHigh
      expr: node_procs_blocked{job="node"} > 10
      for: 10m
      labels:
        severity: warning
        instance: "{{ $labels.instance }}"
      annotations:
        summary: "instance: {{ $labels.instance }} 当前被阻塞的任务的数量过多"
        description: "Process 当前被阻塞的任务的数量超过 10个"
        value: "{{ $value }}"

    - alert: NodeTimeOffsetHigh
      expr: abs(node_timex_offset_seconds{job="node"}) > 3 * 60
      for: 2m
      labels:
        severity: info
        instance: "{{ $labels.instance }}"
      annotations:
        summary: "instance: {{ $labels.instance }} 时间偏差过大"
        description: "Time 节点的时间偏差超过 3m"
        value: "{{ $value }}"