alertmanager.yml（monitoring-prometheus-alertmanager）配置如下(用于配置报警)：

global:
  smtp_smarthost: 'smtp.163.com:25'
  smtp_from: 's@163.com'
  smtp_auth_username: 's@163.com'
  smtp_auth_password: '密码'
receivers:
  - name: default-receiver
    email_configs:
    - to: 'songjxin@*.com,b@c.a'
route:
  group_by: ['alertname']
  group_wait: 10s
  group_interval: 5m
  receiver: default-receiver
  repeat_interval: 1h

alter.rulers(configMap-monitoring-prometheus-alertrules)配置如下（用于配置报警规则）

groups:
- name: test-rule
  rules:
  - alert: clients
    expr: sum(kube_node_info) < 9
    for: 1m
    labels:
      severity: warning 
    annotations:
      summary: \"{{$labels.instance}}: node is not ready\"
      description: \"{{$labels.instance}}: node number is less than 10 (current value is: {{ $value }}\"
  - alert: NodeMemoryUsage
    expr: (((node_memory_MemTotal - node_memory_MemFree - node_memory_Cached) / (node_memory_MemTotal)
      * 100)) > 25
    for: 1m
    labels:
      severity: page
    annotations:
      DESCRIPTION: '{{$labels.instance}}: Memory usage is above 75% (current value
        is: {{ $value }})'
      SUMMARY: '{{$labels.instance}}: High memory usage detected'
  - alert: HighCPUUsage
    expr: ((sum(node_cpu{mode=~\"user|nice|system|irq|softirq|steal|idle|iowait\"})
      BY (instance, job)) - (sum(node_cpu{mode=~\"idle|iowait\"}) BY (instance, job)))
      / (sum(node_cpu{mode=~\"user|nice|system|irq|softirq|steal|idle|iowait\"}) BY
      (instance, job)) * 100 > 30
    for: 1m
    labels:
      service: backend
    annotations:
      description: This machine  has really high CPU usage for over 10m
      summary: High CPU Usage