一 Alertmanager配置

1.1 编辑Alertmanager配置文件

root@node-02:~# cat /usr/local/alertmanager/alertmanager.yml 
global:
  smtp_from: '1304995320@qq.com' 
  smtp_smarthost: 'smtp.qq.com:465'
  smtp_auth_username: '1304995320@qq.com'
  smtp_auth_password: 'xxxxxxxxx'
  smtp_hello: '@qq.com'
  smtp_require_tls: false 
route:
  group_by: ['alertname']
  group_wait: 30s
  group_interval: 5s
  repeat_interval: 1m
  receiver: 'web.hook'
receivers:
- name: 'web.hook'
  email_configs:
    - to: 'wangguishe@hard-chain.cn'
inhibit_rules:
  - source_match:
      severity: 'critical'
    target_match:
      severity: 'critical'
    equal: ['alertname', 'dev', 'instance']

1.2 重启Alertmanager服务

root@node-02:~# systemctl restart alertmanager

二 Prometheus报警设置

2.1 修改Prometheus配置文件

root@prometheus-01:~# cat /usr/local/prometheus/prometheus.yml 
alerting:
  alertmanagers:
    - static_configs:
        - targets:
           - 192.168.174.104:9093
rule_files:
  
  - "rules/*.yaml"
  - "alert_rules/*.yaml"

2.2 创建告警规则文件

root@prometheus-01:~# cat /usr/local/prometheus/alert_rules/instance_down.yaml 
groups:
- name: ALLInstances
  rules:
    - alert: InstanceDown
      expr: up == 0
      for: 1m
      annotations:
        title: 'Instance down'
        description: 'Instance has been down for more than 1 munute.'
      labels:
        severity: 'critical'

2.3 验证规则

root@prometheus-01:~# /usr/local/prometheus/promtool check rules /usr/local/prometheus/alert_rules/instance_down.yaml 
Checking /usr/local/prometheus/alert_rules/instance_down.yaml
  SUCCESS: 1 rules found

2.4 重启Prometheus服务

root@prometheus-01:~# systemctl restart prometheus.service 

2.5 停止node_exporter服务

root@k8s-master-01:~# systemctl stop node-exporter

2.6 Prometheus web界面

2.7 验证Alertmanager界面

2.8  验证邮件告警信息