docker部署钉钉机器人报警通知的实现

[root@node1 ~]# tree prom
prom
├── docker-compose.yml  #docker-compose文件
├── grafana  #grafana数据挂载
├── prometheus_data  #Prometheus数据挂载
├── rules    #报警规则文件
│   ├── cpu_over.yml
│   ├── disk_over.yml
│   ├── memory_over.yml
│   └── node_alived.yml
└── yml
    ├── alertmanager.yml   alertmanager配置
    ├── config.yml   钉钉机器人配置 
    └── prometheus.yml   Prometheus配置

[root@node1 prom]# cat docker-compose.yml 
version: \"3.7\"
services:
  node-exporter:
    image: prom/node-exporter:latest
    container_name: \"node-exporter\"
    ports:
      - \"9100:9100\"
    restart: always
  cadvisor:
    image: google/cadvisor:latest
    container_name: cadvisor
    restart: always
    ports:
      - \'8080:8080\'
  prometheus:
    image: prom/prometheus:latest
    container_name: prometheus
    ports:
      - \"9090:9090\"
    restart: always
    volumes:
      - \"./yml/prometheus.yml:/etc/prometheus/prometheus.yml\"
      - \"./prometheus_data:/prometheus\"
      - \"./rules:/etc/prometheus/rules\"
  grafana:
    image: grafana/grafana
    container_name: \"grafana\"
    ports:
      - \"3000:3000\"
    restart: always
    volumes:
      - \"./grafana:/var/lib/grafana\"
  alertmanager:
    image: prom/alertmanager:latest
    restart: \"always\"
    ports:
      - 9093:9093
    container_name: \"alertmanager\"
    volumes:
      - \"./yml/alertmanager.yml:/etc/alertmanager/alertmanager.yml\"
  webhook:
    image: timonwong/prometheus-webhook-dingtalk
    restart: \"always\"
    ports:
      - 8060:8060
    container_name: \"webhook\"         
    volumes:
      - \"./yml/config.yml:/etc/prometheus-webhook-dingtalk/config.yml\"

[root@node1 prom]# cat yml/prometheus.yml 
# my global config
global:  # 此片段指定的是prometheus的全局配置， 比如采集间隔，抓取超时时间等.
  scrape_interval: 1m  # 抓取间隔 默认1m
  evaluation_interval: 1m   # 评估规则间隔 默认1m
  # scrape_timeout is set to the global default (10s).

# Alertmanager configuration
 # 此片段指定报警配置， 这里主要是指定prometheus将报警规则推送到指定的alertmanager实例地址
alerting: 
  alertmanagers:
    - static_configs:
        - targets:
           - 192.168.10.10:9093

# Load rules once and periodically evaluate them according to the global \'evaluation_interval\'.
rule_files:
   - \"/etc/prometheus/rules/*.yml\"   #报警规则文件
#  - \"cpu_over.yml\"
#  - \"disk_over.yml\"
#  - \"memory_over.yml\"
#  - \"node_alived.yml\"

# A scrape configuration containing exactly one endpoint to scrape:
# Here it\'s Prometheus itself.
# 抓取配置列表
scrape_configs:
  - job_name: \"prometheus\"
    static_configs:
      - targets: [\"localhost:9090\"] 
  - job_name: \"linux\"
    static_configs:
      - targets: [\"192.168.10.10:9100\",\"192.168.10.10:8080\",\"192.168.10.20:9100\",\"192.168.10.20:8080\"]

[root@node1 prom]#cat alertmanager.yml
global:
  resolve_timeout: 5m  #在指定时间内没有新的事件就发送恢复通知
route:
  receiver: webhook  #设置接收人
  group_wait: 1m  #组告警等待时间。在等待时间结束后，如果有同组告警一起发出
  group_interval: 1m  #两组告警间隔时间。
  repeat_interval: 1m  #重复告警间隔时间，减少相同邮件的发送频率。
  group_by: [alertname] #采用那个标签来作为分组。
receivers:   #通知接收者列表
- name: webhook
  webhook_configs:
  - url: http://192.168.10.10:8060/dingtalk/webhook1/send             
    send_resolved: true

#########################################################

[root@node1 prom]# cat yml/config.yml 
targets:
  webhook1:
    url: https://oapi.dingtalk.com/robot/send?access_token=XXXXXX    #webhook
    secret: SEC000000    #加签

[root@node1 prom]#cat alertmanager.yml
global:
  resolve_timeout: 5m  #在指定时间内没有新的事件就发送恢复通知
route:
  receiver: webhook  #设置接收人
  group_wait: 1m  #组告警等待时间。在等待时间结束后，如果有同组告警一起发出
  group_interval: 1m  #两组告警间隔时间。
  repeat_interval: 1m  #重复告警间隔时间，减少相同邮件的发送频率。
  group_by: [alertname] #采用那个标签来作为分组。
receivers:   #通知接收者列表
- name: webhook
  webhook_configs:
  - url: http://192.168.10.10:8060/dingtalk/webhook1/send             
    send_resolved: true

#########################################################

[root@node1 prom]# cat yml/config.yml 
targets:
  webhook1:
    url: https://oapi.dingtalk.com/robot/send?access_token=XXXXXX    #webhook
    secret: SEC000000    #加签