prometheus中的alertmanage配置文件详解

alertmanage学习链接：
路由中标签详解：
https://yunlzheng.gitbook.io/prometheus-book/parti-prometheus-ji-chu/alert/alert-manager-route
alertmanage的配置文件示例
https://blog.csdn.net/qq_22227087/article/details/96483009
alertmanage主配置文件中关键字(方法)详解
https://zhuanlan.zhihu.com/p/74932366

###########################################################
prometheus配置文件和alert,amage配置文件详解

prometheus的主配置文件中包含rule.yml, rule.yml中的rules只负责定义报警的触发条件(下面有rule.yml配置文件的样例)。触发以后会将消息转发到alertmanage,alertmanage的主配置文件中根据路由选择转发给哪个接收者(下面有alertmanage.yml配置文件的样例)





#################################################################
promethuse主配置文件样例

# my global config
global:
  scrape_interval:     15s # Set the scrape interval to every 15 seconds. Default is every 1 minute.
  evaluation_interval: 15s # Evaluate rules every 15 seconds. The default is every 1 minute.
  scrape_timeout: 15s
  # scrape_timeout is set to the global default (10s).

# Alertmanager configuration
#promethuse关联alertmanger
alerting:
  alertmanagers:
  - static_configs:
    - targets:
        - localhost:9093

# Load rules once and periodically evaluate them according to the global 'evaluation_interval'.
rule_files:
  # - "first_rules.yml"
  # - "second_rules.yml"
  - /data/prometheus/alertmanager-0.17.0/netdata-rule.yml
  - /data/prometheus/alertmanager-0.17.0/mysql-rule.yml
  - /data/prometheus/alertmanager-0.17.0/bigdata-rule.yml
  - /data/prometheus/alertmanager-0.17.0/db-rule.yml
  - /data/prometheus/alertmanager-0.17.0/ops-rule.yml
  - /data/prometheus/alertmanager-0.17.0/game-backend-rule.yml
  - /data/prometheus/alertmanager-0.17.0/game-status-rule.yml
  - /data/prometheus/alertmanager-0.17.0/url-rule.yml
  - /data/prometheus/alertmanager-0.17.0/idc-rule.yml

 

############################################################
rule.yml配置样例
groups:
- name: test-rule
  rules:
  - alert: "tcp连接报警"
    expr: netdata_ipv4_tcpsock_active_connections_average{dimension="connections",family="tcp"} > 1
    for: 1s
    labels:
      severity: warning
    annotations:
      summary: "服务名:{{$labels.alertname}}"
      description: "业务500报警: {{ $value }}"
      value: "{{ $value }}"

- name: test-rule2
  rules:
  - alert: "内存报警"
    expr: 100 - ((node_memory_MemAvailable * 100) / node_memory_MemTotal) > 1
    for: 1s
    labels:
      severity: test
    annotations:
      summary: "服务名:{{$labels.alertname}}"
      description: "业务500报警: {{ $value }}"
      value: "{{ $value }}"
##########################################################
global:
  resolve_timeout: 5m
  # smtp_smarthost: 使用email打开服务配置
  smtp_smarthost: 'smtp.gmail.com:465'
  # smtp_from：指定通知报警的邮箱
  smtp_from: 'solomon02040@gmail.com'
  # smtp_auth_username：邮箱用户名
  smtp_auth_username: 'solomon02040@gmail.com'
  # smtp_auth_password：授权密码
  smtp_auth_password: '8899//zz'
  # smtp_require_tls：是否启用tls
  smtp_require_tls: false

templates:
  - '/data/alertmanager/template/*.tmpl'

route:
  receiver: solomontest     #接收人的名字可以自己定义
  group_by: ['alertname']
  group_wait: 10s     #组报警等待时间
  group_interval: 10s  #组报警间隔时间
  repeat_interval: 60s   #重复报警间隔时间
  routes:
  - receiver: solomontest
    group_wait: 10s
    match_re:          #使用match_re方法（使用正则的方式匹配,这里用match更好）
      env: test        #env是报警数据中的标签,test是标签的值


receivers:
- name: solomontest
  email_configs:
  - to: 'solomon02040@gmail.com'
    html: '{{ template "xx.html" . }}'   #指定模板
    headers: { Subject: "[WARN] 报警邮件" }


- name: 'test'
  email_configs:
  - to: 'xxx@xx.xx'
    html: '{{ template "xx.html" . }}'
    headers: { Subject: " {{ 第二路由匹配测试}}" }
########################################################