Prometheus和Alertmanager 的安装与配置

本人配置的时候 观看了很多配置的文章 以下只是自己的配置笔记

这是比较有帮助的文章

https://www.cnblogs.com/anay/p/11871018.html
https://blog.csdn.net/aixiaoyang168/article/details/98474494

Prometheus下载地址

https://prometheus.io/download/

tar -xvf  prometheus-2.17.1.linux-amd64.tar.gz
mv  prometheus-2.17.1.linux-amd64 prometheus-2.17.1
cd /prometheus-2.17.1

修改配置文件

# 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 is set to the global default (10s).
#这是连接Alertmanager告警的配置 xxxxxx:9093 是指向Alertmanager的地址
# Alertmanager configuration
alerting:
  alertmanagers:
  - static_configs:
    - targets:
       - xxxxxx:9093

# 这是告警规则
rule_files:
  - "first_rules.yml"
  # - "second_rules.yml"

# A scrape configuration containing exactly one endpoint to scrape:
# Here it's Prometheus itself.
scrape_configs:
  # The job name is added as a label `job=` to any timeseries scraped from this config.
  - job_name: 'prometheus'
    static_configs:
    - targets: ['localhost:9090']

  - job_name: 'redis_exporter_targets'
    static_configs:
      - targets:
        - redis://localhost:6379
        - redis://xxxxx:6379
    metrics_path: /metrics
    relabel_configs:
      - source_labels: [__address__]
        target_label: __param_target
      - source_labels: [__param_target]
        target_label: instance
      - target_label: __address__
        replacement: xxxxxxx:9121
        
  - job_name: 'redis_exporter'
    static_configs:
      - targets:
        - xxxxxxx:9121
              
  - job_name: 'mysql'
    static_configs:
     - targets: ['xxxxxxx:9104']
       labels:
         instance: xxxxxxx:3306
  - job_name: node_exporter
    scrape_interval: 30s
    scrape_timeout: 10s
    metrics_path: /metrics
    scheme: http
    static_configs:
      - targets:
        - xxxxxx:9100
        - xxxxxx:9100
        
  - job_name: 'zhongcheng'
    metrics_path: '/actuator/prometheus'
    scrape_interval: 5s
    static_configs:
      - targets: ['xxxxxx:8088']

检查配置：

[root@localhost prome]# ./promtool check config prometheus.yml
Checking prometheus.yml
  SUCCESS: 1 rule files found

Checking rules.yml
  SUCCESS: 1 rules found

启动
–config.file=/app/prometheus-2.17.1/prometheus.yml #配置文件位置
–web.enable-lifecycle #开启热启动

./prometheus --config.file=/app/prometheus-2.17.1/prometheus.yml --web.enable-lifecycle

Alertmanager 下载地址
https://prometheus.io/download/

tar -xvf  alertmanager-0.20.0.linux-amd64.tar.gz
mv alertmanager-0.20.0.linux-amd64   alertmanager-0.20.0
cd /alertmanager-0.20.0

配置文件

global:
  resolve_timeout: 5m

  smtp_smarthost: 'smtp.163.com:25' # 定义163邮箱服务器端
  smtp_from: '[email protected]'  #来自哪个邮箱发的
  smtp_auth_username: '[email protected]' 邮箱验证
  smtp_auth_password: 'XXXXXXXX'   # 邮箱授权码，不是登录密码
  smtp_require_tls: false   # 是否启用tls

route:
  group_by: ['alertname']
  group_wait: 10s
  group_interval: 10s
  repeat_interval: 3m  # 发送告警后间隔多久再次发送，减少发送邮件频率
  receiver: 'mail'    #发送的告警媒体

receivers:
- name: 'mail'        # 接收者配置，这里要与接收媒体一致
  email_configs: 
  - to: '[email protected]' #发送给谁的邮箱，多个人多行列出
#inhibit_rules:
#  - source_match:
#      severity: 'critical'
#    target_match:
#      severity: 'warning'
#    equal: ['alertname', 'dev', 'instance']

检查配置：

[root@localhost alertmanager]# ./amtool check-config alertmanager.yml
Checking 'alertmanager.yml'  SUCCESS
Found:
 - global config
 - route
 - 0 inhibit rules
 - 1 receivers
 - 0 templates

启动alertmanager

[root@localhost alertmanager]# ./alertmanager --config.file=./alertmanager.yml &

Alertmanager 配置告警规则文件

放在prometheus.yml 配置文件的同级目录中

开启prometheus.yml中的配置

直接重启prometheus即可 因为部署prometheus时开启了热重启 直接
然后热重启：curl -XPOST http://localhost:9090/-/reload

prometheus热重启
prometheus启动命令添加参数 --web.enable-lifecycle