Prometheus（普罗米修斯）----- Nginx监控-CSDN博客

本文链接：https://blog.csdn.net/qq_18138507/article/details/142816442

一、查看是否安装stub_status模块

1、查看www-nginx是否安装stub_status模块

#进入目录
cd /opt/nginx/www-nginx/sbin
#查看是否安装
./nginx -V 2>&1 | grep -o with-http_stub_status_module
##如果没安装重新安装编译
./configure --prefix=/opt/nginx/www-nginx --with-http_stub_status_module
make & make install

##启动
./nginx
##查看是否配置
curl http://192.168.1.41:20080/stub_status

2、查看www2-nginx是否安装stub_status模块

#进入目录
cd /opt/nginx/www-nginx/sbin
#查看是否安装
./nginx -V 2>&1 | grep -o with-http_stub_status_module
##如果没安装重新安装编译
./configure --prefix=/opt/nginx/www-nginx --with-http_stub_status_module
make & make install

##启动
./nginx
##查看是否配置
curl http://192.168.1.41:60080/stub_status

二、安装nginx_export

wget https://github.com/nginxinc/nginx-prometheus-exporter/releases/download/v1.3.0/nginx-prometheus-exporter_1.3.0_linux_amd64.tar.gz

tar -zxvf  nginx-prometheus-exporter_1.3.0_linux_amd64.tar.gz -C /portal/monitor/nginx-prometheus-exporter

chown prometheus:prometheus -R /portal/monitor/

三、配置nginx的conf文件

   server {
        listen       20080;
        listen       [::]:20080;
        server_name  localhost;

        error_page  404 403  500 502 503 504  /50x.html;

        location / {
            root   html;
            index  index.html index.htm;
        }

        location = /50x.html {
            root   html;
        }

        location = /stub_status { # 具体路径可根据业务情况进行调整
     	stub_status on;
     	access_log off;
     	allow 192.168.1.41;
     	deny all;
 	}        

}

四、配置www-nginx的systemd

cd etc/systemd/system

vim www_nginx_exporter.service

[Unit]
Description=www-nginx-prometheus-exporter
After=network.target
[Service]
Type=simple
User=prometheus
Group=prometheus
Restart=always
ExecStart=/portal/monitor/nginx_exporter/nginx-prometheus-exporter -nginx.scrape-uri=http://192.168.1.41:20080/stub_status -web.listen-address=:9113
  
[Install]
WantedBy=multi-user.target

五、配置www2-nginx的systemd

cd etc/systemd/system

vim www2_nginx_exporter.service

[Unit]
Description=www2-nginx-prometheus-exporter
After=network.target
[Service]
Type=simple
User=prometheus
Group=prometheus
Restart=always
ExecStart=/portal/monitor/nginx_exporter/nginx-prometheus-exporter -nginx.scrape-uri=http://192.168.1.41:60080/stub_status -web.listen-address=:9114
  
[Install]
WantedBy=multi-user.target

systemctl daemon-reload

systemctl start www_nginx_exporter.service

systemctl enable www2_nginx_exporter.service

##访问地址www

http://192.168.1.41:9113/metrics

##访问地址www2

http://192.168.1.41:9114/metrics

六、配置prometheus

# 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).

# Alertmanager configuration
alerting:
  alertmanagers:
    - static_configs:
        - targets:
           - localhost:9193

# Load rules once and periodically evaluate them according to the global 'evaluation_interval'.
rule_files:
    - "alert.yml"
  # - "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=<job_name>` to any timeseries scraped from this config.
  - job_name: "prometheus"

    # metrics_path defaults to '/metrics'
    # scheme defaults to 'http'.
    scrape_interval: 15s
    static_configs:
      - targets: ["localhost:9090"]


  - job_name: "node-exporter"
    scrape_interval: 15s
    static_configs:
      - targets: ["192.168.1.41:9100"]
        labels:
          instance: 192.168.1.41服务器
          
      - targets: ["192.168.1.42:9100"]
        labels:
          instance: 192.168.1.42服务器

      - targets: ["192.168.1.43:9100"]
        labels:
          instance: 192.168.1.43服务器
          
      - targets: ["192.168.1.44:9100"]
        labels:
          instance: 192.168.1.44服务器
## 添加一下内容
  - job_name: "www_nginx_exporter"
    static_configs:
      - targets: ["192.168.1.41:9113"]
        labels:
          instance: prod4-nginx服务器

  - job_name: "www2_nginx_exporter"
    static_configs:
      - targets: ["192.168.1.41:9114"]
        labels:
          instance: prod6-nginx服务器

七、prometheus配置alert

groups:
- name: Prometheus alert
  rules:
  # 对任何实例超过30s无法联系的情况发出警告
  - alert: 服务告警
    expr: up == 0
    for: 30s
    labels:
      severity: critical
    annotations:
      instance: "{{ $labels.instance}}"
      description: "{{ $labels.job}} 服务已关闭"

- name: Nginx
  rules:
  # 检查 nginx_exporter 端口 9113（适用于20080端口的nginx实例）
  - alert: WWWNginxDown
    expr: up{job="nginx_exporter", instance="192.168.1.41:9113"} == 0
    for: 30s
    labels:
      severity: critical
    annotations:
      instances: "nginx异常,实例：{{ $labels.instance }}"
      description: "prod4 的 nginx 已关闭"

  # 检查 nginx_exporter 端口 9114（适用于60080端口的nginx实例）
  - alert: WWW2NginxDown
    expr: up{job="nginx_exporter", instance="192.168.1.41:9114"} == 0
    for: 30s
    labels:
      severity: critical
    annotations:
      instances: "nginx异常,实例：{{ $labels.instance }}"
      description: "prod6 的 nginx 已关闭"