init

alertmanager/config.yml

@@ -0,0 +1,28 @@
+global:
+  #163服务器
+  smtp_smarthost: 'smtp.163.com:465'
+  #发邮件的邮箱
+  smtp_from: 'cdring@163.com'
+  #发邮件的邮箱用户名，也就是你的邮箱　　　　　
+  smtp_auth_username: 'cdring@163.com'
+  #发邮件的邮箱密码
+  smtp_auth_password: 'your-password'
+  #进行tls验证
+  smtp_require_tls: false
+
+route:
+  group_by: ['alertname']
+  # 当收到告警的时候，等待group_wait配置的时间，看是否还有告警，如果有就一起发出去
+  group_wait: 10s
+  #  如果上次告警信息发送成功，此时又来了一个新的告警数据，则需要等待group_interval配置的时间才可以发送出去
+  group_interval: 10s
+  # 如果上次告警信息发送成功，且问题没有解决，则等待 repeat_interval配置的时间再次发送告警数据
+  repeat_interval: 10m
+  # 全局报警组，这个参数是必选的
+  receiver: email
+
+receivers:
+- name: 'email'
+  #收邮件的邮箱
+  email_configs:
+  - to: 'cdring@163.com'

docker-compose.yaml

@@ -0,0 +1,107 @@
+version: '3.3'
+
+volumes:
+  prometheus_data: {}
+  grafana_data: {}
+
+networks:
+  monitoring:
+    driver: bridge
+
+services:
+  prometheus:
+    image: prom/prometheus:v2.37.6
+    container_name: prometheus
+    restart: always
+    volumes:
+      - /etc/localtime:/etc/localtime:ro
+      - ./prometheus/:/etc/prometheus/
+      - prometheus_data:/prometheus
+    command:
+      - '--config.file=/etc/prometheus/prometheus.yml'
+      - '--storage.tsdb.path=/prometheus'
+      - '--web.console.libraries=/usr/share/prometheus/console_libraries'
+      - '--web.console.templates=/usr/share/prometheus/consoles'
+      #热加载配置
+      - '--web.enable-lifecycle'
+      #api配置
+      #- '--web.enable-admin-api'
+      #历史数据最大保留时间，默认15天
+      - '--storage.tsdb.retention.time=30d'  
+    networks:
+      - monitoring
+    links:
+      - alertmanager
+      - cadvisor
+      - node_exporter
+    expose:
+      - '9090'
+    ports:
+      - 9090:9090
+    depends_on:
+      - cadvisor
+
+  alertmanager:
+    image: prom/alertmanager:v0.25.0
+    container_name: alertmanager
+    restart: always
+    volumes:
+      - /etc/localtime:/etc/localtime:ro
+      - ./alertmanager/:/etc/alertmanager/
+    command:
+      - '--config.file=/etc/alertmanager/config.yml'
+      - '--storage.path=/alertmanager'
+    networks:
+      - monitoring
+    expose:
+      - '9093'
+    ports:
+      - 9093:9093
+
+  cadvisor:
+    image: google/cadvisor:latest
+    container_name: cadvisor
+    restart: always
+    volumes:
+      - /etc/localtime:/etc/localtime:ro
+      - /:/rootfs:ro
+      - /var/run:/var/run:rw
+      - /sys:/sys:ro
+      - /var/lib/docker/:/var/lib/docker:ro
+    networks:
+      - monitoring
+    expose:
+      - '8080'
+
+  node_exporter:
+    image: prom/node-exporter:v1.5.0
+    container_name: node-exporter
+    restart: always
+    volumes:
+      - /etc/localtime:/etc/localtime:ro
+      - /proc:/host/proc:ro
+      - /sys:/host/sys:ro
+      - /:/rootfs:ro
+    networks:
+      - monitoring
+    ports:
+      - '9100:9100'
+
+  grafana:
+    image: grafana/grafana:9.4.3
+    container_name: grafana
+    restart: always
+    volumes:
+      - /etc/localtime:/etc/localtime:ro
+      - grafana_data:/var/lib/grafana
+      - ./grafana/provisioning/:/etc/grafana/provisioning/
+    env_file:
+      - ./grafana/config.monitoring
+    networks:
+      - monitoring
+    links:
+      - prometheus
+    ports:
+      - 3000:3000
+    depends_on:
+      - prometheus

grafana/config.monitoring

@@ -0,0 +1,2 @@
+GF_SECURITY_ADMIN_PASSWORD=password
+GF_USERS_ALLOW_SIGN_UP=false

prometheus/alert.yml

@@ -0,0 +1,12 @@
+groups:
+- name: Prometheus alert
+  rules:
+  # 对任何实例超过30秒无法联系的情况发出警报
+  - 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"

prometheus/prometheus.yml

@@ -0,0 +1,36 @@
+# 全局配置
+global:
+  scrape_interval:     15s # 将搜刮间隔设置为每15秒一次。默认是每1分钟一次。
+  evaluation_interval: 15s # 每15秒评估一次规则。默认是每1分钟一次。
+
+# Alertmanager 配置
+alerting:
+  alertmanagers:
+  - static_configs:
+    - targets: ['alertmanager:9093']
+
+# 报警(触发器)配置
+rule_files:
+  - "alert.yml"
+
+# 搜刮配置
+scrape_configs:
+  - job_name: 'prometheus'
+    # 覆盖全局默认值，每15秒从该作业中刮取一次目标
+    scrape_interval: 15s
+    static_configs:
+    - targets: ['localhost:9090']
+
+  - job_name: 'cadvisor'
+    scrape_interval: 15s
+    static_configs:
+    - targets: ['cadvisor:8080']
+      labels:
+        instance: Prometheus服务器 
+
+  - job_name: 'node-exporter'
+    scrape_interval: 15s
+    static_configs:
+    - targets: ['node_exporter:9100']
+      labels:
+        instance: Prometheus服务器