使用docker部署grafana+prometheus配置

version: '2'

networks:
  monitor:
    driver: bridge

services:
  influxdb:
    image: influxdb:latest
    container_name: tig-influxdb
    ports:
      - "18083:8083"
      - "18086:8086"
      - "18090:8090"
    env_file:
      - 'env.influxdb'
    volumes:
      # Data persistency
      # sudo mkdir -p ./influxdb/data
      - ./influxdb/data:/var/lib/influxdb
      # 配置docker里的时间为东八区时间
      - ./timezone:/etc/timezone:ro
      - ./localtime:/etc/localtime:ro
    restart: unless-stopped #停止后自动

  telegraf:
    image: telegraf:latest
    container_name: tig-telegraf
    links:
      - influxdb
    volumes:
      - ./telegraf.conf:/etc/telegraf/telegraf.conf:ro
      - ./timezone:/etc/timezone:ro
      - ./localtime:/etc/localtime:ro
    restart: unless-stopped
  prometheus:
    image: prom/prometheus
    container_name: prometheus
    hostname: prometheus
    restart: always
    volumes:
      - /home/qa/docker/grafana/prometheus.yml:/etc/prometheus/prometheus.yml
      - /home/qa/docker/grafana/node_down.yml:/etc/prometheus/node_down.yml
    ports:
      - '9090:9090'
    networks:
      - monitor

  alertmanager:
    image: prom/alertmanager
    container_name: alertmanager
    hostname: alertmanager
    restart: always
    volumes:
      - /home/qa/docker/grafana/alertmanager.yml:/etc/alertmanager/alertmanager.yml
    ports:
      - '9093:9093'
    networks:
      - monitor

  grafana:
    image: grafana/grafana:6.7.4
    container_name: grafana
    hostname: grafana
    restart: always
    ports:
      - '13000:3000'
    networks:
      - monitor

  node-exporter:
    image: quay.io/prometheus/node-exporter
    container_name: node-exporter
    hostname: node-exporter
    restart: always
    ports:
      - '9100:9100'
    networks:
      - monitor

  cadvisor:
    image: google/cadvisor:latest
    container_name: cadvisor
    hostname: cadvisor
    restart: always
    volumes:
      - /:/rootfs:ro
      - /var/run:/var/run:rw
      - /sys:/sys:ro
      - /var/lib/docker/:/var/lib/docker:ro
    ports:
      - '18080:8080'
    networks:
      - monitor

global:
  resolve_timeout: 5m
  smtp_from: '邮箱'
  smtp_smarthost: 'smtp.exmail.qq.com:25'
  smtp_auth_username: '邮箱'
  smtp_auth_password: '密码'
  smtp_require_tls: false
  smtp_hello: 'qq.com'
route:
  group_by: ['alertname']
  group_wait: 5s
  group_interval: 5s
  repeat_interval: 5m
  receiver: 'email'
receivers:
- name: 'email'
  email_configs:
  - to: '收件邮箱'
    send_resolved: true
inhibit_rules:
  - source_match:
      severity: 'critical'
    target_match:
      severity: 'warning'
    equal: ['alertname', 'dev', 'instance']

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: ['192.168.32.117:9093']
      # - alertmanager:9093

# Load rules once and periodically evaluate them according to the global 'evaluation_interval'.
rule_files:
  - "node_down.yml"
  # - "node-exporter-alert-rules.yml"
  # - "first_rules.yml"
  # - "second_rules.yml"

# A scrape configuration containing exactly one endpoint to scrape:
# Here it's Prometheus itself.
scrape_configs:
  # IO存储节点组
  - job_name: 'io'
    scrape_interval: 8s
    static_configs:　　　　　#端口为node-exporter启动的端口　
      - targets: ['192.168.32.117:9100']
      - targets: ['192.168.32.196:9100']
      - targets: ['192.168.32.136:9100']
      - targets: ['192.168.32.193:9100']
      - targets: ['192.168.32.153:9100']
      - targets: ['192.168.32.185:9100']
      - targets: ['192.168.32.190:19100']
      - targets: ['192.168.32.192:9100']

  # The job name is added as a label `job=<job_name>` to any timeseries scraped from this config.
  - job_name: 'cadvisor'
    static_configs:　　　　　#端口为cadvisor启动的端口
      - targets: ['192.168.32.117:18080']
      - targets: ['192.168.32.193:8080']
      - targets: ['192.168.32.153:8080']
      - targets: ['192.168.32.185:8080']
      - targets: ['192.168.32.190:18080']
      - targets: ['192.168.32.192:18080']

groups:
  - name: node_down
    rules:
      - alert: InstanceDown
        expr: up == 0
        for: 1m
        labels:
          user: test
        annotations:
          summary: 'Instance {{ $labels.instance }} down'
          description: '{{ $labels.instance }} of job {{ $labels.job }} has been down for more than 1 minutes.'

        #剩余内存小于10%
      - alert: 剩余内存小于10%
        expr: node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes * 100 < 10
        for: 2m
        labels:
          severity: warning
        annotations:
          summary: Host out of memory (instance {{ $labels.instance }})
          description: "Node memory is filling up (< 10% left)\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

        #剩余磁盘小于10%
      - alert: 剩余磁盘小于10%
        expr: (node_filesystem_avail_bytes * 100) / node_filesystem_size_bytes < 10 and ON (instance, device, mountpoint) node_filesystem_readonly == 0
        for: 2m
        labels:
          severity: warning
        annotations:
          summary: Host out of disk space (instance {{ $labels.instance }})
          description: "Disk is almost full (< 10% left)\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

        #cpu负载 > 80%
      - alert: CPU负载 > 80%
        expr: 100 - (avg by(instance) (rate(node_cpu_seconds_total{mode="idle"}[2m])) * 100) > 80
        for: 0m
        labels:
          severity: warning
        annotations:
          summary: Host high CPU load (instance {{ $labels.instance }})
          description: "CPU load is > 80%\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"