使用docker-compose快速搭建prometheus

作者: 风吹路过的云 | 来源:发表于2020-01-06 14:32 被阅读0次

docker-compose.yml配置如下

version: '3.7'

networks:
    monitor:
        driver: bridge

services:
    prometheus:
        image: prom/prometheus
        container_name: prometheus
        hostname: prometheus
        restart: always
        volumes:
            - /data/conf/prometheus/prometheus.yml:/etc/prometheus/prometheus.yml
            - /data/conf/prometheus/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:
            - /data/conf/prometheus/alertmanager.yml:/etc/alertmanager/alertmanager.yml
        ports:
            - "9093:9093"
        networks:
            - monitor

    grafana:
        image: grafana/grafana
        container_name: grafana
        hostname: grafana
        restart: always
        ports:
            - "3000:3000"
        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
            - /data/docker_containers/:/var/lib/docker:ro
        ports:
            - "8080:8080"
        networks:
            - monitor

特别注意下面这个映射关系，/data/docker_containers/这个目录，是我修改了的docker存储目录

/data/docker_containers/:/var/lib/docker:ro

centos7在/usr/lib/systemd/system/docker.service文件里

ExecStart=/usr/bin/dockerd --graph=/data/docker_containers -H fd:// --containerd=/run/containerd/containerd.sock

prometheus.yml文件内容：

# 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: ['172.1.5.220:9093']
      # - alertmanager:9093

# Load rules once and periodically evaluate them according to the global 'evaluation_interval'.
rule_files:
  - "node_down.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'
    static_configs:
      - targets: ['172.1.5.220:9090']

  - job_name: 'cadvisor'
    static_configs:
      - targets: ['172.1.5.220:8080']

  - job_name: 'node'
    scrape_interval: 8s
    static_configs:
      - targets: ['172.1.5.220:9100']

node_down.yml文件内容：

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."

alertmanager.yml文件内容，即配置自己的邮件服务器，和接收人邮箱，各位对应修改即可

global: 
  smtp_smarthost: 'smtp.xxx.com:25'
  smtp_from: 'user@xxx.com'
  smtp_auth_username: 'user@xxx.com'
  smtp_auth_password: 'pwd123456'
  smtp_require_tls: false

route: 
  group_by: ['alertname']
  group_wait: 10s
  group_interval: 10s
  repeat_interval: 10m
  receiver: live-monitoring

receivers: 
  - name: 'live-monitoring'
    email_configs: 
    - to: 'xxx@qq.com'

把容器跑起来后，通过http://172.1.5.220:9090/targets
即可查看状态

状态图
从图中可以看出当前为UP状态（健康状态），一开始，全是DOWN状态的，跟防火墙设置有关

[root@172-1-5-220 ~]# setenforce 0
[root@172-1-5-220 ~]# firewall-cmd --zone=public --list-ports

[root@172-1-5-220 ~]# firewall-cmd --zone=public --add-port=9100/tcp --permanent
success
[root@172-1-5-220 ~]# firewall-cmd --zone=public --add-port=9090/tcp --permanent
success
[root@172-1-5-220 ~]# firewall-cmd --zone=public --add-port=9093/tcp --permanent
success
[root@172-1-5-220 ~]# firewall-cmd --zone=public --add-port=3000/tcp --permanent
success
[root@172-1-5-220 ~]# firewall-cmd --zone=public --add-port=8080/tcp --permanent
success
[root@172-1-5-220 ~]# firewall-cmd --reload
success