docker部署Prometheus+Cadvisor+Grafana实现服务器监控

docker pull prom/prometheus

global:
  # 每15s获取一次数据指标
  scrape_interval: 15s
  # 获取数据超时时长 10s
  scrape_timeout: 10s
  # 规则评估评率，即计算指标是否有触发规则的计算频率
  evaluation_interval: 15s

# 规则文件，从所有匹配的文件中读取规则和警报
rule_files:
  - "alert_rules.yml"

# 采集配置列表
scrape_configs:
  - job_name: prometheus
    static_configs:
      - targets: ['localhost:9090']

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

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

groups:
- name: targets
  rules:
  - alert: monitor_service_down
    expr: up == 0
    for: 30s
    labels:
      severity: critical
    annotations:
      summary: "Monitor service non-operational"
      description: "Service {{ $labels.instance }} is down."

- name: host
  rules:
  - alert: high_cpu_load
    expr: node_load1 > 1.5
    for: 30s
    labels:
      severity: warning
    annotations:
      summary: "Server under high load"
      description: "Docker host is under high load, the avg load 1m is at {{ $value}}. Reported by instance {{ $labels.instance }} of job {{ $labels.job }}."

  - alert: high_memory_load
    expr: (sum(node_memory_MemTotal_bytes) - sum(node_memory_MemFree_bytes + node_memory_Buffers_bytes + node_memory_Cached_bytes) ) / sum(node_memory_MemTotal_bytes) * 100 > 85
    for: 30s
    labels:
      severity: warning
    annotations:
      summary: "Server memory is almost full"
      description: "Docker host memory usage is {{ humanize $value}}%. Reported by instance {{ $labels.instance }} of job {{ $labels.job }}."

  - alert: high_storage_load
    expr: (node_filesystem_size_bytes{fstype="aufs"} - node_filesystem_free_bytes{fstype="aufs"}) / node_filesystem_size_bytes{fstype="aufs"}  * 100 > 85
    for: 30s
    labels:
      severity: warning
    annotations:
      summary: "Server storage is almost full"
      description: "Docker host storage usage is {{ humanize $value}}%. Reported by instance {{ $labels.instance }} of job {{ $labels.job }}."

docker run -d --name=prometheus -p 9090:9090 -v ./prometheus[创建的配置文件目录]:/etc/prometheus -v ./opt/data/prometheus[prometheus数据需要存储的地址]:/prometheus prom/prometheus

docker pull google/cadvisor

docker run -d --volume=/:/rootfs:ro --volume=/var/run:/var/run:ro --volume=/sys:/sys:ro --volume=/var/lib/docker/:/var/lib/docker:ro --volume=/dev/disk/:/dev/disk:ro --publish=8080:8080 --detach=true --name=cadvisor google/cadvisor:latest

docker pull grafana/grafana

docker run -d --name=grafana -p 3000:3000 grafana/grafana