2026 Prometheus 自建监控系统：Docker 部署实现服务器全方位监控

1
version: '3.8'
2

3
services:
4
  prometheus:
5
    image: prom/prometheus:latest
6
    container_name: prometheus
7
    restart: unless-stopped
8
    ports:
9
      - \"9090:9090\"
10
    volumes:
11
      - ./prometheus:/etc/prometheus
12
      - prometheus_data:/prometheus
13
    command:
14
      - '--config.file=/etc/prometheus/prometheus.yml'
15
      - '--storage.tsdb.path=/prometheus'
16
      - '--storage.tsdb.retention.time=15d'
17
      - '--web.console.libraries=/usr/share/prometheus/console_libraries'
18
      - '--web.console.templates=/usr/share/prometheus/consoles'
19

20
  node-exporter:
21
    image: prom/node-exporter:latest
22
    container_name: node-exporter
23
    restart: unless-stopped
24
    ports:
25
      - \"9100:9100\"
26
    volumes:
27
      - /proc:/host/proc:ro
28
      - /sys:/host/sys:ro
29
      - /:/rootfs:ro
30
    command:
31
      - '--path.procfs=/host/proc'
32
      - '--path.sysfs=/host/sys'
33
      - '--path.rootfs=/rootfs'
34
      - '--collector.filesystem.ignored-mount-points=^/(sys|proc|dev|host|etc)($$|/)'
35

36
volumes:
37
  prometheus_data:

1
global:
2
  scrape_interval: 15s
3
  evaluation_interval: 15s
4

5
scrape_configs:
6
  # Prometheus 自身指标
7
  - job_name: 'prometheus'
8
    static_configs:
9
      - targets: ['localhost:9090']
10

11
  # 服务器节点指标
12
  - job_name: 'node'
13
    static_configs:
14
      - targets: ['node-exporter:9100']
15

16
  # 如需监控其他服务器，在这里添加
17
  # - job_name: 'remote-node'
18
  #   static_configs:
19
  #     - targets: ['192.168.1.100:9100', '192.168.1.101:9100']
20

21
alerting:
22
  alertmanagers:
23
    - static_configs:
24
        - targets: ['alertmanager:9093']
25

26
rule_files:
27
  - 'alerts.yml'

1
groups:
2
  - name: node_alerts
3
    rules:
4
      - alert: HighCPUUsage
5
        expr: 100 - (avg by (instance) (rate(node_cpu_seconds_total{mode=\"idle\"}[5m])) * 100) > 80
6
        for: 5m
7
        labels:
8
          severity: warning
9
        annotations:
10
          summary: \"CPU 使用率超过 80% ({{ $value }}%)\"
11
          description: \"实例 {{ $labels.instance }} CPU 使用率已超过 80% 持续 5 分钟\"
12

13
      - alert: DiskSpaceLow
14
        expr: (node_filesystem_avail_bytes{mountpoint=\"/\"} / node_filesystem_size_bytes{mountpoint=\"/\"}) * 100 < 10
15
        for: 5m
16
        labels:
17
          severity: critical
18
        annotations:
19
          summary: \"磁盘空间不足 (剩余 {{ $value | humanizePercentage }})\"
20
          description: \"实例 {{ $labels.instance }} 根分区剩余空间不足 10%\"
21

22
      - alert: MemoryHigh
23
        expr: (1 - (node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes)) * 100 > 85
24
        for: 5m
25
        labels:
26
          severity: warning
27
        annotations:
28
          summary: \"内存使用率超过 85% ({{ $value }}%)\"
29
          description: \"实例 {{ $labels.instance }} 内存使用率已超过 85%\"