docker run -d \
  --name prometheus \
  -p 9090:9090 \
  -v /etc/prometheus/prometheus.yml:/etc/prometheus/prometheus.yml \
  prom/prometheus

version: '3.8'

services:
  prometheus:
    image: prom/prometheus:latest
    ports:
      - "9090:9090"
    volumes:
      - ./prometheus.yml:/etc/prometheus/prometheus.yml
      - prometheus_data:/prometheus
    command:
      - '--config.file=/etc/prometheus/prometheus.yml'
      - '--storage.tsdb.retention.time=30d'

  node_exporter:
    image: prom/node-exporter:latest
    ports:
      - "9100:9100"

  grafana:
    image: grafana/grafana:latest
    ports:
      - "3000:3000"

volumes:
  prometheus_data:

# 全局配置
global:
  scrape_interval:     15s   # 每15秒抓取一次
  evaluation_interval: 15s   # 每15秒评估告警规则
  scrape_timeout:      10s

# 告警规则文件
rule_files:
  - "rules/*.yml"

# Alertmanager 地址
alerting:
  alertmanagers:
    - static_configs:
        - targets: ['alertmanager:9093']

# 抓取目标配置
scrape_configs:
  # Prometheus 自监控
  - job_name: 'prometheus'
    static_configs:
      - targets: ['localhost:9090']

  # 主机监控
  - job_name: 'node'
    static_configs:
      - targets:
          - 'server1:9100'
          - 'server2:9100'
    relabel_configs:
      - source_labels: [__address__]
        target_label: instance

  # 动态发现（Kubernetes 示例）
  - job_name: 'kubernetes-pods'
    kubernetes_sd_configs:
      - role: pod

wget https://github.com/prometheus/node_exporter/releases/download/v1.8.0/node_exporter-1.8.0.linux-amd64.tar.gz
tar -xzf node_exporter-1.8.0.linux-amd64.tar.gz
sudo cp node_exporter-1.8.0.linux-amd64/node_exporter /usr/local/bin/

# 创建 systemd 服务
sudo tee /etc/systemd/system/node_exporter.service <<EOF
[Unit]
Description=Node Exporter

[Service]
User=node_exporter
ExecStart=/usr/local/bin/node_exporter

[Install]
WantedBy=multi-user.target
EOF

sudo useradd -rs /bin/false node_exporter
sudo systemctl enable --now node_exporter

# 选择指标（Instant Vector）
up

# 标签过滤（= 等于, != 不等于, =~ 正则, !~ 正则排除）
node_cpu_seconds_total{mode="idle", cpu="0"}

# 范围查询（过去5分钟的数据）
http_requests_total[5m]

# 位移（1小时前的数据）
http_requests_total offset 1h

# 算术运算
node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes * 100

# rate：每秒平均增长率（用于 Counter）
rate(http_requests_total[5m])

# irate：瞬时增长率（最近两个数据点）
irate(http_requests_total[5m])

# increase：时间段内的增量
increase(http_requests_total[1h])

# sum：按标签聚合求和
sum(http_requests_total) by (status_code)

# avg, max, min：平均/最大/最小
avg(node_load1) by (instance)

# topk / bottomk：前N个
topk(5, rate(http_requests_total[5m]))

# histogram_quantile：分位数（P99延迟）
histogram_quantile(0.99, rate(http_request_duration_seconds_bucket[5m]))

# predict_linear：线性预测
predict_linear(node_filesystem_free_bytes[6h], 3600)