Prometheus安装与配置 #

一、安装概述 #

1.1 安装方式 #

text

Prometheus安装方式：

┌─────────────────────────────────────────────┐
│ 1. 二进制安装                               │
│    • 直接下载可执行文件                     │
│    • 适合Linux服务器                        │
│    • 手动配置和管理                         │
├─────────────────────────────────────────────┤
│ 2. Docker安装                               │
│    • 使用Docker容器                         │
│    • 快速部署                               │
│    • 易于管理                               │
├─────────────────────────────────────────────┤
│ 3. Kubernetes安装                           │
│    • 使用Helm或Operator                     │
│    • 云原生部署                             │
│    • 自动化管理                             │
├─────────────────────────────────────────────┤
│ 4. 包管理器安装                             │
│    • apt/yum/brew等                         │
│    • 系统包管理                             │
│    • 版本可能较旧                           │
└─────────────────────────────────────────────┘

1.2 系统要求 #

text

系统要求：

┌─────────────────────────────────────────────┐
│ 硬件要求                                    │
├─────────────────────────────────────────────┤
│ CPU: 2核以上                                │
│ 内存: 4GB以上（推荐8GB+）                   │
│ 磁盘: 根据数据保留时间决定                  │
│       • 1个采集目标约1GB/天                 │
│       • 推荐SSD存储                         │
├─────────────────────────────────────────────┤
│ 软件要求                                    │
├─────────────────────────────────────────────┤
│ 操作系统: Linux/macOS/Windows               │
│ 网络: 需要访问监控目标                      │
│ 端口: 9090（默认）                          │
└─────────────────────────────────────────────┘

二、二进制安装 #

2.1 下载安装 #

bash

# 下载Prometheus
cd /tmp

# Linux amd64
wget https://github.com/prometheus/prometheus/releases/download/v2.48.0/prometheus-2.48.0.linux-amd64.tar.gz

# 解压
tar xvfz prometheus-2.48.0.linux-amd64.tar.gz

# 移动到安装目录
sudo mv prometheus-2.48.0.linux-amd64 /usr/local/prometheus

# 创建数据目录
sudo mkdir -p /var/lib/prometheus

# 创建用户
sudo useradd -rs /bin/false prometheus
sudo chown -R prometheus:prometheus /usr/local/prometheus
sudo chown -R prometheus:prometheus /var/lib/prometheus

2.2 创建配置文件 #

yaml

# /usr/local/prometheus/prometheus.yml

global:
  scrape_interval: 15s
  evaluation_interval: 15s

alerting:
  alertmanagers:
    - static_configs:
        - targets: []

rule_files: []

scrape_configs:
  - job_name: 'prometheus'
    static_configs:
      - targets: ['localhost:9090']

2.3 创建系统服务 #

bash

# 创建systemd服务文件
sudo tee /etc/systemd/system/prometheus.service <<EOF
[Unit]
Description=Prometheus
Wants=network-online.target
After=network-online.target

[Service]
User=prometheus
Group=prometheus
Type=simple
ExecStart=/usr/local/prometheus/prometheus \
    --config.file=/usr/local/prometheus/prometheus.yml \
    --storage.tsdb.path=/var/lib/prometheus \
    --web.console.templates=/usr/local/prometheus/consoles \
    --web.console.libraries=/usr/local/prometheus/console_libraries \
    --web.listen-address=0.0.0.0:9090

[Install]
WantedBy=multi-user.target
EOF

# 重载systemd
sudo systemctl daemon-reload

# 启动服务
sudo systemctl start prometheus

# 设置开机自启
sudo systemctl enable prometheus

# 查看状态
sudo systemctl status prometheus

2.4 验证安装 #

bash

# 检查服务状态
sudo systemctl status prometheus

# 查看日志
sudo journalctl -u prometheus -f

# 访问Web界面
# 浏览器打开 http://localhost:9090

# 检查API
curl http://localhost:9090/api/v1/status/config

三、Docker安装 #

3.1 基本Docker运行 #

bash

# 创建配置目录
mkdir -p ~/prometheus
cd ~/prometheus

# 创建配置文件
cat > prometheus.yml <<EOF
global:
  scrape_interval: 15s
  evaluation_interval: 15s

scrape_configs:
  - job_name: 'prometheus'
    static_configs:
      - targets: ['localhost:9090']
EOF

# 运行容器
docker run -d \
    --name prometheus \
    -p 9090:9090 \
    -v ~/prometheus/prometheus.yml:/etc/prometheus/prometheus.yml \
    prom/prometheus

# 访问Web界面
# http://localhost:9090

3.2 Docker Compose部署 #

yaml

# docker-compose.yml

version: '3.8'

services:
  prometheus:
    image: prom/prometheus:v2.48.0
    container_name: prometheus
    restart: unless-stopped
    ports:
      - "9090:9090"
    volumes:
      - ./prometheus.yml:/etc/prometheus/prometheus.yml
      - ./alerts:/etc/prometheus/alerts
      - prometheus_data:/prometheus
    command:
      - '--config.file=/etc/prometheus/prometheus.yml'
      - '--storage.tsdb.path=/prometheus'
      - '--storage.tsdb.retention.time=30d'
      - '--web.console.libraries=/etc/prometheus/console_libraries'
      - '--web.console.templates=/etc/prometheus/consoles'
      - '--web.enable-lifecycle'
    networks:
      - monitoring

  node-exporter:
    image: prom/node-exporter:v1.7.0
    container_name: node-exporter
    restart: unless-stopped
    ports:
      - "9100:9100"
    volumes:
      - /proc:/host/proc:ro
      - /sys:/host/sys:ro
      - /:/rootfs:ro
    command:
      - '--path.procfs=/host/proc'
      - '--path.sysfs=/host/sys'
      - '--path.rootfs=/rootfs'
    networks:
      - monitoring

  alertmanager:
    image: prom/alertmanager:v0.26.0
    container_name: alertmanager
    restart: unless-stopped
    ports:
      - "9093:9093"
    volumes:
      - ./alertmanager.yml:/etc/alertmanager/alertmanager.yml
    networks:
      - monitoring

  grafana:
    image: grafana/grafana:10.2.0
    container_name: grafana
    restart: unless-stopped
    ports:
      - "3000:3000"
    volumes:
      - grafana_data:/var/lib/grafana
    environment:
      - GF_SECURITY_ADMIN_USER=admin
      - GF_SECURITY_ADMIN_PASSWORD=admin
    networks:
      - monitoring

networks:
  monitoring:
    driver: bridge

volumes:
  prometheus_data:
  grafana_data:

3.3 启动Docker Compose #

bash

# 创建目录
mkdir -p ~/prometheus-stack
cd ~/prometheus-stack

# 创建配置文件
# 创建 prometheus.yml
# 创建 alertmanager.yml

# 启动服务
docker-compose up -d

# 查看状态
docker-compose ps

# 查看日志
docker-compose logs -f prometheus

# 停止服务
docker-compose down

四、Kubernetes安装 #

4.1 使用Helm安装 #

bash

# 添加Prometheus仓库
helm repo add prometheus-community https://prometheus-community.github.io/helm-charts
helm repo update

# 搜索chart
helm search repo prometheus

# 创建命名空间
kubectl create namespace monitoring

# 安装Prometheus
helm install prometheus prometheus-community/prometheus \
    --namespace monitoring \
    --set server.persistentVolume.size=50Gi \
    --set server.retention=30d

# 查看状态
kubectl get pods -n monitoring

# 端口转发
kubectl port-forward -n monitoring svc/prometheus-server 9090:80

4.2 使用kube-prometheus-stack #

bash

# 安装kube-prometheus-stack（推荐）
helm repo add prometheus-community https://prometheus-community.github.io/helm-charts
helm repo update

# 创建values文件
cat > values.yaml <<EOF
prometheus:
  prometheusSpec:
    retention: 30d
    storageSpec:
      volumeClaimTemplate:
        spec:
          storageClassName: standard
          resources:
            requests:
              storage: 50Gi

alertmanager:
  alertmanagerSpec:
    storage:
      volumeClaimTemplate:
        spec:
          storageClassName: standard
          resources:
            requests:
              storage: 10Gi

grafana:
  adminPassword: admin
  persistence:
    enabled: true
    size: 10Gi
EOF

# 安装
helm install prometheus prometheus-community/kube-prometheus-stack \
    --namespace monitoring \
    -f values.yaml

# 访问服务
kubectl port-forward -n monitoring svc/prometheus-grafana 3000:80
kubectl port-forward -n monitoring svc/prometheus-kube-prometheus-prometheus 9090:9090

4.3 手动部署YAML #

yaml

# prometheus-deployment.yaml

apiVersion: v1
kind: Namespace
metadata:
  name: monitoring
---
apiVersion: v1
kind: ConfigMap
metadata:
  name: prometheus-config
  namespace: monitoring
data:
  prometheus.yml: |
    global:
      scrape_interval: 15s
      evaluation_interval: 15s

    scrape_configs:
      - job_name: 'prometheus'
        kubernetes_sd_configs:
          - role: endpoints
        relabel_configs:
          - source_labels: [__meta_kubernetes_namespace, __meta_kubernetes_service_name, __meta_kubernetes_endpoint_port_name]
            action: keep
            regex: monitoring;prometheus;web
---
apiVersion: apps/v1
kind: Deployment
metadata:
  name: prometheus
  namespace: monitoring
spec:
  replicas: 1
  selector:
    matchLabels:
      app: prometheus
  template:
    metadata:
      labels:
        app: prometheus
    spec:
      containers:
        - name: prometheus
          image: prom/prometheus:v2.48.0
          args:
            - "--config.file=/etc/prometheus/prometheus.yml"
            - "--storage.tsdb.path=/prometheus"
            - "--storage.tsdb.retention.time=30d"
          ports:
            - containerPort: 9090
          volumeMounts:
            - name: config
              mountPath: /etc/prometheus
            - name: storage
              mountPath: /prometheus
      volumes:
        - name: config
          configMap:
            name: prometheus-config
        - name: storage
          emptyDir: {}
---
apiVersion: v1
kind: Service
metadata:
  name: prometheus
  namespace: monitoring
spec:
  ports:
    - port: 9090
      targetPort: 9090
  selector:
    app: prometheus

bash

# 应用配置
kubectl apply -f prometheus-deployment.yaml

# 查看状态
kubectl get pods -n monitoring
kubectl get svc -n monitoring

五、配置详解 #

5.1 主配置文件结构 #

yaml

# prometheus.yml 完整配置示例

global:
  # 全局默认采集间隔
  scrape_interval: 15s
  
  # 全局默认规则评估间隔
  evaluation_interval: 15s
  
  # 采集超时时间
  scrape_timeout: 10s
  
  # 外部标签（用于联邦和远程存储）
  external_labels:
    cluster: 'production'
    region: 'cn-east'

# 告警管理器配置
alerting:
  alertmanagers:
    - static_configs:
        - targets:
          - 'alertmanager:9093'
      # 或使用服务发现
      # kubernetes_sd_configs:
      #   - role: endpoints

# 规则文件
rule_files:
  - '/etc/prometheus/alerts/*.yml'
  - '/etc/prometheus/rules/*.yml'

# 远程写入配置
remote_write:
  - url: 'http://remote-storage:9090/api/v1/write'
    queue_config:
      max_samples_per_send: 1000
      max_shards: 200

# 远程读取配置
remote_read:
  - url: 'http://remote-storage:9090/api/v1/read'
    read_recent: true

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

5.2 采集配置详解 #

yaml

# 采集配置示例

scrape_configs:
  # 基本配置
  - job_name: 'node-exporter'
    # 采集间隔（覆盖全局）
    scrape_interval: 10s
    # 采集超时
    scrape_timeout: 5s
    # 指标路径
    metrics_path: /metrics
    # 协议方案
    scheme: http
    
    # 静态配置
    static_configs:
      - targets:
          - 'node1:9100'
          - 'node2:9100'
        labels:
          env: 'production'
    
    # 文件服务发现
    file_sd_configs:
      - files:
          - '/etc/prometheus/targets/*.json'
        refresh_interval: 5m
    
    # Consul服务发现
    consul_sd_configs:
      - server: 'consul:8500'
        services: ['node-exporter']
    
    # Kubernetes服务发现
    kubernetes_sd_configs:
      - role: pod
        namespaces:
          names:
            - monitoring
    
    # 重新标记
    relabel_configs:
      - source_labels: [__meta_kubernetes_pod_label_app]
        target_label: app
      - source_labels: [__address__]
        target_label: instance
    
    # 指标重新标记
    metric_relabel_configs:
      - source_labels: [__name__]
        regex: 'go_.*'
        action: drop

5.3 告警规则配置 #

yaml

# alerts/rules.yml

groups:
  - name: node_alerts
    interval: 30s
    rules:
      - alert: NodeDown
        expr: up{job="node-exporter"} == 0
        for: 1m
        labels:
          severity: critical
        annotations:
          summary: "Node {{ $labels.instance }} is down"
          description: "Node {{ $labels.instance }} has been down for more than 1 minute."
      
      - alert: HighMemoryUsage
        expr: (1 - (node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes)) * 100 > 85
        for: 5m
        labels:
          severity: warning
        annotations:
          summary: "High memory usage on {{ $labels.instance }}"
          description: "Memory usage is {{ $value }}%"

  - name: application_alerts
    rules:
      - alert: HighErrorRate
        expr: rate(http_requests_total{status=~"5.."}[5m]) / rate(http_requests_total[5m]) > 0.05
        for: 5m
        labels:
          severity: critical
        annotations:
          summary: "High error rate detected"
          description: "Error rate is {{ $value | humanizePercentage }}"

六、启动参数 #

6.1 常用启动参数 #

bash

prometheus \
    # 配置文件
    --config.file=/etc/prometheus/prometheus.yml
    
    # 存储路径
    --storage.tsdb.path=/var/lib/prometheus
    
    # 数据保留时间
    --storage.tsdb.retention.time=30d
    
    # 最大数据块大小
    --storage.tsdb.max-block-duration=3h
    
    # 最小数据块大小
    --storage.tsdb.min-block-duration=2h
    
    # Web监听地址
    --web.listen-address=0.0.0.0:9090
    
    # Web最大连接数
    --web.max-connections=512
    
    # 启用生命周期API
    --web.enable-lifecycle
    
    # 启用管理API
    --web.enable-admin-api
    
    # 外部URL
    --web.external-url=http://prometheus.example.com
    
    # 并发查询数
    --query.max-concurrency=20
    
    # 查询超时
    --query.timeout=2m
    
    # 日志级别
    --log.level=info
    
    # 日志格式
    --log.format=logfmt

6.2 运行时配置 #

bash

# 热加载配置（需要启用 --web.enable-lifecycle）
curl -X POST http://localhost:9090/-/reload

# 优雅关闭
curl -X PUT http://localhost:9090/-/quit

# 查看运行状态
curl http://localhost:9090/api/v1/status/runtimeinfo

七、验证安装 #

7.1 检查服务状态 #

bash

# 检查进程
ps aux | grep prometheus

# 检查端口
netstat -tlnp | grep 9090

# 检查API
curl http://localhost:9090/api/v1/status/config

# 检查目标状态
curl http://localhost:9090/api/v1/targets

# 检查健康状态
curl http://localhost:9090/-/healthy

7.2 Web界面验证 #

text

访问 http://localhost:9090

检查项目：
├── Status → Targets
│   └── 查看采集目标状态
├── Graph
│   └── 执行查询测试
├── Status → Configuration
│   └── 查看配置信息
└── Status → Runtime Information
    └── 查看运行时信息

八、总结 #

安装方式对比：

方式	优点	缺点	适用场景
二进制	完全控制、无依赖	手动管理	生产服务器
Docker	快速部署、易管理	需要Docker	开发测试
Kubernetes	自动化、云原生	复杂度高	云原生环境

配置文件要点：

配置项	说明
global	全局配置
alerting	告警管理器
rule_files	规则文件
scrape_configs	采集配置

下一步，让我们学习Prometheus的基础概念！