🏗️ 架构图

📖 Prometheus Docs

🚀 部署指南

Docker

docker run -d \
  -p 9090:9090 \
  -v /path/to/config:/etc/prometheus \  # 挂载配置文件目录
  -v /path/to/data:/prometheus \        # 挂载数据目录，确保数据持久化
  -e TZ=Asia/Shanghai \
  --memory="2g" \
  --cpus="1.0" \
  --user="$(id -u):$(id -g)" \
  --restart=unless-stopped \
  --name=prometheus \
  prom/prometheus:latest \
  --config.file=/etc/prometheus/prometheus.yml \
  --storage.tsdb.path=/prometheus \
  --storage.tsdb.retention.time=30d \
  --web.enable-lifecycle

Docker Compose

查看当前用户的UID和GID

id

services:
  prometheus:
    image: prom/prometheus:latest
    container_name: prometheus
    user: "${UID}:${GID}"
    restart: unless-stopped
    ports:
      - "9090:9090"
    volumes:
      - /path/to/config:/etc/prometheus  # 挂载配置文件目录
      - /path/to/data:/prometheus        # 挂载数据目录，确保数据持久化
    environment:
      - TZ=Asia/Shanghai
    command:
      - '--config.file=/etc/prometheus/prometheus.yml'
      - '--storage.tsdb.path=/prometheus'
      - '--storage.tsdb.retention.time=30d'
      - '--web.enable-lifecycle'
    deploy:
      resources:
        limits:
          memory: '2g'
          cpus: '1.0'

⚙️ 配置样例

📦 Prometheus (itself)

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: 10s       # scrape_timeout is set to the global default (10s).

# Alertmanager configuration
alerting:
  alertmanagers:
    - static_configs:
        - targets:
          # - alertmanager:9093

# Load rules once and periodically evaluate them according to the global 'evaluation_interval'.
rule_files:
# - "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'
    scrape_interval: 30s
    static_configs:
      - targets: [ 'localhost:9090' ]

Node exporter

1. 部署

   • Docker

   docker run -d \
     --net="host" \
     --pid="host" \
     -v "/:/host:ro,rslave" \
     --restart=unless-stopped \
     --name=node-exporter \
     quay.io/prometheus/node-exporter:latest \
     --path.rootfs=/host \
     --path.procfs=/host/proc \
     --path.sysfs=/host/sys \
     --collector.filesystem.mount-points-exclude=^/(sys|proc|dev|host|etc)($$|/)

   • Docker Compose

   services:
     node-exporter:
       image: quay.io/prometheus/node-exporter:latest
       container_name: node-exporter
       restart: unless-stopped
       network_mode: host
       pid: host
       volumes:
         - /:/host:ro,rslave
       command:
         - --path.rootfs=/host
         - --path.procfs=/host/proc
         - --path.sysfs=/host/sys
         - --collector.filesystem.mount-points-exclude=^/(sys|proc|dev|host|etc)($$|/)

2. 配置

   scrape_configs:
   
     - job_name: 'node-exporter'
       scrape_interval: 15s
       static_configs:
         - targets:
           - 'target.homelab.lan:9100'
       relabel_configs:
         # 使用 域名 或 IP地址 作为实例名，缩短名称长度
         - source_labels: [__address__]
           target_label: instance
           regex: '([^:]+):\d+'  # 捕获域名或IP地址
           replacement: '${1}'

3. 重启

   重启Prometheus服务以使配置生效，或采用文件服务发现，方法如下：

   scrape_configs:
   
     - job_name: 'node-exporter'
       scrape_interval: 15s
       static_configs:
         - targets:
           - 'server.homelab.lan:9100'
       file_sd_configs:
         - files:
             - '/etc/prometheus/targets/node-exporters.yml'
           refresh_interval: 1m
       relabel_configs:
         # 使用 域名 或 IP地址 作为实例名，缩短名称长度
         - source_labels: [__address__]
           target_label: instance
           regex: '([^:]+):\d+'  # 捕获域名或IP地址
           replacement: '${1}'

   • /etc/prometheus/targets/node-exporters.yml

   - targets:
       - 'server1.homelab.lan:9100'
       - 'server2.homelab.lan:9100'
       - 'server3.homelab.lan:9100'
     labels:
       group: 'production'

4. 图表

   • 1860 Node Exporter Full
   • 8919 TenSunS自动同步版
   • 16098 通用JOB分组版

cAdvisor

1. 部署

   • Docker

   VERSION=v0.49.1 # use the latest release version from https://github.com/google/cadvisor/releases
   sudo docker run \
     --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 \
     --privileged \
     --device=/dev/kmsg \
     gcr.io/cadvisor/cadvisor:$VERSION

   • Docker Compose

   services:
     cadvisor:
       image: gcr.io/cadvisor/cadvisor:${VERSION:-v0.49.1} # use the latest release version from https://github.com/google/cadvisor/releases
       container_name: cadvisor
       privileged: true
       ports:
         - "8080:8080"
       volumes:
         - '/:/rootfs:ro'
         - '/var/run:/var/run:ro'
         - '/sys:/sys:ro'
         - '/var/lib/docker/:/var/lib/docker:ro'
         - '/dev/disk/:/dev/disk:ro'
       devices:
         - '/dev/kmsg:/dev/kmsg'

2. 配置

   scrape_configs:
   
     - job_name: 'cadvisor'
       scrape_interval: 15s
       static_configs:
         - targets:
           - 'server.homelab.lan:8080'

3. 重启

   重启Prometheus服务以使配置生效，或采用文件服务发现。

4. 图表

   • 193 Docker monitoring
   • 19908 cAdvisor Docker Insights

DCGM-Exporter

1. 部署

   • Docker

   VERSION=4.4.1-4.6.0
   docker run -d \
     -p 9400:9400 \
     --gpus all \
     --cap-add SYS_ADMIN \
     --restart=unless-stopped \
     --name=dcgm-exporter \
     nvcr.io/nvidia/k8s/dcgm-exporter:${VERSION}-ubuntu22.04

   • Docker Compose

   services:
     dcgm-exporter:
       image: nvcr.io/nvidia/k8s/dcgm-exporter:{VERSION:-4.4.1-4.6.0}-ubuntu22.04
       container_name: dcgm-exporter
       restart: unless-stopped
       ports:
         - "9400:9400"
       deploy:
         resources:
           reservations:
             devices:
               - driver: nvidia
                 capabilities: [utility]
                 count: all
       cap_add:
         - SYS_ADMIN

   • Helm

   # 添加仓库
   helm repo add gpu-helm-charts https://nvidia.github.io/dcgm-exporter/helm-charts
   # 更新仓库
   helm repo update
   # 安装部署
   helm install --generate-name gpu-helm-charts/dcgm-exporter

2. 配置

   scrape_configs:
   
     - job_name: 'dcgm-exporter'
       scrape_interval: 15s
       metrics_path: /metrics
       static_configs:
         - targets:
           - 'server.homelab.lan:9400'

3. 重启

   重启Prometheus服务以使配置生效，或采用文件服务发现。

4. 图表

   • 12239 NVIDIA DCGM Exporter Dashboard

nvidia_gpu_exporter

1. 部署

   docker run -d \
     --name nvidia_smi_exporter \
     --restart unless-stopped \
     --device /dev/nvidiactl:/dev/nvidiactl \
     --device /dev/nvidia0:/dev/nvidia0 \
     -v /usr/lib/x86_64-linux-gnu/libnvidia-ml.so:/usr/lib/x86_64-linux-gnu/libnvidia-ml.so \
     -v /usr/lib/x86_64-linux-gnu/libnvidia-ml.so.1:/usr/lib/x86_64-linux-gnu/libnvidia-ml.so.1 \
     -v /usr/bin/nvidia-smi:/usr/bin/nvidia-smi \
     -p 9835:9835 \
     utkuozdemir/nvidia_gpu_exporter:1.3.1

2. 配置

3. 重启

   重启Prometheus服务以使配置生效，或采用文件服务发现。

MinIO

1. 部署

   不涉及。

2. 配置

   • 目录结构

   /etc/prometheus/
   ├── prometheus.yml
   ├── file_sd/
   │   └── minio-targets.yml
   └── secrets/
       ├── minio-token-prod
       └── minio-token-staging

   scrape_configs:
   
     - job_name: 'minio-cluster'
       scrape_interval: 15s
       metrics_path: /minio/v2/metrics/cluster
       scheme: https
       tls_config:
         insecure_skip_verify: false
       file_sd_configs:
         - files:
             - '/etc/prometheus/file_sd/minio-targets.yml'
           refresh_interval: 1m
       relabel_configs:
         # 从目标元数据中提取 Bearer Token 文件路径
         - source_labels: [__meta_minio_auth_token_file]
           target_label: __bearer_token_file
           replacement: /etc/prometheus/secrets/${1}
         # 动态配置 TLS
         - source_labels: [__meta_minio_tls_skip_verify]
           target_label: __tls_insecure_skip_verify
           regex: "false"
           replacement: "true"
         # 环境标识
         - source_labels: [__meta_minio_environment]
           target_label: environment
         - source_labels: [__meta_minio_cluster]
           target_label: cluster
         - source_labels: [__meta_minio_region]
           target_label: region
         # 使用 域名 或 IP地址 作为 实例名
         - source_labels: [__address__]
           target_label: instance
           regex: '([^:]+):\d+'  # 捕获域名或IP地址
           replacement: '${1}'
         - target_label: job
           replacement: "minio"

   • /etc/prometheus/file_sd/minio-targets.yml

   - targets:
       - 'minio.homelab.lan:9000'
     labels:
       # 环境标识
       environment: 'prod'
       cluster: 'xxx'
       region: 'us-east-1'
       # 元数据配置
       __meta_minio_auth_token_file: 'minio-token-prod'
       __meta_minio_tls_skip_verify: 'false'
   
   - targets:
       - 'minio.staging.homelab.lan:9000'
     labels:
       environment: 'staging'
       cluster: 'yyy'
       region: 'us-east-1'
       __meta_minio_auth_token_file: 'minio-token-staging'
       __meta_minio_tls_skip_verify: 'true'
   
   - targets:
       - 'minio.testing.homelab.lan:9000'
     labels:
       environment: 'testing'
       cluster: 'zzz'
       region: 'us-east-1'
       __meta_minio_auth_token_file: 'minio-token-testing'
       __meta_minio_tls_skip_verify: 'true'

3. 重启

   重启Prometheus服务以使配置生效，或采用文件服务发现。

MySQL Server Exporter

1. 部署

   docker run -d \
     -p 9104:9104 \
     -v ./my.cnf:/.my.cnf \
     --restart=unless-stopped \
     --name=mysqld-exporter \
     prom/mysqld-exporter:latest

   • my.cnf

   [client]
   user=exporter
   password=your_password
   [client.prod]
   host=mysql.homelab.lan
   port=3306
   [client.staging]
   host=mysql.staging.homelab.lan
   port=3306

2. 配置

   scrape_configs:
   
     - job_name: mysql
       scrape_interval: 30s
       metrics_path: /probe
       static_configs:
         - targets:
           - mysql.homelab.lan:3306
           - mysql.staging.homelab.lan:3306
       relabel_configs:
         - source_labels: [__address__]
           target_label: __param_target
           regex: '([^:]+)\.homelab\.lan:(\d+)'
           replacement: '${1}.homelab.lan:${2}'
         - source_labels: [__address__]
           target_label: instance
           regex: '([^:]+)\.homelab\.lan:\d+'
           replacement: '${1}'
         - target_label: __address__
           replacement: 'docker.homelab.lan:9104'

3. 重启

   重启Prometheus服务以使配置生效，或采用文件服务发现。

4. 图表

   • 7362 MySQL Overview
   • 14057 MySQL Exporter Quickstart and Dashboard

Prometheus Valkey & Redis Metrics Exporter

1. 部署

   docker run -d \
     -p 9121:9121 \
     --name redis_exporter \
     oliver006/redis_exporter

2. 配置

   scrape_configs:
   
     - job_name: redis
       scrape_interval: 30s
       metrics_path: /scrape
       static_configs:
         - targets:
           - redis://redis.homelab.lan:6379
           - redis://redis.staging.homelab.lan:6379
       relabel_configs:
         - source_labels: [__address__]
           target_label: __param_target
           regex: 'redis://([^:]+\.homelab\.lan:\d+)'
           replacement: 'redis://${1}'
         - source_labels: [__param_target]
           target_label: instance
           regex: 'redis://([^:]+)\.homelab\.lan:\d+'
           replacement: '${1}'
         - target_label: __address__
           replacement: 'docker.homelab.lan:9121'

3. 重启

   重启Prometheus服务以使配置生效，或采用文件服务发现。

4. 图表

   • 14091 Redis Exporter Quickstart and Dashboard

PostgreSQL Server Exporter

1. 部署

   # Start an example database
   docker run --net=host -it --rm -e POSTGRES_PASSWORD=password postgres
   # Connect to it
   docker run \
     --net=host \
     -e DATA_SOURCE_URI="localhost:5432/postgres?sslmode=disable" \
     -e DATA_SOURCE_USER=postgres \
     -e DATA_SOURCE_PASS=password \
     quay.io/prometheuscommunity/postgres-exporter

2. 配置

   scrape_configs:
   
     - job_name: postgres
       scrape_interval: 30s
       metrics_path: /metrics
       static_configs:
         - targets:
           - postgres.homelab.lan:9187
           - postgres.staging.homelab.lan:9187

3. 重启

   重启Prometheus服务以使配置生效，或采用文件服务发现。

4. 图表

   • 12485 PostgreSQL Exporter

APISIX prometheus plugin

1. 部署

   修改config.yaml配置文件

   plugin_attr:
     prometheus:                               # Plugin: prometheus attributes
       export_uri: /apisix/prometheus/metrics  # Set the URI for the Prometheus metrics endpoint.
       metric_prefix: apisix_                  # Set the prefix for Prometheus metrics generated by APISIX.
       enable_export_server: true              # Enable the Prometheus export server.
       export_addr:                            # Set the address for the Prometheus export server.
         ip: 127.0.0.1                         # Set the IP.
         port: 9091                            # Set the port.
       # metrics:                              # Create extra labels for metrics.
       #  http_status:                         # These metrics will be prefixed with `apisix_`.
       #    extra_labels:                      # Set the extra labels for http_status metrics.
       #      - upstream_addr: $upstream_addr
       #      - status: $upstream_status
       #    expire: 0                          # The expiration time of metrics in seconds.
                                               # 0 means the metrics will not expire.
       #  http_latency:
       #    extra_labels:                      # Set the extra labels for http_latency metrics.
       #      - upstream_addr: $upstream_addr
       #    expire: 0                          # The expiration time of metrics in seconds.
                                               # 0 means the metrics will not expire.
       #  bandwidth:
       #    extra_labels:                      # Set the extra labels for bandwidth metrics.
       #      - upstream_addr: $upstream_addr
       #    expire: 0                          # The expiration time of metrics in seconds.
                                               # 0 means the metrics will not expire.
       # default_buckets:                      # Set the default buckets for the `http_latency` metrics histogram.
       #   - 10
       #   - 50
       #   - 100
       #   - 200
       #   - 500
       #   - 1000
       #   - 2000
       #   - 5000
       #   - 10000
       #   - 30000
       #   - 60000
       #   - 500

2. 配置

   scrape_configs:
   
     - job_name: 'apisix'
       scrape_interval: 5s
       metrics_path: /apisix/prometheus/metrics
       static_configs:
         - targets:
           - 'apisix:9091'
           labels:
             service: 'apisix-gateway'
             component: 'api-gateway'

3. 重启

   重启Prometheus服务以使配置生效，或采用文件服务发现。

Blackbox exporter

1. 部署

   Note: You may want to enable ipv6 in your docker configuration

   docker run --rm \
     -p 9115/tcp \
     -v $(pwd):/config \
     --name blackbox_exporter \
     quay.io/prometheus/blackbox-exporter:latest \
     --config.file=/config/blackbox.yml

2. 配置

   scrape_configs:
   
     - job_name: blackbox_all
       metrics_path: /probe
       params:
         module: [ http_2xx ]  # Look for a HTTP 200 response.
       dns_sd_configs:
         - names:
             - example.com
             - prometheus.io
           type: A
           port: 443
       relabel_configs:
         - source_labels: [__address__]
           target_label: __param_target
           replacement: https://$1/  # Make probe URL be like https://1.2.3.4:443/
         - source_labels: [__param_target]
           target_label: instance
         - target_label: __address__
           replacement: 127.0.0.1:9115  # The blackbox exporter's real hostname:port.
         - source_labels: [__meta_dns_name]
           target_label: __param_hostname  # Make domain name become 'Host' header for probe requests
         - source_labels: [__meta_dns_name]
           target_label: vhost  # and store it in 'vhost' label

3. 重启

   重启Prometheus服务以使配置生效，或采用文件服务发现。

Windows exporter

1. 部署

   docker run -d \
     --restart=unless-stopped \
     --name=windows-exporter \
     prometheuscommunity/windows-exporter

2. 配置

3. 重启

   重启Prometheus服务以使配置生效，或采用文件服务发现。

💻 最佳实践

主机&容器 🔥🔥🔥

1. 部署

   networks:
     monitoring:
       driver: bridge
   
   services:
     node-exporter:  # Node Exporter - 收集主机系统指标
       image: quay.io/prometheus/node-exporter:latest
       container_name: node-exporter
       restart: unless-stopped
       pid: host
       ports:
         - 9100:9100
       volumes:
         - /:/host:ro,rslave
       command:
         - --path.rootfs=/host
         - --path.procfs=/host/proc
         - --path.sysfs=/host/sys
         - --collector.filesystem.mount-points-exclude=^/(sys|proc|dev|host|etc)($$|/)
       networks:
         - monitoring
   
     cadvisor:  # cAdvisor - 收集容器指标
       image: gcr.io/cadvisor/cadvisor:v0.49.1
       container_name: cadvisor
       restart: unless-stopped
       privileged: true
       ports:
         - 8080:8080
       volumes:
         - /:/rootfs:ro
         - /var/run:/var/run:ro
         - /sys:/sys:ro
         - /var/lib/docker/:/var/lib/docker:ro
         - /dev/disk/:/dev/disk:ro
       devices:
         - /dev/kmsg:/dev/kmsg
       networks:
         - monitoring

2. 配置

   scrape_configs:
   
     - job_name: 'node-exporter'
       scrape_interval: 15s
       static_configs:
         - targets:
           - 'target.homelab.lan:9100'
       relabel_configs:
         # 使用 域名 或 IP地址 作为实例名，缩短名称长度
         - source_labels: [__address__]
           target_label: instance
           regex: '([^:]+):\d+'  # 捕获域名或IP地址
           replacement: '${1}'
   
     - job_name: 'cadvisor'
       scrape_interval: 15s
       static_configs:
         - targets:
           - 'server.homelab.lan:8080'

3. 图表

   • 1860 Node Exporter Full
   • 16098 通用JOB分组版
   • 193 Docker monitoring
   • 19908 cAdvisor Docker Insights

1Panel 数据库三套件

1. 部署

   networks:
     1panel-network:
       external: true
   
   services:
   
     mysqld-exporter:  # MySQL
       image: prom/mysqld-exporter:latest
       container_name: mysqld-exporter
       restart: unless-stopped
       volumes:
         - ./my.cnf:/.my.cnf
       ports:
         - 9104:9104
       networks:
         - 1panel-network
   
     redis-exporter:  # Redis
       image: oliver006/redis_exporter:latest
       container_name: redis-exporter
       restart: unless-stopped
       ports:
         - 9121:9121
       environment:
         REDIS_ADDR: redis://redis.staging.homelab.lan:6379
         REDIS_PASSWORD: ${REDIS_PASSWORD}
       networks:
         - 1panel-network
   
     postgres-exporter:  # PostgreSQL
       image: quay.io/prometheuscommunity/postgres-exporter:latest
       container_name: postgres-exporter
       restart: unless-stopped
       network_mode: host
       environment:
         DATA_SOURCE_URI: postgresql:5432/postgres?sslmode=disable
         DATA_SOURCE_USER: ${POSTGRE_USERNAME}
         DATA_SOURCE_PASS: ${POSTGRE_PASSWORD}
       networks:
         - 1panel-network
   • my.cnf

   [client]
   user=exporter
   password=your_password
   [client.prod]
   host=mysql.homelab.lan
   port=3306
   [client.staging]
   host=mysql.staging.homelab.lan
   port=3306

   • .env

   COMPOSE_PROJECT_NAME=monitoring
   REDIS_PASSWORD=
   POSTGRE_USERNAME=
   POSTGRE_PASSWORD=

2. 配置

   scrape_configs:
   
     - job_name: mysql
       scrape_interval: 30s
       metrics_path: /probe
       static_configs:
         - targets:
           - mysql.homelab.lan:3306
           - mysql.staging.homelab.lan:3306
       relabel_configs:
         - source_labels: [__address__]
           target_label: __param_target
           regex: '([^:]+)\.homelab\.lan:(\d+)'
           replacement: '${1}.homelab.lan:${2}'
         - source_labels: [__address__]
           target_label: instance
           regex: '([^:]+)\.homelab\.lan:\d+'
           replacement: '${1}'
         - target_label: __address__
           replacement: 'docker.homelab.lan:9104'
   
     - job_name: redis
       scrape_interval: 30s
       metrics_path: /scrape
       static_configs:
         - targets:
           - redis://redis.homelab.lan:6379
           - redis://redis.staging.homelab.lan:6379
       relabel_configs:
         - source_labels: [__address__]
           target_label: __param_target
           regex: 'redis://([^:]+\.homelab\.lan:\d+)'
           replacement: 'redis://${1}'
         - source_labels: [__param_target]
           target_label: instance
           regex: 'redis://([^:]+)\.homelab\.lan:\d+'
           replacement: '${1}'
         - target_label: __address__
           replacement: 'docker.homelab.lan:9121'
   
     - job_name: postgres
       scrape_interval: 30s
       metrics_path: /metrics
       static_configs:
         - targets:
           - postgres.homelab.lan:9187
           - postgres.staging.homelab.lan:9187

3. 图表

   • 7362 MySQL Overview
   • 14091 Redis Exporter Quickstart and Dashboard
   • 12485 PostgreSQL Exporter

GPU

1. 部署

   networks:
     monitoring:
       driver: bridge
   
   services:
     dcgm-exporter:  # DCGM Exporter - 收集 NVIDIA GPU 指标
       image: nvcr.io/nvidia/k8s/dcgm-exporter:4.4.1-4.6.0-ubuntu22.04
       container_name: dcgm-exporter
       restart: unless-stopped
       ports:
         - "9400:9400"
       deploy:
         resources:
           reservations:
             devices:
               - driver: nvidia
                 capabilities: [utility]
                 count: all
       cap_add:
         - SYS_ADMIN
       networks:
         - monitoring

2. 配置

   scrape_configs:
   
     - job_name: 'dcgm-exporter'
       scrape_interval: 15s
       metrics_path: /metrics
       static_configs:
         - targets:
           - 'server.homelab.lan:9400'

3. 图表

   • 12239 Grafana Dashboard

贡献者: LiuKun, LiuKun/Windows

上一页PostgreSQL

下一页RAGFlow 部署指南