完善中央与边缘部署、远程写入与监控文档

- 增加中央与边缘完整配置和部署脚本
- 引入 VictoriaMetrics 数据源与 remote_write 故障排查说明
- 新增 edge-agent 配置脚本、ONVIF 自建 exporter 与 ping 监控示例

Co-authored-by: Cursor <cursoragent@cursor.com>
This commit is contained in:
Super User
2026-02-25 04:24:40 -05:00
parent 9e37f79a36
commit 95a09fd9d8
52 changed files with 5978 additions and 0 deletions

View File

@@ -0,0 +1,90 @@
services:
# 中央Prometheus服务器
prometheus-central:
image: prom/prometheus:latest
container_name: prometheus-central
restart: unless-stopped
ports:
- "${PROMETHEUS_PORT:-9091}:9090"
volumes:
- ${PROMETHEUS_DATA_DIR:-./data/prometheus-data}:/prometheus
- ./prometheus.yml:/etc/prometheus/prometheus.yml:ro
- ./alert_rules.yml:/etc/prometheus/alert_rules.yml:ro
command:
- '--config.file=/etc/prometheus/prometheus.yml'
- "--storage.tsdb.retention.time=${PROMETHEUS_RETENTION_TIME:-30d}"
- '--web.console.libraries=/etc/prometheus/console_libraries'
- '--web.console.templates=/etc/prometheus/consoles'
- '--web.enable-lifecycle'
labels:
- "traefik.enable=${TRAEFIK_ENABLED:-true}"
- "traefik.http.routers.prometheus.rule=Host(`${PROMETHEUS_DOMAIN:-prometheus.example.com}`)"
- "traefik.http.routers.prometheus.entrypoints=${TRAEFIK_ENTRYPOINT:-web}"
- "traefik.http.routers.prometheus.service=prometheus"
- "traefik.http.services.prometheus.loadbalancer.server.port=9090"
- "traefik.docker.network=${TRAEFIK_NETWORK:-traefik}"
# Grafana仪表板
grafana:
image: grafana/grafana:latest
container_name: grafana
restart: unless-stopped
ports:
- "${GRAFANA_PORT:-3000}:3000"
environment:
- GF_SECURITY_ADMIN_PASSWORD=${GRAFANA_ADMIN_PASSWORD:-admin123}
- GF_METRICS_ENABLED=true
- GF_METRICS_BASIC_AUTH_ENABLED=false
- GF_DEFAULT_LANGUAGE=${GRAFANA_DEFAULT_LANGUAGE:-zh-Hans}
- GF_USERS_DEFAULT_THEME=${GRAFANA_DEFAULT_THEME:-light}
# 配置 Grafana 的根 URL用于 Traefik 反向代理)
- GF_SERVER_ROOT_URL=${GRAFANA_ROOT_URL:-http://localhost:3000}
volumes:
- ${GRAFANA_DATA_DIR:-./data/grafana-data}:/var/lib/grafana
- ./grafana/provisioning:/etc/grafana/provisioning
- ./grafana/dashboards:/var/lib/grafana/dashboards
labels:
- "traefik.enable=${TRAEFIK_ENABLED:-true}"
- "traefik.http.routers.grafana.rule=Host(`${GRAFANA_DOMAIN:-grafana.example.com}`)"
- "traefik.http.routers.grafana.entrypoints=${TRAEFIK_ENTRYPOINT:-web}"
- "traefik.http.routers.grafana.service=grafana"
- "traefik.http.services.grafana.loadbalancer.server.port=3000"
- "traefik.docker.network=${TRAEFIK_NETWORK:-traefik}"
# Alertmanager告警管理
alertmanager:
image: prom/alertmanager:latest
container_name: alertmanager
restart: unless-stopped
ports:
- "${ALERTMANAGER_PORT:-9093}:9093"
volumes:
- ./alertmanager/alertmanager.yml:/etc/alertmanager/alertmanager.yml:ro
labels:
- "traefik.enable=${TRAEFIK_ENABLED:-true}"
- "traefik.http.routers.alertmanager.rule=Host(`${ALERTMANAGER_DOMAIN:-alertmanager.example.com}`)"
- "traefik.http.routers.alertmanager.entrypoints=${TRAEFIK_ENTRYPOINT:-web}"
- "traefik.http.routers.alertmanager.service=alertmanager"
- "traefik.http.services.alertmanager.loadbalancer.server.port=9093"
- "traefik.docker.network=${TRAEFIK_NETWORK:-traefik}"
# 远程写入接收器 (VictoriaMetrics)
victoria-metrics:
image: victoriametrics/victoria-metrics:latest
container_name: victoria-metrics
restart: unless-stopped
ports:
- "${VICTORIAMETRICS_PORT:-8428}:8428"
volumes:
- ${VICTORIAMETRICS_DATA_DIR:-./data/victoria-metrics-data}:/victoria-metrics-data
command:
- '--storageDataPath=/victoria-metrics-data'
- "--retentionPeriod=${VICTORIAMETRICS_RETENTION_PERIOD:-30d}"
- "--httpListenAddr=:${VICTORIAMETRICS_PORT:-8428}"
# 定义网络配置(默认使用已存在的 traefik 网络)
networks:
default:
name: ${NETWORK_NAME:-traefik}
external: ${EXTERNAL_NETWORK:-true}