refactor(specs): merge 08-infrastructure into canonical 04-06 dirs

- Append live QNAP configs to 04-01-docker-compose.md (Appendix A) - MariaDB+PMA, Redis+Elasticsearch, NPM, Gitea, n8n, App stack - Append SSH setup + Secrets management to 04-06-security-operations.md - Appendix A: SSH key setup, config, hardening, port forwarding - Appendix B: .env structure, secret generation, rotation, GPG backup - Append QNAP/Gitea CI/CD docs to 04-04-deployment-guide.md - Appendix A: Container Station deployment steps - Appendix B: Gitea Actions CI/CD pipeline setup - Appendix C: act_runner (ASUSTOR) installation - Move Git_command.md -> 05-Engineering-Guidelines/05-05-git-cheatsheet.md - Move docker-compose-app.yml, lcbp3-monitoring.yml, lcbp3-registry.yml, grafana/ -> 04-Infrastructure-OPS/ - Archive lcbp3-db.md -> 99-archives/ - Remove all legacy 08-infrastructure/* files from git - Remove Google OAuth client_secret JSON from git index (security) - Add .gitignore rules: *client_secret*.json, *service_account*.json, specs/08-infrastructure/ - Update 04-Infrastructure-OPS/README.md with new file index
2026-02-23 15:03:35 +07:00
parent b7676777e8
commit 5eff8861e1
23 changed files with 808 additions and 1971 deletions
--- a/specs/04-Infrastructure-OPS/lcbp3-monitoring.yml
+++ b/specs/04-Infrastructure-OPS/lcbp3-monitoring.yml
@@ -0,0 +1,232 @@
+# File: /volume1/np-dms/monitoring/docker-compose.yml
+# DMS Container v1.8.0: Application name: lcbp3-monitoring
+# Deploy on: ASUSTOR AS5403T
+# Services: prometheus, grafana, node-exporter, cadvisor, uptime-kuma, loki, promtail
+
+x-restart: &restart_policy
+  restart: unless-stopped
+
+x-logging: &default_logging
+  logging:
+    driver: "json-file"
+    options:
+      max-size: "10m"
+      max-file: "5"
+
+networks:
+  lcbp3:
+    external: true
+
+services:
+  # ----------------------------------------------------------------
+  # 1. Prometheus (Metrics Collection & Storage)
+  # ----------------------------------------------------------------
+  prometheus:
+    <<: [*restart_policy, *default_logging]
+    image: prom/prometheus:v2.48.0
+    container_name: prometheus
+    stdin_open: true
+    tty: true
+    deploy:
+      resources:
+        limits:
+          cpus: "1.0"
+          memory: 1G
+        reservations:
+          cpus: "0.25"
+          memory: 256M
+    environment:
+      TZ: "Asia/Bangkok"
+    command:
+      - '--config.file=/etc/prometheus/prometheus.yml'
+      - '--storage.tsdb.path=/prometheus'
+      - '--storage.tsdb.retention.time=30d'
+      - '--web.enable-lifecycle'
+    ports:
+      - "9090:9090"
+    networks:
+      - lcbp3
+    volumes:
+      - "/volume1/np-dms/monitoring/prometheus/config:/etc/prometheus:ro"
+      - "/volume1/np-dms/monitoring/prometheus/data:/prometheus"
+    healthcheck:
+      test: ["CMD", "wget", "--spider", "-q", "http://localhost:9090/-/healthy"]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+
+  # ----------------------------------------------------------------
+  # 2. Grafana (Dashboard & Visualization)
+  # ----------------------------------------------------------------
+  grafana:
+    <<: [*restart_policy, *default_logging]
+    image: grafana/grafana:10.2.2
+    container_name: grafana
+    stdin_open: true
+    tty: true
+    deploy:
+      resources:
+        limits:
+          cpus: "1.0"
+          memory: 512M
+        reservations:
+          cpus: "0.25"
+          memory: 128M
+    environment:
+      TZ: "Asia/Bangkok"
+      GF_SECURITY_ADMIN_USER: admin
+      GF_SECURITY_ADMIN_PASSWORD: "Center#2025"
+      GF_SERVER_ROOT_URL: "https://grafana.np-dms.work"
+      GF_INSTALL_PLUGINS: grafana-clock-panel,grafana-piechart-panel
+    ports:
+      - "3000:3000"
+    networks:
+      - lcbp3
+    volumes:
+      - "/volume1/np-dms/monitoring/grafana/data:/var/lib/grafana"
+    depends_on:
+      - prometheus
+    healthcheck:
+      test: ["CMD-SHELL", "wget --spider -q http://localhost:3000/api/health || exit 1"]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+
+  # ----------------------------------------------------------------
+  # 3. Uptime Kuma (Service Availability Monitoring)
+  # ----------------------------------------------------------------
+  uptime-kuma:
+    <<: [*restart_policy, *default_logging]
+    image: louislam/uptime-kuma:1
+    container_name: uptime-kuma
+    deploy:
+      resources:
+        limits:
+          cpus: "0.5"
+          memory: 256M
+    environment:
+      TZ: "Asia/Bangkok"
+    ports:
+      - "3001:3001"
+    networks:
+      - lcbp3
+    volumes:
+      - "/volume1/np-dms/monitoring/uptime-kuma/data:/app/data"
+    healthcheck:
+      test: ["CMD-SHELL", "curl -f http://localhost:3001/api/entry-page || exit 1"]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+
+  # ----------------------------------------------------------------
+  # 4. Node Exporter (Host Metrics - ASUSTOR)
+  # ----------------------------------------------------------------
+  node-exporter:
+    <<: [*restart_policy, *default_logging]
+    image: prom/node-exporter:v1.7.0
+    container_name: node-exporter
+    deploy:
+      resources:
+        limits:
+          cpus: "0.5"
+          memory: 128M
+    environment:
+      TZ: "Asia/Bangkok"
+    command:
+      - '--path.procfs=/host/proc'
+      - '--path.sysfs=/host/sys'
+      - '--collector.filesystem.mount-points-exclude=^/(sys|proc|dev|host|etc)($$|/)'
+    ports:
+      - "9100:9100"
+    networks:
+      - lcbp3
+    volumes:
+      - /proc:/host/proc:ro
+      - /sys:/host/sys:ro
+      - /:/rootfs:ro
+    healthcheck:
+      test: ["CMD", "wget", "--spider", "-q", "http://localhost:9100/metrics"]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+
+  # ----------------------------------------------------------------
+  # 5. cAdvisor (Container Metrics - ASUSTOR)
+  # ----------------------------------------------------------------
+  cadvisor:
+    <<: [*restart_policy, *default_logging]
+    image: gcr.io/cadvisor/cadvisor:v0.47.2
+    container_name: cadvisor
+    deploy:
+      resources:
+        limits:
+          cpus: "0.5"
+          memory: 256M
+    environment:
+      TZ: "Asia/Bangkok"
+    ports:
+      - "8088:8088"
+    networks:
+      - lcbp3
+    volumes:
+      - /:/rootfs:ro
+      - /var/run:/var/run:ro
+      - /sys:/sys:ro
+      - /var/lib/docker/:/var/lib/docker:ro
+    healthcheck:
+      test: ["CMD", "wget", "--spider", "-q", "http://localhost:8080/healthz"]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+
+  # ----------------------------------------------------------------
+  # 6. Loki (Log Aggregation)
+  # ----------------------------------------------------------------
+  loki:
+    <<: [*restart_policy, *default_logging]
+    image: grafana/loki:2.9.0
+    container_name: loki
+    deploy:
+      resources:
+        limits:
+          cpus: "0.5"
+          memory: 512M
+    environment:
+      TZ: "Asia/Bangkok"
+    command: -config.file=/etc/loki/local-config.yaml
+    ports:
+      - "3100:3100"
+    networks:
+      - lcbp3
+    volumes:
+      - "/volume1/np-dms/monitoring/loki/data:/loki"
+    healthcheck:
+      test: ["CMD", "wget", "--spider", "-q", "http://localhost:3100/ready"]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+
+  # ----------------------------------------------------------------
+  # 7. Promtail (Log Shipper)
+  # ----------------------------------------------------------------
+  promtail:
+    <<: [*restart_policy, *default_logging]
+    image: grafana/promtail:2.9.0
+    container_name: promtail
+    user: "0:0"
+    deploy:
+      resources:
+        limits:
+          cpus: "0.5"
+          memory: 256M
+    environment:
+      TZ: "Asia/Bangkok"
+    command: -config.file=/etc/promtail/promtail-config.yml
+    networks:
+      - lcbp3
+    volumes:
+      - "/volume1/np-dms/monitoring/promtail/config:/etc/promtail:ro"
+      - "/var/run/docker.sock:/var/run/docker.sock:ro"
+      - "/var/lib/docker/containers:/var/lib/docker/containers:ro"
+    depends_on:
+      - loki