refactor: 🧱 update monitoring stack (#411)

keinsell · Apr 11, 2024 · 2f2ad3c · 2f2ad3c
1 parent 299d97a
commit 2f2ad3c
Show file tree

Hide file tree

Showing 3 changed files with 127 additions and 141 deletions.
diff --git a/.idea/jsonSchemas.xml b/.idea/jsonSchemas.xml
diff --git a/infrastructure/layers/self-managed/11_monitoring/compose.yaml b/infrastructure/layers/self-managed/11_monitoring/compose.yaml
@@ -0,0 +1,98 @@
+name: monitoring
+services:
+  grafana:
+    image: grafana/grafana
+    user: '472'
+    restart: always
+    environment:
+      - GF_INSTALL_PLUGINS=grafana-clock-panel
+      - GF_RENDERING_SERVER_URL=http://renderer:8081/render
+      - GF_RENDERING_CALLBACK_URL=http://grafana:3000/
+    volumes:
+      - grafana_data:/var/lib/grafana
+      - ./grafana/provisioning/:/etc/grafana/provisioning/
+    env_file:
+      - ./grafana/config.monitoring
+    ports:
+      - 3000:3000
+    depends_on:
+      - prometheus
+    networks:
+      - monitoring
+
+  renderer:
+    image: grafana/grafana-image-renderer:latest
+    ports:
+      - 8081
+    networks:
+      - monitoring
+
+  prometheus:
+    image: prom/prometheus
+    restart: always
+    volumes:
+      - ./prometheus:/etc/prometheus/
+      - prometheus_data:/prometheus
+    command:
+      - '--config.file=/etc/prometheus/prometheus.yml'
+      - '--storage.tsdb.path=/prometheus'
+      - '--web.console.libraries=/usr/share/prometheus/console_libraries'
+      - '--web.console.templates=/usr/share/prometheus/consoles'
+    depends_on:
+      - node-exporter
+      - cadvisor
+    networks:
+      - monitoring
+
+  node-exporter:
+    image: prom/node-exporter
+    volumes:
+      - /proc:/host/proc:ro
+      - /sys:/host/sys:ro
+      - /:/rootfs:ro
+    command:
+      - '--path.procfs=/host/proc'
+      - '--path.sysfs=/host/sys'
+      - --collector.filesystem.ignored-mount-points
+      - '^/(sys|proc|dev|host|etc|rootfs/var/lib/docker/containers|rootfs/var/lib/docker/overlay2|rootfs/run/docker/netns|rootfs/var/lib/docker/aufs)($$|/)'
+    ports:
+      - 9100:9100
+    restart: always
+    privileged: true
+    deploy:
+      mode: global
+    networks:
+      - monitoring
+
+  cadvisor:
+    image: gcr.io/cadvisor/cadvisor
+    container_name: cadvisor
+    privileged: true
+    cgroup: host
+    userns_mode: "host"
+    ipc: private
+    shm_size: 128M
+    expose:
+      - "8080"
+    networks:
+      - monitoring
+    volumes:
+      - /:/rootfs:ro
+      - /var/run:/var/run:rw
+      - /sys:/sys:ro
+      - /var/lib/docker/:/var/lib/docker:ro
+      - /dev/disk/:/dev/disk:ro
+      # Fucking cgroup bullshit
+      - /sys/fs/cgroup:/sys/fs/cgroup:ro
+    deploy:
+      mode: global
+
+networks:
+  monitoring:
+    name: monitoring
+
+volumes:
+  grafana_data:
+    name: "grafana_data"
+  prometheus_data:
+    name: "prometheus_data"
diff --git a/infrastructure/layers/self-managed/docker-compose.yml b/infrastructure/layers/self-managed/docker-compose.yml
@@ -111,36 +111,6 @@ services:
       - docker_proxy
 
   # ----------------------------------------
-  # Server Dashboard
-  # ----------------------------------------
-  # There is a need for two dashboards, the one
-  # for the public network and people who ten use
-  # my infrastructure and applications and
-  # the second one for the internal network and
-  # mostly myself.
-  #
-  # https://github.com/ProductiveOps/dokemon
-  # https://github.com/louislam/dockge?tab=readme-ov-file
-  # https://github.com/hywax/mafl
-  # https://github.com/ordinary-dev/phoenix
-  # ----------------------------------------
-  homepage:
-    image: ghcr.io/gethomepage/homepage:latest
-    container_name: homepage
-    labels:
-      - "traefik.enable=true"
-      - "traefik.http.routers.homepage.rule=PathPrefix(`/`)"
-      - "traefik.http.routers.homepage.entrypoints=http"
-    ports:
-      - 3010:3000
-    volumes:
-      - type: bind
-        source: ./homepage
-        target: /app/config
-    networks:
-      - docker_proxy
-      - reverse_proxy
-  # ----------------------------------------
 
   # ----------------------------------------
   # Object Storage
@@ -331,117 +301,6 @@ services:
   # TODO: IPFS
   # ----------------------------------------
 
-  # ----------------------------------------
-  # Observability Services
-  # ----------------------------------------
-  # These are the core services that are required
-  # to run the application.
-  # ----------------------------------------
-  prometheus:
-    image: prom/prometheus
-    restart: always
-    labels:
-      - "traefik.enable=true"
-      - "traefik.http.routers.prometheus.rule=Host(`prometheus.${DOMAIN}`)"
-      - "traefik.http.services.prometheus.loadbalancer.server.port=9090"
-      - "traefik.http.routers.prometheus.entrypoints=http"
-    volumes:
-      - ./prometheus:/etc/prometheus/
-      - prometheus_data:/prometheus
-    command:
-      - '--config.file=/etc/prometheus/prometheus.yml'
-      - '--storage.tsdb.path=/prometheus'
-      - '--web.console.libraries=/usr/share/prometheus/console_libraries'
-      - '--web.console.templates=/usr/share/prometheus/consoles'
-    depends_on:
-      - node-exporter
-      - cadvisor
-    deploy:
-      resources: *resource-preset-x025
-      restart_policy: *restart_policy
-    networks:
-      - monitoring
-
-  node-exporter:
-    image: prom/node-exporter
-    volumes:
-      - /proc:/host/proc:ro
-      - /sys:/host/sys:ro
-      - /:/rootfs:ro
-    command:
-      - '--path.procfs=/host/proc'
-      - '--path.sysfs=/host/sys'
-      - --collector.filesystem.ignored-mount-points
-      - '^/(sys|proc|dev|host|etc|rootfs/var/lib/docker/containers|rootfs/var/lib/docker/overlay2|rootfs/run/docker/netns|rootfs/var/lib/docker/aufs)($$|/)'
-    ports:
-      - 9100:9100
-    restart: always
-    deploy:
-      mode: global
-      resources: *resource-preset-x025
-      restart_policy: *restart_policy
-    networks:
-      - monitoring
-
-  # https://gvisor.dev/
-  cadvisor:
-    image: gcr.io/cadvisor/cadvisor
-    container_name: cadvisor
-    privileged: true
-    cgroup: host
-    userns_mode: "host"
-    ipc: private
-    shm_size: 128M
-    expose:
-      - "8080"
-    networks:
-      - monitoring
-    volumes:
-      - /:/rootfs:ro
-      - /var/run:/var/run:rw
-      - /sys:/sys:ro
-      - /var/lib/docker/:/var/lib/docker:ro
-      - /dev/disk/:/dev/disk:ro
-      # Fucking cgroup bullshit
-      - /sys/fs/cgroup:/sys/fs/cgroup:ro
-    deploy:
-      mode: global
-      resources: *resource-preset-x025
-      restart_policy: *restart_policy
-
-  grafana:
-    image: grafana/grafana
-    user: '472'
-    restart: always
-    environment:
-      - GF_INSTALL_PLUGINS=grafana-clock-panel
-      - GF_RENDERING_SERVER_URL=http://renderer:8081/render
-      - GF_RENDERING_CALLBACK_URL=http://grafana:3000/
-    volumes:
-      - grafana_data:/var/lib/grafana
-      - ./grafana/provisioning/:/etc/grafana/provisioning/
-    env_file:
-      - 11_monitoring/grafana/config.monitoring
-    ports:
-      - 3000:3000
-    depends_on:
-      - prometheus
-    deploy:
-      resources: *resource-preset-x025
-      restart_policy: *restart_policy
-    networks:
-      - monitoring
-
-  renderer:
-    image: grafana/grafana-image-renderer:latest
-    ports:
-      - 8081
-    deploy:
-      resources: *resource-preset-x025
-      restart_policy: *restart_policy
-    networks:
-      - monitoring
-
   # TODO: HyperDX
   # TODO: Grafana
   # TODO: Prometheus