Add monitoring stack

monitoring/.env.example

@@ -0,0 +1,21 @@
+GRAFANA_ADMIN_USER=
+GRAFANA_ADMIN_PASSWORD=
+GRAFANA_DOMAIN=
+
+GRAFANA_SMTP_ENABLED=true
+GRAFANA_SMTP_HOST=
+GRAFANA_SMTP_USER=
+GRAFANA_SMTP_PASSWORD=
+GRAFANA_SMTP_FROM=
+
+GRAFANA_DATA_DIR=
+GRAFANA_DASHBOARDS_DIR=
+
+PROMETHEUS_CONFIG_PATH=
+PROMETHEUS_ALERT_RULES_PATH=
+PROMETHEUS_DATA_DIR=
+
+ALERTMANAGER_CONFIG_PATH=
+ALERTMANAGER_DATA_DIR=
+
+BLACKBOX_CONFIG_PATH=

monitoring/docker-compose.yml

@@ -0,0 +1,99 @@
+services:
+  # Prometheus - Metrics Collection
+  prometheus:
+    image: prom/prometheus:v3.9.1
+    restart: unless-stopped
+    ports:
+      - "9090:9090"
+    volumes:
+      - ${PROMETHEUS_CONFIG_PATH}:/etc/prometheus/prometheus.yml:ro
+      - ${PROMETHEUS_ALERT_RULES_PATH}:/etc/prometheus/alert_rules.yml
+      - ${PROMETHEUS_DATA_DIR}:/prometheus
+    command:
+      - '--config.file=/etc/prometheus/prometheus.yml'
+      - '--storage.tsdb.path=/prometheus'
+      - '--web.console.libraries=/etc/prometheus/console_libraries'
+      - '--web.console.templates=/etc/prometheus/consoles'
+      - '--storage.tsdb.retention.time=200h'
+      - '--web.enable-lifecycle'
+      - '--web.enable-admin-api'
+
+  # Grafana - Visualization Dashboard
+  grafana:
+    image: grafana/grafana:12.3.1
+    restart: unless-stopped
+    ports:
+      - "3002:3000"
+    volumes:
+      - ${GRAFANA_DATA_DIR}:/var/lib/grafana
+      - ./monitoring/grafana/provisioning:/etc/grafana/provisioning:ro
+      - ${GRAFANA_DASHBOARDS_DIR}:/var/lib/grafana/dashboards
+    environment:
+      - GF_SECURITY_ADMIN_USER=${GRAFANA_ADMIN_USER}
+      - GF_SECURITY_ADMIN_PASSWORD=${GRAFANA_ADMIN_PASSWORD}
+      - GF_USERS_ALLOW_SIGN_UP=false
+      - GF_SERVER_DOMAIN=${GRAFANA_DOMAIN}
+      - GF_SMTP_ENABLED=${GRAFANA_SMTP_ENABLED}
+      - GF_SMTP_HOST=${GRAFANA_SMTP_HOST}
+      - GF_SMTP_USER=${GRAFANA_SMTP_USER}
+      - GF_SMTP_PASSWORD=${GRAFANA_SMTP_PASSWORD}
+      - GF_SMTP_FROM_ADDRESS=${GRAFANA_SMTP_FROM}
+    depends_on:
+      - prometheus
+
+  # Node Exporter - Host System Metrics
+  node_exporter:
+    image: prom/node-exporter:v1.10.2
+    restart: unless-stopped
+    ports:
+      - "9100:9100"
+    volumes:
+      - /proc:/host/proc:ro
+      - /sys:/host/sys:ro
+      - /:/rootfs:ro
+    command:
+      - '--path.procfs=/host/proc'
+      - '--path.rootfs=/rootfs'
+      - '--path.sysfs=/host/sys'
+      - '--collector.filesystem.mount-points-exclude=^/(sys|proc|dev|host|etc)($$|/)'
+
+  # cAdvisor - Container Metrics
+  cadvisor:
+    image: gcr.io/cadvisor/cadvisor:v0.55.1
+    restart: unless-stopped
+    privileged: true
+    ports:
+      - "8081:8080"
+    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
+
+  # Alertmanager - Alert Management
+  alertmanager:
+    image: prom/alertmanager:v0.30.1
+    restart: unless-stopped
+    ports:
+      - "9093:9093"
+    volumes:
+      - ${ALERTMANAGER_CONFIG_PATH}:/etc/alertmanager/alertmanager.yml
+      - ${ALERTMANAGER_DATA_DIR}:/alertmanager
+    command:
+      - '--config.file=/etc/alertmanager/alertmanager.yml'
+      - '--storage.path=/alertmanager'
+      - '--web.external-url=http://localhost:9093'
+    depends_on:
+      - prometheus
+
+  # Blackbox Exporter - Endpoint Monitoring
+  blackbox_exporter:
+    image: prom/blackbox-exporter:v0.28.0
+    restart: unless-stopped
+    ports:
+      - "9115:9115"
+    volumes:
+      - ${BLACKBOX_CONFIG_PATH}:/etc/blackbox_exporter/config.yml

monitoring/grafana/provisioning/dashboards/homelab.yml

@@ -0,0 +1,12 @@
+apiVersion: 1
+
+providers:
+  - name: 'homelab-dashboards'
+    orgId: 1
+    folder: 'Homelab'
+    type: file
+    disableDeletion: false
+    updateIntervalSeconds: 10
+    allowUiUpdates: true
+    options:
+      path: /var/lib/grafana/dashboards

monitoring/grafana/provisioning/datasources/prometheus.yml

@@ -0,0 +1,9 @@
+apiVersion: 1
+
+datasources:
+  - name: Prometheus
+    type: prometheus
+    access: proxy
+    url: http://prometheus:9090
+    isDefault: true
+    editable: true