created monitoring stack

2026-06-03 00:28:45 -07:00
parent 57d779d5d1
commit 51b2bac037
5 changed files with 271 additions and 0 deletions
@@ -0,0 +1,127 @@
+services:
+  loki:
+    image: grafana/loki:${LOKI_VERSION:-3.7.2}
+    container_name: monitor-loki
+    volumes:
+      - ${MONITOR_STACK_CONFIG_PATH}/loki-config.yml:/etc/loki/local-config.yaml
+      - loki_data:/loki
+    command: -config.file=/etc/loki/local-config.yaml
+    environment:
+      - TZ=${TZ:-America/Los_Angeles}
+    networks:
+      - monitor_network
+    healthcheck:
+      test: ["CMD-SHELL", "wget --no-verbose --tries=1 --spider http://localhost:3100/ready || exit 1"]
+      interval: 15s
+      timeout: 5s
+      retries: 5
+      start_period: 30s
+    deploy:
+      resources:
+        limits:
+          memory: 512m
+    restart: unless-stopped
+
+  prometheus:
+    image: prom/prometheus:${PROMETHEUS_VERSION:-3.12.0}
+    container_name: prometheus
+    ports:
+      - "${PROMETHEUS_PORT:-9090}:9090"
+    volumes:
+      - ${MONITOR_STACK_CONFIG_PATH}/prometheus.yml:/etc/prometheus/prometheus.yml
+      - prometheus_data:/prometheus
+    command:
+      - '--config.file=/etc/prometheus/prometheus.yml'
+      - '--storage.tsdb.path=/prometheus'
+      - '--storage.tsdb.retention.time=30d'
+      - '--web.enable-lifecycle'
+    environment:
+      - TZ=${TZ:-America/Los_Angeles}
+    networks:
+      - monitor_network
+    healthcheck:
+      test: ["CMD-SHELL", "wget --no-verbose --tries=1 --spider http://localhost:9090/-/healthy || exit 1"]
+      interval: 15s
+      timeout: 5s
+      retries: 5
+      start_period: 30s
+    deploy:
+      resources:
+        limits:
+          memory: 512m
+    restart: unless-stopped
+
+  alertmanager:
+    image: prom/alertmanager:${ALERTMANAGER_VERSION:-0.32.1}
+    container_name: alertmanager
+    ports:
+      - "${ALERTMANAGER_PORT:-9093}:9093"
+    volumes:
+      - ${MONITOR_STACK_CONFIG_PATH}/alertmanager.yml:/etc/alertmanager/alertmanager.yml
+      - alertmanager_data:/alertmanager
+    command:
+      - '--config.file=/etc/alertmanager/alertmanager.yml'
+      - '--storage.path=/alertmanager'
+    environment:
+      - TZ=${TZ:-America/Los_Angeles}
+    networks:
+      - monitor_network
+    healthcheck:
+      test: ["CMD-SHELL", "wget --no-verbose --tries=1 --spider http://localhost:9093/-/healthy || exit 1"]
+      interval: 15s
+      timeout: 5s
+      retries: 5
+      start_period: 30s
+    deploy:
+      resources:
+        limits:
+          memory: 512m
+    restart: unless-stopped
+
+  grafana:
+    image: grafana/grafana:${GRAFANA_VERSION:-13.0.1}
+    container_name: grafana
+    ports:
+      - "${GRAFANA_PORT:-3000}:3000"
+    volumes:
+      - grafana_data:/var/lib/grafana
+    environment:
+      - TZ=${TZ:-America/Los_Angeles}
+      - GF_SECURITY_ADMIN_USER=${GRAFANA_ADMIN_USER:-admin}
+      - GF_SECURITY_ADMIN_PASSWORD=${GRAFANA_ADMIN_PASSWORD:-changeme}
+      - GF_SECURITY_SECRET_KEY=${GRAFANA_SECRET_KEY}
+      - GF_LOG_MODE=console
+    depends_on:
+      loki:
+        condition: service_healthy
+      prometheus:
+        condition: service_healthy
+      alertmanager:
+        condition: service_healthy
+    networks:
+      - monitor_network
+    healthcheck:
+      test: ["CMD-SHELL", "wget --no-verbose --tries=1 --spider http://localhost:3000/api/health || exit 1"]
+      interval: 15s
+      timeout: 5s
+      retries: 5
+      start_period: 30s
+    deploy:
+      resources:
+        limits:
+          memory: 512m
+    restart: unless-stopped
+
+volumes:
+  loki_data:
+    name: loki_data
+  prometheus_data:
+    name: prometheus_data
+  alertmanager_data:
+    name: alertmanager_data
+  grafana_data:
+    name: grafana_data
+
+networks:
+  monitor_network:
+    external: true