Initial commit: Project setup and switch to VictoriaLogs for observability, with updated tech stack requirements.

infra/docker-compose.yml

@@ -1,6 +1,10 @@
 version: '3.8'
 
 services:
+  # ------------------------------------------------------------------
+  # Core Services
+  # ------------------------------------------------------------------
+
   postgres:
     image: postgres:15
     container_name: camel_ops_db
@@ -13,26 +17,99 @@ services:
     volumes:
       - pg_data:/var/lib/postgresql/data
     restart: unless-stopped
+    networks:
+      - appliance-network
 
+  # ------------------------------------------------------------------
+  # Appliance Hub: Persistence, Telemetry & Alerting
+  # ------------------------------------------------------------------
+
+  # Time Series Database
   victoriametrics:
-    image: victoriametrics/victoria-metrics:v1.93.0
-    container_name: camel_ops_vm
+    image: victoriametrics/victoria-metrics:v1.93.3
     ports:
       - "8428:8428"
     command:
-      - "--retentionPeriod=1y"
+      - "--retentionPeriod=1y" # From my original commit
+      - "--storageDataPath=/vmetrics-data"
+      - "--httpListenAddr=:8428"
     volumes:
-      - vm_data:/victoria-metrics-data
+      - vmetrics-data:/vmetrics-data
+    restart: unless-stopped
+    networks:
+      - appliance-network
+
+  # Alert Evaluation Engine
+  vmalert:
+    image: victoriametrics/vmalert:v1.93.3
+    ports:
+      - "8880:8880"
+    command:
+      - "-rule=/etc/alerts/alerts.yml"
+      - "-datasource.url=http://victoriametrics:8428"
+      - "-notifier.url=http://alertmanager:9093"
+      - "-remoteWrite.url=http://victoriametrics:8428"
+      - "-remoteRead.url=http://victoriametrics:8428"
+    volumes:
+      - ./alerts:/etc/alerts
+    depends_on:
+      - victoriametrics
+      - alertmanager
+    networks:
+      - appliance-network
     restart: unless-stopped
 
-  loki:
-    image: grafana/loki:2.9.2
-    container_name: camel_ops_loki
+  # Alert Routing, Grouping, Deduplication
+  alertmanager:
+    image: prom/alertmanager:v0.26.0
     ports:
-      - "3100:3100"
-    command: -config.file=/etc/loki/local-config.yaml
+      - "9093:9093"
+    command:
+      - "--config.file=/etc/alertmanager/config.yml"
+      - "--storage.path=/alertmanager"
+    volumes:
+      - ./alertmanager-config.yml:/etc/alertmanager/config.yml
+      - alertmanager-data:/alertmanager
+    networks:
+      - appliance-network
+    restart: unless-stopped
+
+  # Log Aggregation (VictoriaLogs instead of Loki)
+  victorialogs:
+    image: victoriametrics/victorialogs:v0.40.0 # Using a recent version, replace v2.9.1 Loki with VictoriaLogs
+    ports:
+      - "9428:9428" # Default VictoriaLogs port
+    command:
+      - "-storageDataPath=/victorialogs-data"
+      - "-httpListenAddr=:9428"
+    volumes:
+      - victorialogs-data:/victorialogs-data
+    networks:
+      - appliance-network
+    restart: unless-stopped
+
+  # OpenTelemetry Collector (receives from Worker nodes)
+  otel-collector:
+    image: otel/opentelemetry-collector-contrib:0.87.0
+    ports:
+      - "4317:4317" # OTLP gRPC
+      - "4318:4318" # OTLP HTTP
+    command: ["--config=/etc/otelcol/config.yaml"]
+    volumes:
+      - ./otel-config.yaml:/etc/otelcol/config.yaml
+    depends_on:
+      - victoriametrics
+      - victorialogs # Depend on victorialogs now
+    networks:
+      - appliance-network
     restart: unless-stopped
 
 volumes:
   pg_data:
-  vm_data:
+  vmetrics-data:
+  alertmanager-data:
+  victorialogs-data: # New volume for VictoriaLogs
+
+networks:
+  appliance-network:
+    driver: bridge