fix(obs): Update observability docker compose stack (#2010)

.docker/observability/docker-compose.yml

@@ -13,93 +13,149 @@
 # limitations under the License.
 
 services:
+  rustfs:
+    security_opt:
+      - "no-new-privileges:true"
+    image: rustfs/rustfs:latest
+    container_name: rustfs-server
+    ports:
+      - "9000:9000" # S3 API port
+      - "9001:9001" # Console port
+    environment:
+      - RUSTFS_VOLUMES=/data/rustfs
+      - RUSTFS_ADDRESS=0.0.0.0:9000
+      - RUSTFS_CONSOLE_ADDRESS=0.0.0.0:9001
+      - RUSTFS_CONSOLE_ENABLE=true
+      - RUSTFS_CORS_ALLOWED_ORIGINS=*
+      - RUSTFS_CONSOLE_CORS_ALLOWED_ORIGINS=*
+      - RUSTFS_ACCESS_KEY=rustfsadmin
+      - RUSTFS_SECRET_KEY=rustfsadmin
+      - RUSTFS_OBS_LOGGER_LEVEL=info
+      - RUSTFS_OBS_ENDPOINT=http://otel-collector:4318
+    volumes:
+      - rustfs-data:/data/rustfs
+    networks:
+      - otel-network
+    restart: unless-stopped
+    healthcheck:
+      test:
+        [
+          "CMD",
+          "sh",
+          "-c",
+          "curl -f http://127.0.0.1:9000/health && curl -f http://127.0.0.1:9001/rustfs/console/health",
+        ]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+      start_period: 40s
+    depends_on:
+      otel-collector:
+        condition: service_started
+
+  rustfs-init:
+    image: alpine
+    container_name: rustfs-init
+    volumes:
+      - rustfs-data:/data
+    networks:
+      - otel-network
+    command: >
+      sh -c "
+        chown -R 10001:10001 /data &&
+        echo 'Volume Permissions fixed' &&
+        exit 0
+      "
+    restart: no
 
   # --- Tracing ---
 
-  tempo-init:
-    image: busybox:latest
-    command: [ "sh", "-c", "chown -R 10001:10001 /var/tempo" ]
-    volumes:
-      - ./tempo-data:/var/tempo
-    user: root
-    networks:
-      - otel-network
-    restart: "no"
-
   tempo:
     image: grafana/tempo:latest
-    user: "10001"
-    command: [ "-config.file=/etc/tempo.yaml" ]
+    container_name: tempo
+    command: ["-config.file=/etc/tempo.yaml"]
     volumes:
       - ./tempo.yaml:/etc/tempo.yaml:ro
-      - ./tempo-data:/var/tempo
+      - tempo-data:/var/tempo
     ports:
       - "3200:3200" # tempo
       - "4317"      # otlp grpc
       - "4318"      # otlp http
-    restart: unless-stopped
     networks:
       - otel-network
+    restart: unless-stopped
+    depends_on:
+      - redpanda
     healthcheck:
-      test: [ "CMD-SHELL", "wget --spider -q http://localhost:3200/metrics || exit 1" ]
+      test: ["CMD", "wget", "--spider", "-q", "http://localhost:3200/ready"]
       interval: 10s
       timeout: 5s
-      retries: 5
-      start_period: 40s
+      retries: 3
+      start_period: 15s
+
+  redpanda:
+    image: redpandadata/redpanda:latest # for tempo ingest
+    container_name: redpanda
+    ports:
+      - "9092:9092"
+    networks:
+      - otel-network
+    restart: unless-stopped
+    command: >
+      redpanda start --overprovisioned
+      --mode=dev-container
+      --kafka-addr=PLAINTEXT://0.0.0.0:9092
+      --advertise-kafka-addr=PLAINTEXT://redpanda:9092
 
   jaeger:
     image: jaegertracing/jaeger:latest
+    container_name: jaeger
     environment:
-      - TZ=Asia/Shanghai
       - SPAN_STORAGE_TYPE=badger
       - BADGER_EPHEMERAL=false
       - BADGER_DIRECTORY_VALUE=/badger/data
       - BADGER_DIRECTORY_KEY=/badger/key
       - COLLECTOR_OTLP_ENABLED=true
     volumes:
-      - ./jaeger-data:/badger
+      - ./jaeger.yaml:/etc/jaeger/config.yml
+      - jaeger-data:/badger
     ports:
       - "16686:16686" # Web UI
       - "14269:14269" # Admin/Metrics
-      - "4317"
-      - "4318"
+      - "4317" # otlp grpc
+      - "4318" # otlp http
+    command: ["--config", "/etc/jaeger/config.yml"]
     networks:
       - otel-network
+    restart: unless-stopped
     healthcheck:
-      test: [ "CMD-SHELL", "wget --spider -q http://localhost:14269 || exit 1" ]
+      test: ["CMD", "wget", "--spider", "-q", "http://localhost:14269"]
       interval: 10s
       timeout: 5s
-      retries: 5
-      start_period: 20s
+      retries: 3
+      start_period: 15s
 
   # --- Metrics ---
 
   prometheus:
     image: prom/prometheus:latest
-    environment:
-      - TZ=Asia/Shanghai
+    container_name: prometheus
     volumes:
       - ./prometheus.yml:/etc/prometheus/prometheus.yml:ro
-      - ./prometheus-data:/prometheus
+      - prometheus-data:/prometheus
     ports:
       - "9090:9090"
     command:
-      - '--config.file=/etc/prometheus/prometheus.yml'
-      - '--web.enable-otlp-receiver'
-      - '--web.enable-remote-write-receiver'
-      - '--enable-feature=promql-experimental-functions'
-      - '--storage.tsdb.min-block-duration=2h'
-      - '--storage.tsdb.max-block-duration=2h'
-      - '--log.level=info'
-      - '--storage.tsdb.retention.time=30d'
-      - '--storage.tsdb.path=/prometheus'
-      - '--web.console.libraries=/usr/share/prometheus/console_libraries'
-      - '--web.console.templates=/usr/share/prometheus/consoles'
+      - "--config.file=/etc/prometheus/prometheus.yml"
+      - "--web.enable-otlp-receiver" # Enable OTLP
+      - "--web.enable-remote-write-receiver" # Enable remote write
+      - "--enable-feature=promql-experimental-functions" # Enable info()
+      - "--storage.tsdb.retention.time=30d"
     restart: unless-stopped
     networks:
       - otel-network
     healthcheck:
-      test: [ "CMD-SHELL", "wget --spider -q http://localhost:9090/-/healthy || exit 1" ]
+      test: ["CMD", "wget", "--spider", "-q", "http://localhost:9090/-/healthy"]
       interval: 10s
       timeout: 5s
       retries: 3
@@ -108,18 +164,18 @@ services:
 
   loki:
     image: grafana/loki:latest
-    environment:
-      - TZ=Asia/Shanghai
+    container_name: loki
     volumes:
-      - ./loki-config.yaml:/etc/loki/local-config.yaml:ro
-      - ./loki-data:/loki
+      - ./loki.yaml:/etc/loki/loki.yaml:ro
+      - loki-data:/loki
     ports:
       - "3100:3100"
-    command: -config.file=/etc/loki/local-config.yaml
+    command: -config.file=/etc/loki/loki.yaml
     networks:
       - otel-network
+    restart: unless-stopped
     healthcheck:
-      test: [ "CMD-SHELL", "wget --spider -q http://localhost:3100/metrics || exit 1" ]
+      test: ["CMD", "wget", "--spider", "-q", "http://localhost:3100/ready"]
       interval: 15s
       timeout: 10s
       retries: 5
@@ -129,8 +185,6 @@ services:
 
   otel-collector:
     image: otel/opentelemetry-collector-contrib:latest
-    environment:
-      - TZ=Asia/Shanghai
     volumes:
       - ./otel-collector-config.yaml:/etc/otelcol-contrib/config.yaml:ro
     ports:
@@ -143,52 +197,51 @@ services:
       - "55679:55679" # zpages
     networks:
       - otel-network
+    restart: unless-stopped
     depends_on:
       - tempo
       - jaeger
       - prometheus
       - loki
     healthcheck:
-      test: [ "CMD-SHELL", "wget --spider -q http://localhost:13133 || exit 1" ]
+      test: ["CMD", "wget", "--spider", "-q", "http://localhost:13133"]
       interval: 10s
       timeout: 5s
       retries: 3
-      start_period: 20s
 
   # --- Visualization ---
 
   grafana:
     image: grafana/grafana:latest
+    container_name: grafana
     ports:
       - "3000:3000"
-    volumes:
-      - ./grafana/provisioning:/etc/grafana/provisioning
-      - ./grafana/dashboards:/var/lib/grafana/dashboards
-      - ./grafana-data:/var/lib/grafana
     environment:
       - GF_SECURITY_ADMIN_PASSWORD=admin
       - GF_SECURITY_ADMIN_USER=admin
-      - TZ=Asia/Shanghai
-      - GF_INSTALL_PLUGINS=grafana-pyroscope-datasource
-      - GF_DASHBOARDS_DEFAULT_HOME_DASHBOARD_PATH=/var/lib/grafana/dashboards/home.json
-    restart: unless-stopped
+    volumes:
+      - ./grafana/provisioning:/etc/grafana/provisioning:ro
+      - ./grafana/dashboards:/etc/grafana/dashboards:ro
+      - grafana-data:/var/lib/grafana
     networks:
       - otel-network
+    restart: unless-stopped
     depends_on:
       - prometheus
       - tempo
       - loki
     healthcheck:
-      test: [ "CMD-SHELL", "wget --spider -q http://localhost:3000/api/health || exit 1" ]
+      test: ["CMD", "wget", "--spider", "-q", "http://localhost:3000/api/health"]
       interval: 10s
       timeout: 5s
       retries: 3
 
 volumes:
-  prometheus-data:
+  rustfs-data:
   tempo-data:
-  loki-data:
   jaeger-data:
+  prometheus-data:
+  loki-data:
   grafana-data:
 
 networks: