Develop

.gitignore

@@ -53,6 +53,7 @@ PRD.md
 
 ### Data ###
 *.csv
+store_ratings.sql
 
 ### Uploads ###
 uploads/

Dockerfile

@@ -23,15 +23,22 @@ RUN apt-get update \
  && apt-get install -y --no-install-recommends wget \
  && rm -rf /var/lib/apt/lists/*
 
+# OpenTelemetry Java Agent — 코드 수정 없이 트레이스 자동 수집
+# Spring MVC, JDBC, HikariCP, HTTP Client 등 자동 계측
+ARG OTEL_AGENT_VERSION=2.10.0
+RUN wget -qO /opentelemetry-javaagent.jar \
+      https://github.com/open-telemetry/opentelemetry-java-instrumentation/releases/download/v${OTEL_AGENT_VERSION}/opentelemetry-javaagent.jar \
+ && chmod 644 /opentelemetry-javaagent.jar
+
 # 비루트 유저로 실행
 RUN useradd -r -u 1001 spring
 USER spring
 
 COPY --from=builder /app/build/libs/*.jar app.jar
 
-# t3.micro(1GB RAM) 환경 고려한 JVM 메모리 튜닝
-# 컨테이너에 할당된 메모리의 70%를 힙으로 사용 (나머지 30%는 metaspace, 스택, 네이티브)
-ENV JAVA_TOOL_OPTIONS="-XX:MaxRAMPercentage=70.0 -XX:InitialRAMPercentage=50.0"
+# t3.small 환경 고려한 JVM 메모리 튜닝 + OTel Agent 자동 활성화
+# OTEL_EXPORTER_OTLP_ENDPOINT가 설정 안 되면 트레이스 전송만 실패할 뿐 앱은 정상 동작
+ENV JAVA_TOOL_OPTIONS="-javaagent:/opentelemetry-javaagent.jar -XX:MaxRAMPercentage=70.0 -XX:InitialRAMPercentage=50.0 -XX:+UseG1GC"
 
 EXPOSE 8080
 

build.gradle

@@ -35,6 +35,7 @@ dependencies {
     implementation 'org.springframework.ai:spring-ai-starter-model-google-genai'
     implementation 'org.jetbrains.kotlin:kotlin-reflect'
     implementation 'org.springframework.boot:spring-boot-starter-actuator'
+    runtimeOnly 'io.micrometer:micrometer-registry-prometheus'
     implementation 'io.github.cdimascio:dotenv-java:3.0.0'
     implementation 'org.springframework.boot:spring-boot-starter-data-jpa'
     implementation 'org.springframework.boot:spring-boot-starter-security'

docker-compose.prod.yml

@@ -7,13 +7,27 @@ services:
     env_file: .env
     expose:
       - "8080"
-    # t3.micro(1GB) 메모리 한계 고려: app은 최대 700MB로 제한
+    # t3.small(2GB) 환경. 모니터링 스택과 공존하기 위해 app은 600M로 제한.
+    # OTel Agent가 약 80MB 추가 사용하므로 500M → 600M로 상향.
+    environment:
+      # JVM 옵션은 Dockerfile의 ENV에 기본값으로 정의됨 (javaagent + 메모리 튜닝).
+      # 여기선 OpenTelemetry Agent의 송신 대상만 지정.
+      OTEL_SERVICE_NAME: catchtable-backend
+      OTEL_EXPORTER_OTLP_ENDPOINT: http://jaeger:4317
+      OTEL_EXPORTER_OTLP_PROTOCOL: grpc
+      OTEL_TRACES_EXPORTER: otlp
+      OTEL_METRICS_EXPORTER: none   # 메트릭은 Micrometer/Prometheus로 처리
+      OTEL_LOGS_EXPORTER: none      # 로그는 Promtail/Loki로 처리
+      OTEL_RESOURCE_ATTRIBUTES: deployment.environment=production
+      # 샘플링: 전체 요청 대비 트레이스 수집 비율 (1.0=100%, 부하 시 0.1로 낮추기 권장)
+      OTEL_TRACES_SAMPLER: parentbased_traceidratio
+      OTEL_TRACES_SAMPLER_ARG: "1.0"
     deploy:
       resources:
         limits:
-          memory: 700M
+          memory: 600M
         reservations:
-          memory: 500M
+          memory: 400M
     healthcheck:
       test: ["CMD", "wget", "-qO-", "http://localhost:8080/actuator/health"]
       interval: 30s
@@ -23,6 +37,11 @@ services:
     restart: unless-stopped
     networks:
       - catchtable-net
+    logging:
+      driver: "json-file"
+      options:
+        max-size: "10m"
+        max-file: "3"
 
   nginx:
     image: nginx:1.26.3-alpine
@@ -50,6 +69,179 @@ services:
     entrypoint: "/bin/sh -c 'trap exit TERM; while :; do certbot renew --quiet; sleep 12h & wait $${!}; done;'"
     restart: unless-stopped
 
+  # ============================================================
+  # 모니터링 스택 (Prometheus + Loki + Promtail + Jaeger + Grafana)
+  # ============================================================
+
+  prometheus:
+    image: prom/prometheus:v2.55.0
+    container_name: catchtable-prometheus
+    volumes:
+      - ./monitoring/prometheus.yml:/etc/prometheus/prometheus.yml:ro
+      - prometheus-data:/prometheus
+    command:
+      - '--config.file=/etc/prometheus/prometheus.yml'
+      - '--storage.tsdb.retention.time=7d'
+      - '--storage.tsdb.retention.size=1GB'
+      - '--web.enable-lifecycle'
+    expose:
+      - "9090"
+    deploy:
+      resources:
+        limits:
+          memory: 350M
+    restart: unless-stopped
+    networks:
+      - catchtable-net
+
+  loki:
+    image: grafana/loki:3.2.0
+    container_name: catchtable-loki
+    volumes:
+      - ./monitoring/loki-config.yml:/etc/loki/local-config.yaml:ro
+      - loki-data:/loki
+    command: -config.file=/etc/loki/local-config.yaml
+    expose:
+      - "3100"
+    deploy:
+      resources:
+        limits:
+          memory: 250M
+    restart: unless-stopped
+    networks:
+      - catchtable-net
+
+  promtail:
+    image: grafana/promtail:3.2.0
+    container_name: catchtable-promtail
+    volumes:
+      - ./monitoring/promtail-config.yml:/etc/promtail/config.yml:ro
+      - /var/run/docker.sock:/var/run/docker.sock:ro
+      - /var/lib/docker/containers:/var/lib/docker/containers:ro
+      - promtail-positions:/tmp
+    command: -config.file=/etc/promtail/config.yml
+    depends_on:
+      - loki
+    deploy:
+      resources:
+        limits:
+          memory: 100M
+    restart: unless-stopped
+    networks:
+      - catchtable-net
+
+  jaeger:
+    image: jaegertracing/all-in-one:1.62.0
+    container_name: catchtable-jaeger
+    user: "0"  # named volume mkdir 퍼미션 회피 (내부 도구라 보안 영향 없음)
+    environment:
+      COLLECTOR_OTLP_ENABLED: "true"
+      SPAN_STORAGE_TYPE: badger
+      BADGER_EPHEMERAL: "false"
+      BADGER_DIRECTORY_VALUE: /badger/data
+      BADGER_DIRECTORY_KEY: /badger/key
+      BADGER_SPAN_STORE_TTL: 168h0m0s
+    volumes:
+      - jaeger-data:/badger
+    ports:
+      - "16686:16686"  # Jaeger UI (외부 접근)
+    expose:
+      - "4317"   # OTLP gRPC (앱에서 전송)
+      - "4318"   # OTLP HTTP
+    deploy:
+      resources:
+        limits:
+          memory: 350M
+    restart: unless-stopped
+    networks:
+      - catchtable-net
+
+  grafana:
+    image: grafana/grafana:11.3.0
+    container_name: catchtable-grafana
+    environment:
+      GF_SECURITY_ADMIN_USER: ${GRAFANA_USER:-admin}
+      GF_SECURITY_ADMIN_PASSWORD: ${GRAFANA_PASSWORD:-admin}
+      GF_USERS_ALLOW_SIGN_UP: "false"
+    volumes:
+      - ./grafana/provisioning:/etc/grafana/provisioning:ro
+      - grafana-data:/var/lib/grafana
+    ports:
+      - "3001:3000"  # Grafana UI (외부 접근, 3000은 프론트 dev와 충돌 회피)
+    depends_on:
+      - prometheus
+      - loki
+      - jaeger
+    deploy:
+      resources:
+        limits:
+          memory: 200M
+    restart: unless-stopped
+    networks:
+      - catchtable-net
+
+  # ============================================================
+  # 고도화 작업 시작 시 주석 해제 (5대 고도화 항목 1, 3번 진행 시)
+  # ============================================================
+
+  # redis:
+  #   image: redis:7-alpine
+  #   container_name: catchtable-redis
+  #   command:
+  #     - redis-server
+  #     - --maxmemory
+  #     - 80mb
+  #     - --maxmemory-policy
+  #     - allkeys-lru
+  #     - --appendonly
+  #     - "yes"
+  #   expose:
+  #     - "6379"
+  #   volumes:
+  #     - redis-data:/data
+  #   deploy:
+  #     resources:
+  #       limits:
+  #         memory: 100M
+  #   restart: unless-stopped
+  #   networks:
+  #     - catchtable-net
+
+  # kafka:
+  #   image: bitnami/kafka:3.8
+  #   container_name: catchtable-kafka
+  #   environment:
+  #     # KRaft 모드 (Zookeeper 불필요, 메모리 절약)
+  #     KAFKA_CFG_NODE_ID: 0
+  #     KAFKA_CFG_PROCESS_ROLES: controller,broker
+  #     KAFKA_CFG_CONTROLLER_QUORUM_VOTERS: 0@kafka:9093
+  #     KAFKA_CFG_LISTENERS: PLAINTEXT://:9092,CONTROLLER://:9093
+  #     KAFKA_CFG_ADVERTISED_LISTENERS: PLAINTEXT://kafka:9092
+  #     KAFKA_CFG_CONTROLLER_LISTENER_NAMES: CONTROLLER
+  #     KAFKA_CFG_LISTENER_SECURITY_PROTOCOL_MAP: CONTROLLER:PLAINTEXT,PLAINTEXT:PLAINTEXT
+  #     # 메모리 다이어트
+  #     KAFKA_HEAP_OPTS: "-Xms256m -Xmx256m"
+  #   expose:
+  #     - "9092"
+  #   volumes:
+  #     - kafka-data:/bitnami/kafka
+  #   deploy:
+  #     resources:
+  #       limits:
+  #         memory: 400M
+  #   restart: unless-stopped
+  #   networks:
+  #     - catchtable-net
+
 networks:
   catchtable-net:
     driver: bridge
+
+volumes:
+  prometheus-data:
+  loki-data:
+  jaeger-data:
+  grafana-data:
+  promtail-positions:
+  # redis-data:
+  # kafka-data:

grafana/.gitignore

@@ -0,0 +1,4 @@
+# Grafana 런타임 데이터 (커밋 금지)
+data/
+plugins/
+*.db

grafana/provisioning/dashboards/dashboards.yml

@@ -0,0 +1,13 @@
+apiVersion: 1
+
+providers:
+  - name: 'default'
+    orgId: 1
+    folder: ''
+    type: file
+    disableDeletion: false
+    updateIntervalSeconds: 30
+    allowUiUpdates: true
+    options:
+      path: /etc/grafana/provisioning/dashboards
+      foldersFromFilesStructure: true

grafana/provisioning/datasources/datasources.yml

@@ -0,0 +1,31 @@
+apiVersion: 1
+
+datasources:
+  - name: Prometheus
+    type: prometheus
+    access: proxy
+    url: http://prometheus:9090
+    isDefault: true
+    editable: true
+    jsonData:
+      timeInterval: "15s"
+
+  - name: Loki
+    type: loki
+    access: proxy
+    url: http://loki:3100
+    editable: true
+    jsonData:
+      derivedFields:
+        # 로그 안의 traceId(OTel) 를 클릭하면 Jaeger 트레이스로 점프
+        - datasourceUid: jaeger
+          matcherRegex: "traceId=(\\w+)"
+          name: TraceID
+          url: "$${__value.raw}"
+
+  - name: Jaeger
+    type: jaeger
+    access: proxy
+    url: http://jaeger:16686
+    uid: jaeger
+    editable: true

monitoring/loki-config.yml

@@ -0,0 +1,48 @@
+auth_enabled: false
+
+server:
+  http_listen_port: 3100
+  grpc_listen_port: 9096
+
+common:
+  instance_addr: 127.0.0.1
+  path_prefix: /loki
+  storage:
+    filesystem:
+      chunks_directory: /loki/chunks
+      rules_directory: /loki/rules
+  replication_factor: 1
+  ring:
+    kvstore:
+      store: inmemory
+
+schema_config:
+  configs:
+    - from: 2024-01-01
+      store: tsdb
+      object_store: filesystem
+      schema: v13
+      index:
+        prefix: index_
+        period: 24h
+
+limits_config:
+  retention_period: 168h  # 7일
+  reject_old_samples: true
+  reject_old_samples_max_age: 168h
+  allow_structured_metadata: true
+  volume_enabled: true
+
+compactor:
+  working_directory: /loki/compactor
+  compaction_interval: 10m
+  retention_enabled: true
+  retention_delete_delay: 2h
+  retention_delete_worker_count: 150
+  delete_request_store: filesystem
+
+ruler:
+  alertmanager_url: http://localhost:9093
+
+analytics:
+  reporting_enabled: false

monitoring/prometheus.yml

@@ -0,0 +1,20 @@
+global:
+  scrape_interval: 15s
+  evaluation_interval: 15s
+  external_labels:
+    cluster: catchtable
+    env: prod
+
+scrape_configs:
+  # Spring Boot Actuator (Micrometer)
+  - job_name: 'catchtable-app'
+    metrics_path: '/actuator/prometheus'
+    static_configs:
+      - targets: ['app:8080']
+        labels:
+          service: catchtable-backend
+
+  # Prometheus 자체 메트릭
+  - job_name: 'prometheus'
+    static_configs:
+      - targets: ['localhost:9090']