compose-prod.yml

services:
  kafka:
    image: 'confluentinc/cp-kafka:7.8.0'
    container_name: kafka
    environment:
      # Enables automatic topic creation on the broker.
      KAFKA_AUTO_CREATE_TOPICS_ENABLE: 'true'
      # KRaft settings
      # The unique identifier for this Kafka node in the cluster.
      KAFKA_NODE_ID: 1
      # Defines the roles of this node. 'broker,controller' means it acts as both a broker and a KRaft controller.
      KAFKA_PROCESS_ROLES: 'broker,controller'
      # The list of voters in the KRaft controller quorum. For a single-node setup, it's just itself.
      KAFKA_CONTROLLER_QUORUM_VOTERS: '1@kafka:9093'
      # Listener settings
      # The listener name used by the KRaft controller.
      KAFKA_CONTROLLER_LISTENER_NAMES: 'CONTROLLER'
      # The listener name for communication between brokers.
      KAFKA_INTER_BROKER_LISTENER_NAME: 'PLAINTEXT'
      # Maps listener names to security protocols.
      KAFKA_LISTENER_SECURITY_PROTOCOL_MAP: 'CONTROLLER:PLAINTEXT,PLAINTEXT:PLAINTEXT,PLAINTEXT_HOST:PLAINTEXT'
      # The listeners advertised to clients. 'PLAINTEXT://kafka:29092' is for internal communication,
      # and 'PLAINTEXT_HOST://localhost:9092' is for external clients on the host machine.
      KAFKA_ADVERTISED_LISTENERS: 'PLAINTEXT://kafka:29092,PLAINTEXT_HOST://kafka:9092'
      # The listeners that the broker will bind to. Use 0.0.0.0 to listen on all interfaces.
      KAFKA_LISTENERS: 'PLAINTEXT://kafka:29092,CONTROLLER://kafka:9093,PLAINTEXT_HOST://kafka:9092'
      # Cluster and topic settings
      # A unique ID for the Kafka cluster, required for KRaft mode.
      # CLUSTER_ID value: docker run --rm -i confluentinc/cp-kafka:7.8.0 sh -c '/bin/kafka-storage random-uuid'
      CLUSTER_ID: 'vgpmmmjLS_e4JdKsu0j69A'
      # The replication factor for the internal offsets' topic. '1' is required for a single-node setup.
      KAFKA_OFFSETS_TOPIC_REPLICATION_FACTOR: 1
      # The replication factor for the transaction state log. '1' is required for a single-node setup.
      KAFKA_TRANSACTION_STATE_LOG_REPLICATION_FACTOR: 1
      # The minimum number of in-sync replicas for the transaction state log. '1' is required for a single-node setup.
      KAFKA_TRANSACTION_STATE_LOG_MIN_ISR: 1
      # Development settings
      # The delay before the first rebalance for a consumer group. '0' speeds up startup in development.
      KAFKA_GROUP_INITIAL_REBALANCE_DELAY_MS: 0
      # Sets the root logger level for Kafka's Log4j logging to reduce noise.
      KAFKA_LOG4J_ROOT_LOGLEVEL: 'ERROR'
      # Broker-wide maximum message size (10MB)
      KAFKA_MESSAGE_MAX_BYTES: 10485760
      # Must also adjust the replica fetch size to handle the larger messages
      KAFKA_REPLICA_FETCH_MAX_BYTES: 10485760
    ports:
      - "9092"
    healthcheck:
      test: [ "CMD", "kafka-broker-api-versions", "--bootstrap-server", "kafka:9092" ]
      interval: 10s
      timeout: 5s
      retries: 3
    restart: on-failure

  kafka-ui:
    image: provectuslabs/kafka-ui:latest
    container_name: kafka-ui
    restart: unless-stopped
    ports:
      - "8081:8080"
    environment:
      KAFKA_CLUSTERS_0_NAME: 'prod-cluster'
      KAFKA_CLUSTERS_0_BOOTSTRAPSERVERS: 'kafka:9092'
    depends_on:
      kafka:
        condition: service_healthy

  demo-app:
    build:
      context: .
      dockerfile: Dockerfile
    image: demo-app:v1
    environment:
      JAVA_OPTS: |-
        -XX:+ExitOnOutOfMemoryError
        -XX:+HeapDumpOnOutOfMemoryError
        -XX:HeapDumpPath=/var/dumps
        -XX:MaxRAMPercentage=50
        -Xss256k
        -XX:ReservedCodeCacheSize=64m
        -XX:MaxMetaspaceSize=96m
        -XX:+UseStringDeduplication
        --enable-native-access=ALL-UNNAMED
      KAFKA_CONSUMER_TOPICS: 'prod-in-topic'
      KAFKA_CONSUMER_GROUP_ID: 'prod-group'
      KAFKA_CONSUMER_BOOTSTRAP_SERVERS: 'kafka:9092'
      KAFKA_PRODUCER_TOPICS: 'prod-out-topic'
      KAFKA_PRODUCER_BOOTSTRAP_SERVERS: 'kafka:9092'
      SPRING_APPLICATION_NAME: 'kafka-app-prod'
    command: |-
      --server.shutdown=graceful
      --spring.profiles.active=kafka,prod
      --spring.threads.virtual.enabled=true
      --management.tracing.sampling.probability=0.5
      --management.otlp.metrics.export.url=http://otel-collector:4318/v1/metrics
      --management.otlp.tracing.endpoint=http://otel-collector:4317/v1/traces
      --management.otlp.logging.endpoint=http://otel-collector:4317/v1/logs
    ports:
      - "8080:8080"
    restart: on-failure
    healthcheck:
      test: ["CMD-SHELL", "nc -z localhost 8080 || exit 1"]
      interval: 10s
      timeout: 5s
      retries: 3
    depends_on:
      kafka:
        condition: service_healthy
      otel-collector:
        condition: service_started
    volumes:
      - /tmp/app/dumps:/var/dumps

  otel-collector:
    image: otel/opentelemetry-collector-contrib:latest
    container_name: otel-collector
    command: ["--config=/etc/otel-collector-config.yaml"]
    restart: always
    ports:
      - "4318:4318"    # OTLP http receiver
      - "4317:4317"    # OTLP gRPC receiver
      - "13133:13133"  # health_check extension: http://localhost:13133
      - "55679:55679"  # zpages extension: http://localhost:55679/debug/servicez
      - "8889:8889"    # Prometheus exporter metrics
    volumes:
      - ./otel/otel-collector-config.yaml:/etc/otel-collector-config.yaml:ro
    depends_on:
      - loki
      - tempo
      - jaeger
      - zipkin

  prometheus:
    image: prom/prometheus:latest
    container_name: prometheus
    command:
      - --config.file=/etc/prometheus/prometheus.yml
      - --enable-feature=exemplar-storage
      - --web.enable-remote-write-receiver
    restart: always
    ports:
      - '9090:9090'   # Prometheus web UI & as grafana datasource
    volumes:
      - ./otel/prometheus.yml:/etc/prometheus/prometheus.yml:ro
    depends_on:
      - otel-collector

  loki:
    image: grafana/loki:latest
    container_name: loki
    command: -config.file=/etc/loki/local-config.yaml
    restart: always
    ports:
      - "3100"  # Loki as grafana datasource

  tempo:
    image: grafana/tempo:latest
    container_name: tempo
    command: -config.file=/etc/tempo/tempo.yaml
    restart: always
    ports:
      - "3200"   # Tempo as grafana datasource
    volumes:
      - ./otel/tempo-config.yaml:/etc/tempo/tempo.yaml:ro

  jaeger:
    image: jaegertracing/all-in-one:latest
    container_name: jaeger
    environment:
      - COLLECTOR_OTLP_ENABLED=true
    restart: always
    ports:
      - "4317"        # OTLP grpc
      - "16686:16686" # Jaeger UI

  zipkin:
    image: openzipkin/zipkin:latest
    container_name: zipkin
    restart: always
    ports:
      - "9411:9411" # Zipkin UI

  grafana:
    container_name: grafana
    image: grafana/grafana:latest
    restart: always
    ports:
      - "3000:3000" # Grafana UI
    volumes:
      - ./otel/grafana-datasources.yml:/etc/grafana/provisioning/datasources/datasources.yml:ro
    depends_on:
      - prometheus
      - loki
      - tempo
      - jaeger
      - zipkin