docker-compose.kafka.yaml

services:
  zookeeper:
    image: confluentinc/cp-zookeeper:7.5.0
    container_name: kafka-zookeeper
    ports:
      - "2181:2181"
    healthcheck:
      test: echo srvr | nc zookeeper 2181 || exit 1
      start_period: 10s
      retries: 20
      interval: 10s
    environment:
      ZOOKEEPER_CLIENT_PORT: 2181
      ZOOKEEPER_TICK_TIME: 2000
    networks:
      - easymlops_network

  # Kafka broker, all configurations you can take a look
  # at https://docs.confluent.io/platform/current/installation/docker/config-reference.html
  broker:
    image: confluentinc/cp-server:7.5.0
    container_name: kafka-broker
    depends_on:
      zookeeper:
        condition: service_healthy
    ports:
      - "9092:9092"
      - "9101:9101"
    healthcheck:
      test: nc -z localhost 9092 || exit -1
      start_period: 15s
      interval: 5s
      timeout: 10s
      retries: 10
    environment:
      # ID of the broker in a cluster
      KAFKA_BROKER_ID:
        1
        # Connect to Zoo Keeper for distributed coordination and leader election
      KAFKA_ZOOKEEPER_CONNECT: "zookeeper:2181"
      KAFKA_LISTENER_SECURITY_PROTOCOL_MAP: PLAINTEXT:PLAINTEXT,PLAINTEXT_HOST:PLAINTEXT
      # Define how clients connect to brokers
      KAFKA_ADVERTISED_LISTENERS: PLAINTEXT://broker:29092,PLAINTEXT_HOST://localhost:9092
      # How many copies are maintained for fault tolerance
      KAFKA_OFFSETS_TOPIC_REPLICATION_FACTOR: 1
      # Schema Registry URL for storing and managing Avro schemas
      KAFKA_CONFLUENT_SCHEMA_REGISTRY_URL: http://schema-registry:8081
      # Confluent Metrics Reporter for Control Center Cluster Monitoring
      KAFKA_METRIC_REPORTERS: io.confluent.metrics.reporter.ConfluentMetricsReporter
      CONFLUENT_METRICS_REPORTER_BOOTSTRAP_SERVERS: "broker:9092"
      CONFLUENT_METRICS_REPORTER_TOPIC_REPLICAS: 1
      CONFLUENT_METRICS_ENABLE: "true"
      # For fixing the bug replication factor 3 > the number of node
      KAFKA_CONFLUENT_BALANCER_TOPIC_REPLICATION_FACTOR: 1
      KAFKA_TRANSACTION_STATE_LOG_MIN_ISR: 1
      KAFKA_TRANSACTION_STATE_LOG_REPLICATION_FACTOR: 1
    networks:
      - easymlops_network

  # For managing Avro schemas
  schema-registry:
    image: confluentinc/cp-schema-registry:7.5.0
    container_name: kafka-schema-registry
    depends_on:
      - broker
    ports:
      - "8081:8081"
    healthcheck:
      start_period: 10s
      interval: 10s
      retries: 20
      test: curl --user superUser:superUser --fail --silent --insecure http://localhost:8081/subjects --output /dev/null || exit 1
    environment:
      SCHEMA_REGISTRY_HOST_NAME: schema-registry
      SCHEMA_REGISTRY_KAFKASTORE_BOOTSTRAP_SERVERS: "broker:29092"
      SCHEMA_REGISTRY_LISTENERS: http://0.0.0.0:8081
    networks:
      - easymlops_network

  # Kafka Connect
  connect:
    image: confluentinc/cp-kafka-connect:7.5.0
    container_name: kafka-connect
    depends_on:
      broker:
        condition: service_healthy
      schema-registry:
        condition: service_healthy
      zookeeper:
        condition: service_healthy
    ports:
      - "8083:8083"
    environment:
      CONNECT_BOOTSTRAP_SERVERS: "broker:29092"
      CONNECT_REST_ADVERTISED_HOST_NAME: connect
      CONNECT_REST_PORT: 8083
      CONNECT_GROUP_ID: compose-connect-group
      CONNECT_CONFIG_STORAGE_TOPIC: docker-connect-configs
      CONNECT_CONFIG_STORAGE_REPLICATION_FACTOR: 1
      CONNECT_OFFSET_FLUSH_INTERVAL_MS: 10000
      CONNECT_OFFSET_STORAGE_TOPIC: docker-connect-offsets
      CONNECT_OFFSET_STORAGE_REPLICATION_FACTOR: 1
      CONNECT_STATUS_STORAGE_TOPIC: docker-connect-status
      CONNECT_STATUS_STORAGE_REPLICATION_FACTOR: 1
      CONNECT_KEY_CONVERTER: org.apache.kafka.connect.storage.StringConverter
      CONNECT_KEY_CONVERTER_SCHEMAS_ENABLE: false
      CONNECT_VALUE_CONVERTER: org.apache.kafka.connect.json.JsonConverter
      CONNECT_VALUE_CONVERTER_SCHEMAS_ENABLE: true
      CONNECT_PLUGIN_PATH: "/usr/share/java,/usr/share/confluent-hub-components,/etc/kafka-connect/jars"
      # AWS Credentials
      AWS_ACCESS_KEY_ID: ${AWS_ACCESS_KEY_ID}
      AWS_SECRET_ACCESS_KEY: ${AWS_SECRET_ACCESS_KEY}
    volumes:
      - $PWD/src/streaming/connectors/config/jars/kafka_connect/jars/:/etc/kafka-connect/jars
    command:
      - bash
      - -c
      - |
        echo "Installing connector plugins"
        confluent-hub install --no-prompt confluentinc/kafka-connect-s3:10.5.7
        echo "Launching Kafka Connect worker"
        /etc/confluent/docker/run
    networks:
      - easymlops_network

  # Confluent control center to manage Kafka
  control-center:
    image: confluentinc/cp-enterprise-control-center:7.5.0
    container_name: kafka-control-center
    depends_on:
      - broker
      - schema-registry
      - connect
    ports:
      - "9021:9021"
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:9021/healthcheck"] # Adjust the URL and options as needed
      interval: 30s
      timeout: 10s
      retries: 3
    environment:
      CONTROL_CENTER_BOOTSTRAP_SERVERS: "broker:29092"
      CONTROL_CENTER_CONNECT_CONNECT-DEFAULT_CLUSTER: "connect:8083,debezium:8083"
      CONTROL_CENTER_SCHEMA_REGISTRY_URL: "http://schema-registry:8081"
      CONTROL_CENTER_REPLICATION_FACTOR: 1
      CONTROL_CENTER_INTERNAL_TOPICS_PARTITIONS: 1
      CONTROL_CENTER_CONNECT_HEALTHCHECK_ENDPOINT: "/connectors"
      CONFLUENT_METRICS_TOPIC_REPLICATION: 1
    networks:
      - easymlops_network

  # Simulation of sending messages to Kafka topics
  kafka_producer:
    container_name: kafka-producer
    build:
      context: src/producer
      dockerfile: Dockerfile
    env_file:
      - src/producer/.env
    depends_on:
      broker:
        condition: service_healthy
    networks:
      - easymlops_network

networks:
  easymlops_network:
    external: true