docker-compose.yml

version: '3.8'

x-spark-common: &spark-common
  build:
    context : .
    dockerfile: DockerFile2
  volumes:
    - ./jobs:/opt/bitnami/spark/jobs
  networks:
    - YNS_NETWORK


x-airflow-common: &airflow-common
  build:
    context: .
    dockerfile: Dockerfile
  env_file:
    - airflow.env
  volumes:
    - ./jobs:/opt/airflow/jobs
    - ./dags:/opt/airflow/dags
    - ./logs:/opt/airflow/logs
    - ./schema:/opt/airflow/schema

  depends_on:
    - postgres
  networks:
    - YNS_NETWORK

services:
  zookeeper:
    image: zookeeper:3.8.1  # Updated to a reliable version
    container_name: zookeeper
    ports:
      - "2181:2181"
    environment:
      ZOOKEEPER_CLIENT_PORT: 2181
      ZOOKEEPER_TICK_TIME: 2000
    networks:
      - YNS_NETWORK

  kafka:
    image: bitnami/kafka:latest
    container_name: kafka
    depends_on:
      - zookeeper
    ports:
      - "9092:9092"
    environment:
      KAFKA_BROKER_ID: 1
      KAFKA_ADVERTISED_LISTENERS: INSIDE://kafka:9093,OUTSIDE://localhost:9092
      KAFKA_LISTENER_SECURITY_PROTOCOL_MAP: INSIDE:PLAINTEXT,OUTSIDE:PLAINTEXT
      KAFKA_LISTENERS: INSIDE://0.0.0.0:9093,OUTSIDE://0.0.0.0:9092
      KAFKA_LISTENER_NAME: INSIDE
      KAFKA_INTER_BROKER_LISTENER_NAME: INSIDE
      KAFKA_ZOOKEEPER_CONNECT: zookeeper:2181
      KAFKA_LOG_RETENTION_HOURS: 168
      KAFKA_LOG_RETENTION_BYTES: 1073741824
      CONFLUENT_METRICS_REPORTER_BOOTSTRAP_SERVERS: kafka:9093
      CONFLUENT_METRICS_REPORTER_TOPIC_REPLICAS: 1
      CONFLUENT_METRICS_ENABLE: 'true'
      CONFLUENT_SUPPORT_CUSTOMER_ID: 'anonymous'
    networks:
      - YNS_NETWORK

  schema-registry:
    image: confluentinc/cp-schema-registry:latest
    hostname: schema-registry
    container_name: schema-registry
    depends_on:
    - kafka
    ports:
      - "8081:8081"
    environment:
      SCHEMA_REGISTRY_HOST_NAME: schema-registry
      SCHEMA_REGISTRY_KAFKASTORE_BOOTSTRAP_SERVERS: 'kafka:9093'
      SCHEMA_REGISTRY_LISTENERS: http://0.0.0.0:8081
    networks:
      - YNS_NETWORK
    healthcheck:
      test: [ "CMD", "curl", "-f", "http://schema-registry:8081" ]
      interval: 30s
      timeout: 10s
      retries: 5

  control-center:
    image: confluentinc/cp-enterprise-control-center:latest
    container_name: control-center
    ports:
      - "9021:9021"
    environment:
      CONTROL_CENTER_BOOTSTRAP_SERVERS: 'kafka:9093'
      CONTROL_CENTER_REPLICATION_FACTOR: 1
      CONTROL_CENTER_INTERNAL_TOPICS_PARTITIONS: 1
      CONTROL_CENTER_MONITORING_INTERCEPTOR_TOPIC_PARTITIONS: 1
      CONFLUENT_METRICS_TOPIC_REPLICATION: 1
      CONFLUENT_METRICS_ENABLE: 'true'
      CONTROL_CENTER_SCHEMA_REGISTRY_URL: 'http://schema-registry:8081'
      PORT: 9021
    networks:
      - YNS_NETWORK
    depends_on:
      - kafka
      - schema-registry
    healthcheck:
      test: [ "CMD", "curl", "-f", "http://localhost:9021/health" ]
      interval: 30s
      timeout: 10s
      retries: 5

  cassandra_db:
    image: cassandra:latest
    container_name: cassandra
    hostname: cassandra
    ports:
      - "9042:9042"
    environment:
      - MAX_HEAP_SIZE=2G                # Increase heap size
      - HEAP_NEWSIZE=500M               # Increase young generation heap size
      - CASSANDRA_USERNAME=cassandra
      - CASSANDRA_PASSWORD=cassandra
      - JVM_OPTS=-Xms2G -Xmx2G          # Set minimum and maximum heap size for JVM
      - GC_GRACE_SECONDS=864000         # Increase GC grace seconds to 10 days
      - CONFLUENT_SUPPORT_CUSTOMER_ID=anonymous
    volumes:
      - ./cassandra_data:/var/lib/cassandr
    networks:
      - YNS_NETWORK

  spark-master:
    <<: *spark-common
    command: bin/spark-class org.apache.spark.deploy.master.Master
    ports:
      - "9090:8080"
      - "7077:7077"  

  spark-worker:
    <<: *spark-common
    command: bin/spark-class org.apache.spark.deploy.worker.Worker spark://spark-master:7077
    depends_on:
      - spark-master
    environment:
      SPARK_MODE: worker
      SPARK_WORKER_CORES: 2
      SPARK_WORKER_MEMORY: 1g
      SPARK_MASTER_URL: spark://spark-master:7077

  spark-worker-2:
    <<: *spark-common
    command: bin/spark-class org.apache.spark.deploy.worker.Worker spark://spark-master:7077
    depends_on:
      - spark-master
    environment:
      SPARK_MODE: worker
      SPARK_WORKER_CORES: 2
      SPARK_WORKER_MEMORY: 1g
      SPARK_MASTER_URL: spark://spark-master:7077

  postgres:
    image: postgres:14.0
    environment:
      POSTGRES_USER: airflow
      POSTGRES_PASSWORD: airflow
      POSTGRES_DB: airflow
    volumes:
      - ./pg_data:/var/lib/postgresql/data
    networks:
      - YNS_NETWORK

  webserver:
    <<: *airflow-common
    command: webserver
    ports:
      - "8080:8080"
    depends_on:
      - scheduler
      - postgres

  scheduler:
    <<: *airflow-common
    command: bash -c "airflow db migrate && airflow users create --username admin --firstname YNS --lastname Bousetta --role Admin --email YNSTEST@gmail.com --password admin && airflow scheduler"

networks:
  YNS_NETWORK:
    driver: bridge