Run Apache Spark in Docker

version: '3'

services:
  spark-master:
    image: bitnami/spark:latest
    environment:
      - SPARK_MODE=master
      - SPARK_RPC_AUTHENTICATION_ENABLED=no
      - SPARK_RPC_ENCRYPTION_ENABLED=no
      - SPARK_LOCAL_STORAGE_ENCRYPTION_ENABLED=no
      - SPARK_SSL_ENABLED=no
    volumes:
      - /somedata:/data
    ports:
      - '8080:8080'
      - '7077:7077'

  spark-worker:
    image: bitnami/spark:latest
    environment:
      - SPARK_MODE=worker
      - SPARK_MASTER_URL=spark://spark-master:7077
      - SPARK_WORKER_MEMORY=16G
      - SPARK_WORKER_CORES=4
      - SPARK_RPC_AUTHENTICATION_ENABLED=no
      - SPARK_RPC_ENCRYPTION_ENABLED=no
      - SPARK_LOCAL_STORAGE_ENCRYPTION_ENABLED=no
      - SPARK_SSL_ENABLED=no
    volumes:
      - /somedata:/data
    depends_on:
      - spark-master

  spark-client-scala:
    image: bitnami/spark:latest
    command: tail -f /dev/null
    depends_on:
      - spark-master
    volumes:
      - /somedata:/data