使用 Docker 部署 Apache Spark 集群的过程

version: '3'
services:
  master:
    image: bitnami/spark:3.5.4
    container_name: master
    user: root
    environment:
      - SPARK_MODE=master
      - SPARK_MASTER_WEBUI_PORT=8080
      - SPARK_MASTER_PORT=7077
    ports:
      - '8080:8080'
      - '7077:7077'
    volumes:
      - ./python:/python
  worker1:
    image: bitnami/spark:3.5.4
    container_name: worker1
    user: root
    environment:
      - SPARK_MODE=worker
      - SPARK_MASTER_URL=spark://master:7077
      - SPARK_WORKER_MEMORY=1G
      - SPARK_WORKER_CORES=1
    depends_on:
      - master
  worker2:
    image: bitnami/spark:3.5.4
    container_name: worker2
    user: root
    environment:
      - SPARK_MODE=worker
      - SPARK_MASTER_URL=spark://master:7077
      - SPARK_WORKER_MEMORY=1G
      - SPARK_WORKER_CORES=1
    depends_on:
      - master
networks:
  default:
    driver: bridge

docker compose up -d

from pyspark.sql import SparkSession
if __name__ == "__main__":
    spark = SparkSession.builder.appName("Pi Calculator").getOrCreate()
    numSamples = 100000000
    count = spark.sparkContext.parallelize(range(1, numSamples)).count()
    print(f"Pi is roughly {4.0 * count / numSamples}")
    spark.stop()

docker-compose exec master /opt/bitnami/spark/bin/spark-submit --master spark://master:7077 /python/pi.py