使用docker compose快速搭建spark集群

在个人学习大数据的过程中，搭建环境永远是最令人头疼的一环，因为分布式的特点，个人爱好者往往只能在自己的单主机上模拟分布式环境，传统的做法是使用虚拟机模拟，但是创建多个虚拟机不仅非常消耗资源，而且费时费力。因此，我推荐使用docker去搭建大数据的环境。

前提条件：已经有docker，docker compose环境

1. 创建docker compose yml

在任意文件夹下，创建这两个文件：

1. docker-compose.yml文件，这个文件中描述了我们要创建的容器信息，我这里使用的是hadoop 3.2.1，spark 3.2.1，容器端口映射了hdfs端口（9000）、spark UI（8080），spark master的url是spark://master:7077：

version: "3.3"
services:
  namenode:
    image: bde2020/hadoop-namenode:2.0.0-hadoop3.2.1-java8
    container_name: namenode
    ports:
      - 9870:9870
      - 9000:9000
    volumes:
      - ./hadoop/dfs/name:/hadoop/dfs/name
      - ./input:/input
    environment:
      - CLUSTER_NAME=test
    env_file:
      - ./hadoop.env

  datanode:
    image: bde2020/hadoop-datanode:2.0.0-hadoop3.2.1-java8
    container_name: datanode
    depends_on:
      - namenode
    volumes:
      - ./hadoop/dfs/data:/hadoop/dfs/data
    environment:
      SERVICE_PRECONDITION: "namenode:9870"
    env_file:
      - ./hadoop.env
  
  resourcemanager:
    image: bde2020/hadoop-resourcemanager:2.0.0-hadoop3.2.1-java8
    container_name: resourcemanager
    environment:
      SERVICE_PRECONDITION: "namenode:9000 namenode:9870 datanode:9864"
    env_file:
      - ./hadoop.env

  nodemanager1:
    image: bde2020/hadoop-nodemanager:2.0.0-hadoop3.2.1-java8
    container_name: nodemanager
    environment:
      SERVICE_PRECONDITION: "namenode:9000 namenode:9870 datanode:9864 resourcemanager:8088"
    env_file:
      - ./hadoop.env
  
  historyserver:
    image: bde2020/hadoop-historyserver:2.0.0-hadoop3.2.1-java8
    container_name: historyserver
    environment:
      SERVICE_PRECONDITION: "namenode:9000 namenode:9870 datanode:9864 resourcemanager:8088"
    volumes:
      - ./hadoop/yarn/timeline:/hadoop/yarn/timeline
    env_file:
      - ./hadoop.env
    
  master:
    image: bitnami/spark:3.2.1
    container_name: master
    user: root
    environment:
      - SPARK_MODE=master
      - SPARK_RPC_AUTHENTICATION_ENABLED=no
      - SPARK_RPC_ENCRYPTION_ENABLED=no
      - SPARK_LOCAL_STORAGE_ENCRYPTION_ENABLED=no
      - SPARK_SSL_ENABLED=no
    ports:
      - '8080:8080'
      - '7077:7077'
    volumes:
      - ./python:/python

  worker1:
    image: bitnami/spark:3.2.1
    container_name: worker1
    user: root
    environment:
      - SPARK_MODE=worker
      - SPARK_MASTER_URL=spark://master:7077
      - SPARK_WORKER_MEMORY=1G
      - SPARK_WORKER_CORES=1
      - SPARK_RPC_AUTHENTICATION_ENABLED=no
      - SPARK_RPC_ENCRYPTION_ENABLED=no
      - SPARK_LOCAL_STORAGE_ENCRYPTION_ENABLED=no
      - SPARK_SSL_ENABLED=no
  worker2:
    image: bitnami/spark:3.2.1
    container_name: worker2
    user: root
    environment:
      - SPARK_MODE=worker
      - SPARK_MASTER_URL=spark://master:7077
      - SPARK_WORKER_MEMORY=1G
      - SPARK_WORKER_CORES=1
      - SPARK_RPC_AUTHENTICATION_ENABLED=no
      - SPARK_RPC_ENCRYPTION_ENABLED=no
      - SPARK_LOCAL_STORAGE_ENCRYPTION_ENABLED=no
      - SPARK_SSL_ENABLED=no

2. hadoop.env（在docker-compose.yml中定义容器的时候使用了这个文件来指定设置）

CORE_CONF_fs_defaultFS=hdfs://namenode:9000
CORE_CONF_hadoop_http_staticuser_user=root
CORE_CONF_hadoop_proxyuser_hue_hosts=*
CORE_CONF_hadoop_proxyuser_hue_groups=*
CORE_CONF_io_compression_codecs=org.apache.hadoop.io.compress.SnappyCodec

HDFS_CONF_dfs_webhdfs_enabled=true
HDFS_CONF_dfs_permissions_enabled=false
HDFS_CONF_dfs_namenode_datanode_registration_ip___hostname___check=false

YARN_CONF_yarn_log___aggregation___enable=true
YARN_CONF_yarn_log_server_url=http://historyserver:8188/applicationhistory/logs/
YARN_CONF_yarn_resourcemanager_recovery_enabled=true
YARN_CONF_yarn_resourcemanager_store_class=org.apache.hadoop.yarn.server.resourcemanager.recovery.FileSystemRMStateStore
YARN_CONF_yarn_resourcemanager_scheduler_class=org.apache.hadoop.yarn.server.resourcemanager.scheduler.capacity.CapacityScheduler
YARN_CONF_yarn_scheduler_capacity_root_default_maximum___allocation___mb=8192
YARN_CONF_yarn_scheduler_capacity_root_default_maximum___allocation___vcores=4
YARN_CONF_yarn_resourcemanager_fs_state___store_uri=/rmstate
YARN_CONF_yarn_resourcemanager_system___metrics___publisher_enabled=true
YARN_CONF_yarn_resourcemanager_hostname=resourcemanager
YARN_CONF_yarn_resourcemanager_address=resourcemanager:8032
YARN_CONF_yarn_resourcemanager_scheduler_address=resourcemanager:8030
YARN_CONF_yarn_resourcemanager_resource__tracker_address=resourcemanager:8031
YARN_CONF_yarn_timeline___service_enabled=true
YARN_CONF_yarn_timeline___service_generic___application___history_enabled=true
YARN_CONF_yarn_timeline___service_hostname=historyserver
YARN_CONF_mapreduce_map_output_compress=true
YARN_CONF_mapred_map_output_compress_codec=org.apache.hadoop.io.compress.SnappyCodec
YARN_CONF_yarn_nodemanager_resource_memory___mb=16384
YARN_CONF_yarn_nodemanager_resource_cpu___vcores=8
YARN_CONF_yarn_nodemanager_disk___health___checker_max___disk___utilization___per___disk___percentage=98.5
YARN_CONF_yarn_nodemanager_remote___app___log___dir=/app-logs
YARN_CONF_yarn_nodemanager_aux___services=mapreduce_shuffle

MAPRED_CONF_mapreduce_framework_name=yarn
MAPRED_CONF_mapred_child_java_opts=-Xmx4096m
MAPRED_CONF_mapreduce_map_memory_mb=4096
MAPRED_CONF_mapreduce_reduce_memory_mb=8192
MAPRED_CONF_mapreduce_map_java_opts=-Xmx3072m
MAPRED_CONF_mapreduce_reduce_java_opts=-Xmx6144m
MAPRED_CONF_yarn_app_mapreduce_am_env=HADOOP_MAPRED_HOME=/data/docker-compose/hadoop-3.2.1/
MAPRED_CONF_mapreduce_map_env=HADOOP_MAPRED_HOME=/data/docker-compose/hadoop-3.2.1/
MAPRED_CONF_mapreduce_reduce_env=HADOOP_MAPRED_HOME=/data/docker-compose/hadoop-3.2.1/

2. 启动容器

在这个文件夹下运行：

docker-compose up -d

等待docker下载镜像，启动容器之后，就可以查看容器情况了：

3. 运行spark任务

进入spark master容器：

sudo docker exec -it ${master容器id} /bin/bash

运行spark示例程序：

./bin/spark-submit --class org.apache.spark.examples.SparkPi ./examples/jars/spark-examples_2.12-3.2.1.jar 100

启动任务之后，我们在虚拟机中使用localhost:8080查看程序（其实是master上面的8080端口映射到物理机上的）

感想：虚拟化真是个好玩意，日常后悔没有去浙大去做虚拟化技术。