Hadoop分布式集群介绍

本次Hadoop搭建使用GitHub - kiwenlau/hadoop-cluster-docker: Run Hadoop Custer within Docker Containers进行。

首先需要明确Hadoop集群的启动顺序如下：

namenode -> datanode -> resourcemanager -> nodemanager -> historyserver

可使用浏览器通过如下地址监视hadoop集群的状况：

• Namenode: http://<dockerhadoop_IP_address>:9870/dfshealth.html#tab-overview
• History server: http://<dockerhadoop_IP_address>:8188/applicationhistory
• Datanode: http://<dockerhadoop_IP_address>:9864/
• Nodemanager: http://<dockerhadoop_IP_address>:8042/node
• Resource manager: http://<dockerhadoop_IP_address>:8088/

准备docker-compose相关文件

准备docker-compose.yml如下所示：

version: "3"

services:
  namenode:
    image: bde2020/hadoop-namenode:2.0.0-hadoop3.1.3-java8
    container_name: namenode
    ports:
      - 9870:9870
    volumes:
      - hadoop_namenode:/hadoop/dfs/name
    environment:
      - CLUSTER_NAME=test
    env_file:
      - ./hadoop.env

  datanode:
    image: bde2020/hadoop-datanode:2.0.0-hadoop3.1.3-java8
    container_name: datanode
    volumes:
      - hadoop_datanode:/hadoop/dfs/data
    environment:
      SERVICE_PRECONDITION: "namenode:9870"
    env_file:
      - ./hadoop.env
  
  resourcemanager:
    image: hadoop-resourcemanager:2.0.0-hadoop3.1.3-java8
    container_name: resourcemanager
    environment:
      SERVICE_PRECONDITION: "namenode:9870 datanode:9864"
    env_file:
      - ./hadoop.env
    ports:
      - 8088:8088

  nodemanager1:
    image: bde2020/hadoop-nodemanager:2.0.0-hadoop3.1.3-java8
    container_name: nodemanager
    environment:
      SERVICE_PRECONDITION: "namenode:9870 datanode:9864 resourcemanager:8088"
    env_file:
      - ./hadoop.env
  
  historyserver:
    image: bde2020/hadoop-historyserver:2.0.0-hadoop3.1.3-java8
    container_name: historyserver
    environment:
      SERVICE_PRECONDITION: "namenode:9870 datanode:9864 resourcemanager:8088"
    volumes:
      - hadoop_historyserver:/hadoop/yarn/timeline
    env_file:
      - ./hadoop.env
  
volumes:
  hadoop_namenode:
  hadoop_datanode:
  hadoop_historyserver:

hadoop.env文件如下：

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=/opt/hadoop-3.1.3/
MAPRED_CONF_mapreduce_map_env=HADOOP_MAPRED_HOME=/opt/hadoop-3.1.3/
MAPRED_CONF_mapreduce_reduce_env=HADOOP_MAPRED_HOME=/opt/hadoop-3.1.3/

构建resourcemanager镜像

由于namenode处于安全模式，resourcemanager需要延迟30秒启动。

修改run.sh如下：

#!/bin/bash

sleep 30
$HADOOP_PREFIX/bin/yarn --config $HADOOP_CONF_DIR resourcemanager

Dockerfile

FROM bde2020/hadoop-base

MAINTAINER Ivan Ermilov <ivan.s.ermilov@gmail.com>

HEALTHCHECK CMD curl -f http://localhost:8088/ || exit 1

ADD run.sh /run.sh
RUN chmod a+x /run.sh

EXPOSE 8088

CMD ["/run.sh"]

运行如下命令构建resourcemanager镜像文件：

docker build -t hadoop-resourcemanager:2.0.0-hadoop3.1.3-java8 .

启动Hadoop集群

运行如下命令启动Hadoop集群

docker-compose up -d

可通过浏览器正常访问相应的监视地址。