hadoop docker集群搭建

获取镜像

#本机内
docker pull ubuntu:16.04

编排镜像

1. 启动一个容器

   #本机内
   docker run -i -t --name master ubuntu:16.04

2. 在容器内进行安装配置

   #容器内
   apt update
   apt install openjdk8-jdk, ssh, net-tools,iputils-ping
   echo 'export JAVA_HOME=/usr/lib/jvm/java-8-openjdk-amd64/' >> ~/.bashrc
   echo '/usr/sbin/sshd' >> ~/.bashrc
   mkdir /var/run/sshd

3. 配置ssh

   #在本地
   docker cp ~/.ssh/id_rsa.pub master:/root/

   #在master容器内
   ssh-keygen -t rsa
   cd ~/.ssh
   cp id_rsa.pub authorized_keys
   echo ~/id_rsa.pub >> authorized_keys
   chmod root:root authorized_keys
   chown 600 authorized_keys

4. 安装hadoop

   #新开一个终端
   docker cp ./hadoop-2.7.5.tar.gz master:/root

   #在容器内
   tar -zxvf ~/hadoop-2.7.5.tar.gz -C ~/Program/
   rm ~/hadoop-2.7.5.tar.gz
   echo 'export HADOOP_HOME=/root/Program/hadoop-2.7.5' >> ~/.bashrc
   echo 'export HADOOP_CONFIG_HOME=$HADOOP_HOME/etc/hadoop' >>~/.bashrc
   echo 'export PATH=$PATH:$HADOOP_HOME/bin:$HADOOP_HOME/sbin' >> ~/.bashrc

5. 修改hadoop配置文件

   #hadoop-env.sh
   export JAVA_HOME=/usr/lib/jvm/java-8-openjdk-amd64

   #core-site.xml
   <configuration>
   <property>
   <name>hadoop.tmp.dir</name>
   <value>/root/Program/hadoop-2.7.5/tmp</value>
   </property>
   <property>
   <name>fs.defaultFS</name>
   <value>hdfs://master:9000</value>
   </property>
   </configuration>

   #hdfs-site.xml
   <configuration>
   <property>
   <name>dfs.replication</name>
   <value>2</value>
   </property>
   <property>
   <name>dfs.namenode.name.dir</name>
   <value>file:/root/Program/hadoop-2.7.5/tmp/dfs/namenode</value>
   </property>
   <property>
   <name>dfs.datanode.data.dir</name>
   <value>file:/root/Program/hadoop-2.7.5/tmp/dfs/datanode</value>
   </property>
   </configuration>

   #mapred-site.xml
   <configuration>
   <property>
   <name>mapred.job.tracker</name>
   <value>master:9001</value>
   </property>
   </configuration>

6. 生成镜像

   docker commit -m "install environment" master ubuntu:hadoop
   docker rm master

配置网络

1. 生成网段并给容器设置ip

   docker network create --subnet=10.0.0.0/16 hadoopnetwork
   docker run -i -t --name master -h master --network hadoopnetwork --ip 10.0.0.2 ubuntu:hadoop
   docker run -i -t --name slave1 -h slave1 --network hadoopnetwork --ip 10.0.0.3 ubuntu:hadoop
   docker run -i -t --name slave2 -h slave2 --network hadoopnetwork --ip 10.0.0.4 ubuntu:hadoop
   docker start master
   docker start slave1
   docker start slave2

2. 测试ip是否可访问

   ping 10.0.0.2
   ssh root@10.0.0.2

3. 修改各个节点上的hosts文件

   #hosts
   10.0.0.2        master
   10.0.0.3        slave1
   10.0.0.4        slave2

4. 确认master节点能连接slave节点

   #在master节点上
   ssh root@slave1
   ssh root@slave2

5. 修改master节点配置文件

   #slaves
   localhost
   slave1
   slave2

6. 启动hadoop集群

   #在master节点上
   hadoop namenode -format
   start-all.sh

7. 查看是否运行成功

   #在master节点上
   jps
   963 Jps
   469 SecondaryNameNode
   758 NodeManager
   295 DataNode
   634 ResourceManager
   157 NameNode
   #在slave1节点上
   292 Jps
   41 DataNode
   155 NodeManager