hadoop3 集群搭建

1 环境准备

hadoop1 192.168.38.150 jdk1.8
hadoop2 192.168.38.151 jdk1.8
hadoop3 192.168.38.152 jdk1.8

2 环境准备

#3台
yum install ssh pdsh

#修改host
vim /etc/hosts

192.168.38.150 hadoop1
192.168.38.151 hadoop2
192.168.38.152 hadoop3

#修改主机名
hostnamectl set-hostname hadoop1
hostnamectl set-hostname hadoop2
hostnamectl set-hostname hadoop3

3 集群规划

4 解压配置环境变量

#3台解压
tar -zxvf hadoop-3.1.3.tar.gz

#3台配置环境变量
vim /etc/profile

export HDFS_NAMENODE_USER=root
export HDFS_DATANODE_USER=root
export HDFS_SECONDARYNAMENODE_USER=root
export YARN_RESOURCEMANAGER_USER=root
export YARN_NODEMANAGER_USER=root

export JAVA_HOME=/usr/local/jdk1.8
export HADOOP_HOME=/usr/local/hadoop-3.1.3
export PATH=.:$JAVA_HOME/bin:$HADOOP_HOME/bin:$HADOOP_HOME/sbin:$PATH

source /etc/profile

#查看是否配置成功
hadoop version

5 免密登录

#hadoop 1
ssh-keygen -t rsa

ssh-copy-id hadoop1
ssh-copy-id hadoop2
ssh-copy-id hadoop3

#hadoop 2
ssh-keygen -t rsa

ssh-copy-id hadoop1
ssh-copy-id hadoop2
ssh-copy-id hadoop3

#hadoop 3
ssh-keygen -t rsa

ssh-copy-id hadoop1
ssh-copy-id hadoop2
ssh-copy-id hadoop3

6 配置core-site.xml

#3台
cd /usr/local/hadoop-3.1.3/etc/hadoop

vim core-site.xml

<configuration>

        <!-- 指定 NameNode 的地址 -->
        <property>
                <name>fs.defaultFS</name>
                <value>hdfs://hadoop1:8020</value>
        </property>
        <!-- 指定 hadoop 数据的存储目录 -->
        <property>
                <name>hadoop.tmp.dir</name>
                <value>/usr/local/hadoop-3.1.3/data</value>
        </property>

</configuration>

7 配置hdfs-site.xml

#3台
vim hdfs-site.xml

<configuration>

        <!-- NameNode web 端访问地址-->
        <property>
                <name>dfs.namenode.http-address</name>
                <value>hadoop1:9870</value>
        </property>
        <!-- SecondNameNode web 端访问地址-->
        <property>
                <name>dfs.namenode.secondary.http-address</name>
                <value>hadoop3:9868</value>
        </property>


</configuration>

8 配置yarn-site.xml

#3台
vim yarn-site.xml

<configuration>

				<!-- Site specific YARN configuration properties -->

        <!-- 指定 MR 走 shuffle -->
        <property>
                <name>yarn.nodemanager.aux-services</name>
                <value>mapreduce_shuffle</value>
        </property>
        <!-- 指定 ResourceManager 的地址-->
        <property>
                <name>yarn.resourcemanager.hostname</name>
                <value>hadoop2</value>
        </property>

</configuration>

9 配置 mapred-site.xml

#3台
vim mapred-site.xml


<configuration>

        <!-- 指定 MapReduce 程序运行在 Yarn 上 -->
        <property>
                <name>mapreduce.framework.name</name>
                <value>yarn</value>
        </property>
			  <property>
							  <name>yarn.app.mapreduce.am.env</name>
							  <value>HADOOP_MAPRED_HOME=/usr/local/hadoop-3.1.3</value>
				</property>
        <property>
                  <name>mapreduce.map.env</name>
                  <value>HADOOP_MAPRED_HOME=/usr/local/hadoop-3.1.3</value>
        </property>
        <property>
                  <name>mapreduce.reduce.env</name>
                  <value>HADOOP_MAPRED_HOME=/usr/local/hadoop-3.1.3</value>
        </property>

</configuration>

10 配置workers

#3台
vim workers

hadoop1
hadoop2
hadoop3

11 配置JAVA_HOME HADOOP_CONF_DIR

#3台
vim hadoop-env.sh

export JAVA_HOME=/usr/local/jdk1.8
export HADOOP_CONF_DIR=/usr/local/hadoop-3.1.3/etc/hadoop

12 启动NameNode集群

#hadoop1 初始化（第一次需要初始化）
hdfs namenode -format

#hadoop01 启动集群
start-dfs.sh

#访问页面
http://192.168.38.150:9870/

13 启动Yarn

## hadoop2上启动
start-yarn.sh
## 查看yarn
http://hadoop2:8088/

14 检查

jps

15 集群基本测试

#创建目录
hadoop fs -mkdir /wcinput
#上传小文件
hadoop fs -put ./word.txt  /wcinput

#执行wordcount
hadoop jar share/hadoop/mapreduce/hadoop-mapreduce-examples-3.1.3.jar wordcount /wcinput /wcoutput