centos 7 hadoop 3.1 集群搭建

前言

hadoop 是一个由Apache基金会所开发的分布式系统基础架构。用户可以在不了解分布式底层细节的情况下，开发分布式程序。充分利用集群的威力进行高速运算和存储。 [ 百度百科 ]

开始

1 .在三个虚拟机中分别下载好 hadoop(3.1.0) 和 java(1.8)

cd /usr/local
wget wget http://download.oracle.com/otn-pub/java/jdk/8u181-b13/96a7b8442fe848ef90c96a2fad6ed6d1/jdk-8u181-linux-x64.tar.gz?AuthParam=1533698216_4d96320e63a975b4cec59c2616d523dd
wget http://mirrors.hust.edu.cn/apache/hadoop/common/hadoop-3.1.0/hadoop-3.1.0.tar.gz
mkdir /usr/local/java
mkdir /usr/local/hadoop
tar  -zxvf   jdk-8u181-linux-x64.tar.gz\?AuthParam\=1533698216_4d96320e63a975b4cec59c2616d523dd    -C      /usr/local/java
tar  -zxvf   hadoop-3.1.0.tar.gz    -C      /usr/local/hadoop

2 .设置各个机器的host，然后重启

vim /etc/hosts
	192.168.1.76   hserver1
	192.168.1.77   hserver2
	192.168.1.78   hserver3
reboot

3 .设置各个机器的ssh互通

vim /etc/ssh/sshd_config
	PermitRootLogin yes
ssh-keygen -t rsa 

hserver1：

scp /root/.ssh/id_rsa.pub root@hserver2:/root/.ssh/id_rsa_hserver1.pub
scp /root/.ssh/id_rsa.pub root@hserver3:/root/.ssh/id_rsa_hserver1.pub

hserver2

scp /root/.ssh/id_rsa.pub root@hserver1:/root/.ssh/id_rsa_hserver2.pub
scp /root/.ssh/id_rsa.pub root@hserver3:/root/.ssh/id_rsa_hserver2.pub

hserver3：

scp /root/.ssh/id_rsa.pub root@hserver1:/root/.ssh/id_rsa_hserver3.pub
scp /root/.ssh/id_rsa.pub root@hserver2:/root/.ssh/id_rsa_hserver3.pub

hserver1：

cd /root/.ssh
cat id_rsa_hserver2.pub >> authorized_keys
cat id_rsa_hserver3.pub >> authorized_keys

hserver2：

cd /root/.ssh
cat id_rsa_hserver1.pub >> authorized_keys
cat id_rsa_hserver3.pub >> authorized_keys

hserver3：

cd /root/.ssh
cat id_rsa_hserver1.pub >> authorized_keys
cat id_rsa_hserver2.pub >> authorized_keys

ssh连接测试：

ssh hserver2
ssh hserver3

4 .创建三个文件夹

mkdir  -p  /usr/local/hadoop/hadoop-3.1.0/data/datanode
mkdir  -p  /usr/local/hadoop/hadoop-3.1.0/data/name
mkdir  -p  /usr/local/hadoop/hadoop-3.1.0/data/tmp

5 .配置环境变量

vim /etc/profile
	export JAVA_HOME=/usr/local/java/jdk1.8.0_181
	export JRE_HOME=${JAVA_HOME}/jre
	export CLASSPATH=.:${JAVA_HOME}/lib:${JRE_HOME}/lib
	export HADOOP_HOME=/usr/local/hadoop/hadoop-3.1.0
	export PATH=$PATH:$JAVA_HOME/bin:$HADOOP_HOME/bin:$HADOOP_HOME/sbin
source /etc/profile

6 .配置hadoop环境变量

cd /usr/local/hadoop/hadoop-3.1.0/etc/hadoop
vim hadoop-env.sh
	export JAVA_HOME=/usr/local/java/jdk1.8.0_181
	export HADOOP_HOME=/usr/local/hadoop/hadoop-3.1.0
	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

7 .设置hadoop文件core-site.xml

vim core-site.xml
	<configuration>
		<property>
			<name>fs.defaultFS</name>
			<value>hdfs://hserver1:9000</value>
		</property>
		<property>
			<name>hadoop.tmp.dir</name>
			<value>/usr/local/hadoop/hadoop-3.1.0/data/tmp</value>
		</property>
	</configuration>

8 .设置hadoop文件hdfs-site.xml
hserver1：

vim hdfs-site.xml
	<configuration>
		<property>
			<name>dfs.namenode.http-address</name>
			<value>hserver1:9001</value>
		</property> 
		<property>
			<name>dfs.namenode.secondary.http-address</name>
			<value>hserver2:9002</value>
		</property>
		<property>
			<name>dfs.namenode.name.dir</name>
			<value>file:///usr/local/hadoop/hadoop-3.1.0/data/name</value>
		</property>
		<property>
			<name>dfs.replication</name>
			<value>1</value>
		</property>
		<property>
			<name>dfs.datanode.data.dir</name>
			<value>/usr/local/hadoop/hadoop-3.1.0/data/datanode</value>
		</property>
		<property>
			<name>dfs.permissions</name>
			<value>false</value>
		</property>
	</configuration>

hserver2：

vim hdfs-site.xml
	<configuration>
		<property>
			<name>dfs.replication</name>
			<value>1</value>
		</property>
		<property>
			<name>dfs.namenode.name.dir</name>
			<value>file:///usr/local/hadoop/hadoop-3.1.0/data/name</value>
		</property>
		<property>
			<name>dfs.datanode.data.dir</name>
			<value>/usr/local/hadoop/hadoop-3.1.0/data/datanode</value>
		</property>
		<property>
			<name>dfs.permissions</name>
			<value>false</value>
		</property>
	</configuration>

hserver3：

vim hdfs-site.xml
	<configuration> 
		<property>
			<name>dfs.replication</name>
			<value>1</value>
		</property>
		<property>
			<name>dfs.datanode.data.dir</name>
			<value>/usr/local/hadoop/hadoop-3.1.0/data/datanode</value>
		</property>
		<property>
			<name>dfs.permissions</name>
			<value>false</value>
		</property>
	</configuration>

9 .设置hadoop文件mapred-site.xml

vim mapred-site.xml
	<configuration>
		<property>
			<name>mapreduce.framework.name</name>
			<value>yarn</value>
		</property>
		<property>
			<name>mapreduce.application.classpath</name>
			<value>
	        /usr/local/hadoop/hadoop-3.1.0/etc/hadoop,
	        /usr/local/hadoop/hadoop-3.1.0/share/hadoop/common/*,
	        /usr/local/hadoop/hadoop-3.1.0/share/hadoop/common/lib/*,
	        /usr/local/hadoop/hadoop-3.1.0/share/hadoop/hdfs/*,
	        /usr/local/hadoop/hadoop-3.1.0/share/hadoop/hdfs/lib/*,
	        /usr/local/hadoop/hadoop-3.1.0/share/hadoop/mapreduce/*,
	        /usr/local/hadoop/hadoop-3.1.0/share/hadoop/mapreduce/lib/*,
	        /usr/local/hadoop/hadoop-3.1.0/share/hadoop/yarn/*,
	        /usr/local/hadoop/hadoop-3.1.0/share/hadoop/yarn/lib/*
			</value>
		</property>
	</configuration>

10 .设置hadoop文件yarn-site.xml
hserver1：

vim yarn-site.xml
	<configuration>
		<property>  
			<name>yarn.nodemanager.aux-services</name>  
			<value>mapreduce_shuffle</value>  
		</property> 
		<property>
			<name>yarn.nodemanager.aux-services</name>
			<value>mapreduce_shuffle</value>
		</property>
	</configuration>

hserver2：

vim yarn-site.xml
	<configuration>
		<property>  
			<name>yarn.nodemanager.aux-services</name>  
			<value>mapreduce_shuffle</value>  
		</property> 
		<property>
			<name>yarn.nodemanager.aux-services</name>
			<value>mapreduce_shuffle</value>
		</property>
		<property>
			<name>yarn.resourcemanager.address</name>
			<value>hserver1:8032</value>
		</property>
		<property>
			<name>yarn.resourcemanager.scheduler.address</name>
			<value>hserver1:8030</value>
		</property>
		<property>
			<name>yarn.resourcemanager.resource-tracker.address</name>
			<value>hserver1:8031</value>
		</property>
	</configuration>

hserver3：

vim yarn-site.xml
	<configuration>
		<property>  
			<name>yarn.nodemanager.aux-services</name>  
			<value>mapreduce_shuffle</value>  
		</property> 
		<property>
			<name>yarn.nodemanager.aux-services</name>
			<value>mapreduce_shuffle</value>
		</property>
		<property>
			<name>yarn.resourcemanager.address</name>
			<value>hserver1:8032</value>
		</property>
		<property>
			<name>yarn.resourcemanager.scheduler.address</name>
			<value>hserver1:8030</value>
		</property>
		<property>
			<name>yarn.resourcemanager.resource-tracker.address</name>
			<value>hserver1:8031</value>
		</property>
	</configuration>

11 .新建文件，设置 第二NameNode 和 集群
hserver1：

cd /usr/local/hadoop/hadoop-3.1.0/etc/hadoop/
vim masters
	hserver2
vim workers
	hserver2
	hserver3

12 .格式化(首次需要格式化hserver1)和启动hadoop
hserver1：

/usr/local/hadoop/hadoop-3.1.0/bin/hdfs namenode -format
cd /usr/local/hadoop/hadoop-3.1.0/sbin
start-all.sh
stop-all.sh

---

结束

附上图片一张：