一、基础配置

1.主机映射

vim /etc/hosts

192.168.200.154 master
192.168.200.155 worker1
192.168.200.156 worker2

ssh-keygen

ssh-copy-id master

ssh-copy-id worker1

ssh-copy-id worker2

yum install -y vim

2.关闭防火墙

systemctl stop firewalld
systemctl disable firewalld
setenforce 0

二、安装jdk与hadoop

1.解压资源包

mkdir /usr/local/jdk
tar -zxf jdk-8u152-linux-x64.tar.gz -C /usr/local/jdk/
tar -zxf hadoop-3.3.1.tar.gz -C /usr/local/
mv /usr/local/hadoop-3.3.1/ /usr/local/hadoop

 2.修改环境变量

vim /etc/profile

#JAVA HOME
export JAVA_HOME=/usr/local/jdk/jdk1.8.0_152/
export PATH=$PATH:$JAVA_HOME/bin

#Hadoop
export HADOOP_HOME=/usr/local/hadoop/
export PATH=$PATH:$HADOOP_HOME/bin
export PATH=$PATH:$HADOOP_HOME/sbin

3.让环境变量生效与验证

source /etc/profile
java -version
hadoop version

三、配置集群环境

1. hadoop-env.sh

vim /usr/local/hadoop/etc/hadoop/hadoop-env.sh

export JAVA_HOME=/usr/local/jdk/jdk1.8.0_152/
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

2-1 core-site.xml （均在<configuration> </configuration>中间添加）

cd /usr/local/hadoop/etc/hadoop/
vim core-site.xm

<configuration>
<property>
        <name>fs.defaultFS</name>
    <value>hdfs://master:9000</value>
</property>
<!-- 临时文件存放位置 -->
<property>
        <name>hadoop.tmp.dir</name>
    <value>/usr/local/hadoop/tmp</value>
</property>
</configuration>

 2-2  hdfs-site.xml

vim hdfs-site.xml

<property>
        <name>dfs.replication</name>
    <value>2</value>
</property>
<!-- namenode存放的位置，老版本是用dfs.name.dir -->
<property>
        <name>dfs.namenode.name.dir</name>
    <value>/usr/local/hadoop/name</value>
</property>
<!-- datanode存放的位置，老版本是dfs.data.dir -->
<property>
        <name>dfs.datanode.data.dir</name>
    <value>/usr/local/hadoop/data</value>
</property>
<!-- 关闭文件上传权限检查 -->
<property>
        <name>dfs.permissions.enalbed</name>
    <value>false</value>
</property>
<!-- namenode运行在哪儿节点，默认是0.0.0.0:9870,在hadoop3.x中端口从原先的50070改为了9870 -->
<property>
        <name>dfs.namenode.http-address</name>
    <value>master:9870</value>
</property>
<!-- secondarynamenode运行在哪个节点，默认0.0.0.0:9868 -->
<property>
        <name>dfs.namenode.secondary.http-address</name>
    <value>master:9868</value>
</property>

2-3  yarn-site.xml

vim yarn-site.xml

<property>
        <name>yarn.resourcemanager.hostname</name>
    <value>master</value>
</property>
<!-- nodemanager获取数据的方式 -->
<property>
        <name>yarn.nodemanager.aux-services</name>
    <value>mapreduce_shuffle</value>
</property>
<!-- 关闭虚拟内存检查 -->
<property>
        <name>yarn.nodemanager.vmem-check-enabled</name>
    <value>false</value>
</property>

 2-4 mapred-site.xml

vim mapred-site.xml

<property>
        <name>mapreduce.framework.name</name>
    <value>yarn</value>
</property>
<!-- 配了上面这个下面这个也得配， 不然跑mapreduce会找不到主类。MR应用程序的CLASSPATH-->
<property>
        <name>mapreduce.application.classpath</name>
    <value>/usr/local/hadoop/share/hadoop/mapreduce/*:/usr/local/hadoop/share/hadoop/mapreduce/lib/*</value>
</property>

 2-5 workers（将原来的一行删除，添加下列两行）

vim workers

worker1
worker2

3.scp至其他节点

scp /usr/local/hadoop/etc/hadoop/core-site.xml worker1:/usr/local/hadoop/etc/hadoop/core-site.xml
scp /usr/local/hadoop/etc/hadoop/core-site.xml worker2:/usr/local/hadoop/etc/hadoop/core-site.xml
scp /usr/local/hadoop/etc/hadoop/hdfs-site.xml worker2:/usr/local/hadoop/etc/hadoop/hdfs-site.xml
scp /usr/local/hadoop/etc/hadoop/hdfs-site.xml worker1:/usr/local/hadoop/etc/hadoop/hdfs-site.xml
scp /usr/local/hadoop/etc/hadoop/core-site.xml worker1:/usr/local/hadoop/etc/hadoop/core-site.xml
scp /usr/local/hadoop/etc/hadoop/core-site.xml worker2:/usr/local/hadoop/etc/hadoop/core-site.xml
scp /usr/local/hadoop/etc/hadoop/yarn-site.xml worker2:/usr/local/hadoop/etc/hadoop/yarn-site.xml
scp /usr/local/hadoop/etc/hadoop/yarn-site.xml worker1:/usr/local/hadoop/etc/hadoop/yarn-site.xml
scp /usr/local/hadoop/etc/hadoop/mapred-site.xml worker1:/usr/local/hadoop/etc/hadoop/mapred-site.xml
scp /usr/local/hadoop/etc/hadoop/mapred-site.xml worker2:/usr/local/hadoop/etc/hadoop/mapred-site.xml
scp /usr/local/hadoop/etc/hadoop/workers worker1:/usr/local/hadoop/etc/hadoop/workers
scp /usr/local/hadoop/etc/hadoop/workers worker2:/usr/local/hadoop/etc/hadoop/workers
scp /usr/local/hadoop/etc/hadoop/hadoop-env.sh worker1:/usr/local/hadoop/etc/hadoop/hadoop-env.sh
scp /usr/local/hadoop/etc/hadoop/hadoop-env.sh worker2:/usr/local/hadoop/etc/hadoop/hadoop-env.sh

4.格式化

hdfs namenode -format

5.启动服务（在第一台）

start-all.sh

6.访问ip:9870和ip:8088