Hadoop伪分布环境搭建（超详细）

---

实验环境：Centos7虚拟机一台
关闭防火墙 # systemctl stop firewalld

---

配置完成环境变量一定得：# source /etc/profile

---

配置静态IP

[root@localhost ~]# vi /etc/sysconfig/network-scripts/ifcfg-eno16777736 

检测：ping baidu.com

配置免密登录

# 生成密钥
ssh-keygen
# 生成授权文件authorized_keys
ssh-copy-id localhost

安装jdk

上传jdk文件到虚拟机
解压jdk-8u251-linux-x64.tar.gz

配置jdk环境变量

[root@localhost jdk1.8.0_251]# vi /etc/profile
[root@localhost jdk1.8.0_251]# tail -5 /etc/profile
unset i
unset -f pathmunge

export JAVA_HOME=/root/jdk1.8.0_251
export PATH=$PATH:$JAVA_HOME/bin
[root@localhost jdk1.8.0_251]# source /etc/profile
[root@localhost jdk1.8.0_251]# java -version
java version "1.8.0_251"
Java(TM) SE Runtime Environment (build 1.8.0_251-b08)
Java HotSpot(TM) 64-Bit Server VM (build 25.251-b08, mixed mode)
[root@localhost jdk1.8.0_251]# 

安装hadoop

上传hadoop压缩包
解压hadoop-2.7.7

配置hadoop环境变量

[root@localhost ~]# tail -5 /etc/profile
export JAVA_HOME=/root/jdk1.8.0_251
export PATH=$PATH:$JAVA_HOME/bin

export HADOOP_HOME=/root/hadoop-2.7.7
export PATH=$HADOOP_HOME/sbin:$PATH:$HADOOP_HOME/bin

配置hadoop配置文件

hadoop-env.sh
core-site.xml
hdfs-site.xml
yarn-env.sh
mapred-site.xml
yarn-site.xml
slaves

# vi hadoop-env.sh

# vi core-site.xml

<configuration>
<property>
        <name>fs.defaultFS</name>
        <value>hdfs://localhost:9000</value>
</property>
<property>
        <name>hadoop.tmp.dir</name>
        <value>/home/zran/hadoopdata</value>
</property>
</configuration>

# vi hdfs-site.xml

<configuration>
<property>
        <name>dfs.replication</name>
        <value>2</value>
</property>
</configuration>

修改mapred-site.xml（注意要将mapred-site.xml.template重命名为 .xml的文件）
命令：mv mapred-site.xml.template mapred-site.xml

<configuration> 
<property>  
        <name>mapreduce.framework.name</name>
        <value>yarn</value>
</property>
</configuration>

# vi yarn-site.xml

<configuration>
 
<property>
        <name>yarn.resourcemanger.hostname</name>
        <value>localhost</value>
</property>
<property>
        <name>yarn.nodemanager.aux-services</name>
        <value>mapreduce_shuffle</value>
</property>
 
</configuration>

# vi yarn-env.sh

格式化 namenode

# hdfs namenode -format

验证

开启hadoop伪分布集群

# 开启伪分布集群
start-all.sh
# jps进程检测
[root@localhost hadoop]# jps
10673 NodeManager
10979 Jps
10436 SecondaryNameNode
10581 ResourceManager
10167 NameNode
10252 DataNode