CentOS7搭建Hadoop-2.7集群

首先机器需要修改好静态ip

1.创建目录

mkdir -p /root/data/hadoop
mkdir -p /root/data/hadoop/tmp
mkdir -p /root/data/hadoop/var
mkdir -p /root/data/hadoop/dfs
mkdir -p /root/data/hadoop/dfs/name
mkdir -p /root/data/hadoop/dfs/data

2.修改/opt/hadoop-2.7/etc/hadoop/core-site.xml

<property>
    <name>hadoop.tmp.dir</name>
    <value>/root/data/hadoop/tmp</value>
</property>

<property>
     <name>fs.default.name</name>
     <value>hdfs://hserver-1:9000</value>
</property>

<property>
     <name>hadoop.proxyuser.root.hosts</name>
     <value>*</value>
</property>

<property>
     <name>hadoop.proxyuser.root.groups</name>
     <value>*</value>
</property>

3.修改/opt/hadoop-2.7/etc/hadoop/hadoop-env.sh

export JAVA_HOME=/opt/jdk-1.8

4.修改/opt/hadoop-2.7/etc/hadoop/hdfs-site.xml

<property>
    <name>dfs.name.dir</name>
    <value>/root/data/hadoop/dfs/name</value>
</property>

<property>
    <name>dfs.data.dir</name>
    <value>/root/data/hadoop/dfs/data</value>
</property>

<property>
    <name>dfs.tmp.dir</name>
    <value>/root/data/hadoop/tmp</value>
</property>

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

<property>
    <name>dfs.permissions</name>
    <value>false</value>
</property>

5.修改mapred-site.xml文件

cp mapred.site.xml.template mapred.site.xml

<property>
    <name>mapred.job.tracker</name>
    <value>hserver-1:49001</value>
</property>

<property>
    <name>mapred.local.dir</name>
    <value>/root/data/hadoop/var</value>
</property>

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

6.修改yarn-site.xml

<property>
    <name>yarn.resourcemanager.hostname</name>
    <value>hserver-1</value>
</property>

<property>
    <name>yarn.nodemanager.aux-services</name>
    <value>mapreduce_shuffle</value>
</property>

7.修改slaves文件

hserver-2
hserver-3

8.安装另外两台机器

需要从修改静态ip开始

在namenode格式化之前要实现三台机器的ssh免密登录