hadoop2.7.7 测试安装 centos7

useradd –m hadoop –s /bin/bash

passwd hadoop

 

增加sudo权限

chmod u+w /etc/sudoers

vi /etc/sudoers

root    ALL=(ALL)       ALL

hadoop ALL=(ALL) ALL

chmod u-w /etc/sudoers

 

 

su hadoop && cd ~

 

wget http://mirror.bit.edu.cn/apache/hadoop/common/hadoop-2.7.7/hadoop-2.7.7.tar.gz

 

tar -zxf hadoop-2.7.7.tar.gz

sudo mkdir /usr/local/hadoop

sudo mv hadoop-2.7.7 /usr/local/hadoop

mkdir dfs

mkdir dfs/name

mkdir dfs/data

mkdir tmp

 

cd /usr/local/hadoop/hadoop-2.7.7/etc/hadoop

 

涉及到的配置文件有7个：

安装路径/hadoop-2.7.7/etc/hadoop/hadoop-env.sh

安装路径/hadoop-2.7.7/etc/hadoop/yarn-env.sh

安装路径/hadoop-2.7.7/etc/hadoop/slaves

安装路径/hadoop-2.7.7/etc/hadoop/core-site.xml

安装路径/hadoop-2.7.7/etc/hadoop/hdfs-site.xml

安装路径/hadoop-2.7.7/etc/hadoop/mapred-site.xml

安装路径/hadoop-2.7.7/etc/hadoop/yarn-site.xml

 

hadoop-env.sh和yarn-env.sh 里修改JAVA_HOME
===

cat core-site.xml
<?xml version="1.0" encoding="UTF-8"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>

<!-- Put site-specific property overrides in this file. -->

<configuration>
      <property>
               <name>fs.defaultFS</name>
               <value>hdfs://localhost:8020</value>
      </property>
      <property>
               <name>io.file.buffer.size</name>
               <value>131072</value>
       </property>
      <property>
              <name>hadoop.tmp.dir</name>
               <value>file:/home/hadoop/tmp</value>
              <description>Abase for other temporary   directories.</description>
      </property>
       <property>
               <name>hadoop.proxyuser.hadoop.hosts</name>
              <value>*</value>
      </property>
      <property>
               <name>hadoop.proxyuser.hadoop.groups</name>
              <value>*</value>
      </property>
      <property>
       <name>hadoop.proxyuser.root.groups</name>
       <value>*</value>
       <description>Allow the superuser oozie to impersonate any members of the group group1 and group2</description>
     </property>
     <property>
       <name>hadoop.proxyuser.root.hosts</name>
       <value>*</value>
       <description>The superuser can connect only from host1 and host2 to impersonate a user</description>
     </property>

</configuration>

===

cat hdfs-site.xml
<?xml version="1.0" encoding="UTF-8"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>

<!-- Put site-specific property overrides in this file. -->

<configuration>
       <property>
               <name>dfs.namenode.secondary.http-address</name>
              <value>localhost:9001</value>
       </property>
     <property>
            <name>dfs.namenode.name.dir</name>
             <value>file:/home/hadoop/dfs/name</value>
       </property>
      <property>
              <name>dfs.datanode.data.dir</name>
              <value>file:/home/hadoop/dfs/data</value>
       </property>
       <property>
              <name>dfs.replication</name>
              <value>3</value>
        </property>
        <property>
                 <name>dfs.webhdfs.enabled</name>
                 <value>true</value>
         </property>
</configuration>
===

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

 

cat mapred-site.xml
<?xml version="1.0"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>

<configuration>
       <property>
               <name>mapreduce.framework.name</name>
               <value>yarn</value>
          </property>
         <property>
                 <name>mapreduce.jobhistory.address</name>
                 <value>localhost:10020</value>
         </property>
         <property>
                <name>mapreduce.jobhistory.webapp.address</name>
               <value>localhost:19888</value>
      </property>
</configuration>
=======

 cat yarn-site.xml
<?xml version="1.0"?>
<configuration>
<property>
              <name>yarn.nodemanager.aux-services</name>
              <value>mapreduce_shuffle</value>
       </property>
       <property>                                                               
              <name>yarn.nodemanager.aux-services.mapreduce.shuffle.class</name>
              <value>org.apache.hadoop.mapred.ShuffleHandler</value>
       </property>
       <property>
              <name>yarn.resourcemanager.address</name>
              <value>localhost:8032</value>
      </property>
      <property>
              <name>yarn.resourcemanager.scheduler.address</name>
              <value>localhost:8030</value>
      </property>
      <property>
           <name>yarn.resourcemanager.resource-tracker.address</name>
            <value>localhost:8031</value>
     </property>
     <property>
              <name>yarn.resourcemanager.admin.address</name>
              <value>localhost:8033</value>
      </property>
      <property>
              <name>yarn.resourcemanager.webapp.address</name>
              <value>localhost:8088</value>
      </property>
</configuration>
====

设置环境变量

HADOOP_HOME=/usr/local/hadoop/hadoop-2.7.7

并将其中的bin和sbin加入path中

 

格式化namenode：hdfs namenode –format或使用hadoop namenode format

 

$ start-dfs.sh
Starting namenodes on [localhost]
localhost: starting namenode, logging to /usr/local/hadoop/hadoop-2.7.7/logs/hadoop-hadoop-namenode-mhc-linux.out
localhost: starting datanode, logging to /usr/local/hadoop/hadoop-2.7.7/logs/hadoop-hadoop-datanode-mhc-linux.out
Starting secondary namenodes [localhost]
localhost: starting secondarynamenode, logging to /usr/local/hadoop/hadoop-2.7.7/logs/hadoop-hadoop-secondarynamenode-mhc-linux.out

 

 启动namenode报错

ulimit -a for user root

stop-dfs.sh

这里我们直接重新格式化namenode，然后启动namenode就可以了

 hadoop namenode -format  

$ start-dfs.sh
ps -ef|grep node

有三个进程
proc_namenode proc_datanode proc_secondarynamenode

start-yarn.sh

访问http://localhost:8088