CentOS6.4安装Hadoop2.0.5 alpha - Single Node Cluster

1.安装JDK7 rpm到/usr/java/jdk1.7.0_40，并建立软链接/usr/java/default到/usr/java/jdk1.7.0_40

[root@server-308 ~]# rpm -ivh jdk-7u40-linux-x64.rpm
Preparing... ########################################### [100%]
1:jdk ########################################### [100%]
Unpacking JAR files...
rt.jar...
jsse.jar...
charsets.jar...
tools.jar...
localedata.jar...
jfxrt.jar...

[root@server-308 ~]# java -version
java version "1.7.0_40"
Java(TM) SE Runtime Environment (build 1.7.0_40-b43)
Java HotSpot(TM) 64-Bit Server VM (build 24.0-b56, mixed mode)

2.下载hadoop2.1beta并解压至/opt/hadoop-2.1.0-beta，并建立软链/opt/hadoop接到/opt/hadoop-2.1.0-beta

 

[root@server-308 ~]# cd /opt
[root@server-308 opt]# tar -zxvf /root/hadoop-2.1.0-beta.tar.gz

  [root@server-308 opt]# ln -s hadoop-2.1.0-beta hadoop
  [root@server-308 opt]# ls
  cedar hadoop hadoop-2.1.0-beta rh

 

3. 设置环境变量

[root@server-308 opt]# vim /etc/profile

在文件末尾添加如下内容:

export JAVA_HOME=/usr/java/default
export PATH=${JAVA_HOME}/bin:${PATH}

export HADOOP_PREFIX=/opt/hadoop
export PATH=$PATH:$HADOOP_PREFIX/bin
export PATH=$PATH:$HADOOP_PREFIX/sbin
export HADOOP_MAPRED_HOME=${HADOOP_PREFIX}
export HADOOP_COMMON_HOME=${HADOOP_PREFIX}
export HADOOP_HDFS_HOME=${HADOOP_PREFIX}
export YARN_HOME=${HADOOP_PREFIX}

使上述修改生效:

[root@server-308 opt]# source /etc/profile

4.建立用户和组

[root@server-308 opt]# groupadd hadoop
[root@server-308 opt]# useradd -g hadoop yarn
[root@server-308 opt]# useradd -g hadoop hdfs
[root@server-308 opt]# useradd -g hadoop mapred

5.创建相关路径和文件

[root@server-308 opt]# mkdir -p /var/data/hadoop/hdfs/nn
[root@server-308 opt]# mkdir -p /var/data/hadoop/hdfs/snn
[root@server-308 opt]# mkdir -p /var/data/hadoop/hdfs/dn
[root@server-308 opt]# mkdir -p /opt/hadoop/logs
[root@server-308 opt]# mkdir -p /var/log/hadoop/yarn
[root@server-308 opt]# chown hdfs:hadoop /var/data/hadoop/hdfs -R
[root@server-308 opt]# chown yarn:hadoop /var/log/hadoop/yarn -R
[root@server-308 opt]# chown yarn:hadoop /opt/hadoop/logs -R
[root@server-308 opt]# chmod g+w /opt/hadoop/logs 

 6.修改hadoop配置文件

[root@server-308 ~]# vim /opt/hadoop/etc/hadoop/core-site.xml

 

<configuration>
  <property>
    <name>fs.default.name</name>
    <value>hdfs://192.168.32.31:8020</value>
  </property>
  <property>
    <name>hadoop.http.staticuser.user</name>
    <value>hdfs</value>
  </property>
</configuration>

 7.修改hdfs-site.xml

[root@server-308 ~]# vim /opt/hadoop/etc/hadoop/hdfs-site.xml

 

<configuration>
  <property>
    <name>dfs.namenode.name.dir</name>
    <value>file:/var/data/hadoop/hdfs/nn</value>
  </property>
  <property>
    <name>fs.checkpoint.dir</name>
    <value>file:/var/data/hadoop/hdfs/snn</value>
  </property>
  <property>
    <name>fs.checkpoint.edits.dir</name>
    <value>file:/var/data/hadoop/hdfs/snn</value>
  </property>
  <property>
    <name>dfs.datanode.data.dir</name>
    <value>file:/var/data/hadoop/hdfs/dn</value>
  </property>
  <property>
    <name>dfs.replication</name>
    <value>1</value>
  </property>
  <property>
    <name>dfs.permissions</name>
    <value>false</value>
  </property>
</configuration>

 6.修改mapred-site.xml

#cp mapred-site.xml.template mapred-site.xml
#vi mapred-site.xml

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

 7.修改yarn-site.xml

<configuration>

<!-- Site specific YARN configuration properties -->
  <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>
</configuration>

8.格式化集群

su - hdfs
cd /opt/hadoop/bin
./hdfs namenode -format

9.启动hdfs

cd ../sbin
./hadoop-daemon.sh start namenode
./hadoop-daemon.sh start secondarynamenode
./hadoop-daemon.sh start datanode

10.检查hdfs是否正常工作

hadoop fs -mkdir /user/shaochen
hadoop fs -put mr-jobhistory-daemon.sh /user/shaochen/mr-jobhistory-daemon.sh
hadoop fs -cat /user/shaochen/mr-jobhistory-daemon.sh

12.启动yarn

su - yarn
cd /opt/hadoop/sbin
./yarn-daemon.sh start resourcemanager
./yarn-daemon.sh start nodemanager

 13.检验yarn是否正常工作

./hadoop jar ../share/hadoop/mapreduce/hadoop-mapreduce-examples-2.0.5-alpha.jar pi 16 1000