1.VirtualBox下新建虚拟机ubuntu12.04 32bit
2.root下安装jdk:
apt-get install openjdk-7-jdk
3.创建hadoop用户及hadoop组,赋予hadoop超级用户权限:
sudo addgroup hadoop
sudo adduser --ingroup hadoop hadoop
vim /etc/sudoers
在root ALL=(ALL:ALL) ALL下添加一行:hadoop ALL=(ALL:ALL) ALL
4.安装ssh,实现无密码登陆:
sudo apt-get install openssh-server
ssh-keygen -t rsa -P ""
cat ~/.ssh/id_rsa.pub >> ~/.ssh/authorized_keys
5.解压hadoop2.2.0到/usr/local
tar -zxvf hadoop-2.2.0.tar.gz
6.配置环境变量/etc/profile
export JAVA_HOME=/usr/lib/jvm/java-1.7.0-openjdk-i386
export HADOOP_HOME=/usr/local/lib/hadoop-2.2.0
export PATH=$PATH:$JAVA_HOME/bin:$HADOOP_HOME/sbin:$HADOOP_HOME/bin
source /etc/profile
7.修改hadoop配置文件
7.1.hadoop-env.sh
修改JAVA_HOME:export JAVA_HOME=/usr/lib/jvm/java-1.7.0-openjdk-i386
7.2.core-site.xml
<configuration>
<property>
<name>fs.default.name</name>
<value>hdfs://localhost:9000</value>
</property>
</configuration>
7.3.hdfs-site.xml
<configuration>
<property>
<name>dfs.replication</name>
<value>1</value>
<property>
</property>
<name>dfs.namenode.name.dir</name>
<value>/home/hadoop/namenode</value>
</property>
<property>
<name>dfs.datanode.data.dir</name>
<value>/home/hadoop/datanode</value>
</property>
</configuration>
7.4.mapred-site.xml
<configuration>
<property>
<name>mapreduce.framework.name</name>
<value>yarn</value>
</property>
</configuration>
7.5.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hdfs
hadoop namenode -format
9.启动hadoop
start-dfs.sh
start-yarn.sh
jps
若namenode、secondarynamenode、datanode、nodemanager、resourcemanager都已启动说明已成功安装
还可通过wordcount例子来检验是否安装成功。