在Ubuntu 13.10 中安装配置 Hadoop 2.2.0

预备条件：

1. 已安装JDK

Add Hadoop Group and User

$ sudo addgroup hadoop
$ sudo adduser --ingroup hadoop hduser
$ sudo adduser hduser sudo

 

 

切换到hduser账户下操作

 

 

SSH-server 安装

$ sudo apt-get install openssh-server

 

Setup SSH Certificate

 

$ ssh-keygen -t rsa -P ''

...

Your identification has been saved in /home/hduser/.ssh/id_rsa.

Your public key has been saved in /home/hduser/.ssh/id_rsa.pub.

...

$ cat ~/.ssh/id_rsa.pub >> ~/.ssh/authorized_keys

$ ssh localhost

 

 

 

Hadoop安装

 

Download Hadoop 2.2.0

 

$ cd ~

$ wget http://www.trieuvan.com/apache/hadoop/common/hadoop-2.2.0/hadoop-2.2.0.tar.gz

$ sudo tar vxzf hadoop-2.2.0.tar.gz -C /usr/local

$ cd /usr/local

$ sudo mv hadoop-2.2.0 hadoop

$ sudo chown -R hduser:hadoop hadoop

 

Setup Hadoop Environment Variables

$cd ~

$sudo gedit .bashrc

 

paste following to the end of the file

 

#Hadoop variables
export JAVA_HOME=/usr/lib/jvm/jdk1.7.0_45
export HADOOP_INSTALL=/usr/local/hadoop
export PATH=$PATH:$HADOOP_INSTALL/bin
export PATH=$PATH:$HADOOP_INSTALL/sbin
export HADOOP_MAPRED_HOME=$HADOOP_INSTALL
export HADOOP_COMMON_HOME=$HADOOP_INSTALL
export HADOOP_HDFS_HOME=$HADOOP_INSTALL
export YARN_HOME=$HADOOP_INSTALL
###end of paste

 

$ cd /usr/local/hadoop/etc/hadoop
$ vi hadoop-env.sh
 
#modify JAVA_HOME
export JAVA_HOME=/usr/lib/jvm/jdk1.7.0_45

 

Re-login into Ubuntu using hdser and check hadoop version

$ hadoop version

Hadoop 2.2.0
Subversion https://svn.apache.org/repos/asf/hadoop/common -r 1529768
Compiled by hortonmu on 2013-10-07T06:28Z
Compiled with protoc 2.5.0
From source with checksum 79e53ce7994d1628b240f09af91e1af4
This command was run using /usr/local/hadoop-2.2.0/share/hadoop/common/hadoop-common-2.2.0.jar

 

At this point, hadoop is installed.

 

 

根据上面步骤，制作自动安装脚本如下：

#!/bin/bash

# 该脚本将在单个节点上安装 Hadoop 2.2.0

cd ~
sudo apt-get update

#### HADOOP 安装 ###

# Download java jdk
#if [ ! -f jdk-7u45-linux-i586.tar.gz ]; then
#    wget http://uni-smr.ac.ru/archive/dev/java/SDKs/sun/j2se/7/jdk-7u45-linux-i586.tar.gz
#fi
#sudo mkdir /usr/lib/jvm
#sudo tar zxvf jdk-7u45-linux-i586.tar.gz  -C /usr/lib/jvm

# 再修改环境变量
#sudo sh -c 'echo export JAVA_HOME=/usr/lib/jvm/jdk1.7.0_45 >> ~/.bashrc'
#sudo sh -c 'echo export JRE_HOME=${JAVA_HOME}/jre >> ~/.bashrc'
#sudo sh -c 'echo export CLASSPATH=.:${JAVA_HOME}/lib:${JRE_HOME}/lib >> ~/.bashrc'
#sudo sh -c 'echo export PATH=${JAVA_HOME}/bin:$PATH >> ~/.bashrc'

# 使之立即生效
#source ~/.bashrc

# 配置默认JDK版本
#sudo update-alternatives --install /usr/bin/java java /usr/lib/jvm/jdk1.7.0_45/bin/java 300
#sudo update-alternatives --install /usr/bin/javac javac /usr/lib/jvm/jdk1.7.0_45/bin/javac 300
#sudo update-alternatives --install /usr/bin/jar jar /usr/lib/jvm/jdk1.7.0_45/bin/jar 300
#sudo update-alternatives --install /usr/bin/javah javah /usr/lib/jvm/jdk1.7.0_45/bin/javah 300
#sudo update-alternatives --install /usr/bin/javap javap /usr/lib/jvm/jdk1.7.0_45/bin/javap 300
# 查看设置是否成功
#sudo update-alternatives --config java

#查看JDK版本，判断是否安装成功
#java -version

# 专门添加hadoop用户用来做hadoop计算
#sudo addgroup hadoop
#sudo adduser --ingroup hadoop hduser
#sudo adduser hduser sudo

# 安装openssh-server
sudo apt-get install openssh-server

# 产生ssh key 并添加到授权文件
sudo -u hduser ssh-keygen -t rsa -P ''
sudo sh -c 'cat /home/hduser/.ssh/id_rsa.pub >> /home/hduser/.ssh/authorized_keys'
#ssh localhost

# 下载安装Hadoop，并更改文件夹权限
cd ~
if [ ! -f hadoop-2.2.0.tar.gz ]; then
    #wget http://apache.osuosl.org/hadoop/common/hadoop-2.2.0.tar.gz
    wget http://xx.xx.xx.xx/downloads/hadoop-2.2.0.tar.gz
fi
sudo tar vxzf hadoop-2.2.0.tar.gz -C /usr/local
cd /usr/local
sudo mv hadoop-2.2.0 hadoop
sudo chown -R hduser:hadoop hadoop

# 将Hadoop 环境变量添加到.bashrc
cd ~cd ~
sudo sh -c "echo export JAVA_HOME=/usr/lib/jvm/jdk1.7.0_45 >> /home/hduser/.bashrc"
sudo sh -c 'echo export HADOOP_INSTALL=/usr/local/hadoop >> /home/hduser/.bashrc'
sudo sh -c 'echo export PATH=\$PATH:\$JAVA_HOME/bin >> /home/hduser/.bashrc'
sudo sh -c 'echo export PATH=\$PATH:\$HADOOP_INSTALL/bin >> /home/hduser/.bashrc'
sudo sh -c 'echo export PATH=\$PATH:\$HADOOP_INSTALL/sbin >> /home/hduser/.bashrc'
sudo sh -c 'echo export HADOOP_MAPRED_HOME=\$HADOOP_INSTALL >> /home/hduser/.bashrc'
sudo sh -c 'echo export HADOOP_COMMON_HOME=\$HADOOP_INSTALL >> /home/hduser/.bashrc'
sudo sh -c 'echo export HADOOP_HDFS_HOME=\$HADOOP_INSTALL >> /home/hduser/.bashrc'
sudo sh -c 'echo export YARN_HOME=\$HADOOP_INSTALL >> /home/hduser/.bashrc'
sudo sh -c 'echo export HADOOP_COMMON_LIB_NATIVE_DIR=\$\{HADOOP_INSTALL\}/lib/native >> /home/hduser/.bashrc'
sudo sh -c 'echo export HADOOP_OPTS=\"-Djava.library.path=\$HADOOP_INSTALL/lib\" >> /home/hduser/.bashrc'

# 修改Hadoop 的JAVA_HOME，在hadoop-env.sh 文件中
cd /usr/local/hadoop/etc/hadoop
sudo -u hduser sed -i.bak s=\${JAVA_HOME}=/usr/lib/jvm/jdk1.7.0_45/=g hadoop-env.sh
pwd

# Check that Hadoop is installed
/usr/local/hadoop/bin/hadoop version

# Edit configuration files
sudo -u hduser sed -i.bak 's=<configuration>=<configuration>\<property>\<name>fs\.default\.name\</name>\<value>hdfs://localhost:9000\</value>\</property>=g' core-site.xml
sudo -u hduser sed -i.bak 's=<configuration>=<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>=g' yarn-site.xml
 
sudo -u hduser cp mapred-site.xml.template mapred-site.xml
sudo -u hduser sed -i.bak 's=<configuration>=<configuration>\<property>\<name>mapreduce\.framework\.name</name>\<value>yarn</value>\</property>=g' mapred-site.xml
 
cd ~
sudo mkdir -p mydata/hdfs/namenode
sudo mkdir -p mydata/hdfs/datanode
sudo chown -R hduser:hadoop mydata

cd /usr/local/hadoop/etc/hadoop
sudo -u hduser sed -i.bak 's=<configuration>=<configuration>\<property>\<name>dfs\.replication</name>\<value>1\</value>\</property>\<property>\<name>dfs\.namenode\.name\.dir</name>\<value>file:/home/hduser/mydata/hdfs/namenode</value>\</property>\<property>\<name>dfs\.datanode\.data\.dir</name>\<value>file:/home/hduser/mydata/hdfs/datanode</value>\</property>=g' hdfs-site.xml

### Testing Hadoop

## Run the following commands as hduser to start and test hadoop
#sudo su hduser
# Format Namenode
#hdfs namenode -format
# Start Hadoop Service
#start-dfs.sh
#start-yarn.sh
# Check status
#hduser jps
# Example
#cd /usr/local/hadoop
#hadoop jar ./share/hadoop/mapreduce/hadoop-mapreduce-examples-2.2.0.jar pi 2 5

集群设置：

禁用IPV6

编辑文件/etc/sysctl.conf，在最后插入

net.ipv6.conf.all.disable_ipv6 = 1

net.ipv6.conf.default.disable_ipv6 = 1

net.ipv6.conf.lo.disable_ipv6 = 1

重启生效

cat /proc/sys/net/ipv6/conf/all/disable_ipv6

若返回0则IPV6生效，返回1则说明没有生效

配置 hosts文件

将以下条目加入到 master以及每个slave的 /etc/hosts文件

xxx.xxx.xxx.xx0 master
xxx.xxx.xxx.xx1 b-w01
xxx.xxx.xxx.xx2 b-w02
xxx.xxx.xxx.xx3 b-w03
xxx.xxx.xxx.xx4 b-w04

配置ssh，以使master可以无密码连接slaves

ssh-copy-id -i $HOME/.ssh/id_rsa.pub hduser@slaveXXXX

在弹出密码提示时输入slaves的密码

然后再测试 ssh slave，即可看到成功登陆的消息

配置文件：slaves

b-w01
b-w02
b-w03
b-w04

配置文件core-site.XML

<configuration>
<property>
<name>fs.defaultFS</name>
<value>hdfs://master:9000</value>
</property>
<property>
<name>io.file.buffer.size</name>
<value>131072</value>
</property>
<property>
<name>hadoop.tmp.dir</name>
<value>/home/hduser/mydata/hadoop_temp</value>
</property>

</configuration>

配置文件：hdfs-site.xml

<configuration>
<property>
<name>dfs.replication</name>
<value>2</value>
</property>
<property>
<name>dfs.namenode.name.dir</name>
<value>file:/home/hduser/mydata/hdfs/namenode</value>
</property>
<property>
<name>dfs.datanode.data.dir</name>
<value>file:/home/hduser/mydata/hdfs/datanode</value>
</property>
<property>
<name>dfs.webhdfs.enabled</name>
<value>true</value>
</property>
</configuration>

配置文件：mapred-site.xml

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

配置文件：yarn-site.xml

<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.nodemanager.aux-services.mapreduce.shuffle.class</name>
<value>org.apache.hadoop.mapred.ShuffleHandler</value>
</property>

<property>
  <name>yarn.resourcemanager.hostname</name>
  <value>master</value>
</property>

</configuration>

最后通过脚本把上述配置文件迁移到每个slave

#!/bin/bash
scp /usr/local/hadoop/etc/hadoop/slaves hduser@b-w01:/usr/local/hadoop/etc/hadoop/slaves
scp /usr/local/hadoop/etc/hadoop/slaves hduser@b-w02:/usr/local/hadoop/etc/hadoop/slaves
scp /usr/local/hadoop/etc/hadoop/slaves hduser@b-w03:/usr/local/hadoop/etc/hadoop/slaves
scp /usr/local/hadoop/etc/hadoop/slaves hduser@b-w04:/usr/local/hadoop/etc/hadoop/slaves

scp /usr/local/hadoop/etc/hadoop/core-site.xml hduser@b-w01:/usr/local/hadoop/etc/hadoop/core-site.xml
scp /usr/local/hadoop/etc/hadoop/core-site.xml hduser@b-w02:/usr/local/hadoop/etc/hadoop/core-site.xml
scp /usr/local/hadoop/etc/hadoop/core-site.xml hduser@b-w03:/usr/local/hadoop/etc/hadoop/core-site.xml
scp /usr/local/hadoop/etc/hadoop/core-site.xml hduser@b-w04:/usr/local/hadoop/etc/hadoop/core-site.xml

scp /usr/local/hadoop/etc/hadoop/hdfs-site.xml hduser@b-w01:/usr/local/hadoop/etc/hadoop/hdfs-site.xml
scp /usr/local/hadoop/etc/hadoop/hdfs-site.xml hduser@b-w02:/usr/local/hadoop/etc/hadoop/hdfs-site.xml
scp /usr/local/hadoop/etc/hadoop/hdfs-site.xml hduser@b-w03:/usr/local/hadoop/etc/hadoop/hdfs-site.xml
scp /usr/local/hadoop/etc/hadoop/hdfs-site.xml hduser@b-w04:/usr/local/hadoop/etc/hadoop/hdfs-site.xml

scp /usr/local/hadoop/etc/hadoop/mapred-site.xml hduser@b-w01:/usr/local/hadoop/etc/hadoop/mapred-site.xml
scp /usr/local/hadoop/etc/hadoop/mapred-site.xml hduser@b-w02:/usr/local/hadoop/etc/hadoop/mapred-site.xml
scp /usr/local/hadoop/etc/hadoop/mapred-site.xml hduser@b-w03:/usr/local/hadoop/etc/hadoop/mapred-site.xml
scp /usr/local/hadoop/etc/hadoop/mapred-site.xml hduser@b-w04:/usr/local/hadoop/etc/hadoop/mapred-site.xml

scp /usr/local/hadoop/etc/hadoop/yarn-site.xml hduser@b-w01:/usr/local/hadoop/etc/hadoop/yarn-site.xml
scp /usr/local/hadoop/etc/hadoop/yarn-site.xml hduser@b-w02:/usr/local/hadoop/etc/hadoop/yarn-site.xml
scp /usr/local/hadoop/etc/hadoop/yarn-site.xml hduser@b-w03:/usr/local/hadoop/etc/hadoop/yarn-site.xml
scp /usr/local/hadoop/etc/hadoop/yarn-site.xml hduser@b-w04:/usr/local/hadoop/etc/hadoop/yarn-site.xml

查看JOBMANAGER：

http://master:8088

查看namenode：

http://master:50070/

测试：

cd /usr/local/hadoop

hadoop fs -mkdir /output

hadoop fs -mkdir /input

hadoop dfs -put ~/wordCounterTest.txt /input/wordCounterTest.txt

hadoop jar ./share/hadoop/mapreduce/hadoop-mapreduce-examples-2.2.0.jar wordcount /input/wordCounterTest.txt /output/wordcountresult