CentOS6.5编译部署64位Hadoop2.2.0

1 root用户，建立haoop用户

useradd -g root hadoop

2 编译hadoop（64位hadoop需要自己编译）

2.1 下载jdk、maven、hadoop-src

http://www.oracle.com/technetwork/java/javase/downloads/jdk7-downloads-1880260.html

http://maven.apache.org/download.cgi

http://mirrors.hust.edu.cn/apache/hadoop/common/

2.2 配置环境变量

sudo vim /etc/profile
JAVA_HOME=/usr/local/jdk1.7.0_25
JRE_HOME=$JAVA_HOME/jre
CLASSPATH=.:$JAVA_HOME/lib:$JRE_HOME/lib:$CLASSPATH
MAVEN_HOME=/usr/local/apache-maven-3.2.2
PATH=$JAVA_HOME/bin:$JRE_HOME/bin:$MAVEN_HOME/bin:$PATH
export JAVA_HOME JRE_HOMECLASSPATH MAVEN_HOME PATH

2.3 maven配置

<?xmlversion="1.0" encoding="utf-8"?>
<settingsxmlns="http://maven.apache.org/SETTINGS/1.0.0"
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xsi:schemaLocation="http://maven.apache.org/SETTINGS/1.0.0http://maven.apache.org/xsd/settings-1.0.0.xsd">
<pluginGroups></pluginGroups>
<proxies></proxies>
<servers></servers>
<mirrors>
<mirror>
<id>nexus-osc</id>
<mirrorOf>*</mirrorOf>
<name>Nexusosc</name>
<url>http://maven.oschina.net/content/groups/public/</url>
</mirror>
</mirrors>
<profiles>
<profile>
<id>jdk-1.7</id>
<activation>
<jdk>1.7</jdk>
</activation>
<repositories>
<repository>
<id>nexus</id>
<name>local privatenexus</name>
<url>http://maven.oschina.net/content/groups/public/</url>
<releases>
<enabled>true</enabled>
</releases>
<snapshots>
<enabled>false</enabled>
</snapshots>
</repository>
</repositories>
<pluginRepositories>
<pluginRepository>
<id>nexus</id>
<name>local privatenexus</name>
<url>http://maven.oschina.net/content/groups/public/</url>
<releases>
<enabled>true</enabled>
</releases>
<snapshots>
<enabled>false</enabled>
</snapshots>
</pluginRepository>
</pluginRepositories>
</profile>
</profiles>
</settings>

2.4 安装依赖

yum install gcc
yum intall gcc-c++
yum install make

https://protobuf.googlecode.com/files/protobuf-2.5.0.tar.gz

tar -xvf protobuf-2.5.0.tar.bz2
cd protobuf-2.5.0
./configure --prefix=/usr/local/protoc/
make && make install

将/usr/local/protoc/bin 加入 path。

yum install cmake
yum install openssl-devel
yum install ncurses-devel

2.5 编译

打上Patch :https://issues.apache.org/jira/browse/HADOOP-10110

cd hadoop-2.2.0-src
mvn package -Pdist,native -DskipTests -Dtar

编译后的路径在:hadoop-2.2.0-src/hadoop-dist/target/hadoop-2.2.0

3 root用户，关闭防火墙

chkconfig iptables off #重启后永久性生效
service iptables stop #即时生效，重启后失效
service iptables status #查看防火墙状态

4 root用户，hosts配置

192.168.101.128 master
192.168.101.129 slave1
192.168.101.130 slave2
192.168.101.131 slave3
ifconfig eth2192.168.101.130 netmask 255.255.255.0 #设置ip

5 hadoop用户，ssh免登陆

ssh-keygen -t rsa
cd .ssh
cat id_rsa.pub >authorized_keys
#如果autorized_keys是新创建的，要更改权限为600：
chmod 600 authorized_keys
#如果其他机器是克隆机，就不必执行下面的拷贝：
scp .ssh/authorized_keys hadoop@192.168.101.129:/home/hadoop/.ssh/
scp .ssh/authorized_keys hadoop@192.168.101.130:/home/hadoop/.ssh/
scp .ssh/authorized_keys hadoop@192.168.101.131:/home/hadoop/.ssh/

6 hadoop配置

6.1 创建三个目录，用来放hadoop文件、日志、临时文件

mkdir -p ~/dfs/name
mkdir -p ~/dfs/data
mkdir -p ~/temp

6.2 hadoop-env.sh和yarn-env.sh修改JAVA_HOME

6.3 core-site.xml

<property>
  <name>fs.defaultFS</name>
  <value>hdfs://master:9000</value>
</property>
<property>
  <name>hadoop.tmp.dir</name>
  <value>file:/home/hadoop/temp</value>
</property>
<property>
  <name>io.file.buffer.size</name>
  <value>4096</value>
</property>
<property>
  <name>hadoop.http.staticuser.user</name>
  <value>hadoop</value>
</property>

6.4 hdfs-site.xml

<property>
  <name>dfs.namenode.secondary.http-address</name>
  <value>master:9001</value>
</property>
<property>
  <name>dfs.namenode.name.dir</name>
  <value>/home/hadoop/dfs/name</value>
</property>
<property>
  <name>dfs.datanode.data.dir</name>
  <value>/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>
<property>
  <name>dfs.permissions</name>
  <value>false</value>
</property>

6.5 mapred-site.xml

<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>

6.6 yarn-site.xml

<property>
<name>yarn.resourcemanager.address</name>
<value>master:8032</value>
</property>
<property>
<name>yarn.resourcemanager.scheduler.address</name>
<value>master:8030</value>
</property>
<property>
<name>yarn.resourcemanager.resource-tracker.address</name>
<value>master:8031</value>
</property>
<property>
<name>yarn.resourcemanager.admin.address</name>
<value>master:8033</value>
</property>
<property>
<name>yarn.resourcemanager.webapp.address</name>
<value>master:8088</value>
</property>
<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.resource.memory-mb</name>
<value>8192</value>
</property>

6.7 slaves

slave1
slave2
slave3

7 启动hadoop和yarn

bin/hdfs namenode -format
sbin/start-dfs.sh
sbin/start-yarn.sh

8 管理地址

hadoop： http://master:50070

yarn： http://master:8088

9 基本命令

hadoop fs -mkdir /test
hadoop fs -put /usr/local/hadoop-2.2.0/bin/hdfs /test
hadoop fs -get/test/hdfs.cmd /usr/local/
hadoop fs -rm/test/hdfs.cmd
hadoop fs -rmr /test