1.系统环境说明
CentOS 7.0 x64 版本
192.168.1.7 master
192.168.1.8 slave
192.168.1.9 slave
192.168.1.10 slave
2.安装前的准备工作
2.1 关闭防火墙
# systemctl status firewalld.service --查看防火墙状态 # systemctl stop firewalld.service --关闭防火墙 # systemctl disable firewalld.service --永久关闭防火墙
2.2 检查ssh安装情况,如果没有则安装ssh
# systemctl status sshd.service --查看ssh状态 # yum install openssh-server openssh-clients
2.3 安装vim
# yum -y install vim
2.4 设置静态ip地址
# vim /etc/sysconfig/network-scripts/ifcfg-eno16777736
BOOTPROTO="static"
ONBOOT="yes"
IPADDR0="192.168.1.7"
PREFIX0="255.255.255.0"
GATEWAY0="192.168.1.1"
DNS1="61.147.37.1"
DNS2="101.226.4.6"
2.5 修改host名称
# vim /etc/sysconfig/network
HOSTNAME=master
# vim /etc/hosts
192.168.1.7 master 192.168.1.8 slave1 192.168.1.9 slave2 192.168.1.10 slave3
# hostnamectl set-hostname master (CentOS7 下原有的修改host方法无效了)
2.6 创建hadoop用户
# useradd hadoop --创建用户名为hadoop的用户# passwd hadoop --为用户hadoop设置密码
2.7 配置ssh无密钥登录
-----------下面是在master上面的操作
# su hadoop --切换到hadoop用户$ cd ~ --打开用户文件夹 $ ssh-keygen -t rsa -P ‘‘ --生成密码对,/home/hadoop/.ssh/id_rsa和/home/hadoop/.ssh/id_rsa.pub $ cat ~/.ssh/id_rsa.pub >> ~/.ssh/authorized_keys --把id_rsa.pub追加到授权的key里面去 $ chmod 600 ~/.ssh/authorized_keys --修改权限 $ su --切换到root用户# vim /etc/ssh/sshd_config --修改ssh配置文件 RSAAuthentication yes #启用RSA认证 PubkeyAuthentication yes #启用公钥私钥配对认证方式 AuthorizedKeysFile .ssh/authorized_keys #公钥文件路径 # su hadoop --切换到hadoop用户 $ scp ~/.ssh/id_rsa.pub [email protected]:~/ --把公钥复制所有的Slave机器上
----------下面是在slave1上面的操作
# su hadoop --切换到hadoop用户 $ mkdir ~/.ssh $ chmod 700 ~/.ssh $ cat ~/id_rsa.pub >> ~/.ssh/authorized_keys --追加到授权文件"authorized_keys" $ chmod 600 ~/.ssh/authorized_keys --修改权限 $ su --切换回root用户 # vim /etc/ssh/sshd_config --修改ssh配置文件 RSAAuthentication yes #启用RSA认证 PubkeyAuthentication yes #启用公钥私钥配对认证方式 AuthorizedKeysFile .ssh/authorized_keys #公钥文件路径
3.安装必须的软件
3.1 安装JDK
# rpm -ivh jdk-7u67-linux-x64.rpm
Preparing...
##################################### [100%]
1:jdk
##################################### [100%]
Unpacking JAR files...
rt.jar...
jsse.jar...
charsets.jar...
tools.jar...
localedata.jar...
# vim /etc/profile export JAVA_HOME=/usr/java/jdk1.7.0_67 export PATH=$PATH:$JAVA_HOME/bin # source profile --修改生效
3.2 安装其他必须软件
# yum install maven svn ncurses-devel gcc* lzo-devel zlib-devel autoconf automake libtool cmake openssl-devel
3.3 安装ant
# tar zxvf apache-ant-1.9.4-bin.tar.gz# vim /etc/profile export ANT_HOME=/usr/local/apache-ant-1.9.4 export PATH=$PATH:$ANT_HOME/bin
3.4 安装findbugs
# tar zxvf findbugs-3.0.0.tar.gz# vim /etc/profile export FINDBUGS_HOME=/usr/local/findbugs-3.0.0 export PATH=$PATH:$FINDBUGS_HOME/bin
3.5 安装protobuf
# tar zxvf protobuf-2.5.0.tar.gz(必须是2.5.0版本的,不然编译hadoop的时候报错) # cd protobuf-2.5.0 # ./configure --prefix=/usr/local # make && make install
4. 编译hadoop源码
# tar zxvf hadoop-2.5.0-src.tar.gz # cd hadoop-2.5.0-src # mvn package -Pdist,native,docs -DskipTests -Dtar
4.1 maven中央仓库的配置(改成oschina,增加访问速度)
# vim /usr/share/mavem/conf/settings.xml<mirrors> <mirror> <id>nexus-osc</id> <mirrorOf>*</mirrorOf> <name>Nexus osc</name> <url>http://maven.oschina.net/content/groups/public/</url> </mirror></mirrors><profiles> <profile> <id>jdk17</id> <activation> <activeByDefault>true</activeByDefault> <jdk>1.7</jdk> </activation> <properties> <maven.compiler.source>1.7</maven.compiler.source> <maven.compiler.target>1.7</maven.compiler.target> <maven.compiler.compilerVersion>1.7</maven.compiler.compilerVersion> </properties> <repositories> <repository> <id>nexus</id> <name>local private nexus</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 private nexus</name> <url>http://maven.oschina.net/content/groups/public/</url> <releases> <enabled>true</enabled> </releases> <snapshots> <enabled>false</enabled> </snapshots> </pluginRepository> </pluginRepositories> </profile></profiles>
4.2 编译完成之后,目录/usr/hadoop-2.5.0-src/hadoop-dist/target/hadoop-2.5.0
# ./bin/hadoop versionHadoop 2.5.0Subversion Unknown -r Unknown Compiled by root on 2014-09-12T00:47Z Compiled with protoc 2.5.0From source with checksum 423dcd5a752eddd8e45ead6fd5ff9a24 This command was run using /usr/hadoop-2.5.0-src/hadoop-dist/target/hadoop-2.5.0/share/hadoop/common/hadoop-common-2.5.0.jar # file lib//native/*lib//native/libhadoop.a: current ar archivelib//native/libhadooppipes.a: current ar archivelib//native/libhadoop.so: symbolic link to `libhadoop.so.1.0.0‘lib//native/libhadoop.so.1.0.0: ELF 64-bit LSB shared object, x86-64, version 1 (SYSV), dynamically linked, BuildID[sha1]=0x972b31264a1ce87a12cfbcc331c8355e32d0e774, not strippedlib//native/libhadooputils.a: current ar archivelib//native/libhdfs.a: current ar archivelib//native/libhdfs.so: symbolic link to `libhdfs.so.0.0.0‘lib//native/libhdfs.so.0.0.0: ELF 64-bit LSB shared object, x86-64, version 1 (SYSV), dynamically linked, BuildID[sha1]=0x200ccf97f44d838239db3347ad5ade435b472cfa, not stripped
5. 配置hadoop
5.1 基础操作
# cp -r /usr/hadoop-2.5.0-src/hadoop-dist/target/hadoop-2.5.0 /opt/hadoop-2.5.0 # chown -R hadoop:hadoop /opt/hadoop-2.5.0 # vi /etc/profile export HADOOP_HOME=/opt/hadoop-2.5.0 export PATH=$PATH:$HADOOP_HOME/bin # su hadoop $ cd /opt/hadoop-2.5.0 $ mkdir -p dfs/name $ mkdir -p dfs/data $ mkdir -p tmp $ cd etc/hadoop
5.2 配置所有slave节点
$ vim slaves slave1 slave2 slave3
5.3 修改hadoop-env.sh和yarn-env.sh
$ vim hadoop-env.sh / vim yarn-env.sh export JAVA_HOME=/usr/java/jdk1.7.0_67
5.4 修改core-site.xml
<configuration>
<property>
<name>fs.defaultFS</name>
<value>hdfs://master:9000</value>
</property>
<property>
<name>io.file.buffer.size</name>
<value>131702</value>
</property>
<property>
<name>hadoop.tmp.dir</name>
<value>file:/opt/hadoop-2.5.0/tmp</value>
</property>
<property>
<name>hadoop.proxyuser.hadoop.hosts</name>
<value></value>
</property>
<property>
<name>hadoop.proxyuser.hadoop.groups</name>
<value></value>
</property>
</configuration>
5.5 修改hdfs-site.xml
<configuration>
<property>
<name>dfs.namenode.name.dir</name>
<value>/opt/hadoop-2.5.0/dfs/name</value>
</property>
<property>
<name>dfs.datanode.data.dir</name>
<value>/opt/hadoop-2.5.0/dfs/data</value>
</property>
<property>
<name>dfs.replication</name>
<value>3</value>
</property>
<property>
<name>dfs.namenode.secondary.http-address</name>
<value>master:9001</value>
</property>
<property>
<name>dfs.webhdfs.enabled</name>
<value>true</value>
</property>
</configuration>
5.6 修改mapred-site.xml
# cp mapred-site.xml.template 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>
5.7 配置yarn-site.xml
<configuration>
<property>
<name>yarn.nodemanager.aux-services</name>
<value>mapreduce_shuffle</value>
</property>
<property>
<name>yarn.nodemanager.auxservices.mapreduce.shuffle.class</name>
<value>org.apache.hadoop.mapred.ShuffleHandler</value>
</property>
<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.resource.memory-mb</name>
<value>768</value>
</property>
</configuration>
5.8 格式化namenode
$ ./bin/hdfs namenode -format
5.9 启动hdfs
$ ./sbin/start-dfs.sh $ ./sbin/start-yarn.sh
5.10 检查启动情况
http://192.168.1.7:8088http://192.168.1.7:50070
参考 http://www.it165.net/admin/html/201403/2453.html
Hadoop- - 2.2.0 4 64 位源码编译及分布式安装.pdf