1到hadoop官网下载2.5.2版本,虽然现在的版本已经是3.0
http://apache.fayea.com/hadoop/common/hadoop-2.5.2/hadoop-2.5.2.tar.gz
下载解压到:
/usr/hadoop/hadoop-2.5.2
2安装java环境,我的里用的是jdk1.7
下载解压到:
/usr/tool/java7/jdk1.7.0_79
修改配置文件~/.bashrc:
--------------------------------------------------------------------------------------------------
AVA_HOME=/usr/tool/java7/jdk1.7.0_79
CLASSPATH=$JAVA_HOME/lib/
SCALA_HOME=/usr/scala/scala-2.10.4
SPARK_HOME=/usr/spark/spark-1.0.0-bin-hadoop1
export HADOOP_INSTALL=/usr/hadoop/hadoop-2.5.2
PATH=$PATH:$HADOOP_INSTALL/bin:$JAVA_HOME/bin:$HADOOP_INSTALL/sbin:$SCALA_HOME/bin:$SPARK_HOME/bin
PATH=$PATH:/usr/tool/idea-IC-163.12024.16/bin
export HADOOP_COMMON_HOME=$HADOOP_INSTALL
export SCALA_HOME JAVA_HOME CLASSPATH
export HADOOP_HDFS_HOME=$HADOOP_INSTALL
export YARN_HOME=$HADOOP_INSTALL
export HADOOP_COMMON_LIB_NATIVE_DIR=$HADOOP_INSTALL/lib/native
export HADOOP_OPTS="-Djava.library.path=$HADOOP_INSTALL/lib"
export PATH JAVA_HOME CLASSPATH SPARK_HOME
--------------------------------------------------------------------------------------------------
修改配置文件/etc/profile:
--------------------------------------------------------------------------------------------------
JAVA_HOME=/usr/tool/java7/jdk1.7.0_79
CLASSPATH=$JAVA_HOME/lib/
SCALA_HOME=/usr/scala/scala-2.10.4
SPARK_HOME=/usr/spark/spark-1.0.0-bin-hadoop1
PATH=$PATH:$JAVA_HOME/bin:$SCALA_HOME/bin:$SPARK_HOME/bin
HADOOP_HOME=/usr/hadoop/hadoop-2.5.2
PATH=$PATH:$HADOOP_HOME/bin:$HADOOP_HOME/sbin
export PATH JAVA_HOME CLASSPATH HADOOP_HOME SCALA_HOME SPARK_HOME
--------------------------------------------------------------------------------------------------
3安装ssh:
<value>/usr/hadoop/tmp</value>
<description>Abase for other temporary directories.</description>
</property>
<property>
<name>fs.defaultFS</name>
<value>hdfs://Master:9000</value>
</property>
<property>
<name>io.file.buffer.size</name>
<value>4096 </value>
</property>
</configuration>
<property>
<name>dfs.nameservices</name>
<value>hadoop-cluster1</value>
</property>
<property>
<name>dfs.namenode.secondary.http-address</name>
<value>Master:50090</value>
</property>
<property>
<name>dfs.namenode.name.dir</name>
<value> file:///home/hadoop/dfs/name</value>
</property>
<property>
<name>dfs.datanode.data.dir</name>
<value>file:///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>
</configuration>
<property>
<name>mapreduce.framework.name</name>
<value>yarn</value>
</property>
<property>
<name>mapreduce.jobtracker.http.address</name>
<value>Master:50030</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>
<property>
<name>yarn.nodemanager.aux-services</name>
<value>mapreduce_shuffle</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>
</configuration>
export JAVA_HOME=/usr/tool/java7/jdk1.7.0_79
export HADOOP_HOME=/usr/hadoop/hadoop-2.5.2/
export PATH=$PATH:/usr/hadoop/hadoop-2.5.2/bin
3、格式化文件系统
- bin/hdfs namenode -format
bin/hdfs namenode -format
这里的格式化文件系统并不是硬盘格式化,只是针对主服务器hdfs-site.xml的dfs.namenode.name.dir和dfs.datanode.data.dir目录做相应的清理工作。
4、启动和停止服务
启动
- sbin/start-dfs.sh
sbin/start-dfs.sh
- sbin/start-yarn.sh
sbin/start-yarn.sh
停止
- sbin/stop-dfs.sh
sbin/stop-dfs.sh
- sbin/stop-yarn.sh
sbin/stop-yarn.sh
5、查看启动的进程
- jps
jps
三、通过浏览器访问
http://Master:50070/
http://Master:8088/