hadoop集群配置

hadoop配置

集群部署规划

	hadoop000	hadoop001	hadoop002
HDFS	NameNode /DataNode	SecondaryNameNode /DataNode	DataNode
YARN	ResourceManager /NodeManager	NodeManager	NodeManager

（1）core-site.xml

<!-- 指定HDFS中NameNode的地址 -->
<property>
	<name>fs.defaultFS</name>
	<value>hdfs://hadoop000:9000</value>
</property>
<!-- 指定hadoop运行时产生文件的存储目录 -->
<property>
	<name>hadoop.tmp.dir</name>
	<value>/home/hadoop/app/hadoop-2.6.0-cdh5.10.0/data/tmp</value>
</property>

（2）Hdfs

	hadoop-env.sh
export JAVA_HOME=/home/hadoop/app/jdk1.8.0_65
	
	hdfs-site.xml
<property>
	<name>dfs.replication</name>
	<value>3</value>
</property>
<property>
	<name>dfs.namenode.secondary.http-address</name>
	<value>hadoop001:50090</value>
</property>

（3）yarn

	yarn-env.sh
export JAVA_HOME=/home/hadoop/app/jdk1.8.0_65
	
	yarn-site.xml
<!-- reducer获取数据的方式 -->
<property>
	<name>yarn.nodemanager.aux-services</name>
	<value>mapreduce_shuffle</value>
</property>
<!-- 指定YARN的ResourceManager的地址 -->
<property>
	<name>yarn.resourcemanager.hostname</name>
	<value>hadoop000</value>
</property>

（4）mapreduce

	mapred-env.sh
export JAVA_HOME=/home/hadoop/app/jdk1.8.0_65
	
	mapred-site.xml
<!-- 指定mr运行在yarn上 -->
<property>
	<name>mapreduce.framework.name</name>
	<value>yarn</value>
</property>

（5）slaves

hadoop000
hadoop001
hadoop002

scp -r /home/hadoop/app/hadoop-2.6.0-cdh5.10.0 hadoop@hadoop001:~/app
scp -r ~/.bash_profile hadoop@hadoop001:~/app
bin/hdfs namenode -format