Hadoop_05_CDH伪分布文件配置

core-site.xml

<configuration>
	<property>
		<name>fs.defaultFS</name>
		<value>hdfs://node01:8020</value>
	</property>
	<property>
		<name>hadoop.tmp.dir</name>
		<value>/export/servers/hadoop-2.6.0-cdh5.14.0/hadoopDatas/tempDatas</value>
	</property>
	<!--  缓冲区大小，实际工作中根据服务器性能动态调整 -->
	<property>
		<name>io.file.buffer.size</name>
		<value>4096</value>
	</property>

	<!--  开启hdfs的垃圾桶机制，删除掉的数据可以从垃圾桶中回收，单位分钟 -->
	<property>
		<name>fs.trash.interval</name>
		<value>10080</value>
	</property>
</configuration>

hdfs-site.xml

<configuration>
	<!-- NameNode存储元数据信息的路径，实际工作中，一般先确定磁盘的挂载目录，然后多个目录用，进行分割   --> 
	<!--   集群动态上下线 
	<property>
		<name>dfs.hosts</name>
		<value>/export/servers/hadoop-2.6.0-cdh5.14.0/etc/hadoop/accept_host</value>
	</property>
	
	<property>
		<name>dfs.hosts.exclude</name>
		<value>/export/servers/hadoop-2.6.0-cdh5.14.0/etc/hadoop/deny_host</value>
	</property>
	 -->
	 
	 <property>
			<name>dfs.namenode.secondary.http-address</name>
			<value>node01:50090</value>
	</property>

	<property>
		<name>dfs.namenode.http-address</name>
		<value>node01:50070</value>
	</property>
	<property>
		<name>dfs.namenode.name.dir</name>
		<value>file:///export/servers/hadoop-2.6.0-cdh5.14.0/hadoopDatas/namenodeDatas</value>
	</property>
	<!--  定义dataNode数据存储的节点位置，实际工作中，一般先确定磁盘的挂载目录，然后多个目录用，进行分割  -->
	<property>
		<name>dfs.datanode.data.dir</name>
		<value>file:///export/servers/hadoop-2.6.0-cdh5.14.0/hadoopDatas/datanodeDatas</value>
	</property>
	
	<property>
		<name>dfs.namenode.edits.dir</name>
		<value>file:///export/servers/hadoop-2.6.0-cdh5.14.0/hadoopDatas/dfs/nn/edits</value>
	</property>
	<property>
		<name>dfs.namenode.checkpoint.dir</name>
		<value>file:///export/servers/hadoop-2.6.0-cdh5.14.0/hadoopDatas/dfs/snn/name</value>
	</property>
	<property>
		<name>dfs.namenode.checkpoint.edits.dir</name>
		<value>file:///export/servers/hadoop-2.6.0-cdh5.14.0/hadoopDatas/dfs/nn/snn/edits</value>
	</property>
	<property>
		<name>dfs.replication</name>
		<value>2</value>
	</property>
	<property>
		<name>dfs.permissions</name>
		<value>false</value>
	</property>
<property>
		<name>dfs.blocksize</name>
		<value>134217728</value>
	</property>
</configuration>

hadoop-env.sh

这里把原本JAVA_HOME后面的地址改成虚拟机中jdk的地址

export JAVA_HOME=/export/servers/jdk1.8.0_141

mapred-site.xml

<configuration>
	<property>
		<name>mapreduce.framework.name</name>
		<value>yarn</value>
	</property>

	<property>
		<name>mapreduce.job.ubertask.enable</name>
		<value>true</value>
	</property>
	
	<property>
		<name>mapreduce.jobhistory.address</name>
		<value>node01:10020</value>
	</property>

	<property>
		<name>mapreduce.jobhistory.webapp.address</name>
		<value>node01:19888</value>
	</property>
</configuration>

yarn-site.xml

<configuration>
	<property>
		<name>yarn.resourcemanager.hostname</name>
		<value>node01</value>
	</property>
	<property>
		<name>yarn.nodemanager.aux-services</name>
		<value>mapreduce_shuffle</value>
	</property>
	
	<property>
		<name>yarn.log-aggregation-enable</name>
		<value>true</value>
	</property>
	<property>
		<name>yarn.log-aggregation.retain-seconds</name>
		<value>604800</value>
	</property>
</configuration>

slaves

node02
node03