完全分布式配置
1.core-site.xml
<configuration> <!-- 指定文件系统 --> <property> <name>fs.defaultFS</name> <value>hdfs://master:9000</value> </property> <!-- 指定HDFS的数据存储位置 --> <property> <name>hadoop.tmp.dir</name> <value>/opt/soft/hadoop-2.7.7/tmp</value> </property> </configuration>
2.hdfs-site.xml
<configuration> <!-- 指定HDFS中的副本数量 --> <property> <name>dfs.replication</name> <value>3</value> </property> <property> <name>dfs.namenode.secondary.http-address</name> <value>slave2:50090</value> </property> <!--关闭HDFS的权限检查--> <property> <name>dfs.permissions</name> <value>false</value> </property> </configuration>
3.yarn-site.xml
<configuration> <property> <name>yarn.nodemanager.aux-services</name> <value>mapreduce_shuffle</value> </property> <property> <name>yarn.resourcemanager.hostname</name> <value>slave1</value> </property> <!-- 日志聚集功能开启 --> <property> <name>yarn.log-aggregation-enable</name> <value>true</value> </property> <!-- 日志文件保存的时间,以秒为单位 --> <property> <name>yarn.log-aggregation.retain-seconds</name> <value>640800</value> </property> </configuration>
4.mapreduce-site.xml
<configuration> <!-- 将MapReduce配置成基于YARN的系统 --> <property> <name>mapreduce.framework.name</name> <value>yarn</value> </property> <property> <name>mapreduce.jobhistory.address</name> <value>slave1:10020</value> </property> <property> <name>mapreduce.jobhistory.webapp.address</name> <value>slave1:19888</value> </property> </configuration>
5.slaves
master
slave1
slave2