1.配置hadoop-env.sh:
export JAVA_HOME=/usr/lib/jvm/jdk1.8.201
2.配置core-site.xml文件:
<!-- 指定hadoop所使用的文件系统schema(URL),HDFS的老大(NameNode)的地址 -->
<property>
<name>fs.defaultFS</name>
<value>hdfs://master1:9000</value>
</property>
<!-- 指定hadoop运行时产生的文件存储目录 -->
<property>
<name>hadoop.tmp.dir</name>
<value>/usr/local/hadoop/tmp</value>
</property>
3.配置hdfs-site.xml文件:
<!-- 指定HDFS副本数量 -->
<property>
<name>dfs.replication</name>
<value>2</value>
</property>
<property>
<name>dfs.namenode.secondary.http-address</name>
<value>master2:50090</value>
</property>
4.mapred-site.xml:
<!-- 指定mr运行时框架,这里指定在yarn上,默认是local -->
<property>
<name>mapreduce.framework.name</name>
<value>yarn</value>
</property>
5.yarn-site.xml
<!-- 指定yarn的老大(ResourceManager)的地址 -->
<property>
<name>yarn.resourcemanager.hostname</name>
<value>master1</value>
</property>
<propety>
<name>yarn.nodemanager.aux-services</name>
<value>mapreduce_shuffle</value>
</property>
6.slaves文件 ,里面添加节点主机名字:
master1
master2
masters
7.配置环境变量/etc/profile:
export HADOOP_HOME=/usr/local/hadoop
export HADOOP_CONF_DIR=${HADOOP_HOME}/etc/hadoop
export YARN_HOME=/usr/local/hadoop
export YARN_CONF_DIR=${YARN_HOME}/etc/hadoop