hadoop2.7.2 basic configuration (Pseudo-Distributed)

#core-site.xml
<configuration>
    <property>
        <name>fs.defaultFS</name>
        <value>hdfs://namenode_public_hostname:9999</value>
    </property>
</configuration>

#hdfs-site.xml
<configuration>
    <property>
        <name>dfs.replication</name>
        <value>1</value>
    </property>

    <property>
        <name>dfs.namenode.name.dir</name>
        <value>file:///usr/local/hadoop/data/hdfs/namenode</value>
    </property>

    <property>
        <name>dfs.datanode.data.dir</name>
        <value>file:///usr/local/hadoop/data/hdfs/datanode</value>
    </property>
</configuration>

#hadoop-env.sh
set JAVA_HOME

#mapred-site.xml
<configuration>
    <property>
        <name>mapreduce.framework.name</name>
        <value>yarn</value>
    </property>
</configuration>

#yarn-site.xml
    <configuration>
    <!-- Site specific YARN configuration properties -->
    <property>
        <name>yarn.nodemanager.aux-services</name>
        <value>mapreduce_shuffle</value>
    </property>
</configuration>

#format namenode
hdfs namenode -format

#start dfs and create dfs directory
start-dfs.sh
hadoop fs --mkdir -p /usr/<username> (don't know why,default path?)

#start yarn
start-yarn.sh

#core-site.xml

<name>fs.defaultFS</name>

<value>hdfs://namenode_public_hostname:9999</value>

</property>

</configuration>

#hdfs-site.xml

<name>dfs.replication</name>

</property>

<name>dfs.namenode.name.dir</name>

<value>file:///usr/local/hadoop/data/hdfs/namenode</value>

</property>

<name>dfs.datanode.data.dir</name>

<value>file:///usr/local/hadoop/data/hdfs/datanode</value>

</property>

</configuration>

#hadoop-env.sh

set JAVA_HOME

#mapred-site.xml

<name>mapreduce.framework.name</name>

</property>

</configuration>

#yarn-site.xml

<name>yarn.nodemanager.aux-services</name>

<value>mapreduce_shuffle</value>

</property>

</configuration>

#format namenode

hdfs namenode -format

#start dfs and create dfs directory

start-dfs.sh

hadoop fs --mkdir -p /usr/<username> (don't know why,default path?)

#start yarn

start-yarn.sh