伪分布式&&完全分布式&&高可用（zookeeper）的配置文件内容

【伪分布式】

①[core-site.xml]

<configuration>
<property>
<name>fs.defaultFS</name>
<value>hdfs://localhost/</value>
</property>
</configuration>

②[mapred-site.xml]

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

③yarn-site.xml

<configuration>
<property>
<name>yarn.resourcemanager.hostname</name>
<value>localhost</value>
</property>
<property>
<name>yarn.nodemanager.aux-services</name>
<value>mapreduce_shuffle</value>
</property>
</configuration>

④hdfs-site.xml

<configuration>
<property>
<name>dfs.replication</name>
<value>1</value>
</property>
</configuration>

⑤slaves

localhost

[完全分布式：]

①core-site.xml

<configuration>
<property>
<name>fs.defaultFS</name>
<value>hdfs://s100/</value>
</property>
<property>
<name>hadoop.tmp.dir</name>
<value>/home/neworigin/hadoop</value>
</property>

</configuration>

②hdfs-site.xml

<configuration>
<property>
<name>dfs.replication</name>
<value>3</value>
</property>
<property>
<name>dfs.replication.min</name>
<value>1</value>
</property>

<property>
<name>dfs.namenode.name.dir</name>
<value>file://${hadoop.tmp.dir}/hdfs/name1,file://${hadoop.tmp.dir}/hdfs/name2</value>
</property>

<property>
<name>dfs.datanode.data.dir</name>
<value>file://${hadoop.tmp.dir}/hdfs/data1,file://${hadoop.tmp.dir}/hdfs/data2</value>
</property>
<property>
<name>dfs.namenode.checkpoint.dir</name>
<value>file://${hadoop.tmp.dir}/hdfs/namesecondary</value>
</property>
<property>
<name>dfs.datanode.http.address</name>
<value>0.0.0.0:50075</value>

</property>

</configuration>

③yarn-site.xml

<property>
<name>yarn.resourcemanager.hostname</name>
<value>s100</value>
</property>
<property>
<name>yarn.nodemanager.local-dirs</name>
<value>file://${hadoop.tmp.dir}/nm-local-dir</value>
</property>
<property>
<name>yarn.nodemanager.aux-services</name>
<value>mapreduce_shuffle</value>
</property>
<property>
<name>yarn.nodemanager.resource.memory-mb</name>
<value>16384</value>

</property>
<property>
<name>yarn.nodemanager.resource.cpu-vcores</name>
<value>16</value>
</property>
</configuration>

④mapred-site.xml

<configuration>
<property>
<name>mapreduce.framework.name</name>
<value>yarn</value>
</property>
<property>
<name>mapred.jobtracker.http.address</name>
<value>0.0.0.0:50030</value>
</property>
<property>
<name>mapred.tasktracker.http.address</name>
<value>0.0.0.0:50060</value>
</property>

</configuration>

⑤slaves

s100
s101
s102

start-all.sh

[zookeeper]

yarn-site.xml

<property>
<name>yarn.nodemanager.resource.cpu-vcores</name>
<value>16</value>
</property>
<property>
<name>yarn.nodemanager.aux-services</name>
<value>mapreduce_shuffle</value>
</property>

<property>
<name>yarn.resourcemanager.ha.enabled</name>
<value>true</value>
</property>

<property>
<name>yarn.resourcemanager.cluster-id</name>
<value>cluster1</value>
</property>
<property>
<name>yarn.resourcemanager.ha.rm-ids</name>
<value>rm1,rm2</value>
</property>
<property>
<name>yarn.resourcemanager.hostname.rm1</name>
<value>s102</value>
</property>
<property>

<name>yarn.resourcemanager.hostname.rm2</name>
<value>s103</value>
</property>
<property>
<name>yarn.resourcemanager.zk-address</name>
<value>s100:2181,s101:2181,s102:2181</value>
</property>
</configuration>

②hdfs-site.xml

<configuration>
<property>
<name>dfs.replication</name>
<value>3</value>
</property>
<property>
<name>dfs.replication.min</name>
<value>1</value>
</property>

<property>
<name>dfs.namenode.name.dir</name>
<value>file://${hadoop.tmp.dir}/hdfs/name1,file://${hadoop.tmp.dir}/hd$
</property>
<property>
<name>dfs.datanode.data.dir</name>
<value>file://${hadoop.tmp.dir}/hdfs/data1,file://${hadoop.tmp.dir}/hd$
</property>
<property>

<name>dfs.datanode.http.address</name>
<value>0.0.0.0:50075</value>
</property>
<property>
<name>dfs.nameservices</name>
<value>neworigin</value>
</property>
<property>
<name>dfs.ha.namenodes.neworigin</name>

<value>nn1,nn2</value>
</property>
<property>
<name>dfs.namenode.rpc-address.neworigin.nn1</name>
<value>s100:9000</value>
</property>
<property>
<name>dfs.namenode.rpc-address.neworigin.nn2</name>
<value>s101:9000</value>
</property>
<property>
<name>dfs.namenode.http-address.neworigin.nn1</name>
<value>s100:50070</value>

</property>
<property>
<name>dfs.namenode.http-address.neworigin.nn2</name>
<value>s101:50070</value>
</property>
<property>
<name>dfs.namenode.shared.edits.dir</name>
<value>qjournal://s101:8485;s102:8485;s103:8485/neworigin</value>
</property>
<property>
<name>dfs.client.failover.proxy.provider.neworigin</name>
<value>org.apache.hadoop.hdfs.server.namenode.ha.ConfiguredFailoverPro$
</property>

<property>
<name>dfs.ha.fencing.methods</name>
<value>sshfence</value>
</property>
<property>
<name>dfs.ha.fencing.ssh.private-key-files</name>
<value>/home/neworigin/.ssh/id_rsa</value>
</property>
<property>
<name>dfs.journalnode.edits.dir</name>
<value>/home/neworigin/journal/data</value>
</property>

<property>
<name>dfs.ha.automatic-failover.enabled</name>
<value>true</value>
</property>

</configuration>

③core-site.xml

<configuration>
<property>
<name>fs.defaultFS</name>
<value>hdfs://neworigin</value>
</property>
<property>
<name>hadoop.tmp.dir</name>
<value>/home/neworigin/hadoop</value>
</property>
<property>
<name>ha.zookeeper.quorum</name>
<value>s100:2181,s101:2181,s102:2181</value>
</property>

</configuration>

④mapred-site.xml

</configuration>