2.4.2. hdfs-site.xml

To the hdfs-site.xml file on every host in your cluster, you must add the following information:

Following is the XML for these entries:

<property> 
     <name>dfs.permissions</name> 
     <value>true</value> 
     <description> If "true", enable permission checking in
     HDFS. If "false", permission checking is turned
     off, but all other behavior is
     unchanged. Switching from one parameter value to the other does
     not change the mode, owner or group of files or
     directories. </description> 
</property> 
 
<property> 
     <name>dfs.permissions.supergroup</name> 
     <value>hdfs</value> 
     <description>The name of the group of
     super-users.</description> 
</property> 
 
<property> 
     <name>dfs.namenode.handler.count</name> 
     <value>100</value> 
     <description>Added to grow Queue size so that more
     client connections are allowed</description> 
</property> 
 
<property> 
     <name>ipc.server.max.response.size</name> 
     <value>5242880</value> 
</property> 
 
<property> 
     <name>dfs.block.access.token.enable</name> 
     <value>true</value> 
     <description> If "true", access tokens are used as capabilities
     for accessing datanodes. If "false", no access tokens are checked on
     accessing datanodes. </description> 
</property> 
 
<property> 
     <name>dfs.namenode.kerberos.principal</name> 
     <value>nn/_HOST@EXAMPLE.COM</value> 
     <description> Kerberos principal name for the
     NameNode </description> 
</property> 
 
<property> 
     <name>dfs.secondary.namenode.kerberos.principal</name> 
     <value>nn/_HOST@EXAMPLE.COM</value> 
     <description>Kerberos principal name for the secondary NameNode. 
     </description> 
</property> 
 
<property> 
     <!--cluster variant --> 
     <name>dfs.secondary.http.address</name> 
     <value>ip-10-72-235-178.ec2.internal:50090</value> 
     <description>Address of secondary namenode web server</description> 
</property> 
 
<property> 
     <name>dfs.secondary.https.port</name> 
     <value>50490</value> 
     <description>The https port where secondary-namenode
     binds</description> 
</property> 
 
<property> 
     <name>dfs.web.authentication.kerberos.principal</name> 
     <value>HTTP/_HOST@EXAMPLE.COM</value> 
     <description> The HTTP Kerberos principal used by Hadoop-Auth in the HTTP endpoint.
     The HTTP Kerberos principal MUST start with 'HTTP/' per Kerberos HTTP
     SPNEGO specification. 
     </description> 
</property> 
 
<property> 
     <name>dfs.web.authentication.kerberos.keytab</name> 
     <value>/etc/security/keytabs/spnego.service.keytab</value> 
     <description>The Kerberos keytab file with the credentials for the HTTP
     Kerberos principal used by Hadoop-Auth in the HTTP endpoint. 
     </description> 
</property> 
 
<property> 
     <name>dfs.datanode.kerberos.principal</name> 
     <value>dn/_HOST@EXAMPLE.COM</value> 
     <description> 
     The Kerberos principal that the DataNode runs as. "_HOST" is replaced by the real
     host name. 
     </description> 
</property> 
 
<property> 
     <name>dfs.namenode.keytab.file</name> 
     <value>/etc/security/keytabs/nn.service.keytab</value> 
     <description> 
     Combined keytab file containing the namenode service and host
     principals. 
     </description> 
</property> 
 
<property> 
     <name>dfs.secondary.namenode.keytab.file</name> 
     <value>/etc/security/keytabs/nn.service.keytab</value> 
     <description> 
     Combined keytab file containing the namenode service and host
     principals. 
     </description> 
</property> 
 
<property> 
     <name>dfs.datanode.keytab.file</name> 
     <value>/etc/security/keytabs/dn.service.keytab</value> 
     <description> 
     The filename of the keytab file for the DataNode. 
     </description> 
</property> 
 
<property> 
     <name>dfs.https.port</name> 
     <value>50470</value> 
     <description>The https port where namenode
     binds</description> 
</property> 
 
<property> 
     <name>dfs.https.address</name> 
     <value>ip-10-111-59-170.ec2.internal:50470</value> 
     <description>The https address where namenode binds</description> 
</property> 
 
<property> 
     <name>dfs.datanode.data.dir.perm</name> 
     <value>750</value> 
     <description>The permissions that should be there on
     dfs.data.dir directories. The datanode will not come up if the
     permissions are different on existing dfs.data.dir directories. If
     the directories don't exist, they will be created with this
     permission.</description> 
</property> 
 
<property> 
     <name>dfs.access.time.precision</name> 
     <value>0</value> 
     <description>The access time for HDFS file is precise upto this
     value.The default value is 1 hour. Setting a value of 0
     disables access times for HDFS. 
     </description> 
</property> 
 
<property> 
     <name>dfs.cluster.administrators</name> 
     <value> hdfs</value> 
     <description>ACL for who all can view the default
     servlets in the HDFS</description> 
</property> 
 
<property> 
     <name>ipc.server.read.threadpool.size</name> 
     <value>5</value> 
     <description></description> 
</property> 
 
<property> 
     <name>dfs.namenode.kerberos.internal.spnego.principal</name> 
     <value>${dfs.web.authentication.kerberos.principal}</value> 
</property> 
 
<property> 
     <name>dfs.secondary.namenode.kerberos.internal.spnego.principal</name> 
     <value>${dfs.web.authentication.kerberos.principal}</value> 
</property> 

In addition, you must set the user on all secure DataNodes:

export HADOOP_SECURE_DN_USER=hdfs

export HADOOP_SECURE_DN_PID_DIR=/grid/0/var/run/hadoop/$HADOOP_SECURE_DN_USER