2.3.1. Configure Secure Hadoop - Hortonworks Data Platform

Edit the core-site.xml file on every host in your cluster, to add the following information:

<property>   
        <name>hadoop.security.authentication</name>   
        <value>kerberos</value>   
        <description>Set the authentication for the cluster. Valid values are: simple or kerberos.   
        </description>  
</property>

<property>   
        <name>hadoop.rpc.protection</name>   
        <value>authentication</value>   
        <description>This is an [OPTIONAL] setting. If not set, defaults to authentication.authentication= authentication only; the client and server mutually authenticate during connection setup.integrity = authentication and integrity; guarantees the integrity of data exchanged between client and server aswell as authentication.privacy = authentication, integrity, and confidentiality; guarantees that data exchanged between client andserver is encrypted and is not readable by a “man in the middle”.
        </description>  
</property>

<property>  
        <name>hadoop.security.authorization</name>  
        <value>true</value>  
        <description>Enable authorization for different protocols.  
        </description> 
</property>

<property>
    
        <name>hadoop.security.auth_to_local</name>    
        <value>RULE:[2:$1@$0]([jt]t@.*EXAMPLE.COM)s/.*/$MAPRED_USER/
RULE:[2:$1@$0]([nd]n@.*EXAMPLE.COM)s/.*/$HDFS_USER/
DEFAULT</value> 
        <description>The mapping from Kerberos principal names to local OS user names. </description>
</property>

For mapping from Kerberos principal names to local OS user names, see Creating Mappings Between Principals and UNIX Usernames.

<property>
  <name>hadoop.proxyuser.hive.groups</name>
  <value>users</value>
  <description>Allow the superuser hive to impersonate any members of the group users. Required only when installing Hive.
  </description>
</property>

where $HIVE_USER is the user owning Hive Services. For example, hive.

<property>
  <name>hadoop.proxyuser.hive.hosts</name>
  <value>$Hive_Hostname_FQDN</value>
  <description>Hostname from where superuser hive can connect. Required only when installing Hive.
  </description>
</property>

<property>
  <name>hadoop.proxyuser.oozie.groups</name>
 <value>users</value>
  <description>Allow the superuser oozie to impersonate any members of the group users. Required only when installing Oozie.
 </description>
</property>

<property>
  <name>hadoop.proxyuser.oozie.hosts</name>
  <value>$Oozie_Hostname_FQDN</value>
 <description>Hostname from where superuser oozie can connect. Required only when installing Oozie.
  </description>
</property>

<property>
 <name>hadoop.proxyuser.hcat.hosts</name>
  <value>$WebHCat_Hostname_FQDN</value>
  <description>Hostname from where superuser hcat can connect. Required only when installing WebHCat.
  </description>
</property>

<property>
  <name>hadoop.proxyuser.HTTP.groups</name>
 <value>users</value>
 <description>Allow the superuser HTTP to impersonate any members of the group users.
  </description>
</property>

<property>
  <name>hadoop.proxyuser.HTTP.hosts</name>
  <value>$WebHCat_Hostname_FQDN</value>
 <description>Hostname from where superuser HTTP can connect.
 </description>
</property>

 <property>
  <name>hadoop.proxyuser.hcat.groups</name>
 <value>users</value>
  <description>Allow the superuser hcat to impersonate any members of the group users. Required only when installing WebHCat.
 </description>
</property>

<property>
 <name>hadoop.proxyuser.hcat.hosts</name>
  <value>$WebHCat_Hostname_FQDN</value>
  <description>Hostname from where superuser hcat can connect. This is required only when installing webhcat on the cluster.
  </description>
</property>

Edit the hdfs-site.xml file on every host in your cluster, to add the following information:

<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>$Secondary.NameNode.FQDN</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>$HTTPS_Address_for_NameNode</value>  
        <description>The https address where namenode binds. Example: ip-10-111-59-170.ec2.internal:50470</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>

<property>
        <name>dfs.datanode.address</name>
        <value></value>
        <description>The address, with a privileged port - any port number under 1023. Example: 0.0.0.0:1019</description>
</property>

<property>
        <name>dfs.datanode.http.address</name>
        <value>The address, with a privileged port - any port number under 1023. Example: 0.0.0.0:1022</value>
</property>

For the DataNodes to run in secure mode, you must set the user-name which the DataNode process should run as by setting HADOOP_SECURE_DN_USER as shown below:

export HADOOP_SECURE_DN_USER=$HDFS_USER

where $HDFS_USER is the user owning HDFS services. For example, hdfs.

	Note
	The DataNode daemon must be started as `root`.

Optionally, you can allow that user to access the directories where PID and log files are stored. For example:

export HADOOP_SECURE_DN_PID_DIR=/var/run/hadoop/$HADOOP_SECURE_DN_USER
export HADOOP_SECURE_DN_LOG_DIR=/var/run/hadoop/$HADOOP_SECURE_DN_USER

Edit the mapred-site.xml file on every host in your cluster to add the following information:

<property>  
        <name>mapreduce.jobtracker.kerberos.principal</name>  
        <value>jt/_HOST@EXAMPLE.COM</value>  
        <description>Kerberos principal name for the JobTracker   </description> 
</property>

<property>  
        <name>mapreduce.tasktracker.kerberos.principal</name>   
        <value>tt/_HOST@EXAMPLE.COM</value>  
        <description>Kerberos principal name for the TaskTracker."_HOST" is replaced by the host name of the TaskTracker.  
        </description> 
</property>

<property>   
        <name>mapreduce.jobtracker.keytab.file</name>   
        <value>/etc/security/keytabs/jt.service.keytab</value>   
        <description>The keytab for the JobTracker principal.   
        </description>   
</property>

<property>   
        <name>mapreduce.tasktracker.keytab.file</name>   
        <value>/etc/security/keytabs/tt.service.keytab</value>    
        <description>The filename of the keytab for the TaskTracker</description>  
</property>

<property>    
        <name>mapreduce.jobhistory.kerberos.principal</name>     
        <!--cluster variant -->  
        <value>jt/_HOST@EXAMPLE.COM</value>    
        <description> Kerberos principal name for JobHistory. This must map to the same user as the JobTracker user (mapred).
        </description>  
</property>

<property>   
        <name>mapreduce.jobhistory.keytab.file</name>     
        <!--cluster variant -->   
        <value>/etc/security/keytabs/jt.service.keytab</value>   
        <description>The keytab for the JobHistory principal.
        </description>  
</property>