Appendix: Minimal cdap-site.xml

The following properties are the minimal required configuration for the cdap-site.xml file. They are included in the distribution in the file cdap-site.xml.example. See the installation instructions for details on how to configure a cdap-site.xml file for your particular distribution and situtation.

A complete list of properties possible for the cdap-site.xml is in the appendix.

<configuration>

  <!-- General Configuration -->

  <property>
    <name>hdfs.namespace</name>
    <value>/${root.namespace}</value>
    <description>
      Root directory for HDFS files written by CDAP
    </description>
  </property>
  
  <property>
    <name>hdfs.user</name>
    <value>yarn</value>
    <description>
      User name for accessing HDFS
    </description>
  </property>

  <property>
    <name>root.namespace</name>
    <value>cdap</value>
    <description>
      Root for this CDAP instance; used as the parent (or root) node for
      ZooKeeper, as the directory under which all CDAP data and metadata is
      stored in HDFS, and as the prefix for all HBase tables created by
      CDAP; must be composed of alphanumeric characters
    </description>
  </property>

  <property>
    <name>zookeeper.quorum</name>
    <value>FQDN1:2181,FQDN2:2181/${root.namespace}</value>
    <description>
      ZooKeeper quorum string; specifies the ZooKeeper host:port; substitute the quorum
      (FQDN1:2181,FQDN2:2181,...) for the components shown here
    </description>
  </property>


  <!-- Applications Configuration -->

  <property>
    <name>app.bind.address</name>
    <value>0.0.0.0</value>
    <description>
      App Fabric service bind address
    </description>
  </property>


  <!-- Datasets Configuration -->

  <property>
    <name>data.tx.bind.address</name>
    <value>0.0.0.0</value>
    <description>
      Transaction service bind address
    </description>
  </property>


  <!-- Kafka Server Configuration -->

  <property>
    <name>kafka.default.replication.factor</name>
    <value>1</value>
    <description>
      CDAP Kafka replication factor; used to replicate Kafka messages across
      multiple machines to prevent data loss in the event of a hardware
      failure. The recommended setting is to run at least two CDAP Kafka servers.
      If you are running two Kafka servers, set this value to 2; otherwise,
      set it to the number of Kafka servers.
    </description>
  </property>
  
  <property>
    <name>kafka.log.dir</name>
    <value>/tmp/kafka-logs</value>
    <description>
      CDAP Kafka service log storage directory
    </description>
  </property>

  <property>
    <name>kafka.seed.brokers</name>
    <value>FQDN1:9092,FQDN2:9092</value>
    <description>
      Comma-separated list of CDAP Kafka service brokers; for distributed CDAP, 
      replace with list of FQDN:port brokers
    </description>
  </property>


  <!-- Metrics Configuration -->
  
  <property>
    <name>metrics.query.bind.address</name>
    <value>0.0.0.0</value>
    <description>
      Metrics Query service bind address
    </description>
  </property>


  <!-- Router Configuration -->

  <property>
    <name>router.bind.address</name>
    <value>0.0.0.0</value>
    <description>
      CDAP Router service bind address
    </description>
  </property>
  
  <property>
    <name>router.bind.port</name>
    <value>10000</value>
    <description>
      CDAP Router service bind port
    </description>
  </property>

  <property>
    <name>router.server.address</name>
    <value>{ROUTER-HOST-IP}</value>
    <description>
      CDAP Router service address to which CDAP UI connects
    </description>
  </property>

  <property>
    <name>router.server.port</name>
    <value>${router.bind.port}</value>
    <description>
      CDAP Router service port to which CDAP UI connects
    </description>
  </property>


  <!-- UI Configuration -->
  
  <property>
    <name>dashboard.bind.port</name>
    <value>9999</value>
    <description>
      CDAP UI bind port
    </description>
  </property>

</configuration>