path: root/ambari-server/src/main/resources/common-services/HDFS/2.1.0.2.0/configuration/hdfs-site.xml

<?xml version="1.0"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>

<!--
   Licensed to the Apache Software Foundation (ASF) under one or more
   contributor license agreements.  See the NOTICE file distributed with
   this work for additional information regarding copyright ownership.
   The ASF licenses this file to You under the Apache License, Version 2.0
   (the "License"); you may not use this file except in compliance with
   the License.  You may obtain a copy of the License at

       http://www.apache.org/licenses/LICENSE-2.0

   Unless required by applicable law or agreed to in writing, software
   distributed under the License is distributed on an "AS IS" BASIS,
   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
   See the License for the specific language governing permissions and
   limitations under the License.
-->

<!-- Put site-specific property overrides in this file. -->

<configuration supports_final="true">

  <!-- file system properties -->

  <property>
    <name>dfs.namenode.name.dir</name>
    <!-- cluster variant -->
    <value>/hadoop/hdfs/namenode</value>
    <display-name>NameNode directories</display-name>
    <description>Determines where on the local filesystem the DFS name node
      should store the name table.  If this is a comma-delimited list
      of directories then the name table is replicated in all of the
      directories, for redundancy. </description>
    <final>true</final>
    <value-attributes>
      <type>directories</type>
      <overridable>false</overridable>
    </value-attributes>
  </property>

  <property>
    <name>dfs.support.append</name>
    <value>true</value>
    <description>to enable dfs append</description>
    <final>true</final>
  </property>

  <property>
    <name>dfs.webhdfs.enabled</name>
    <value>true</value>
    <display-name>WebHDFS enabled</display-name>
    <description>Whether to enable WebHDFS feature</description>
    <final>true</final>
    <value-attributes>
      <type>boolean</type>
      <overridable>false</overridable>
    </value-attributes>
  </property>

  <property>
    <name>dfs.datanode.failed.volumes.tolerated</name>
    <value>0</value>
    <description> Number of failed disks a DataNode would tolerate before it stops offering service</description>
    <final>true</final>
    <display-name>DataNode failed disk tolerance</display-name>
    <value-attributes>
      <type>int</type>
      <minimum>0</minimum>
      <maximum>2</maximum>
      <increment-step>1</increment-step>
    </value-attributes>
    <depends-on>
      <property>
        <type>hdfs-site</type>
        <name>dfs.datanode.data.dir</name>
      </property>
    </depends-on>
  </property>

  <property>
    <name>dfs.datanode.data.dir</name>
    <value>/hadoop/hdfs/data</value>
    <display-name>DataNode directories</display-name>
    <description>Determines where on the local filesystem an DFS data node
      should store its blocks.  If this is a comma-delimited
      list of directories, then data will be stored in all named
      directories, typically on different devices.
      Directories that do not exist are ignored.
    </description>
    <final>true</final>
    <value-attributes>
      <type>directories</type>
    </value-attributes>
  </property>

  <property>
    <name>dfs.hosts.exclude</name>
    <value>/etc/hadoop/conf/dfs.exclude</value>
    <description>Names a file that contains a list of hosts that are
      not permitted to connect to the namenode.  The full pathname of the
      file must be specified.  If the value is empty, no hosts are
      excluded.</description>
  </property>

  <!--
    <property>
      <name>dfs.hosts</name>
      <value>/etc/hadoop/conf/dfs.include</value>
      <description>Names a file that contains a list of hosts that are
      permitted to connect to the namenode. The full pathname of the file
      must be specified.  If the value is empty, all hosts are
      permitted.</description>
    </property>
  -->

  <property>
    <name>dfs.namenode.checkpoint.dir</name>
    <value>/hadoop/hdfs/namesecondary</value>
    <display-name>SecondaryNameNode Checkpoint directories</display-name>
    <description>Determines where on the local filesystem the DFS secondary
      name node should store the temporary images to merge.
      If this is a comma-delimited list of directories then the image is
      replicated in all of the directories for redundancy.
    </description>
    <value-attributes>
      <type>directories</type>
      <overridable>false</overridable>
    </value-attributes>
  </property>

  <property>
    <name>dfs.namenode.checkpoint.edits.dir</name>
    <value>${dfs.namenode.checkpoint.dir}</value>
    <description>Determines where on the local filesystem the DFS secondary
      name node should store the temporary edits to merge.
      If this is a comma-delimited list of directories then the edits are
      replicated in all of the directories for redundancy.
      Default value is same as dfs.namenode.checkpoint.dir
    </description>
  </property>


  <property>
    <name>dfs.namenode.checkpoint.period</name>
    <value>21600</value>
    <display-name>HDFS Maximum Checkpoint Delay</display-name>
    <description>The number of seconds between two periodic checkpoints.</description>
    <value-attributes>
      <type>int</type>
      <unit>seconds</unit>
    </value-attributes>
  </property>

  <property>
    <name>dfs.namenode.checkpoint.txns</name>
    <value>1000000</value>
    <description>The Secondary NameNode or CheckpointNode will create a checkpoint
      of the namespace every 'dfs.namenode.checkpoint.txns' transactions,
      regardless of whether 'dfs.namenode.checkpoint.period' has expired.
    </description>
  </property>

  <property>
    <name>dfs.replication.max</name>
    <value>50</value>
    <description>Maximal block replication.
    </description>
  </property>

  <property>
    <name>dfs.replication</name>
    <value>3</value>
    <display-name>Block replication</display-name>
    <description>Default block replication.
    </description>
    <value-attributes>
      <type>int</type>
    </value-attributes>
  </property>

  <property>
    <name>dfs.heartbeat.interval</name>
    <value>3</value>
    <description>Determines datanode heartbeat interval in seconds.</description>
  </property>

  <property>
    <name>dfs.namenode.safemode.threshold-pct</name>
    <value>0.999</value>
    <description>
      Specifies the percentage of blocks that should satisfy
      the minimal replication requirement defined by dfs.namenode.replication.min.
      Values less than or equal to 0 mean not to start in safe mode.
      Values greater than 1 will make safe mode permanent.
    </description>
    <display-name>Minimum replicated blocks %</display-name>
    <value-attributes>
      <type>float</type>
      <minimum>0.990</minimum>
      <maximum>1.000</maximum>
      <increment-step>0.001</increment-step>
    </value-attributes>
  </property>

  <property>
    <name>dfs.datanode.balance.bandwidthPerSec</name>
    <value>6250000</value>
    <description>
      Specifies the maximum amount of bandwidth that each datanode
      can utilize for the balancing purpose in term of
      the number of bytes per second.
    </description>
  </property>

  <property>
    <name>dfs.https.port</name>
    <value>50470</value>
    <description>
      This property is used by HftpFileSystem.
    </description>
  </property>

  <property>
    <name>dfs.datanode.address</name>
    <value>0.0.0.0:50010</value>
    <description>
      The datanode server address and port for data transfer.
    </description>
  </property>

  <property>
    <name>dfs.datanode.http.address</name>
    <value>0.0.0.0:50075</value>
    <description>
      The datanode http server address and port.
    </description>
  </property>

  <property>
    <name>dfs.datanode.https.address</name>
    <value>0.0.0.0:50475</value>
    <description>
      The datanode https server address and port.
    </description>
  </property>

  <property>
    <name>dfs.blocksize</name>
    <value>134217728</value>
    <description>The default block size for new files.</description>
  </property>

  <property>
    <name>dfs.namenode.http-address</name>
    <value>localhost:50070</value>
    <description>The name of the default file system.  Either the
      literal string "local" or a host:port for HDFS.</description>
    <final>true</final>
  </property>

  <property>
    <name>dfs.namenode.rpc-address</name>
    <value>localhost:8020</value>
    <property-type>DONT_ADD_ON_UPGRADE</property-type>
    <description>RPC address that handles all clients requests.</description>
  </property>

  <property>
    <name>dfs.datanode.du.reserved</name>
    <!-- cluster variant -->
    <value>1073741824</value>
    <display-name>Reserved space for HDFS</display-name>
    <description>Reserved space in bytes per volume. Always leave this much space free for non dfs use.
    </description>
    <value-attributes>
      <type>int</type>
      <unit>bytes</unit>
    </value-attributes>
    <depends-on>
      <property>
        <type>hdfs-site</type>
        <name>dfs.datanode.data.dir</name>
      </property>
    </depends-on>
  </property>

  <property>
    <name>dfs.datanode.ipc.address</name>
    <value>0.0.0.0:8010</value>
    <description>
      The datanode ipc server address and port.
      If the port is 0 then the server will start on a free port.
    </description>
  </property>

  <property>
    <name>dfs.blockreport.initialDelay</name>
    <value>120</value>
    <description>Delay for first block report in seconds.</description>
  </property>

  <property>
    <name>dfs.datanode.max.transfer.threads</name>
    <value>1024</value>
    <description>Specifies the maximum number of threads to use for transferring data in and out of the datanode.</description>
    <display-name>DataNode max data transfer threads</display-name>
    <value-attributes>
      <type>int</type>
      <minimum>0</minimum>
      <maximum>48000</maximum>
    </value-attributes>
  </property>

  <!-- Permissions configuration -->

  <property>
    <name>fs.permissions.umask-mode</name>
    <value>022</value>
    <description>
      The octal umask used when creating files and directories.
    </description>
  </property>

  <property>
    <name>dfs.permissions.enabled</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.superusergroup</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>
    <display-name>NameNode Server threads</display-name>
    <value-attributes>
      <type>int</type>
      <minimum>1</minimum>
      <maximum>200</maximum>
    </value-attributes>
  </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>
    <!-- cluster variant -->
    <name>dfs.namenode.secondary.http-address</name>
    <value>localhost:50090</value>
    <description>Address of secondary namenode web server</description>
  </property>


  <property>
    <name>dfs.namenode.https-address</name>
    <value>localhost:50470</value>
    <description>The https address where namenode binds</description>

  </property>

  <property>
    <name>dfs.datanode.data.dir.perm</name>
    <value>750</value>
    <display-name>DataNode directories permission</display-name>
    <description>The permissions that should be there on dfs.datanode.data.dir
      directories. The datanode will not come up if the permissions are
      different on existing dfs.datanode.data.dir directories. If the directories
      don't exist, they will be created with this permission.</description>
    <value-attributes>
      <type>int</type>
    </value-attributes>
  </property>

  <property>
    <name>dfs.namenode.accesstime.precision</name>
    <value>0</value>
    <display-name>Access time precision</display-name>
    <description>The access time for HDFS file is precise up to this value.
      The default value is 1 hour. Setting a value of 0 disables
      access times for HDFS.
    </description>
    <value-attributes>
      <type>int</type>
    </value-attributes>
  </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>dfs.namenode.avoid.read.stale.datanode</name>
    <value>true</value>
    <description>
      Indicate whether or not to avoid reading from stale datanodes whose
      heartbeat messages have not been received by the namenode for more than a
      specified time interval.
    </description>
  </property>
  <property>
    <name>dfs.namenode.avoid.write.stale.datanode</name>
    <value>true</value>
    <description>
      Indicate whether or not to avoid writing to stale datanodes whose
      heartbeat messages have not been received by the namenode for more than a
      specified time interval.
    </description>
  </property>
  <property>
    <name>dfs.namenode.write.stale.datanode.ratio</name>
    <value>1.0f</value>
    <description>When the ratio of number stale datanodes to total datanodes marked is greater
      than this ratio, stop avoiding writing to stale nodes so as to prevent causing hotspots.
    </description>
  </property>
  <property>
    <name>dfs.namenode.stale.datanode.interval</name>
    <value>30000</value>
    <description>Datanode is stale after not getting a heartbeat in this interval in ms</description>
  </property>

  <property>
    <name>dfs.journalnode.http-address</name>
    <value>0.0.0.0:8480</value>
    <description>The address and port the JournalNode web UI listens on.
      If the port is 0 then the server will start on a free port. </description>
  </property>

  <property>
    <name>dfs.journalnode.https-address</name>
    <value>0.0.0.0:8481</value>
    <description>The address and port the JournalNode HTTPS server listens on.
      If the port is 0 then the server will start on a free port. </description>
  </property>

  <property>
    <name>dfs.journalnode.edits.dir</name>
    <value>/grid/0/hdfs/journal</value>
    <description>The path where the JournalNode daemon will store its local state. </description>
  </property>

  <!-- HDFS Short-Circuit Local Reads -->

  <property>
    <name>dfs.client.read.shortcircuit</name>
    <value>true</value>
    <display-name>HDFS Short-circuit read</display-name>
    <description>
      This configuration parameter turns on short-circuit local reads.
    </description>
    <value-attributes>
      <type>boolean</type>
    </value-attributes>
  </property>

  <property>
    <name>dfs.domain.socket.path</name>
    <value>/var/lib/hadoop-hdfs/dn_socket</value>
    <description>
      This is a path to a UNIX domain socket that will be used for communication between the DataNode and local HDFS clients.
      If the string "_PORT" is present in this path, it will be replaced by the TCP port of the DataNode.
    </description>
  </property>

  <property>
    <name>dfs.client.read.shortcircuit.streams.cache.size</name>
    <value>4096</value>
    <description>
      The DFSClient maintains a cache of recently opened file descriptors. This
      parameter controls the size of that cache. Setting this higher will use
      more file descriptors, but potentially provide better performance on
      workloads involving lots of seeks.
    </description>
  </property>

  <property>
    <name>dfs.namenode.name.dir.restore</name>
    <value>true</value>
    <description>Set to true to enable NameNode to attempt recovering a previously failed dfs.namenode.name.dir.
      When enabled, a recovery of any failed directory is attempted during checkpoint.</description>
  </property>

  <property>
    <name>dfs.http.policy</name>
    <value>HTTP_ONLY</value>
    <description>
      Decide if HTTPS(SSL) is supported on HDFS This configures the HTTP endpoint for HDFS daemons:
      The following values are supported: - HTTP_ONLY : Service is provided only on http - HTTPS_ONLY :
      Service is provided only on https - HTTP_AND_HTTPS : Service is provided both on http and https
    </description>
  </property>

</configuration>