hadoop/hadoop-hdfs-project/hadoop-hdfs/src/main/resources/hdfs-default.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.
-->

<!-- Do not modify this file directly.  Instead, copy entries that you -->
<!-- wish to modify from this file into hdfs-site.xml and change them -->
<!-- there.  If hdfs-site.xml does not already exist, create it.      -->

<configuration>

<property>
  <name>hadoop.hdfs.configuration.version</name>
  <value>1</value>
  <description>version of this configuration file</description>
</property>

<property>
  <name>dfs.namenode.logging.level</name>
  <value>info</value>
  <description>
    The logging level for dfs namenode. Other values are "dir" (trace
    namespace mutations), "block" (trace block under/over replications
    and block creations/deletions), or "all".
  </description>
</property>

<property>
  <name>dfs.namenode.secondary.http-address</name>
  <value>0.0.0.0:50090</value>
  <description>
    The secondary namenode http server address and port.
    If the port is 0 then the server will start on a free port.
  </description>
</property>

<property>
  <name>dfs.datanode.address</name>
  <value>0.0.0.0:50010</value>
  <description>
    The address where the datanode server will listen to.
    If the port is 0 then the server will start on a free port.
  </description>
</property>

<property>
  <name>dfs.datanode.http.address</name>
  <value>0.0.0.0:50075</value>
  <description>
    The datanode http server address and port.
    If the port is 0 then the server will start on a free port.
  </description>
</property>

<property>
  <name>dfs.datanode.ipc.address</name>
  <value>0.0.0.0:50020</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.datanode.handler.count</name>
  <value>3</value>
  <description>The number of server threads for the datanode.</description>
</property>

<property>
  <name>dfs.namenode.http-address</name>
  <value>0.0.0.0:50070</value>
  <description>
    The address and the base port where the dfs namenode web ui will listen on.
    If the port is 0 then the server will start on a free port.
  </description>
</property>

<property>
  <name>dfs.https.enable</name>
  <value>false</value>
  <description>Decide if HTTPS(SSL) is supported on HDFS
  </description>
</property>

<property>
  <name>dfs.client.https.need-auth</name>
  <value>false</value>
  <description>Whether SSL client certificate authentication is required
  </description>
</property>

<property>
  <name>dfs.https.server.keystore.resource</name>
  <value>ssl-server.xml</value>
  <description>Resource file from which ssl server keystore
  information will be extracted
  </description>
</property>

<property>
  <name>dfs.client.https.keystore.resource</name>
  <value>ssl-client.xml</value>
  <description>Resource file from which ssl client keystore
  information will be extracted
  </description>
</property>

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

<property>
  <name>dfs.namenode.https-address</name>
  <value>0.0.0.0:50470</value>
  <description>The namenode secure http server address and port.</description>
</property>

 <property>
  <name>dfs.datanode.dns.interface</name>
  <value>default</value>
  <description>The name of the Network Interface from which a data node should 
  report its IP address.
  </description>
 </property>
 
<property>
  <name>dfs.datanode.dns.nameserver</name>
  <value>default</value>
  <description>The host name or IP address of the name server (DNS)
  which a DataNode should use to determine the host name used by the
  NameNode for communication and display purposes.
  </description>
 </property>
 
 <property>
  <name>dfs.namenode.backup.address</name>
  <value>0.0.0.0:50100</value>
  <description>
    The backup node server address and port.
    If the port is 0 then the server will start on a free port.
  </description>
</property>
 
 <property>
  <name>dfs.namenode.backup.http-address</name>
  <value>0.0.0.0:50105</value>
  <description>
    The backup node http server address and port.
    If the port is 0 then the server will start on a free port.
  </description>
</property>

<property>
  <name>dfs.namenode.replication.considerLoad</name>
  <value>true</value>
  <description>Decide if chooseTarget considers the target's load or not
  </description>
</property>
<property>
  <name>dfs.default.chunk.view.size</name>
  <value>32768</value>
  <description>The number of bytes to view for a file on the browser.
  </description>
</property>

<property>
  <name>dfs.datanode.du.reserved</name>
  <value>0</value>
  <description>Reserved space in bytes per volume. Always leave this much space free for non dfs use.
  </description>
</property>

<property>
  <name>dfs.namenode.name.dir</name>
  <value>file://${hadoop.tmp.dir}/dfs/name</value>
  <description>Determines where on the local filesystem the DFS name node
      should store the name table(fsimage).  If this is a comma-delimited list
      of directories then the name table is replicated in all of the
      directories, for redundancy. </description>
</property>

<property>
  <name>dfs.namenode.name.dir.restore</name>
  <value>false</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.namenode.fs-limits.max-component-length</name>
  <value>0</value>
  <description>Defines the maximum number of characters in each component
      of a path.  A value of 0 will disable the check.</description>
</property>

<property>
  <name>dfs.namenode.fs-limits.max-directory-items</name>
  <value>0</value>
  <description>Defines the maximum number of items that a directory may
      contain.  A value of 0 will disable the check.</description>
</property>

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

<property>
  <name>dfs.namenode.shared.edits.dir</name>
  <value></value>
  <description>A directory on shared storage between the multiple namenodes
  in an HA cluster. This directory will be written by the active and read
  by the standby in order to keep the namespaces synchronized. This directory
  does not need to be listed in dfs.namenode.edits.dir above. It should be
  left empty in a non-HA cluster.
  </description>
</property>
  
<property>
  <name>dfs.web.ugi</name>
  <value>webuser,webgroup</value>
  <description>The user account used by the web interface.
    Syntax: USERNAME,GROUP1,GROUP2, ...
  </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>supergroup</value>
  <description>The name of the group of super-users.</description>
</property>
<!--
<property>
   <name>dfs.cluster.administrators</name>
   <value>ACL for the admins</value>
   <description>This configuration is used to control who can access the
                default servlets in the namenode, etc.
   </description>
</property>
-->

<property>
  <name>dfs.block.access.token.enable</name>
  <value>false</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.block.access.key.update.interval</name>
  <value>600</value>
  <description>
    Interval in minutes at which namenode updates its access keys.
  </description>
</property>

<property>
  <name>dfs.block.access.token.lifetime</name>
  <value>600</value>
  <description>The lifetime of access tokens in minutes.</description>
</property>

<property>
  <name>dfs.datanode.data.dir</name>
  <value>file://${hadoop.tmp.dir}/dfs/data</value>
  <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>
</property>

<property>
  <name>dfs.datanode.data.dir.perm</name>
  <value>700</value>
  <description>Permissions for the directories on on the local filesystem where
  the DFS data node store its blocks. The permissions can either be octal or
  symbolic.</description>
</property>

<property>
  <name>dfs.replication</name>
  <value>3</value>
  <description>Default block replication. 
  The actual number of replications can be specified when the file is created.
  The default is used if replication is not specified in create time.
  </description>
</property>

<property>
  <name>dfs.replication.max</name>
  <value>512</value>
  <description>Maximal block replication. 
  </description>
</property>

<property>
  <name>dfs.namenode.replication.min</name>
  <value>1</value>
  <description>Minimal block replication. 
  </description>
</property>

<property>
  <name>dfs.blocksize</name>
  <value>67108864</value>
  <description>
      The default block size for new files, in bytes.
      You can use the following suffix (case insensitive):
      k(kilo), m(mega), g(giga), t(tera), p(peta), e(exa) to specify the size (such as 128k, 512m, 1g, etc.),
      Or provide complete size in bytes (such as 134217728 for 128 MB).
  </description>
</property>

<property>
  <name>dfs.client.block.write.retries</name>
  <value>3</value>
  <description>The number of retries for writing blocks to the data nodes, 
  before we signal failure to the application.
  </description>
</property>

<property>
  <name>dfs.client.block.write.replace-datanode-on-failure.enable</name>
  <value>true</value>
  <description>
    If there is a datanode/network failure in the write pipeline,
    DFSClient will try to remove the failed datanode from the pipeline
    and then continue writing with the remaining datanodes. As a result,
    the number of datanodes in the pipeline is decreased.  The feature is
    to add new datanodes to the pipeline.

    This is a site-wide property to enable/disable the feature.

    When the cluster size is extremely small, e.g. 3 nodes or less, cluster
    administrators may want to set the policy to NEVER in the default
    configuration file or disable this feature.  Otherwise, users may
    experience an unusually high rate of pipeline failures since it is
    impossible to find new datanodes for replacement.

    See also dfs.client.block.write.replace-datanode-on-failure.policy
  </description>
</property>

<property>
  <name>dfs.client.block.write.replace-datanode-on-failure.policy</name>
  <value>DEFAULT</value>
  <description>
    This property is used only if the value of
    dfs.client.block.write.replace-datanode-on-failure.enable is true.

    ALWAYS: always add a new datanode when an existing datanode is removed.
    
    NEVER: never add a new datanode.

    DEFAULT: 
      Let r be the replication number.
      Let n be the number of existing datanodes.
      Add a new datanode only if r is greater than or equal to 3 and either
      (1) floor(r/2) is greater than or equal to n; or
      (2) r is greater than n and the block is hflushed/appended.
  </description>
</property>

<property>
  <name>dfs.blockreport.intervalMsec</name>
  <value>21600000</value>
  <description>Determines block reporting interval in milliseconds.</description>
</property>

<property>
  <name>dfs.blockreport.initialDelay</name>  <value>0</value>
  <description>Delay for first block report in seconds.</description>
</property>

<property>
  <name>dfs.datanode.directoryscan.interval</name>
  <value>21600</value>
  <description>Interval in seconds for Datanode to scan data directories and
  reconcile the difference between blocks in memory and on the disk.
  </description>
</property>

<property>
  <name>dfs.datanode.directoryscan.threads</name>
  <value>1</value>
  <description>How many threads should the threadpool used to compile reports
  for volumes in parallel have.
  </description>
</property>

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

<property>
  <name>dfs.namenode.handler.count</name>
  <value>10</value>
  <description>The number of server threads for the namenode.</description>
</property>

<property>
  <name>dfs.namenode.safemode.threshold-pct</name>
  <value>0.999f</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 wait for any particular
    percentage of blocks before exiting safemode.
    Values greater than 1 will make safe mode permanent.
  </description>
</property>

<property>
  <name>dfs.namenode.safemode.min.datanodes</name>
  <value>0</value>
  <description>
    Specifies the number of datanodes that must be considered alive
    before the name node exits safemode.
    Values less than or equal to 0 mean not to take the number of live
    datanodes into account when deciding whether to remain in safe mode
    during startup.
    Values greater than the number of datanodes in the cluster
    will make safe mode permanent.
  </description>
</property>

<property>
  <name>dfs.namenode.safemode.extension</name>
  <value>30000</value>
  <description>
    Determines extension of safe mode in milliseconds 
    after the threshold level is reached.
  </description>
</property>

<property>
  <name>dfs.datanode.balance.bandwidthPerSec</name>
  <value>1048576</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.hosts</name>
  <value></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.hosts.exclude</name>
  <value></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.namenode.max.objects</name>
  <value>0</value>
  <description>The maximum number of files, directories and blocks
  dfs supports. A value of zero indicates no limit to the number
  of objects that dfs supports.
  </description>
</property>

<property>
  <name>dfs.namenode.decommission.interval</name>
  <value>30</value>
  <description>Namenode periodicity in seconds to check if decommission is 
  complete.</description>
</property>

<property>
  <name>dfs.namenode.decommission.nodes.per.interval</name>
  <value>5</value>
  <description>The number of nodes namenode checks if decommission is complete
  in each dfs.namenode.decommission.interval.</description>
</property>

<property>
  <name>dfs.namenode.replication.interval</name>
  <value>3</value>
  <description>The periodicity in seconds with which the namenode computes 
  repliaction work for datanodes. </description>
</property>

<property>
  <name>dfs.namenode.accesstime.precision</name>
  <value>3600000</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.datanode.plugins</name>
  <value></value>
  <description>Comma-separated list of datanode plug-ins to be activated.
  </description>
</property>

<property>
  <name>dfs.namenode.plugins</name>
  <value></value>
  <description>Comma-separated list of namenode plug-ins to be activated.
  </description>
</property>

<property>
  <name>dfs.stream-buffer-size</name>
  <value>4096</value>
  <description>The size of buffer to stream files.
  The size of this buffer should probably be a multiple of hardware
  page size (4096 on Intel x86), and it determines how much data is
  buffered during read and write operations.</description>
</property>

<property>
  <name>dfs.bytes-per-checksum</name>
  <value>512</value>
  <description>The number of bytes per checksum.  Must not be larger than
  dfs.stream-buffer-size</description>
</property>

<property>
  <name>dfs.client-write-packet-size</name>
  <value>65536</value>
  <description>Packet size for clients to write</description>
</property>

<property>
  <name>dfs.namenode.checkpoint.dir</name>
  <value>file://${hadoop.tmp.dir}/dfs/namesecondary</value>
  <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>
</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 directoires then teh edits is
      replicated in all of the directoires for redundancy.
      Default value is same as dfs.namenode.checkpoint.dir
  </description>
</property>

<property>
  <name>dfs.namenode.checkpoint.period</name>
  <value>3600</value>
  <description>The number of seconds between two periodic checkpoints.
  </description>
</property>

<property>
  <name>dfs.namenode.checkpoint.txns</name>
  <value>40000</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.namenode.checkpoint.check.period</name>
  <value>60</value>
  <description>The SecondaryNameNode and CheckpointNode will poll the NameNode
  every 'dfs.namenode.checkpoint.check.period' seconds to query the number
  of uncheckpointed transactions.
  </description>
</property>

<property>
  <name>dfs.namenode.num.checkpoints.retained</name>
  <value>2</value>
  <description>The number of image checkpoint files that will be retained by
  the NameNode and Secondary NameNode in their storage directories. All edit
  logs necessary to recover an up-to-date namespace from the oldest retained
  checkpoint will also be retained.
  </description>
</property>

<property>
  <name>dfs.namenode.num.extra.edits.retained</name>
  <value>1000000</value>
  <description>The number of extra transactions which should be retained
  beyond what is minimally necessary for a NN restart. This can be useful for
  audit purposes or for an HA setup where a remote Standby Node may have
  been offline for some time and need to have a longer backlog of retained
  edits in order to start again.
  Typically each edit is on the order of a few hundred bytes, so the default
  of 1 million edits should be on the order of hundreds of MBs or low GBs.
  </description>
</property>

<property>
  <name>dfs.namenode.delegation.key.update-interval</name>
  <value>86400000</value>
  <description>The update interval for master key for delegation tokens 
       in the namenode in milliseconds.
  </description>
</property>

<property>
  <name>dfs.namenode.delegation.token.max-lifetime</name>
  <value>604800000</value>
  <description>The maximum lifetime in milliseconds for which a delegation 
      token is valid.
  </description>
</property>

<property>
  <name>dfs.namenode.delegation.token.renew-interval</name>
  <value>86400000</value>
  <description>The renewal interval for delegation token in milliseconds.
  </description>
</property>

<property>
  <name>dfs.datanode.failed.volumes.tolerated</name>
  <value>0</value>
  <description>The number of volumes that are allowed to
  fail before a datanode stops offering service. By default
  any volume failure will cause a datanode to shutdown.
  </description>
</property>

<property>
  <name>dfs.image.compress</name>
  <value>false</value>
  <description>Should the dfs image be compressed?
  </description>
</property>

<property>
  <name>dfs.image.compression.codec</name>
  <value>org.apache.hadoop.io.compress.DefaultCodec</value>
  <description>If the dfs image is compressed, how should they be compressed?
               This has to be a codec defined in io.compression.codecs.
  </description>
</property>

<property>
  <name>dfs.image.transfer.bandwidthPerSec</name>
  <value>0</value>
  <description>
        Specifies the maximum amount of bandwidth that can be utilized for image
        transfer in term of the number of bytes per second.
        A default value of 0 indicates that throttling is disabled. 
  </description>
</property>

<property>
  <name>dfs.namenode.support.allow.format</name>
  <value>true</value>
  <description>Does HDFS namenode allow itself to be formatted?
               You may consider setting this to false for any production
               cluster, to avoid any possibility of formatting a running DFS.
  </description>
</property>

<property>
  <name>dfs.datanode.max.transfer.threads</name>
  <value>4096</value>
  <description>
        Specifies the maximum number of threads to use for transferring data
        in and out of the DN.
  </description>
</property>

<property>
  <name>dfs.client.failover.max.attempts</name>
  <value>15</value>
  <description>
    Expert only. The number of client failover attempts that should be
    made before the failover is considered failed.
  </description>
</property>

<property>
  <name>dfs.client.failover.sleep.base.millis</name>
  <value>500</value>
  <description>
    Expert only. The time to wait, in milliseconds, between failover
    attempts increases exponentially as a function of the number of
    attempts made so far, with a random factor of +/- 50%. This option
    specifies the base value used in the failover calculation. The
    first failover will retry immediately. The 2nd failover attempt
    will delay at least dfs.client.failover.sleep.base.millis
    milliseconds. And so on.
  </description>
</property>

<property>
  <name>dfs.client.failover.sleep.max.millis</name>
  <value>15000</value>
  <description>
    Expert only. The time to wait, in milliseconds, between failover
    attempts increases exponentially as a function of the number of
    attempts made so far, with a random factor of +/- 50%. This option
    specifies the maximum value to wait between failovers. 
    Specifically, the time between two failover attempts will not
    exceed +/- 50% of dfs.client.failover.sleep.max.millis
    milliseconds.
  </description>
</property>

<property>
  <name>dfs.client.failover.connection.retries</name>
  <value>0</value>
  <description>
    Expert only. Indicates the number of retries a failover IPC client
    will make to establish a server connection.
  </description>
</property>

<property>
  <name>dfs.client.failover.connection.retries.on.timeouts</name>
  <value>0</value>
  <description>
    Expert only. The number of retry attempts a failover IPC client
    will make on socket timeout when establishing a server connection.
  </description>
</property>

<property>
  <name>dfs.federation.nameservices</name>
  <value></value>
  <description>
    Comma-separated list of nameservices.
  </description>
</property>

<property>
  <name>dfs.federation.nameservice.id</name>
  <value></value>
  <description>
    The ID of this nameservice. If the nameservice ID is not
    configured or more than one nameservice is configured for
    dfs.federation.nameservices it is determined automatically by
    matching the local node's address with the configured address.
  </description>
</property>

<property>
  <name>dfs.ha.namenodes.EXAMPLENAMESERVICE</name>
  <value></value>
  <description>
    The prefix for a given nameservice, contains a comma-separated
    list of namenodes for a given nameservice (eg EXAMPLENAMESERVICE).
  </description>
</property>

<property>
  <name>dfs.ha.namenode.id</name>
  <value></value>
  <description>
    The ID of this namenode. If the namenode ID is not configured it
    is determined automatically by matching the local node's address
    with the configured address.
  </description>
</property>

<property>
  <name>dfs.ha.log-roll.period</name>
  <value>120</value>
  <description>
    How often, in seconds, the StandbyNode should ask the active to
    roll edit logs. Since the StandbyNode only reads from finalized
    log segments, the StandbyNode will only be as up-to-date as how
    often the logs are rolled. Note that failover triggers a log roll
    so the StandbyNode will be up to date before it becomes active.
  </description>
</property>

<property>
  <name>dfs.ha.tail-edits.period</name>
  <value>60</value>
  <description>
    How often, in seconds, the StandbyNode should check for new
    finalized log segments in the shared edits log.
  </description>
</property>

<property>
  <name>dfs.support.append</name>
  <value>true</value>
  <description>
    Does HDFS allow appends to files?
  </description>
</property>

<property>
  <name>dfs.client.local.interfaces</name>
  <value></value>
  <description>A comma separated list of network interface names to use
    for data transfer between the client and datanodes. When creating
    a connection to read from or write to a datanode, the client
    chooses one of the specified interfaces at random and binds its
    socket to the IP of that interface. Individual names may be
    specified as either an interface name (eg "eth0"), a subinterface
    name (eg "eth0:0"), or an IP address (which may be specified using
    CIDR notation to match a range of IPs).
  </description>
</property>

</configuration>