conf/hadoop-default.xml

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

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

<configuration>

<!--- logging properties -->

<property>
  <name>hadoop.logfile.size</name>
  <value>10000000</value>
  <description>The max size of each log file</description>
</property>

<property>
  <name>hadoop.logfile.count</name>
  <value>10</value>
  <description>The max number of log files</description>
</property>

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

<!-- i/o properties -->

<property>
  <name>io.sort.factor</name>
  <value>10</value>
  <description>The number of streams to merge at once while sorting
  files.  This determines the number of open file handles.</description>
</property>

<property>
  <name>io.sort.mb</name>
  <value>100</value>
  <description>The total amount of buffer memory to use while sorting 
  files, in megabytes.  By default, gives each merge stream 1MB, which
  should minimize seeks.</description>
</property>

<property>
  <name>io.file.buffer.size</name>
  <value>4096</value>
  <description>The size of buffer for use in sequence 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>io.bytes.per.checksum</name>
  <value>512</value>
  <description>The number of bytes per checksum.  Must not be larger than
  io.file.buffer.size.</description>
</property>

<property>
  <name>io.skip.checksum.errors</name>
  <value>false</value>
  <description>If true, when a checksum error is encountered while
  reading a sequence file, entries are skipped, instead of throwing an
  exception.</description>
</property>
  
<property>
  <name>io.map.index.skip</name>
  <value>0</value>
  <description>Number of index entries to skip between each entry.
  Zero by default. Setting this to values larger than zero can
  facilitate opening large map files using less memory.</description>
</property>

<!-- file system properties -->

<property>
  <name>fs.default.name</name>
  <value>local</value>
  <description>The name of the default file system.  Either the
  literal string "local" or a host:port for DFS.</description>
</property>

<property>
  <name>dfs.datanode.port</name>
  <value>50010</value>
  <description>The port number that the dfs datanode server uses as a starting 
	       point to look for a free port to listen on.
</description>
</property>

<property>
  <name>dfs.info.port</name>
  <value>50070</value>
  <description>The base port number for the dfs namenode web ui.
  </description>
</property>

<property>
  <name>dfs.default.chunk.view.size</name>
  <value>2048</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. Always leave this much space free for non dfs use
  </description>
</property>

<property>
  <name>dfs.datanode.du.pct</name>
  <value>0.98f</value>
  <description>When calculating remaining space, only use this percentage of the real available space
  </description>
</property>

<property>
  <name>dfs.name.dir</name>
  <value>/tmp/hadoop/dfs/name</value>
  <description>Determines where on the local filesystem the DFS name node
      should store the name table.</description>
</property>

<property>
  <name>dfs.data.dir</name>
  <value>/tmp/hadoop/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.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.replication.min</name>
  <value>1</value>
  <description>Minimal block replication. 
  </description>
</property>

<property>
  <name>dfs.block.size</name>
  <value>67108864</value>
  <description>The default block size for new files.</description>
</property>

<property>
  <name>dfs.df.interval</name>
  <value>3000</value>
  <description>Disk usage statistics refresh interval in msec.</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>


<!-- map/reduce properties -->

<property>
  <name>mapred.job.tracker</name>
  <value>local</value>
  <description>The host and port that the MapReduce job tracker runs
  at.  If "local", then jobs are run in-process as a single map
  and reduce task.
  </description>
</property>

<property>
  <name>mapred.job.tracker.info.port</name>
  <value>50030</value>
  <description>The port that the MapReduce job tracker info webserver runs at.
  </description>
</property>

<property>
  <name>mapred.task.tracker.output.port</name>
  <value>50040</value>
  <description>The port number that the MapReduce task tracker output server uses as a starting
               point to look for a free port to listen on.
  </description>
</property>

<property>
  <name>mapred.task.tracker.report.port</name>
  <value>50050</value>
  <description>The port number that the MapReduce task tracker report server uses as a starting
               point to look for a free port to listen on.
  </description>
</property>

<property>
  <name>mapred.local.dir</name>
  <value>/tmp/hadoop/mapred/local</value>
  <description>The local directory where MapReduce stores intermediate
  data files.  May be a comma-separated list of
  directories on different devices in order to spread disk i/o.
  Directories that do not exist are ignored.
  </description>
</property>

<property>
  <name>mapred.system.dir</name>
  <value>/tmp/hadoop/mapred/system</value>
  <description>The shared directory where MapReduce stores control files.
  </description>
</property>

<property>
  <name>mapred.temp.dir</name>
  <value>/tmp/hadoop/mapred/temp</value>
  <description>A shared directory for temporary files.
  </description>
</property>

<property>
  <name>mapred.local.dir.minspacestart</name>
  <value>0</value>
  <description>If the space in mapred.local.dir drops under this, 
  do not ask for more tasks.
  Value in bytes.
  </description>
</property>

<property>
  <name>mapred.local.dir.minspacekill</name>
  <value>0</value>
  <description>If the space in mapred.local.dir drops under this, 
  	do not ask more tasks until all the current ones have finished and 
  	cleaned up. Also, to save the rest of the tasks we have running, 
  	kill one of them, to clean up some space. Start with the reduce tasks,
  	then go with the ones that have finished the least.
  	Value in bytes.
  </description>
</property>

<property>
  <name>mapred.map.tasks</name>
  <value>2</value>
  <description>The default number of map tasks per job.  Typically set
  to a prime several times greater than number of available hosts.
  Ignored when mapred.job.tracker is "local".  
  </description>
</property>

<property>
  <name>mapred.reduce.tasks</name>
  <value>1</value>
  <description>The default number of reduce tasks per job.  Typically set
  to a prime close to the number of available hosts.  Ignored when
  mapred.job.tracker is "local".
  </description>
</property>

<property>
  <name>mapred.reduce.parallel.copies</name>
  <value>5</value>
  <description>The default number of parallel transfers run by reduce
  during the copy(shuffle) phase.
  </description>
</property>

<property>
  <name>mapred.task.timeout</name>
  <value>600000</value>
  <description>The number of milliseconds before a task will be
  terminated if it neither reads an input, writes an output, nor
  updates its status string.
  </description>
</property>

<property>
  <name>mapred.tasktracker.tasks.maximum</name>
  <value>2</value>
  <description>The maximum number of tasks that will be run
  simultaneously by a task tracker.
  </description>
</property>

<property>
  <name>mapred.child.java.opts</name>
  <value>-Xmx200m</value>
  <description>Java opts for the task tracker child processes.  Subsumes
  'mapred.child.heap.size' (If a mapred.child.heap.size value is found
  in a configuration, its maximum heap size will be used and a warning
  emitted that heap.size has been deprecated). Also, the following symbols,
  if present, will be interpolated: @taskid@ is replaced by current TaskID;
  and @port@ will be replaced by mapred.task.tracker.report.port + 1 (A second
  child will fail with a port-in-use if mapred.tasktracker.tasks.maximum is
  greater than one). Any other occurrences of '@' will go unchanged. For
  example, to enable verbose gc logging to a file named for the taskid in
  /tmp and to set the heap maximum to be a gigabyte, pass a 'value' of:

        -Xmx1024m -verbose:gc -Xloggc:/tmp/@taskid@.gc
  </description>
</property>

<property>
  <name>mapred.combine.buffer.size</name>
  <value>100000</value>
  <description>The number of entries the combining collector caches before
  combining them and writing to disk.</description>
</property>

<property>
  <name>mapred.speculative.execution</name>
  <value>true</value>
  <description>If true, then multiple instances of some map tasks may
  be executed in parallel.</description>
</property>

<property>
  <name>mapred.min.split.size</name>
  <value>0</value>
  <description>The minimum size chunk that map input should be split
  into.  Note that some file formats may have minimum split sizes that
  take priority over this setting.</description>
</property>

<property>
  <name>mapred.submit.replication</name>
  <value>10</value>
  <description>The replication level for submitted job files.  This
  should be around the square root of the number of nodes.
  </description>
</property>

<property>
  <name>tasktracker.http.threads</name>
  <value>40</value>
  <description>The number of worker threads that for the http server. This is
               used for map output fetching
  </description>
</property>

<property>
  <name>tasktracker.http.port</name>
  <value>50060</value>
  <description>The default port for task trackers to use as their http server.
  </description>
</property>

<property>
  <name>keep.failed.task.files</name>
  <value>false</value>
  <description>Should the files for failed tasks be kept. This should only be 
               used on jobs that are failing, because the storage is never
               reclaimed. It also prevents the map outputs from being erased
               from the reduce directory as they are consumed.</description>
</property>

<!-- 
  <property>
  <name>keep.task.files.pattern</name>
  <value>.*_m_123456_0</value>
  <description>Keep all files from tasks whose task names match the given
               regular expression. Defaults to none.</description>
  </property>
-->

<property>
  <name>mapred.compress.map.output</name>
  <value>false</value>
  <description>Should the outputs of the maps be compressed before being
               sent across the network. Uses SequenceFile compression.
  </description>
</property>

<!-- ipc properties -->

<property>
  <name>ipc.client.timeout</name>
  <value>60000</value>
  <description>Defines the timeout for IPC calls in milliseconds.</description>
</property>

<property>
  <name>ipc.client.idlethreshold</name>
  <value>4000</value>
  <description>Defines the threshold numner of connections after which
               connections will be inspected for idleness.
  </description>
</property>

<property>
  <name>ipc.client.maxidletime</name>
  <value>120000</value>
  <description>Defines the maximum idle time for a connected client after 
               which it may be disconnected.
  </description>
</property>

<property>
  <name>ipc.client.kill.max</name>
  <value>10</value>
  <description>Defines the maximum number of clients to disconnect in one go.
  </description>
</property>


</configuration>