hadoop2.2.0 mapred-site.xml--i/o properties

<!-- i/o properties -->

<property>  <name>mapreduce.task.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>

注释：

<property>  <name>mapreduce.task.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>

注释：

<property>  <name>mapreduce.map.sort.spill.percent</name>  <value>0.80</value>  <description>The soft limit in the serialization buffer. Once reached, a  thread will begin to spill the contents to disk in the background. Note that  collection will not block if this threshold is exceeded while a spill is  already in progress, so spills may be larger than this threshold when it is  set to less than .5</description></property>

注释：

<property>  <name>mapreduce.jobtracker.address</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>

注释：

<property>  <name>mapreduce.local.clientfactory.class.name</name>  <value>org.apache.hadoop.mapred.LocalClientFactory</value>  <description>This the client factory that is responsible for   creating local job runner client</description></property>

注释：

<property>  <name>mapreduce.jobtracker.handler.count</name>  <value>10</value>  <description>    The number of server threads for the JobTracker. This should be roughly    4% of the number of tasktracker nodes.  </description></property>

注释：

<property>  <name>mapreduce.tasktracker.report.address</name>  <value>127.0.0.1:0</value>  <description>The interface and port that task tracker server listens on.   Since it is only connected to by the tasks, it uses the local interface.  EXPERT ONLY. Should only be changed if your host does not have the loopback   interface.</description></property>

注释：

<property>  <name>mapreduce.cluster.local.dir</name>  <value>${hadoop.tmp.dir}/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>

注释： 

<property>  <name>mapreduce.jobtracker.system.dir</name>  <value>${hadoop.tmp.dir}/mapred/system</value>  <description>The directory where MapReduce stores control files.  </description></property>

注释： 

<property>  <name>mapreduce.jobtracker.staging.root.dir</name>  <value>${hadoop.tmp.dir}/mapred/staging</value>  <description>The root of the staging area for users' job files  In practice, this should be the directory where users' home   directories are located (usually /user)  </description></property>

注释： 

<property>  <name>mapreduce.cluster.temp.dir</name>  <value>${hadoop.tmp.dir}/mapred/temp</value>  <description>A shared directory for temporary files.  </description></property>

注释： 

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

注释： 

<property>  <name>mapreduce.tasktracker.local.dir.minspacekill</name>  <value>0</value>  <description>If the space in mapreduce.cluster.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>

注释： 

<property>  <name>mapreduce.jobtracker.expire.trackers.interval</name>  <value>600000</value>  <description>Expert: The time-interval, in miliseconds, after which  a tasktracker is declared 'lost' if it doesn't send heartbeats.  </description></property>

注释： 

<property>  <name>mapreduce.tasktracker.instrumentation</name>  <value>org.apache.hadoop.mapred.TaskTrackerMetricsInst</value>  <description>Expert: The instrumentation class to associate with each TaskTracker.  </description></property>

注释： 

<property>  <name>mapreduce.tasktracker.resourcecalculatorplugin</name>  <value></value>  <description>   Name of the class whose instance will be used to query resource information   on the tasktracker.      The class must be an instance of    org.apache.hadoop.util.ResourceCalculatorPlugin. If the value is null, the   tasktracker attempts to use a class appropriate to the platform.    Currently, the only platform supported is Linux.  </description></property>

注释： 

<property>  <name>mapreduce.tasktracker.taskmemorymanager.monitoringinterval</name>  <value>5000</value>  <description>The interval, in milliseconds, for which the tasktracker waits   between two cycles of monitoring its tasks' memory usage. Used only if   tasks' memory management is enabled via mapred.tasktracker.tasks.maxmemory.   </description></property>

注释： 

<property>  <name>mapreduce.tasktracker.tasks.sleeptimebeforesigkill</name>  <value>5000</value>  <description>The time, in milliseconds, the tasktracker waits for sending a  SIGKILL to a task, after it has been sent a SIGTERM. This is currently  not used on WINDOWS where tasks are just sent a SIGTERM.  </description></property>

注释： 

<property>  <name>mapreduce.job.maps</name>  <value>2</value>  <description>The default number of map tasks per job.  Ignored when mapreduce.jobtracker.address is "local".    </description></property>

注释： 

<property>  <name>mapreduce.job.reduces</name>  <value>1</value>  <description>The default number of reduce tasks per job. Typically set to 99%  of the cluster's reduce capacity, so that if a node fails the reduces can   still be executed in a single wave.  Ignored when mapreduce.jobtracker.address is "local".  </description></property>

注释： 

<property>  <name>mapreduce.jobtracker.restart.recover</name>  <value>false</value>  <description>"true" to enable (job) recovery upon restart,               "false" to start afresh  </description></property>

注释：

<property>  <name>mapreduce.jobtracker.jobhistory.block.size</name>  <value>3145728</value>  <description>The block size of the job history file. Since the job recovery               uses job history, its important to dump job history to disk as                soon as possible. Note that this is an expert level parameter.               The default value is set to 3 MB.  </description></property>

注释：

<property>  <name>mapreduce.jobtracker.taskscheduler</name>  <value>org.apache.hadoop.mapred.JobQueueTaskScheduler</value>  <description>The class responsible for scheduling the tasks.</description></property>

注释：

<property>  <name>mapreduce.job.split.metainfo.maxsize</name>  <value>10000000</value>  <description>The maximum permissible size of the split metainfo file.   The JobTracker won't attempt to read split metainfo files bigger than  the configured value.  No limits if set to -1.  </description></property>

注释：

<property>  <name>mapreduce.jobtracker.taskscheduler.maxrunningtasks.perjob</name>  <value></value>  <description>The maximum number of running tasks for a job before  it gets preempted. No limits if undefined.  </description></property>

注释：

<property>  <name>mapreduce.map.maxattempts</name>  <value>4</value>  <description>Expert: The maximum number of attempts per map task.  In other words, framework will try to execute a map task these many number  of times before giving up on it.  </description></property>

注释：

<property>  <name>mapreduce.reduce.maxattempts</name>  <value>4</value>  <description>Expert: The maximum number of attempts per reduce task.  In other words, framework will try to execute a reduce task these many number  of times before giving up on it.  </description></property>

注释：

<property>  <name>mapreduce.reduce.shuffle.retry-delay.max.ms</name>  <value>60000</value>  <description>The maximum number of ms the reducer will delay before retrying  to download map data.  </description></property>

注释：

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

注释：

<property>  <name>mapreduce.reduce.shuffle.connect.timeout</name>  <value>180000</value>  <description>Expert: The maximum amount of time (in milli seconds) reduce  task spends in trying to connect to a tasktracker for getting map output.  </description></property>

注释：

<property>  <name>mapreduce.reduce.shuffle.read.timeout</name>  <value>180000</value>  <description>Expert: The maximum amount of time (in milli seconds) reduce  task waits for map output data to be available for reading after obtaining  connection.  </description></property>

注释：

<property>  <name>mapreduce.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.  A value of 0 disables the timeout.  </description></property>

注释：

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

注释：

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

注释：

<property>  <name>mapreduce.jobtracker.retiredjobs.cache.size</name>  <value>1000</value>  <description>The number of retired job status to keep in the cache.  </description></property>

注释：

<property>  <name>mapreduce.tasktracker.outofband.heartbeat</name>  <value>false</value>  <description>Expert: Set this to true to let the tasktracker send an   out-of-band heartbeat on task-completion for better latency.  </description></property>

注释：

<property>  <name>mapreduce.jobtracker.jobhistory.lru.cache.size</name>  <value>5</value>  <description>The number of job history files loaded in memory. The jobs are   loaded when they are first accessed. The cache is cleared based on LRU.  </description></property>

注释：

<property>  <name>mapreduce.jobtracker.instrumentation</name>  <value>org.apache.hadoop.mapred.JobTrackerMetricsInst</value>  <description>Expert: The instrumentation class to associate with each JobTracker.  </description></property>

注释：

<property>  <name>mapred.child.java.opts</name>  <value>-Xmx200m</value>  <description>Java opts for the task tracker child processes.    The following symbol, if present, will be interpolated: @taskid@ is replaced   by current TaskID. 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    Usage of -Djava.library.path can cause programs to no longer function if  hadoop native libraries are used. These values should instead be set as part   of LD_LIBRARY_PATH in the map / reduce JVM env using the mapreduce.map.env and   mapreduce.reduce.env config settings.   </description></property>

注释：

<property>  <name>mapred.child.env</name>  <value></value>  <description>User added environment variables for the task tracker child   processes. Example :  1) A=foo  This will set the env variable A to foo  2) B=$B:c This is inherit tasktracker's B env variable.    </description></property>

注释：

<property>  <name>mapreduce.admin.user.env</name>  <value>LD_LIBRARY_PATH=$HADOOP_COMMON_HOME/lib/native</value>  <description>Expert: Additional execution environment entries for   map and reduce task processes. This is not an additive property.  You must preserve the original value if you want your map and  reduce tasks to have access to native libraries (compression, etc).   </description></property>

注释：

<property>  <name>mapreduce.task.tmp.dir</name>  <value>./tmp</value>  <description> To set the value of tmp directory for map and reduce tasks.  If the value is an absolute path, it is directly assigned. Otherwise, it is  prepended with task's working directory. The java tasks are executed with  option -Djava.io.tmpdir='the absolute path of the tmp dir'. Pipes and  streaming are set with environment variable,   TMPDIR='the absolute path of the tmp dir'  </description></property>

注释：

<property>  <name>mapreduce.map.log.level</name>  <value>INFO</value>  <description>The logging level for the map task. The allowed levels are:  OFF, FATAL, ERROR, WARN, INFO, DEBUG, TRACE and ALL.  </description></property>

注释：

<property>  <name>mapreduce.reduce.log.level</name>  <value>INFO</value>  <description>The logging level for the reduce task. The allowed levels are:  OFF, FATAL, ERROR, WARN, INFO, DEBUG, TRACE and ALL.  </description></property>

注释：

<property>  <name>mapreduce.reduce.merge.inmem.threshold</name>  <value>1000</value>  <description>The threshold, in terms of the number of files   for the in-memory merge process. When we accumulate threshold number of files  we initiate the in-memory merge and spill to disk. A value of 0 or less than  0 indicates we want to DON'T have any threshold and instead depend only on  the ramfs's memory consumption to trigger the merge.  </description></property>

注释：

<property>  <name>mapreduce.reduce.shuffle.merge.percent</name>  <value>0.66</value>  <description>The usage threshold at which an in-memory merge will be  initiated, expressed as a percentage of the total memory allocated to  storing in-memory map outputs, as defined by  mapreduce.reduce.shuffle.input.buffer.percent.  </description></property>

注释：

<property>  <name>mapreduce.reduce.shuffle.input.buffer.percent</name>  <value>0.70</value>  <description>The percentage of memory to be allocated from the maximum heap  size to storing map outputs during the shuffle.  </description></property>

注释：

<property>  <name>mapreduce.reduce.input.buffer.percent</name>  <value>0.0</value>  <description>The percentage of memory- relative to the maximum heap size- to  retain map outputs during the reduce. When the shuffle is concluded, any  remaining map outputs in memory must consume less than this threshold before  the reduce can begin.  </description></property>

注释：

<property>  <name>mapreduce.reduce.shuffle.memory.limit.percent</name>  <value>0.25</value>  <description>Expert: Maximum percentage of the in-memory limit that a  single shuffle can consume</description></property>

注释：

<property>  <name>mapreduce.reduce.markreset.buffer.percent</name>  <value>0.0</value>  <description>The percentage of memory -relative to the maximum heap size- to  be used for caching values when using the mark-reset functionality.  </description></property>

注释：

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

注释：

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

注释：

<property>  <name>mapreduce.job.speculative.speculativecap</name>  <value>0.1</value>  <description>The max percent (0-1) of running tasks that  can be speculatively re-executed at any time.</description></property>

注释：

<property>  <name>mapreduce.job.speculative.slowtaskthreshold</name>  <value>1.0</value>The number of standard deviations by which a task's   ave progress-rates must be lower than the average of all running tasks'  for the task to be considered too slow.  <description>  </description></property>

注释：

<property>  <name>mapreduce.job.speculative.slownodethreshold</name>  <value>1.0</value>  <description>The number of standard deviations by which a Task   Tracker's ave map and reduce progress-rates (finishTime-dispatchTime)  must be lower than the average of all successful map/reduce task's for  the TT to be considered too slow to give a speculative task to.  </description></property>

注释：

<property>  <name>mapreduce.job.jvm.numtasks</name>  <value>1</value>  <description>How many tasks to run per jvm. If set to -1, there is  no limit.   </description></property>

注释：

<property>  <name>mapreduce.job.ubertask.enable</name>  <value>false</value>  <description>Whether to enable the small-jobs "ubertask" optimization,  which runs "sufficiently small" jobs sequentially within a single JVM.  "Small" is defined by the following maxmaps, maxreduces, and maxbytes  settings.  Users may override this value.  </description></property>

注释：

<property>  <name>mapreduce.job.ubertask.maxmaps</name>  <value>9</value>  <description>Threshold for number of maps, beyond which job is considered  too big for the ubertasking optimization.  Users may override this value,  but only downward.  </description></property>

注释：

<property>  <name>mapreduce.job.ubertask.maxreduces</name>  <value>1</value>  <description>Threshold for number of reduces, beyond which job is considered  too big for the ubertasking optimization.  CURRENTLY THE CODE CANNOT SUPPORT  MORE THAN ONE REDUCE and will ignore larger values.  (Zero is a valid max,  however.)  Users may override this value, but only downward.  </description></property>

注释：

<property>  <name>mapreduce.job.ubertask.maxbytes</name>  <value></value>  <description>Threshold for number of input bytes, beyond which job is  considered too big for the ubertasking optimization.  If no value is  specified, dfs.block.size is used as a default.  Be sure to specify a  default value in mapred-site.xml if the underlying filesystem is not HDFS.  Users may override this value, but only downward.  </description></property>

注释：

<property>  <name>mapreduce.input.fileinputformat.split.minsize</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>

注释：

<property>  <name>mapreduce.jobtracker.maxtasks.perjob</name>  <value>-1</value>  <description>The maximum number of tasks for a single job.  A value of -1 indicates that there is no maximum.  </description></property>

注释：

<property>  <name>mapreduce.client.submit.file.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>

注释：

<property>  <name>mapreduce.tasktracker.dns.interface</name>  <value>default</value>  <description>The name of the Network Interface from which a task  tracker should report its IP address.  </description> </property>

注释：

<property>  <name>mapreduce.tasktracker.dns.nameserver</name>  <value>default</value>  <description>The host name or IP address of the name server (DNS)  which a TaskTracker should use to determine the host name used by  the JobTracker for communication and display purposes.  </description> </property>

注释：

<property>  <name>mapreduce.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>

注释：

<property>  <name>mapreduce.tasktracker.http.address</name>  <value>0.0.0.0:50060</value>  <description>    The task tracker http server address and port.    If the port is 0 then the server will start on a free port.  </description></property>

注释：

<property>  <name>mapreduce.task.files.preserve.failedtasks</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>

注释：

<!--   <property>  <name>mapreduce.task.files.preserve.filepattern</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>-->

注释：

<property>  <name>mapreduce.output.fileoutputformat.compress</name>  <value>false</value>  <description>Should the job outputs be compressed?  </description></property>

注释：

<property>  <name>mapreduce.output.fileoutputformat.compress.type</name>  <value>RECORD</value>  <description>If the job outputs are to compressed as SequenceFiles, how should               they be compressed? Should be one of NONE, RECORD or BLOCK.  </description></property>

注释：

<property>  <name>mapreduce.output.fileoutputformat.compress.codec</name>  <value>org.apache.hadoop.io.compress.DefaultCodec</value>  <description>If the job outputs are compressed, how should they be compressed?  </description></property>

注释：

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

注释：

<property>  <name>mapreduce.map.output.compress.codec</name>  <value>org.apache.hadoop.io.compress.DefaultCodec</value>  <description>If the map outputs are compressed, how should they be                compressed?  </description></property>

注释：

<property>  <name>map.sort.class</name>  <value>org.apache.hadoop.util.QuickSort</value>  <description>The default sort class for sorting keys.  </description></property>

注释：

<property>  <name>mapreduce.task.userlog.limit.kb</name>  <value>0</value>  <description>The maximum size of user-logs of each task in KB. 0 disables the cap.  </description></property>

注释：

<property>  <name>mapreduce.job.userlog.retain.hours</name>  <value>24</value>  <description>The maximum time, in hours, for which the user-logs are to be                retained after the job completion.  </description></property>

注释：

<property>  <name>mapreduce.jobtracker.hosts.filename</name>  <value></value>  <description>Names a file that contains the list of nodes that may  connect to the jobtracker.  If the value is empty, all hosts are  permitted.</description></property>

注释：

<property>  <name>mapreduce.jobtracker.hosts.exclude.filename</name>  <value></value>  <description>Names a file that contains the list of hosts that  should be excluded by the jobtracker.  If the value is empty, no  hosts are excluded.</description></property>

注释：

<property>  <name>mapreduce.jobtracker.heartbeats.in.second</name>  <value>100</value>  <description>Expert: Approximate number of heart-beats that could arrive                at JobTracker in a second. Assuming each RPC can be processed                in 10msec, the default value is made 100 RPCs in a second.  </description></property> 

注释：

<property>  <name>mapreduce.jobtracker.tasktracker.maxblacklists</name>  <value>4</value>  <description>The number of blacklists for a taskTracker by various jobs               after which the task tracker could be blacklisted across               all jobs. The tracker will be given a tasks later               (after a day). The tracker will become a healthy               tracker after a restart.  </description></property> 

注释：

<property>  <name>mapreduce.job.maxtaskfailures.per.tracker</name>  <value>3</value>  <description>The number of task-failures on a tasktracker of a given job                after which new tasks of that job aren't assigned to it. It               MUST be less than mapreduce.map.maxattempts and               mapreduce.reduce.maxattempts otherwise the failed task will               never be tried on a different node.  </description></property>

注释：

<property>  <name>mapreduce.client.output.filter</name>  <value>FAILED</value>  <description>The filter for controlling the output of the task's userlogs sent               to the console of the JobClient.                The permissible options are: NONE, KILLED, FAILED, SUCCEEDED and                ALL.  </description></property>

注释：

  <property>    <name>mapreduce.client.completion.pollinterval</name>    <value>5000</value>    <description>The interval (in milliseconds) between which the JobClient    polls the JobTracker for updates about job status. You may want to set this    to a lower value to make tests run faster on a single node system. Adjusting    this value in production may lead to unwanted client-server traffic.    </description>  </property>

注释：

  <property>    <name>mapreduce.client.progressmonitor.pollinterval</name>    <value>1000</value>    <description>The interval (in milliseconds) between which the JobClient    reports status to the console and checks for job completion. You may want to set this    to a lower value to make tests run faster on a single node system. Adjusting    this value in production may lead to unwanted client-server traffic.    </description>  </property>

注释：

  <property>    <name>mapreduce.jobtracker.persist.jobstatus.active</name>    <value>true</value>    <description>Indicates if persistency of job status information is      active or not.    </description>  </property>

注释：

  <property>  <name>mapreduce.jobtracker.persist.jobstatus.hours</name>  <value>1</value>  <description>The number of hours job status information is persisted in DFS.    The job status information will be available after it drops of the memory    queue and between jobtracker restarts. With a zero value the job status    information is not persisted at all in DFS.  </description></property>

注释：

  <property>    <name>mapreduce.jobtracker.persist.jobstatus.dir</name>    <value>/jobtracker/jobsInfo</value>    <description>The directory where the job status information is persisted      in a file system to be available after it drops of the memory queue and      between jobtracker restarts.    </description>  </property>

注释：

  <property>    <name>mapreduce.task.profile</name>    <value>false</value>    <description>To set whether the system should collect profiler     information for some of the tasks in this job? The information is stored     in the user log directory. The value is "true" if task profiling     is enabled.</description>  </property>

注释：

  <property>    <name>mapreduce.task.profile.maps</name>    <value>0-2</value>    <description> To set the ranges of map tasks to profile.    mapreduce.task.profile has to be set to true for the value to be accounted.    </description>  </property>

注释：

  <property>    <name>mapreduce.task.profile.reduces</name>    <value>0-2</value>    <description> To set the ranges of reduce tasks to profile.    mapreduce.task.profile has to be set to true for the value to be accounted.    </description>  </property>

注释：

  <property>    <name>mapreduce.task.skip.start.attempts</name>    <value>2</value>    <description> The number of Task attempts AFTER which skip mode     will be kicked off. When skip mode is kicked off, the     tasks reports the range of records which it will process     next, to the TaskTracker. So that on failures, TT knows which     ones are possibly the bad records. On further executions,     those are skipped.    </description>  </property>

注释：

  <property>    <name>mapreduce.map.skip.proc.count.autoincr</name>    <value>true</value>    <description> The flag which if set to true,     SkipBadRecords.COUNTER_MAP_PROCESSED_RECORDS is incremented     by MapRunner after invoking the map function. This value must be set to     false for applications which process the records asynchronously     or buffer the input records. For example streaming.     In such cases applications should increment this counter on their own.    </description>  </property>

注释：

  <property>    <name>mapreduce.reduce.skip.proc.count.autoincr</name>    <value>true</value>    <description> The flag which if set to true,     SkipBadRecords.COUNTER_REDUCE_PROCESSED_GROUPS is incremented     by framework after invoking the reduce function. This value must be set to     false for applications which process the records asynchronously     or buffer the input records. For example streaming.     In such cases applications should increment this counter on their own.    </description>  </property>

注释：

  <property>    <name>mapreduce.job.skip.outdir</name>    <value></value>    <description> If no value is specified here, the skipped records are     written to the output directory at _logs/skip.    User can stop writing skipped records by giving the value "none".     </description>  </property>

注释：

  <property>    <name>mapreduce.map.skip.maxrecords</name>    <value>0</value>    <description> The number of acceptable skip records surrounding the bad     record PER bad record in mapper. The number includes the bad record as well.    To turn the feature of detection/skipping of bad records off, set the     value to 0.    The framework tries to narrow down the skipped range by retrying      until this threshold is met OR all attempts get exhausted for this task.     Set the value to Long.MAX_VALUE to indicate that framework need not try to     narrow down. Whatever records(depends on application) get skipped are     acceptable.    </description>  </property>

注释：

  <property>    <name>mapreduce.reduce.skip.maxgroups</name>    <value>0</value>    <description> The number of acceptable skip groups surrounding the bad     group PER bad group in reducer. The number includes the bad group as well.    To turn the feature of detection/skipping of bad groups off, set the     value to 0.    The framework tries to narrow down the skipped range by retrying      until this threshold is met OR all attempts get exhausted for this task.     Set the value to Long.MAX_VALUE to indicate that framework need not try to     narrow down. Whatever groups(depends on application) get skipped are     acceptable.    </description>  </property>

注释：