mapred-site.xml 默认参数
<?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 mapred-site.xml and change them -->
<!-- there. If mapred-site.xml does not already exist, create it. -->
<configuration>
<property>
<name>hadoop.job.history.location</name>
<value></value>
<description> If job tracker is static the history files are stored
in this single well known place. If No value is set here, by default,
it is in the local file system at ${hadoop.log.dir}/history.
</description>
</property>
<property>
<name>hadoop.job.history.user.location</name>
<value></value>
<description> User can specify a location to store the history files of
a particular job. If nothing is specified, the logs are stored in
output directory. The files are stored in "_logs/history/" in the directory.
User can stop logging by giving the value "none".
</description>
</property>
<property>
<name>mapred.job.tracker.history.completed.location</name>
<value></value>
<description> The completed job history files are stored at this single well
known location. If nothing is specified, the files are stored at
${hadoop.job.history.location}/done.
</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.sort.record.percent</name>
<value>0.05</value>
<description>The percentage of io.sort.mb dedicated to tracking record
boundaries. Let this value be r, io.sort.mb be x. The maximum number
of records collected before the collection thread must block is equal
to (r * x) / 4</description>
</property>
<property>
<name>io.sort.spill.percent</name>
<value>0.80</value>
<description>The soft limit in either the buffer or record collection
buffers. Once reached, a thread will begin to spill the contents to disk
in the background. Note that this does not imply any chunking of data to
the spill. A value less than 0.5 is not recommended.</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>
<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.http.address</name>
<value>0.0.0.0:50030</value>
<description>
The job tracker http server address and port the server will listen on.
If the port is 0 then the server will start on a free port.
</description>
</property>
<property>
<name>mapred.job.tracker.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>
<property>
<name>mapred.task.tracker.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>
<property>
<name>mapred.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>
<property>
<name>mapred.system.dir</name>
<value>${hadoop.tmp.dir}/mapred/system</value>
<description>The directory where MapReduce stores control files.
</description>
</property>
<property>
<name>mapreduce.jobtracker.staging.root.dir</name>
<value>${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>
<property>
<name>mapred.temp.dir</name>
<value>${hadoop.tmp.dir}/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.tasktracker.expiry.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>
<!--
<property>
<name>mapred.tasktracker.instrumentation</name>
<value>com.example.hadoop.TaskTrackerInstrumentation</value>
<description>Expert: The instrumentation class to associate with each TaskTracker.
</description>
</property>
-->
<property>
<name>mapred.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>
<property>
<name>mapred.tasktracker.taskmemorymanager.monitoring-interval</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>
<property>
<name>mapred.tasktracker.tasks.sleeptime-before-sigkill</name>
<value>5000</value>
<description>The time, in milliseconds, the tasktracker waits for sending a
SIGKILL to a process, after it has been sent a SIGTERM.</description>
</property>
<property>
<name>mapred.map.tasks</name>
<value>2</value>
<description>The default number of map tasks per job.
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 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 mapred.job.tracker is "local".
</description>
</property>
<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>
<property>
<name>mapreduce.tasktracker.outofband.heartbeat.damper</name>
<value>1000000</value>
<description>When out-of-band heartbeats are enabled, provides
damping to avoid overwhelming the JobTracker if too many out-of-band
heartbeats would occur. The damping is calculated such that the
heartbeat interval is divided by (T*D + 1) where T is the number
of completed tasks and D is the damper value.
Setting this to a high value like the default provides no damping --
as soon as any task finishes, a heartbeat will be sent. Setting this
parameter to 0 is equivalent to disabling the out-of-band heartbeat feature.
A value of 1 would indicate that, after one task has completed, the
time to wait before the next heartbeat would be 1/2 the usual time.
After two tasks have finished, it would be 1/3 the usual time, etc.
</description>
</property>
<property>
<name>mapred.jobtracker.restart.recover</name>
<value>false</value>
<description>"true" to enable (job) recovery upon restart,
"false" to start afresh
</description>
</property>
<property>
<name>mapred.jobtracker.job.history.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>
<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>
<property>
<name>mapred.jobtracker.taskScheduler</name>
<value>org.apache.hadoop.mapred.JobQueueTaskScheduler</value>
<description>The class responsible for scheduling the tasks.</description>
</property>
<property>
<name>mapred.jobtracker.taskScheduler.maxRunningTasksPerJob</name>
<value></value>
<description>The maximum number of running tasks for a job before
it gets preempted. No limits if undefined.
</description>
</property>
<property>
<name>mapred.map.max.attempts</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>
<property>
<name>mapred.reduce.max.attempts</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>
<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>mapreduce.reduce.shuffle.maxfetchfailures</name>
<value>10</value>
<description>The maximum number of times a reducer tries to
fetch a map output before it reports it.
</description></property>
<property>
<name>mapreduce.reduce.shuffle.connect.timeout</name>
<value>180000</value>
<description>Expert: The maximum amount of time (in milli seconds) a reduce
task spends in trying to connect to a tasktracker for getting map output.
</description>
</property>
<property>
<name>mapreduce.reduce.shuffle.read.timeout</name>
<value>180000</value>
<description>Expert: The maximum amount of time (in milli seconds) a reduce
task waits for map output data to be available for reading after obtaining
connection.
</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.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>
<property>
<name>mapred.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>
<property>
<name>mapred.jobtracker.completeuserjobs.maximum</name>
<value>100</value>
<description>The maximum number of complete jobs per user to keep around
before delegating them to the job history.</description>
</property>
<property>
<name>mapreduce.reduce.input.limit</name>
<value>-1</value>
<description>The limit on the input size of the reduce. If the estimated
input size of the reduce is greater than this value, job is failed. A
value of -1 means that there is no limit set. </description>
</property>
<property>
<name>mapred.job.tracker.retiredjobs.cache.size</name>
<value>1000</value>
<description>The number of retired job status to keep in the cache.
</description>
</property>
<property>
<name>mapred.job.tracker.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>
<!--
<property>
<name>mapred.jobtracker.instrumentation</name>
<value>com.example.hadoop.JobTrackerInstrumentation</value>
<description>Expert: The instrumentation class to associate with each JobTracker.
</description>
</property>
-->
<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
The configuration variable mapred.child.ulimit can be used to control the
maximum virtual memory of the child processes.
</description>
</property>
<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>
<property>
<name>mapred.child.ulimit</name>
<value></value>
<description>The maximum virtual memory, in KB, of a process launched by the
Map-Reduce framework. This can be used to control both the Mapper/Reducer
tasks and applications using Hadoop Pipes, Hadoop Streaming etc.
By default it is left unspecified to let cluster admins control it via
limits.conf and other such relevant mechanisms.
Note: mapred.child.ulimit must be greater than or equal to the -Xmx passed to
JavaVM, else the VM might not start.
</description>
</property>
<property>
<name>mapred.cluster.map.memory.mb</name>
<value>-1</value>
<description>The size, in terms of virtual memory, of a single map slot
in the Map-Reduce framework, used by the scheduler.
A job can ask for multiple slots for a single map task via
mapred.job.map.memory.mb, upto the limit specified by
mapred.cluster.max.map.memory.mb, if the scheduler supports the feature.
The value of -1 indicates that this feature is turned off.
</description>
</property>
<property>
<name>mapred.cluster.reduce.memory.mb</name>
<value>-1</value>
<description>The size, in terms of virtual memory, of a single reduce slot
in the Map-Reduce framework, used by the scheduler.
A job can ask for multiple slots for a single reduce task via
mapred.job.reduce.memory.mb, upto the limit specified by
mapred.cluster.max.reduce.memory.mb, if the scheduler supports the feature.
The value of -1 indicates that this feature is turned off.
</description>
</property>
<property>
<name>mapred.cluster.max.map.memory.mb</name>
<value>-1</value>
<description>The maximum size, in terms of virtual memory, of a single map
task launched by the Map-Reduce framework, used by the scheduler.
A job can ask for multiple slots for a single map task via
mapred.job.map.memory.mb, upto the limit specified by
mapred.cluster.max.map.memory.mb, if the scheduler supports the feature.
The value of -1 indicates that this feature is turned off.
</description>
</property>
<property>
<name>mapred.cluster.max.reduce.memory.mb</name>
<value>-1</value>
<description>The maximum size, in terms of virtual memory, of a single reduce
task launched by the Map-Reduce framework, used by the scheduler.
A job can ask for multiple slots for a single reduce task via
mapred.job.reduce.memory.mb, upto the limit specified by
mapred.cluster.max.reduce.memory.mb, if the scheduler supports the feature.
The value of -1 indicates that this feature is turned off.
</description>
</property>
<property>
<name>mapred.job.map.memory.mb</name>
<value>-1</value>
<description>The size, in terms of virtual memory, of a single map task
for the job.
A job can ask for multiple slots for a single map task, rounded up to the
next multiple of mapred.cluster.map.memory.mb and upto the limit
specified by mapred.cluster.max.map.memory.mb, if the scheduler supports
the feature.
The value of -1 indicates that this feature is turned off iff
mapred.cluster.map.memory.mb is also turned off (-1).
</description>
</property>
<property>
<name>mapred.job.reduce.memory.mb</name>
<value>-1</value>
<description>The size, in terms of virtual memory, of a single reduce task
for the job.
A job can ask for multiple slots for a single map task, rounded up to the
next multiple of mapred.cluster.reduce.memory.mb and upto the limit
specified by mapred.cluster.max.reduce.memory.mb, if the scheduler supports
the feature.
The value of -1 indicates that this feature is turned off iff
mapred.cluster.reduce.memory.mb is also turned off (-1).
</description>
</property>
<property>
<name>mapred.child.tmp</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>
<property>
<name>mapred.inmem.merge.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>
<property>
<name>mapred.job.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
mapred.job.shuffle.input.buffer.percent.
</description>
</property>
<property>
<name>mapred.job.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>
<property>
<name>mapred.job.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>
<property>
<name>mapred.map.tasks.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.reduce.tasks.speculative.execution</name>
<value>true</value>
<description>If true, then multiple instances of some reduce tasks
may be executed in parallel.</description>
</property>
<property>
<name>mapred.job.reuse.jvm.num.tasks</name>
<value>1</value>
<description>How many tasks to run per jvm. If set to -1, there is
no limit.
</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.jobtracker.maxtasks.per.job</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>
<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>mapred.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>
<property>
<name>mapred.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>
<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>mapred.task.tracker.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>
<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.output.compress</name>
<value>false</value>
<description>Should the job outputs be compressed?
</description>
</property>
<property>
<name>mapred.output.compression.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>
<property>
<name>mapred.output.compression.codec</name>
<value>org.apache.hadoop.io.compress.DefaultCodec</value>
<description>If the job outputs are compressed, how should they be compressed?
</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>
<property>
<name>mapred.map.output.compression.codec</name>
<value>org.apache.hadoop.io.compress.DefaultCodec</value>
<description>If the map outputs are compressed, how should they be
compressed?
</description>
</property>
<property>
<name>map.sort.class</name>
<value>org.apache.hadoop.util.QuickSort</value>
<description>The default sort class for sorting keys.
</description>
</property>
<property>
<name>mapred.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>
<property>
<name>mapred.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>
<property>
<name>mapred.user.jobconf.limit</name>
<value>5242880</value>
<description>The maximum allowed size of the user jobconf. The
default is set to 5 MB</description>
</property>
<property>
<name>mapred.hosts</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>
<property>
<name>mapred.hosts.exclude</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>
<property>
<name>mapred.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>
<property>
<name>mapred.max.tracker.blacklists</name>
<value>4</value>
<description>The number of blacklists for a tasktracker by various jobs
after which the tasktracker will be marked as potentially
faulty and is a candidate for graylisting across all jobs.
(Unlike blacklisting, this is advisory; the tracker remains
active. However, it is reported as graylisted in the web UI,
with the expectation that chronically graylisted trackers
will be manually decommissioned.) This value is tied to
mapred.jobtracker.blacklist.fault-timeout-window; faults
older than the window width are forgiven, so the tracker
will recover from transient problems. It will also become
healthy after a restart.
</description>
</property>
<property>
<name>mapred.jobtracker.blacklist.fault-timeout-window</name>
<value>180</value>
<description>The timeout (in minutes) after which per-job tasktracker
faults are forgiven. The window is logically a circular
buffer of time-interval buckets whose width is defined by
mapred.jobtracker.blacklist.fault-bucket-width; when the
"now" pointer moves across a bucket boundary, the previous
contents (faults) of the new bucket are cleared. In other
words, the timeout's granularity is determined by the bucket
width.
</description>
</property>
<property>
<name>mapred.jobtracker.blacklist.fault-bucket-width</name>
<value>15</value>
<description>The width (in minutes) of each bucket in the tasktracker
fault timeout window. Each bucket is reused in a circular
manner after a full timeout-window interval (defined by
mapred.jobtracker.blacklist.fault-timeout-window).
</description>
</property>
<property>
<name>mapred.max.tracker.failures</name>
<value>4</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.
</description>
</property>
<property>
<name>jobclient.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>
<property>
<name>mapred.job.tracker.persist.jobstatus.active</name>
<value>false</value>
<description>Indicates if persistency of job status information is
active or not.
</description>
</property>
<property>
<name>mapred.job.tracker.persist.jobstatus.hours</name>
<value>0</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>
<property>
<name>mapred.job.tracker.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>
<property>
<name>mapreduce.job.complete.cancel.delegation.tokens</name>
<value>true</value>
<description> if false - do not unregister/cancel delegation tokens
from renewal, because same tokens may be used by spawned jobs
</description>
</property>
<property>
<name>mapred.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>
<property>
<name>mapred.task.profile.maps</name>
<value>0-2</value>
<description> To set the ranges of map tasks to profile.
mapred.task.profile has to be set to true for the value to be accounted.
</description>
</property>
<property>
<name>mapred.task.profile.reduces</name>
<value>0-2</value>
<description> To set the ranges of reduce tasks to profile.
mapred.task.profile has to be set to true for the value to be accounted.
</description>
</property>
<property>
<name>mapred.line.input.format.linespermap</name>
<value>1</value>
<description> Number of lines per split in NLineInputFormat.
</description>
</property>
<property>
<name>mapred.skip.attempts.to.start.skipping</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>
<property>
<name>mapred.skip.map.auto.incr.proc.count</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>
<property>
<name>mapred.skip.reduce.auto.incr.proc.count</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>
<property>
<name>mapred.skip.out.dir</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>
<property>
<name>mapred.skip.map.max.skip.records</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>
<property>
<name>mapred.skip.reduce.max.skip.groups</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>
<!-- Job Notification Configuration -->
<!--
<property>
<name>job.end.notification.url</name>
<value>http://localhost:8080/jobstatus.php?jobId=$jobId&jobStatus=$jobStatus</value>
<description>Indicates url which will be called on completion of job to inform
end status of job.
User can give at most 2 variables with URI : $jobId and $jobStatus.
If they are present in URI, then they will be replaced by their
respective values.
</description>
</property>
-->
<property>
<name>job.end.retry.attempts</name>
<value>0</value>
<description>Indicates how many times hadoop should attempt to contact the
notification URL </description>
</property>
<property>
<name>job.end.retry.interval</name>
<value>30000</value>
<description>Indicates time in milliseconds between notification URL retry
calls</description>
</property>
<!-- Proxy Configuration -->
<property>
<name>hadoop.rpc.socket.factory.class.JobSubmissionProtocol</name>
<value></value>
<description> SocketFactory to use to connect to a Map/Reduce master
(JobTracker). If null or empty, then use hadoop.rpc.socket.class.default.
</description>
</property>
<property>
<name>mapred.task.cache.levels</name>
<value>2</value>
<description> This is the max level of the task cache. For example, if
the level is 2, the tasks cached are at the host level and at the rack
level.
</description>
</property>
<property>
<name>mapred.queue.names</name>
<value>default</value>
<description> Comma separated list of queues configured for this jobtracker.
Jobs are added to queues and schedulers can configure different
scheduling properties for the various queues. To configure a property
for a queue, the name of the queue must match the name specified in this
value. Queue properties that are common to all schedulers are configured
here with the naming convention, mapred.queue.$QUEUE-NAME.$PROPERTY-NAME,
for e.g. mapred.queue.default.submit-job-acl.
The number of queues configured in this parameter could depend on the
type of scheduler being used, as specified in
mapred.jobtracker.taskScheduler. For example, the JobQueueTaskScheduler
supports only a single queue, which is the default configured here.
Before adding more queues, ensure that the scheduler you've configured
supports multiple queues.
</description>
</property>
<property>
<name>mapred.acls.enabled</name>
<value>false</value>
<description> Specifies whether ACLs should be checked
for authorization of users for doing various queue and job level operations.
ACLs are disabled by default. If enabled, access control checks are made by
JobTracker and TaskTracker when requests are made by users for queue
operations like submit job to a queue and kill a job in the queue and job
operations like viewing the job-details (See mapreduce.job.acl-view-job)
or for modifying the job (See mapreduce.job.acl-modify-job) using
Map/Reduce APIs, RPCs or via the console and web user interfaces.
</description>
</property>
<property>
<name>mapred.queue.default.state</name>
<value>RUNNING</value>
<description>
This values defines the state , default queue is in.
the values can be either "STOPPED" or "RUNNING"
This value can be changed at runtime.
</description>
</property>
<property>
<name>mapred.job.queue.name</name>
<value>default</value>
<description> Queue to which a job is submitted. This must match one of the
queues defined in mapred.queue.names for the system. Also, the ACL setup
for the queue must allow the current user to submit a job to the queue.
Before specifying a queue, ensure that the system is configured with
the queue, and access is allowed for submitting jobs to the queue.
</description>
</property>
<property>
<name>mapreduce.job.acl-modify-job</name>
<value> </value>
<description> Job specific access-control list for 'modifying' the job. It
is only used if authorization is enabled in Map/Reduce by setting the
configuration property mapred.acls.enabled to true.
This specifies the list of users and/or groups who can do modification
operations on the job. For specifying a list of users and groups the
format to use is "user1,user2 group1,group". If set to '*', it allows all
users/groups to modify this job. If set to ' '(i.e. space), it allows
none. This configuration is used to guard all the modifications with respect
to this job and takes care of all the following operations:
o killing this job
o killing a task of this job, failing a task of this job
o setting the priority of this job
Each of these operations are also protected by the per-queue level ACL
"acl-administer-jobs" configured via mapred-queues.xml. So a caller should
have the authorization to satisfy either the queue-level ACL or the
job-level ACL.
Irrespective of this ACL configuration, job-owner, the user who started the
cluster, cluster administrators configured via
mapreduce.cluster.administrators and queue administrators of the queue to
which this job is submitted to configured via
mapred.queue.queue-name.acl-administer-jobs in mapred-queue-acls.xml can
do all the modification operations on a job.
By default, nobody else besides job-owner, the user who started the cluster,
cluster administrators and queue administrators can perform modification
operations on a job.
</description>
</property>
<property>
<name>mapreduce.job.acl-view-job</name>
<value> </value>
<description> Job specific access-control list for 'viewing' the job. It is
only used if authorization is enabled in Map/Reduce by setting the
configuration property mapred.acls.enabled to true.
This specifies the list of users and/or groups who can view private details
about the job. For specifying a list of users and groups the
format to use is "user1,user2 group1,group". If set to '*', it allows all
users/groups to modify this job. If set to ' '(i.e. space), it allows
none. This configuration is used to guard some of the job-views and at
present only protects APIs that can return possibly sensitive information
of the job-owner like
o job-level counters
o task-level counters
o tasks' diagnostic information
o task-logs displayed on the TaskTracker web-UI and
o job.xml showed by the JobTracker's web-UI
Every other piece of information of jobs is still accessible by any other
user, for e.g., JobStatus, JobProfile, list of jobs in the queue, etc.
Irrespective of this ACL configuration, job-owner, the user who started the
cluster, cluster administrators configured via
mapreduce.cluster.administrators and queue administrators of the queue to
which this job is submitted to configured via
mapred.queue.queue-name.acl-administer-jobs in mapred-queue-acls.xml can do
all the view operations on a job.
By default, nobody else besides job-owner, the user who started the
cluster, cluster administrators and queue administrators can perform
view operations on a job.
</description>
</property>
<property>
<name>mapred.tasktracker.indexcache.mb</name>
<value>10</value>
<description> The maximum memory that a task tracker allows for the
index cache that is used when serving map outputs to reducers.
</description>
</property>
<property>
<name>mapred.combine.recordsBeforeProgress</name>
<value>10000</value>
<description> The number of records to process during combine output collection
before sending a progress notification to the TaskTracker.
</description>
</property>
<property>
<name>mapred.merge.recordsBeforeProgress</name>
<value>10000</value>
<description> The number of records to process during merge before
sending a progress notification to the TaskTracker.
</description>
</property>
<property>
<name>mapred.reduce.slowstart.completed.maps</name>
<value>0.05</value>
<description>Fraction of the number of maps in the job which should be
complete before reduces are scheduled for the job.
</description>
</property>
<property>
<name>mapred.task.tracker.task-controller</name>
<value>org.apache.hadoop.mapred.DefaultTaskController</value>
<description>TaskController which is used to launch and manage task execution
</description>
</property>
<property>
<name>mapreduce.tasktracker.group</name>
<value></value>
<description>Expert: Group to which TaskTracker belongs. If
LinuxTaskController is configured via mapreduce.tasktracker.taskcontroller,
the group owner of the task-controller binary should be same as this group.
</description>
</property>
<!-- Node health script variables -->
<property>
<name>mapred.healthChecker.script.path</name>
<value></value>
<description>Absolute path to the script which is
periodicallyrun by the node health monitoring service to determine if
the node is healthy or not. If the value of this key is empty or the
file does not exist in the location configured here, the node health
monitoring service is not started.</description>
</property>
<property>
<name>mapred.healthChecker.interval</name>
<value>60000</value>
<description>Frequency of the node health script to be run,
in milliseconds</description>
</property>
<property>
<name>mapred.healthChecker.script.timeout</name>
<value>600000</value>
<description>Time after node health script should be killed if
unresponsive and considered that the script has failed.</description>
</property>
<property>
<name>mapred.healthChecker.script.args</name>
<value></value>
<description>List of arguments which are to be passed to
node health script when it is being launched comma seperated.
</description>
</property>
<property>
<name>mapreduce.job.counters.limit</name>
<value>120</value>
<description>Limit on the number of counters allowed per job.
</description>
</property>
<!-- end of node health script variables -->
</configuration>
