| <html> |
| <body> |
| <table border="1"> |
| <tr> |
| <td>name</td><td>value</td><td>description</td> |
| </tr> |
| <tr> |
| <td><a name="hadoop.tmp.dir">hadoop.tmp.dir</a></td><td>/tmp/hadoop-${user.name}</td><td>A base for other temporary directories.</td> |
| </tr> |
| <tr> |
| <td><a name="hadoop.native.lib">hadoop.native.lib</a></td><td>true</td><td>Should native hadoop libraries, if present, be used.</td> |
| </tr> |
| <tr> |
| <td><a name="hadoop.logfile.size">hadoop.logfile.size</a></td><td>10000000</td><td>The max size of each log file</td> |
| </tr> |
| <tr> |
| <td><a name="hadoop.logfile.count">hadoop.logfile.count</a></td><td>10</td><td>The max number of log files</td> |
| </tr> |
| <tr> |
| <td><a name="hadoop.job.history.location">hadoop.job.history.location</a></td><td></td><td> 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. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="hadoop.job.history.user.location">hadoop.job.history.user.location</a></td><td></td><td> 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". |
| </td> |
| </tr> |
| <tr> |
| <td><a name="dfs.namenode.logging.level">dfs.namenode.logging.level</a></td><td>info</td><td>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".</td> |
| </tr> |
| <tr> |
| <td><a name="io.sort.factor">io.sort.factor</a></td><td>10</td><td>The number of streams to merge at once while sorting |
| files. This determines the number of open file handles.</td> |
| </tr> |
| <tr> |
| <td><a name="io.sort.mb">io.sort.mb</a></td><td>100</td><td>The total amount of buffer memory to use while sorting |
| files, in megabytes. By default, gives each merge stream 1MB, which |
| should minimize seeks.</td> |
| </tr> |
| <tr> |
| <td><a name="io.sort.record.percent">io.sort.record.percent</a></td><td>0.05</td><td>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</td> |
| </tr> |
| <tr> |
| <td><a name="io.sort.spill.percent">io.sort.spill.percent</a></td><td>0.80</td><td>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.</td> |
| </tr> |
| <tr> |
| <td><a name="io.file.buffer.size">io.file.buffer.size</a></td><td>4096</td><td>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.</td> |
| </tr> |
| <tr> |
| <td><a name="io.bytes.per.checksum">io.bytes.per.checksum</a></td><td>512</td><td>The number of bytes per checksum. Must not be larger than |
| io.file.buffer.size.</td> |
| </tr> |
| <tr> |
| <td><a name="io.skip.checksum.errors">io.skip.checksum.errors</a></td><td>false</td><td>If true, when a checksum error is encountered while |
| reading a sequence file, entries are skipped, instead of throwing an |
| exception.</td> |
| </tr> |
| <tr> |
| <td><a name="io.map.index.skip">io.map.index.skip</a></td><td>0</td><td>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.</td> |
| </tr> |
| <tr> |
| <td><a name="io.compression.codecs">io.compression.codecs</a></td><td>org.apache.hadoop.io.compress.DefaultCodec,org.apache.hadoop.io.compress.GzipCodec</td><td>A list of the compression codec classes that can be used |
| for compression/decompression.</td> |
| </tr> |
| <tr> |
| <td><a name="io.serializations">io.serializations</a></td><td>org.apache.hadoop.io.serializer.WritableSerialization</td><td>A list of serialization classes that can be used for |
| obtaining serializers and deserializers.</td> |
| </tr> |
| <tr> |
| <td><a name="fs.default.name">fs.default.name</a></td><td>file:///</td><td>The name of the default file system. A URI whose |
| scheme and authority determine the FileSystem implementation. The |
| uri's scheme determines the config property (fs.SCHEME.impl) naming |
| the FileSystem implementation class. The uri's authority is used to |
| determine the host, port, etc. for a filesystem.</td> |
| </tr> |
| <tr> |
| <td><a name="fs.trash.interval">fs.trash.interval</a></td><td>0</td><td>Number of minutes between trash checkpoints. |
| If zero, the trash feature is disabled. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="fs.file.impl">fs.file.impl</a></td><td>org.apache.hadoop.fs.LocalFileSystem</td><td>The FileSystem for file: uris.</td> |
| </tr> |
| <tr> |
| <td><a name="fs.hdfs.impl">fs.hdfs.impl</a></td><td>org.apache.hadoop.dfs.DistributedFileSystem</td><td>The FileSystem for hdfs: uris.</td> |
| </tr> |
| <tr> |
| <td><a name="fs.s3.impl">fs.s3.impl</a></td><td>org.apache.hadoop.fs.s3.S3FileSystem</td><td>The FileSystem for s3: uris.</td> |
| </tr> |
| <tr> |
| <td><a name="fs.s3n.impl">fs.s3n.impl</a></td><td>org.apache.hadoop.fs.s3native.NativeS3FileSystem</td><td>The FileSystem for s3n: (Native S3) uris.</td> |
| </tr> |
| <tr> |
| <td><a name="fs.kfs.impl">fs.kfs.impl</a></td><td>org.apache.hadoop.fs.kfs.KosmosFileSystem</td><td>The FileSystem for kfs: uris.</td> |
| </tr> |
| <tr> |
| <td><a name="fs.hftp.impl">fs.hftp.impl</a></td><td>org.apache.hadoop.dfs.HftpFileSystem</td><td></td> |
| </tr> |
| <tr> |
| <td><a name="fs.hsftp.impl">fs.hsftp.impl</a></td><td>org.apache.hadoop.dfs.HsftpFileSystem</td><td></td> |
| </tr> |
| <tr> |
| <td><a name="fs.ftp.impl">fs.ftp.impl</a></td><td>org.apache.hadoop.fs.ftp.FTPFileSystem</td><td>The FileSystem for ftp: uris.</td> |
| </tr> |
| <tr> |
| <td><a name="fs.ramfs.impl">fs.ramfs.impl</a></td><td>org.apache.hadoop.fs.InMemoryFileSystem</td><td>The FileSystem for ramfs: uris.</td> |
| </tr> |
| <tr> |
| <td><a name="fs.har.impl">fs.har.impl</a></td><td>org.apache.hadoop.fs.HarFileSystem</td><td>The filesystem for Hadoop archives. </td> |
| </tr> |
| <tr> |
| <td><a name="fs.inmemory.size.mb">fs.inmemory.size.mb</a></td><td>75</td><td>The size of the in-memory filsystem instance in MB</td> |
| </tr> |
| <tr> |
| <td><a name="fs.checkpoint.dir">fs.checkpoint.dir</a></td><td>${hadoop.tmp.dir}/dfs/namesecondary</td><td>Determines where on the local filesystem the DFS secondary |
| name node should store the temporary images and edits to merge. |
| If this is a comma-delimited list of directories then the image is |
| replicated in all of the directories for redundancy. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="fs.checkpoint.period">fs.checkpoint.period</a></td><td>3600</td><td>The number of seconds between two periodic checkpoints. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="fs.checkpoint.size">fs.checkpoint.size</a></td><td>67108864</td><td>The size of the current edit log (in bytes) that triggers |
| a periodic checkpoint even if the fs.checkpoint.period hasn't expired. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="dfs.secondary.http.address">dfs.secondary.http.address</a></td><td>0.0.0.0:50090</td><td> |
| The secondary namenode http server address and port. |
| If the port is 0 then the server will start on a free port. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="dfs.datanode.address">dfs.datanode.address</a></td><td>0.0.0.0:50010</td><td> |
| The address where the datanode server will listen to. |
| If the port is 0 then the server will start on a free port. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="dfs.datanode.http.address">dfs.datanode.http.address</a></td><td>0.0.0.0:50075</td><td> |
| The datanode http server address and port. |
| If the port is 0 then the server will start on a free port. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="dfs.datanode.ipc.address">dfs.datanode.ipc.address</a></td><td>0.0.0.0:50020</td><td> |
| The datanode ipc server address and port. |
| If the port is 0 then the server will start on a free port. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="dfs.datanode.handler.count">dfs.datanode.handler.count</a></td><td>3</td><td>The number of server threads for the datanode.</td> |
| </tr> |
| <tr> |
| <td><a name="dfs.http.address">dfs.http.address</a></td><td>0.0.0.0:50070</td><td> |
| 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. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="dfs.datanode.https.address">dfs.datanode.https.address</a></td><td>0.0.0.0:50475</td><td></td> |
| </tr> |
| <tr> |
| <td><a name="dfs.https.address">dfs.https.address</a></td><td>0.0.0.0:50470</td><td></td> |
| </tr> |
| <tr> |
| <td><a name="https.keystore.info.rsrc">https.keystore.info.rsrc</a></td><td>sslinfo.xml</td><td>The name of the resource from which ssl keystore information |
| will be extracted |
| </td> |
| </tr> |
| <tr> |
| <td><a name="dfs.datanode.dns.interface">dfs.datanode.dns.interface</a></td><td>default</td><td>The name of the Network Interface from which a data node should |
| report its IP address. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="dfs.datanode.dns.nameserver">dfs.datanode.dns.nameserver</a></td><td>default</td><td>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. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="dfs.replication.considerLoad">dfs.replication.considerLoad</a></td><td>true</td><td>Decide if chooseTarget considers the target's load or not |
| </td> |
| </tr> |
| <tr> |
| <td><a name="dfs.default.chunk.view.size">dfs.default.chunk.view.size</a></td><td>32768</td><td>The number of bytes to view for a file on the browser. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="dfs.datanode.du.reserved">dfs.datanode.du.reserved</a></td><td>0</td><td>Reserved space in bytes per volume. Always leave this much space free for non dfs use. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="dfs.datanode.du.pct">dfs.datanode.du.pct</a></td><td>0.98f</td><td>When calculating remaining space, only use this percentage of the real available space |
| </td> |
| </tr> |
| <tr> |
| <td><a name="dfs.name.dir">dfs.name.dir</a></td><td>${hadoop.tmp.dir}/dfs/name</td><td>Determines where on the local filesystem the DFS name node |
| should store the name table. If this is a comma-delimited list |
| of directories then the name table is replicated in all of the |
| directories, for redundancy. </td> |
| </tr> |
| <tr> |
| <td><a name="dfs.web.ugi">dfs.web.ugi</a></td><td>webuser,webgroup</td><td>The user account used by the web interface. |
| Syntax: USERNAME,GROUP1,GROUP2, ... |
| </td> |
| </tr> |
| <tr> |
| <td><a name="dfs.permissions">dfs.permissions</a></td><td>true</td><td> |
| If "true", enable permission checking in HDFS. |
| If "false", permission checking is turned off, |
| but all other behavior is unchanged. |
| Switching from one parameter value to the other does not change the mode, |
| owner or group of files or directories. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="dfs.permissions.supergroup">dfs.permissions.supergroup</a></td><td>supergroup</td><td>The name of the group of super-users.</td> |
| </tr> |
| <tr> |
| <td><a name="dfs.client.buffer.dir">dfs.client.buffer.dir</a></td><td>${hadoop.tmp.dir}/dfs/tmp</td><td>Determines where on the local filesystem an DFS client |
| should store its blocks before it sends them to the datanode. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="dfs.data.dir">dfs.data.dir</a></td><td>${hadoop.tmp.dir}/dfs/data</td><td>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. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="dfs.replication">dfs.replication</a></td><td>3</td><td>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. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="dfs.replication.max">dfs.replication.max</a></td><td>512</td><td>Maximal block replication. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="dfs.replication.min">dfs.replication.min</a></td><td>1</td><td>Minimal block replication. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="dfs.block.size">dfs.block.size</a></td><td>67108864</td><td>The default block size for new files.</td> |
| </tr> |
| <tr> |
| <td><a name="dfs.df.interval">dfs.df.interval</a></td><td>60000</td><td>Disk usage statistics refresh interval in msec.</td> |
| </tr> |
| <tr> |
| <td><a name="dfs.client.block.write.retries">dfs.client.block.write.retries</a></td><td>3</td><td>The number of retries for writing blocks to the data nodes, |
| before we signal failure to the application. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="dfs.blockreport.intervalMsec">dfs.blockreport.intervalMsec</a></td><td>3600000</td><td>Determines block reporting interval in milliseconds.</td> |
| </tr> |
| <tr> |
| <td><a name="dfs.blockreport.initialDelay">dfs.blockreport.initialDelay</a></td><td>0</td><td>Delay for first block report in seconds.</td> |
| </tr> |
| <tr> |
| <td><a name="dfs.heartbeat.interval">dfs.heartbeat.interval</a></td><td>3</td><td>Determines datanode heartbeat interval in seconds.</td> |
| </tr> |
| <tr> |
| <td><a name="dfs.namenode.handler.count">dfs.namenode.handler.count</a></td><td>10</td><td>The number of server threads for the namenode.</td> |
| </tr> |
| <tr> |
| <td><a name="dfs.safemode.threshold.pct">dfs.safemode.threshold.pct</a></td><td>0.999f</td><td> |
| Specifies the percentage of blocks that should satisfy |
| the minimal replication requirement defined by dfs.replication.min. |
| Values less than or equal to 0 mean not to start in safe mode. |
| Values greater than 1 will make safe mode permanent. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="dfs.safemode.extension">dfs.safemode.extension</a></td><td>30000</td><td> |
| Determines extension of safe mode in milliseconds |
| after the threshold level is reached. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="dfs.balance.bandwidthPerSec">dfs.balance.bandwidthPerSec</a></td><td>1048576</td><td> |
| Specifies the maximum amount of bandwidth that each datanode |
| can utilize for the balancing purpose in term of |
| the number of bytes per second. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="dfs.hosts">dfs.hosts</a></td><td></td><td>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.</td> |
| </tr> |
| <tr> |
| <td><a name="dfs.hosts.exclude">dfs.hosts.exclude</a></td><td></td><td>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.</td> |
| </tr> |
| <tr> |
| <td><a name="dfs.max.objects">dfs.max.objects</a></td><td>0</td><td>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. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="dfs.namenode.decommission.interval">dfs.namenode.decommission.interval</a></td><td>30</td><td>Namenode periodicity in seconds to check if decommission is complete.</td> |
| </tr> |
| <tr> |
| <td><a name="dfs.namenode.decommission.nodes.per.interval">dfs.namenode.decommission.nodes.per.interval</a></td><td>5</td><td>The number of nodes namenode checks if decommission is complete |
| in each dfs.namenode.decommission.interval.</td> |
| </tr> |
| <tr> |
| <td><a name="dfs.replication.interval">dfs.replication.interval</a></td><td>3</td><td>The periodicity in seconds with which the namenode computes repliaction work for datanodes. </td> |
| </tr> |
| <tr> |
| <td><a name="fs.s3.block.size">fs.s3.block.size</a></td><td>67108864</td><td>Block size to use when writing files to S3.</td> |
| </tr> |
| <tr> |
| <td><a name="fs.s3.buffer.dir">fs.s3.buffer.dir</a></td><td>${hadoop.tmp.dir}/s3</td><td>Determines where on the local filesystem the S3 filesystem |
| should store files before sending them to S3 |
| (or after retrieving them from S3). |
| </td> |
| </tr> |
| <tr> |
| <td><a name="fs.s3.maxRetries">fs.s3.maxRetries</a></td><td>4</td><td>The maximum number of retries for reading or writing files to S3, |
| before we signal failure to the application. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="fs.s3.sleepTimeSeconds">fs.s3.sleepTimeSeconds</a></td><td>10</td><td>The number of seconds to sleep between each S3 retry. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="mapred.job.tracker">mapred.job.tracker</a></td><td>local</td><td>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. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="mapred.job.tracker.http.address">mapred.job.tracker.http.address</a></td><td>0.0.0.0:50030</td><td> |
| 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. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="mapred.job.tracker.handler.count">mapred.job.tracker.handler.count</a></td><td>10</td><td> |
| The number of server threads for the JobTracker. This should be roughly |
| 4% of the number of tasktracker nodes. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="mapred.task.tracker.report.address">mapred.task.tracker.report.address</a></td><td>127.0.0.1:0</td><td>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.</td> |
| </tr> |
| <tr> |
| <td><a name="mapred.local.dir">mapred.local.dir</a></td><td>${hadoop.tmp.dir}/mapred/local</td><td>The local directory where MapReduce stores intermediate |
| data files. May be a comma-separated list of |
| directories on different devices in order to spread disk i/o. |
| Directories that do not exist are ignored. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="local.cache.size">local.cache.size</a></td><td>10737418240</td><td>The limit on the size of cache you want to keep, set by default |
| to 10GB. This will act as a soft limit on the cache directory for out of band data. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="mapred.system.dir">mapred.system.dir</a></td><td>${hadoop.tmp.dir}/mapred/system</td><td>The shared directory where MapReduce stores control files. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="mapred.temp.dir">mapred.temp.dir</a></td><td>${hadoop.tmp.dir}/mapred/temp</td><td>A shared directory for temporary files. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="mapred.local.dir.minspacestart">mapred.local.dir.minspacestart</a></td><td>0</td><td>If the space in mapred.local.dir drops under this, |
| do not ask for more tasks. |
| Value in bytes. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="mapred.local.dir.minspacekill">mapred.local.dir.minspacekill</a></td><td>0</td><td>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. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="mapred.tasktracker.expiry.interval">mapred.tasktracker.expiry.interval</a></td><td>600000</td><td>Expert: The time-interval, in miliseconds, after which |
| a tasktracker is declared 'lost' if it doesn't send heartbeats. |
| </td> |
| </tr> |
| <tr> |
| <<<<<<< .working |
| ======= |
| <td><a name="mapred.tasktracker.instrumentation">mapred.tasktracker.instrumentation</a></td><td>org.apache.hadoop.mapred.TaskTrackerMetricsInst</td><td>Expert: The instrumentation class to associate with each TaskTracker. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="mapred.tasktracker.vmem.reserved">mapred.tasktracker.vmem.reserved</a></td><td>-1</td><td>Configuration property to specify the amount of virtual memory |
| that has to be reserved by the TaskTracker for system usage (OS, TT etc). |
| The reserved virtual memory should be a part of the total virtual memory |
| available on the TaskTracker. |
| |
| The reserved virtual memory and the total virtual memory values are |
| reported by the TaskTracker as part of heart-beat so that they can |
| considered by a scheduler. Please refer to the documentation of the |
| configured scheduler to see how this property is used. |
| |
| These two values are also used by a TaskTracker for tracking tasks' memory |
| usage. Memory management functionality on a TaskTracker is disabled if this |
| property is set to -1, if it more than the total virtual memory on the |
| tasktracker, or if either of the values is negative. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="mapred.tasktracker.pmem.reserved">mapred.tasktracker.pmem.reserved</a></td><td>-1</td><td>Configuration property to specify the amount of physical memory |
| that has to be reserved by the TaskTracker for system usage (OS, TT etc). |
| The reserved physical memory should be a part of the total physical memory |
| available on the TaskTracker. |
| |
| The reserved physical memory and the total physical memory values are |
| reported by the TaskTracker as part of heart-beat so that they can |
| considered by a scheduler. Please refer to the documentation of the |
| configured scheduler to see how this property is used. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="mapred.task.default.maxvmem">mapred.task.default.maxvmem</a></td><td>-1</td><td> |
| Cluster-wide configuration in bytes to be set by the administrators that |
| provides default amount of maximum virtual memory for job's tasks. This has |
| to be set on both the JobTracker node for the sake of scheduling decisions |
| and on the TaskTracker nodes for the sake of memory management. |
| |
| If a job doesn't specify its virtual memory requirement by setting |
| mapred.task.maxvmem to -1, tasks are assured a memory limit set |
| to this property. This property is set to -1 by default. |
| |
| This value should in general be less than the cluster-wide |
| configuration mapred.task.limit.maxvmem. If not or if it is not set, |
| TaskTracker's memory management will be disabled and a scheduler's memory |
| based scheduling decisions may be affected. Please refer to the |
| documentation of the configured scheduler to see how this property is used. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="mapred.task.limit.maxvmem">mapred.task.limit.maxvmem</a></td><td>-1</td><td> |
| Cluster-wide configuration in bytes to be set by the site administrators |
| that provides an upper limit on the maximum virtual memory that can be |
| specified by a job via mapred.task.maxvmem. This has to be set on both the |
| JobTracker node for the sake of scheduling decisions and on the TaskTracker |
| nodes for the sake of memory management. |
| |
| The job configuration mapred.task.maxvmem should not be more than this |
| value, otherwise depending on the scheduler being configured, the job may |
| be rejected or the job configuration may just be ignored. Please refer to |
| the documentation of the configured scheduler to see how this property is |
| used. |
| |
| If it is not set a TaskTracker, TaskTracker's memory management will be |
| disabled. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="mapred.task.maxvmem">mapred.task.maxvmem</a></td><td>-1</td><td> |
| The maximum amount of virtual memory any task of a job will use, in bytes. |
| |
| This value will be used by TaskTrackers for monitoring the memory usage of |
| tasks of this jobs. If a TaskTracker's memory management functionality is |
| enabled, each task of this job will be allowed to use a maximum virtual |
| memory specified by this property. If the task's memory usage goes over |
| this value, the task will be failed by the TT. If not set, the |
| cluster-wide configuration mapred.task.default.maxvmem is used as the |
| default value for memory requirements. If this property cascaded with |
| mapred.task.default.maxvmem becomes equal to -1, the job's tasks will |
| not be assured any particular amount of virtual memory and may be killed by |
| a TT that intends to control the total memory usage of the tasks via memory |
| management functionality. If the memory management functionality is |
| disabled on a TT, this value is ignored. |
| |
| This value should not be more than the cluster-wide configuration |
| mapred.task.limit.maxvmem. |
| |
| This value may be used by schedulers that support scheduling based on job's |
| memory requirements. Please refer to the documentation of the scheduler |
| being configured to see if it does memory based scheduling and if it does, |
| how this property is used by that scheduler. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="mapred.task.maxpmem">mapred.task.maxpmem</a></td><td>-1</td><td> |
| The maximum amount of physical memory any task of a job will use in bytes. |
| |
| This value may be used by schedulers that support scheduling based on job's |
| memory requirements. In general, a task of this job will be scheduled on a |
| TaskTracker, only if the amount of physical memory still unoccupied on the |
| TaskTracker is greater than or equal to this value. Different schedulers can |
| take different decisions, some might just ignore this value. Please refer to |
| the documentation of the scheduler being configured to see if it does |
| memory based scheduling and if it does, how this variable is used by that |
| scheduler. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="mapred.tasktracker.memory_calculator_plugin">mapred.tasktracker.memory_calculator_plugin</a></td><td></td><td> |
| Name of the class whose instance will be used to query memory information |
| on the tasktracker. |
| |
| The class must be an instance of |
| org.apache.hadoop.util.MemoryCalculatorPlugin. If the value is null, the |
| tasktracker attempts to use a class appropriate to the platform. |
| Currently, the only platform supported is Linux. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="mapred.tasktracker.taskmemorymanager.monitoring-interval">mapred.tasktracker.taskmemorymanager.monitoring-interval</a></td><td>5000</td><td>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. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="mapred.tasktracker.procfsbasedprocesstree.sleeptime-before-sigkill">mapred.tasktracker.procfsbasedprocesstree.sleeptime-before-sigkill</a></td><td>5000</td><td>The time, in milliseconds, the tasktracker waits for sending a |
| SIGKILL to a process that has overrun memory limits, after it has been sent |
| a SIGTERM. Used only if tasks' memory management is enabled via |
| mapred.tasktracker.tasks.maxmemory.</td> |
| </tr> |
| <tr> |
| >>>>>>> .merge-right.r725504 |
| <td><a name="mapred.map.tasks">mapred.map.tasks</a></td><td>2</td><td>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". |
| </td> |
| </tr> |
| <tr> |
| <td><a name="mapred.reduce.tasks">mapred.reduce.tasks</a></td><td>1</td><td>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". |
| </td> |
| </tr> |
| <tr> |
| <td><a name="mapred.map.max.attempts">mapred.map.max.attempts</a></td><td>4</td><td>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. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="mapred.reduce.max.attempts">mapred.reduce.max.attempts</a></td><td>4</td><td>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. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="mapred.reduce.parallel.copies">mapred.reduce.parallel.copies</a></td><td>5</td><td>The default number of parallel transfers run by reduce |
| during the copy(shuffle) phase. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="mapred.reduce.copy.backoff">mapred.reduce.copy.backoff</a></td><td>300</td><td>The maximum amount of time (in seconds) a reducer spends on |
| fetching one map output before declaring it as failed. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="mapred.task.timeout">mapred.task.timeout</a></td><td>600000</td><td>The number of milliseconds before a task will be |
| terminated if it neither reads an input, writes an output, nor |
| updates its status string. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="mapred.tasktracker.map.tasks.maximum">mapred.tasktracker.map.tasks.maximum</a></td><td>2</td><td>The maximum number of map tasks that will be run |
| simultaneously by a task tracker. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="mapred.tasktracker.reduce.tasks.maximum">mapred.tasktracker.reduce.tasks.maximum</a></td><td>2</td><td>The maximum number of reduce tasks that will be run |
| simultaneously by a task tracker. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="mapred.jobtracker.completeuserjobs.maximum">mapred.jobtracker.completeuserjobs.maximum</a></td><td>100</td><td>The maximum number of complete jobs per user to keep around before delegating them to the job history. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="mapred.child.java.opts">mapred.child.java.opts</a></td><td>-Xmx200m</td><td>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. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="mapred.child.ulimit">mapred.child.ulimit</a></td><td></td><td>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. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="mapred.child.tmp">mapred.child.tmp</a></td><td>./tmp</td><td> 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' |
| </td> |
| </tr> |
| <tr> |
| <td><a name="mapred.inmem.merge.threshold">mapred.inmem.merge.threshold</a></td><td>1000</td><td>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. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="mapred.map.tasks.speculative.execution">mapred.map.tasks.speculative.execution</a></td><td>true</td><td>If true, then multiple instances of some map tasks |
| may be executed in parallel.</td> |
| </tr> |
| <tr> |
| <td><a name="mapred.reduce.tasks.speculative.execution">mapred.reduce.tasks.speculative.execution</a></td><td>true</td><td>If true, then multiple instances of some reduce tasks |
| may be executed in parallel.</td> |
| </tr> |
| <tr> |
| <td><a name="mapred.min.split.size">mapred.min.split.size</a></td><td>0</td><td>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.</td> |
| </tr> |
| <tr> |
| <td><a name="mapred.submit.replication">mapred.submit.replication</a></td><td>10</td><td>The replication level for submitted job files. This |
| should be around the square root of the number of nodes. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="mapred.tasktracker.dns.interface">mapred.tasktracker.dns.interface</a></td><td>default</td><td>The name of the Network Interface from which a task |
| tracker should report its IP address. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="mapred.tasktracker.dns.nameserver">mapred.tasktracker.dns.nameserver</a></td><td>default</td><td>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. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="tasktracker.http.threads">tasktracker.http.threads</a></td><td>40</td><td>The number of worker threads that for the http server. This is |
| used for map output fetching |
| </td> |
| </tr> |
| <tr> |
| <td><a name="mapred.task.tracker.http.address">mapred.task.tracker.http.address</a></td><td>0.0.0.0:50060</td><td> |
| The task tracker http server address and port. |
| If the port is 0 then the server will start on a free port. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="keep.failed.task.files">keep.failed.task.files</a></td><td>false</td><td>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.</td> |
| </tr> |
| <tr> |
| <td><a name="mapred.output.compress">mapred.output.compress</a></td><td>false</td><td>Should the job outputs be compressed? |
| </td> |
| </tr> |
| <tr> |
| <td><a name="mapred.output.compression.type">mapred.output.compression.type</a></td><td>RECORD</td><td>If the job outputs are to compressed as SequenceFiles, how should |
| they be compressed? Should be one of NONE, RECORD or BLOCK. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="mapred.output.compression.codec">mapred.output.compression.codec</a></td><td>org.apache.hadoop.io.compress.DefaultCodec</td><td>If the job outputs are compressed, how should they be compressed? |
| </td> |
| </tr> |
| <tr> |
| <td><a name="mapred.compress.map.output">mapred.compress.map.output</a></td><td>false</td><td>Should the outputs of the maps be compressed before being |
| sent across the network. Uses SequenceFile compression. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="mapred.map.output.compression.codec">mapred.map.output.compression.codec</a></td><td>org.apache.hadoop.io.compress.DefaultCodec</td><td>If the map outputs are compressed, how should they be |
| compressed? |
| </td> |
| </tr> |
| <tr> |
| <td><a name="io.seqfile.compress.blocksize">io.seqfile.compress.blocksize</a></td><td>1000000</td><td>The minimum block size for compression in block compressed |
| SequenceFiles. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="io.seqfile.lazydecompress">io.seqfile.lazydecompress</a></td><td>true</td><td>Should values of block-compressed SequenceFiles be decompressed |
| only when necessary. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="io.seqfile.sorter.recordlimit">io.seqfile.sorter.recordlimit</a></td><td>1000000</td><td>The limit on number of records to be kept in memory in a spill |
| in SequenceFiles.Sorter |
| </td> |
| </tr> |
| <tr> |
| <td><a name="map.sort.class">map.sort.class</a></td><td>org.apache.hadoop.util.QuickSort</td><td>The default sort class for sorting keys. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="mapred.userlog.limit.kb">mapred.userlog.limit.kb</a></td><td>0</td><td>The maximum size of user-logs of each task in KB. 0 disables the cap. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="mapred.userlog.retain.hours">mapred.userlog.retain.hours</a></td><td>24</td><td>The maximum time, in hours, for which the user-logs are to be |
| retained. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="mapred.hosts">mapred.hosts</a></td><td></td><td>Names a file that contains the list of nodes that may |
| connect to the jobtracker. If the value is empty, all hosts are |
| permitted.</td> |
| </tr> |
| <tr> |
| <td><a name="mapred.hosts.exclude">mapred.hosts.exclude</a></td><td></td><td>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.</td> |
| </tr> |
| <tr> |
| <td><a name="mapred.max.tracker.blacklists">mapred.max.tracker.blacklists</a></td><td>4</td><td>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. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="mapred.max.tracker.failures">mapred.max.tracker.failures</a></td><td>4</td><td>The number of task-failures on a tasktracker of a given job |
| after which new tasks of that job aren't assigned to it. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="jobclient.output.filter">jobclient.output.filter</a></td><td>FAILED</td><td>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. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="mapred.job.tracker.persist.jobstatus.active">mapred.job.tracker.persist.jobstatus.active</a></td><td>false</td><td>Indicates if persistency of job status information is |
| active or not. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="mapred.job.tracker.persist.jobstatus.hours">mapred.job.tracker.persist.jobstatus.hours</a></td><td>0</td><td>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. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="mapred.job.tracker.persist.jobstatus.dir">mapred.job.tracker.persist.jobstatus.dir</a></td><td>/jobtracker/jobsInfo</td><td>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. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="mapred.task.profile">mapred.task.profile</a></td><td>false</td><td>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.</td> |
| </tr> |
| <tr> |
| <td><a name="mapred.task.profile.maps">mapred.task.profile.maps</a></td><td>0-2</td><td> To set the ranges of map tasks to profile. |
| mapred.task.profile has to be set to true for the value to be accounted. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="mapred.task.profile.reduces">mapred.task.profile.reduces</a></td><td>0-2</td><td> To set the ranges of reduce tasks to profile. |
| mapred.task.profile has to be set to true for the value to be accounted. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="mapred.line.input.format.linespermap">mapred.line.input.format.linespermap</a></td><td>1</td><td> Number of lines per split in NLineInputFormat. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="ipc.client.idlethreshold">ipc.client.idlethreshold</a></td><td>4000</td><td>Defines the threshold number of connections after which |
| connections will be inspected for idleness. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="ipc.client.kill.max">ipc.client.kill.max</a></td><td>10</td><td>Defines the maximum number of clients to disconnect in one go. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="ipc.client.connection.maxidletime">ipc.client.connection.maxidletime</a></td><td>10000</td><td>The maximum time in msec after which a client will bring down the |
| connection to the server. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="ipc.client.connect.max.retries">ipc.client.connect.max.retries</a></td><td>10</td><td>Indicates the number of retries a client will make to establish |
| a server connection. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="ipc.server.listen.queue.size">ipc.server.listen.queue.size</a></td><td>128</td><td>Indicates the length of the listen queue for servers accepting |
| client connections. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="ipc.server.tcpnodelay">ipc.server.tcpnodelay</a></td><td>false</td><td>Turn on/off Nagle's algorithm for the TCP socket connection on |
| the server. Setting to true disables the algorithm and may decrease latency |
| with a cost of more/smaller packets. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="ipc.client.tcpnodelay">ipc.client.tcpnodelay</a></td><td>false</td><td>Turn on/off Nagle's algorithm for the TCP socket connection on |
| the client. Setting to true disables the algorithm and may decrease latency |
| with a cost of more/smaller packets. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="job.end.retry.attempts">job.end.retry.attempts</a></td><td>0</td><td>Indicates how many times hadoop should attempt to contact the |
| notification URL </td> |
| </tr> |
| <tr> |
| <td><a name="job.end.retry.interval">job.end.retry.interval</a></td><td>30000</td><td>Indicates time in milliseconds between notification URL retry |
| calls</td> |
| </tr> |
| <tr> |
| <td><a name="webinterface.private.actions">webinterface.private.actions</a></td><td>false</td><td> If set to true, the web interfaces of JT and NN may contain |
| actions, such as kill job, delete file, etc., that should |
| not be exposed to public. Enable this option if the interfaces |
| are only reachable by those who have the right authorization. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="hadoop.rpc.socket.factory.class.default">hadoop.rpc.socket.factory.class.default</a></td><td>org.apache.hadoop.net.StandardSocketFactory</td><td> Default SocketFactory to use. This parameter is expected to be |
| formatted as "package.FactoryClassName". |
| </td> |
| </tr> |
| <tr> |
| <td><a name="hadoop.rpc.socket.factory.class.ClientProtocol">hadoop.rpc.socket.factory.class.ClientProtocol</a></td><td></td><td> SocketFactory to use to connect to a DFS. If null or empty, use |
| hadoop.rpc.socket.class.default. This socket factory is also used by |
| DFSClient to create sockets to DataNodes. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="hadoop.rpc.socket.factory.class.JobSubmissionProtocol">hadoop.rpc.socket.factory.class.JobSubmissionProtocol</a></td><td></td><td> SocketFactory to use to connect to a Map/Reduce master |
| (JobTracker). If null or empty, then use hadoop.rpc.socket.class.default. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="hadoop.socks.server">hadoop.socks.server</a></td><td></td><td> Address (host:port) of the SOCKS server to be used by the |
| SocksSocketFactory. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="topology.node.switch.mapping.impl">topology.node.switch.mapping.impl</a></td><td>org.apache.hadoop.net.ScriptBasedMapping</td><td> The default implementation of the DNSToSwitchMapping. It |
| invokes a script specified in topology.script.file.name to resolve |
| node names. If the value for topology.script.file.name is not set, the |
| default value of DEFAULT_RACK is returned for all node names. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="topology.script.file.name">topology.script.file.name</a></td><td></td><td> The script name that should be invoked to resolve DNS names to |
| NetworkTopology names. Example: the script would take host.foo.bar as an |
| argument, and return /rack1 as the output. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="topology.script.number.args">topology.script.number.args</a></td><td>20</td><td> The max number of args that the script configured with |
| topology.script.file.name should be run with. Each arg is an |
| IP address. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="mapred.task.cache.levels">mapred.task.cache.levels</a></td><td>2</td><td> 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. |
| </td> |
| </tr> |
| <tr> |
| <td><a name="mapred.merge.recordsBeforeProgress">mapred.merge.recordsBeforeProgress</a></td><td>10000</td><td> The number of records to process during merge before |
| sending a progress notification to the TaskTracker. |
| </td> |
| </tr> |
| </table> |
| </body> |
| </html> |