|
|
@@ -2,11 +2,55 @@
|
|
|
<?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. -->
|
|
|
+<!-- wish to modify from this file into hadoop-site.xml and change them -->
|
|
|
+<!-- there. If hadoop-site.xml does not already exist, create it. -->
|
|
|
|
|
|
<configuration>
|
|
|
|
|
|
+<!--- global properties -->
|
|
|
+
|
|
|
+<property>
|
|
|
+ <name>hadoop.tmp.dir</name>
|
|
|
+ <value>/tmp/hadoop-${user.name}</value>
|
|
|
+ <description>A base for other temporary directories.</description>
|
|
|
+</property>
|
|
|
+
|
|
|
+<property>
|
|
|
+ <name>hadoop.native.lib</name>
|
|
|
+ <value>true</value>
|
|
|
+ <description>Should native hadoop libraries, if present, be used.</description>
|
|
|
+</property>
|
|
|
+
|
|
|
+<property>
|
|
|
+ <name>hadoop.http.filter.initializers</name>
|
|
|
+ <value></value>
|
|
|
+ <description>A comma separated list of class names. Each class in the list
|
|
|
+ must extend org.apache.hadoop.http.FilterInitializer. The corresponding
|
|
|
+ Filter will be initialized. Then, the Filter will be applied to all user
|
|
|
+ facing jsp and servlet web pages. The ordering of the list defines the
|
|
|
+ ordering of the filters.</description>
|
|
|
+</property>
|
|
|
+
|
|
|
+<property>
|
|
|
+ <name>hadoop.security.authorization</name>
|
|
|
+ <value>false</value>
|
|
|
+ <description>Is service-level authorization enabled?</description>
|
|
|
+</property>
|
|
|
+
|
|
|
+<!--- logging properties -->
|
|
|
+
|
|
|
+<property>
|
|
|
+ <name>hadoop.logfile.size</name>
|
|
|
+ <value>10000000</value>
|
|
|
+ <description>The max size of each log file</description>
|
|
|
+</property>
|
|
|
+
|
|
|
+<property>
|
|
|
+ <name>hadoop.logfile.count</name>
|
|
|
+ <value>10</value>
|
|
|
+ <description>The max number of log files</description>
|
|
|
+</property>
|
|
|
+
|
|
|
<property>
|
|
|
<name>hadoop.job.history.location</name>
|
|
|
<value></value>
|
|
|
@@ -26,6 +70,14 @@
|
|
|
</description>
|
|
|
</property>
|
|
|
|
|
|
+<property>
|
|
|
+ <name>dfs.namenode.logging.level</name>
|
|
|
+ <value>info</value>
|
|
|
+ <description>The logging level for dfs namenode. Other values are "dir"(trac
|
|
|
+e namespace mutations), "block"(trace block under/over replications and block
|
|
|
+creations/deletions), or "all".</description>
|
|
|
+</property>
|
|
|
+
|
|
|
<!-- i/o properties -->
|
|
|
|
|
|
<property>
|
|
|
@@ -61,6 +113,30 @@
|
|
|
the spill. A value less than 0.5 is not recommended.</description>
|
|
|
</property>
|
|
|
|
|
|
+<property>
|
|
|
+ <name>io.file.buffer.size</name>
|
|
|
+ <value>4096</value>
|
|
|
+ <description>The size of buffer for use in sequence files.
|
|
|
+ The size of this buffer should probably be a multiple of hardware
|
|
|
+ page size (4096 on Intel x86), and it determines how much data is
|
|
|
+ buffered during read and write operations.</description>
|
|
|
+</property>
|
|
|
+
|
|
|
+<property>
|
|
|
+ <name>io.bytes.per.checksum</name>
|
|
|
+ <value>512</value>
|
|
|
+ <description>The number of bytes per checksum. Must not be larger than
|
|
|
+ io.file.buffer.size.</description>
|
|
|
+</property>
|
|
|
+
|
|
|
+<property>
|
|
|
+ <name>io.skip.checksum.errors</name>
|
|
|
+ <value>false</value>
|
|
|
+ <description>If true, when a checksum error is encountered while
|
|
|
+ reading a sequence file, entries are skipped, instead of throwing an
|
|
|
+ exception.</description>
|
|
|
+</property>
|
|
|
+
|
|
|
<property>
|
|
|
<name>io.map.index.skip</name>
|
|
|
<value>0</value>
|
|
|
@@ -69,6 +145,502 @@
|
|
|
facilitate opening large map files using less memory.</description>
|
|
|
</property>
|
|
|
|
|
|
+<property>
|
|
|
+ <name>io.compression.codecs</name>
|
|
|
+ <value>org.apache.hadoop.io.compress.DefaultCodec,org.apache.hadoop.io.compress.GzipCodec,org.apache.hadoop.io.compress.BZip2Codec</value>
|
|
|
+ <description>A list of the compression codec classes that can be used
|
|
|
+ for compression/decompression.</description>
|
|
|
+</property>
|
|
|
+
|
|
|
+<property>
|
|
|
+ <name>io.serializations</name>
|
|
|
+ <value>org.apache.hadoop.io.serializer.WritableSerialization</value>
|
|
|
+ <description>A list of serialization classes that can be used for
|
|
|
+ obtaining serializers and deserializers.</description>
|
|
|
+</property>
|
|
|
+
|
|
|
+<!-- file system properties -->
|
|
|
+
|
|
|
+<property>
|
|
|
+ <name>fs.default.name</name>
|
|
|
+ <value>file:///</value>
|
|
|
+ <description>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.</description>
|
|
|
+</property>
|
|
|
+
|
|
|
+<property>
|
|
|
+ <name>fs.trash.interval</name>
|
|
|
+ <value>0</value>
|
|
|
+ <description>Number of minutes between trash checkpoints.
|
|
|
+ If zero, the trash feature is disabled.
|
|
|
+ </description>
|
|
|
+</property>
|
|
|
+
|
|
|
+<property>
|
|
|
+ <name>fs.file.impl</name>
|
|
|
+ <value>org.apache.hadoop.fs.LocalFileSystem</value>
|
|
|
+ <description>The FileSystem for file: uris.</description>
|
|
|
+</property>
|
|
|
+
|
|
|
+<property>
|
|
|
+ <name>fs.hdfs.impl</name>
|
|
|
+ <value>org.apache.hadoop.hdfs.DistributedFileSystem</value>
|
|
|
+ <description>The FileSystem for hdfs: uris.</description>
|
|
|
+</property>
|
|
|
+
|
|
|
+<property>
|
|
|
+ <name>fs.s3.impl</name>
|
|
|
+ <value>org.apache.hadoop.fs.s3.S3FileSystem</value>
|
|
|
+ <description>The FileSystem for s3: uris.</description>
|
|
|
+</property>
|
|
|
+
|
|
|
+<property>
|
|
|
+ <name>fs.s3n.impl</name>
|
|
|
+ <value>org.apache.hadoop.fs.s3native.NativeS3FileSystem</value>
|
|
|
+ <description>The FileSystem for s3n: (Native S3) uris.</description>
|
|
|
+</property>
|
|
|
+
|
|
|
+<property>
|
|
|
+ <name>fs.kfs.impl</name>
|
|
|
+ <value>org.apache.hadoop.fs.kfs.KosmosFileSystem</value>
|
|
|
+ <description>The FileSystem for kfs: uris.</description>
|
|
|
+</property>
|
|
|
+
|
|
|
+<property>
|
|
|
+ <name>fs.hftp.impl</name>
|
|
|
+ <value>org.apache.hadoop.hdfs.HftpFileSystem</value>
|
|
|
+</property>
|
|
|
+
|
|
|
+<property>
|
|
|
+ <name>fs.hsftp.impl</name>
|
|
|
+ <value>org.apache.hadoop.hdfs.HsftpFileSystem</value>
|
|
|
+</property>
|
|
|
+
|
|
|
+<property>
|
|
|
+ <name>fs.ftp.impl</name>
|
|
|
+ <value>org.apache.hadoop.fs.ftp.FTPFileSystem</value>
|
|
|
+ <description>The FileSystem for ftp: uris.</description>
|
|
|
+</property>
|
|
|
+
|
|
|
+<property>
|
|
|
+ <name>fs.ramfs.impl</name>
|
|
|
+ <value>org.apache.hadoop.fs.InMemoryFileSystem</value>
|
|
|
+ <description>The FileSystem for ramfs: uris.</description>
|
|
|
+</property>
|
|
|
+
|
|
|
+<property>
|
|
|
+ <name>fs.har.impl</name>
|
|
|
+ <value>org.apache.hadoop.fs.HarFileSystem</value>
|
|
|
+ <description>The filesystem for Hadoop archives. </description>
|
|
|
+</property>
|
|
|
+
|
|
|
+<property>
|
|
|
+ <name>fs.checkpoint.dir</name>
|
|
|
+ <value>${hadoop.tmp.dir}/dfs/namesecondary</value>
|
|
|
+ <description>Determines where on the local filesystem the DFS secondary
|
|
|
+ name node should store the temporary images to merge.
|
|
|
+ If this is a comma-delimited list of directories then the image is
|
|
|
+ replicated in all of the directories for redundancy.
|
|
|
+ </description>
|
|
|
+</property>
|
|
|
+
|
|
|
+<property>
|
|
|
+ <name>fs.checkpoint.edits.dir</name>
|
|
|
+ <value>${fs.checkpoint.dir}</value>
|
|
|
+ <description>Determines where on the local filesystem the DFS secondary
|
|
|
+ name node should store the temporary edits to merge.
|
|
|
+ If this is a comma-delimited list of directoires then teh edits is
|
|
|
+ replicated in all of the directoires for redundancy.
|
|
|
+ Default value is same as fs.checkpoint.dir
|
|
|
+ </description>
|
|
|
+</property>
|
|
|
+
|
|
|
+<property>
|
|
|
+ <name>fs.checkpoint.period</name>
|
|
|
+ <value>3600</value>
|
|
|
+ <description>The number of seconds between two periodic checkpoints.
|
|
|
+ </description>
|
|
|
+</property>
|
|
|
+
|
|
|
+<property>
|
|
|
+ <name>fs.checkpoint.size</name>
|
|
|
+ <value>67108864</value>
|
|
|
+ <description>The size of the current edit log (in bytes) that triggers
|
|
|
+ a periodic checkpoint even if the fs.checkpoint.period hasn't expired.
|
|
|
+ </description>
|
|
|
+</property>
|
|
|
+
|
|
|
+<property>
|
|
|
+ <name>dfs.secondary.http.address</name>
|
|
|
+ <value>0.0.0.0:50090</value>
|
|
|
+ <description>
|
|
|
+ The secondary namenode http server address and port.
|
|
|
+ If the port is 0 then the server will start on a free port.
|
|
|
+ </description>
|
|
|
+</property>
|
|
|
+
|
|
|
+<property>
|
|
|
+ <name>dfs.datanode.address</name>
|
|
|
+ <value>0.0.0.0:50010</value>
|
|
|
+ <description>
|
|
|
+ The address where the datanode server will listen to.
|
|
|
+ If the port is 0 then the server will start on a free port.
|
|
|
+ </description>
|
|
|
+</property>
|
|
|
+
|
|
|
+<property>
|
|
|
+ <name>dfs.datanode.http.address</name>
|
|
|
+ <value>0.0.0.0:50075</value>
|
|
|
+ <description>
|
|
|
+ The datanode http server address and port.
|
|
|
+ If the port is 0 then the server will start on a free port.
|
|
|
+ </description>
|
|
|
+</property>
|
|
|
+
|
|
|
+<property>
|
|
|
+ <name>dfs.datanode.ipc.address</name>
|
|
|
+ <value>0.0.0.0:50020</value>
|
|
|
+ <description>
|
|
|
+ The datanode ipc server address and port.
|
|
|
+ If the port is 0 then the server will start on a free port.
|
|
|
+ </description>
|
|
|
+</property>
|
|
|
+
|
|
|
+<property>
|
|
|
+ <name>dfs.datanode.handler.count</name>
|
|
|
+ <value>3</value>
|
|
|
+ <description>The number of server threads for the datanode.</description>
|
|
|
+</property>
|
|
|
+
|
|
|
+<property>
|
|
|
+ <name>dfs.http.address</name>
|
|
|
+ <value>0.0.0.0:50070</value>
|
|
|
+ <description>
|
|
|
+ The address and the base port where the dfs namenode web ui will listen on.
|
|
|
+ If the port is 0 then the server will start on a free port.
|
|
|
+ </description>
|
|
|
+</property>
|
|
|
+
|
|
|
+<property>
|
|
|
+ <name>dfs.https.enable</name>
|
|
|
+ <value>false</value>
|
|
|
+ <description>Decide if HTTPS(SSL) is supported on HDFS
|
|
|
+ </description>
|
|
|
+</property>
|
|
|
+
|
|
|
+<property>
|
|
|
+ <name>dfs.https.need.client.auth</name>
|
|
|
+ <value>false</value>
|
|
|
+ <description>Whether SSL client certificate authentication is required
|
|
|
+ </description>
|
|
|
+</property>
|
|
|
+
|
|
|
+<property>
|
|
|
+ <name>dfs.https.server.keystore.resource</name>
|
|
|
+ <value>ssl-server.xml</value>
|
|
|
+ <description>Resource file from which ssl server keystore
|
|
|
+ information will be extracted
|
|
|
+ </description>
|
|
|
+</property>
|
|
|
+
|
|
|
+<property>
|
|
|
+ <name>dfs.https.client.keystore.resource</name>
|
|
|
+ <value>ssl-client.xml</value>
|
|
|
+ <description>Resource file from which ssl client keystore
|
|
|
+ information will be extracted
|
|
|
+ </description>
|
|
|
+</property>
|
|
|
+
|
|
|
+<property>
|
|
|
+ <name>dfs.datanode.https.address</name>
|
|
|
+ <value>0.0.0.0:50475</value>
|
|
|
+</property>
|
|
|
+
|
|
|
+<property>
|
|
|
+ <name>dfs.https.address</name>
|
|
|
+ <value>0.0.0.0:50470</value>
|
|
|
+</property>
|
|
|
+
|
|
|
+ <property>
|
|
|
+ <name>dfs.datanode.dns.interface</name>
|
|
|
+ <value>default</value>
|
|
|
+ <description>The name of the Network Interface from which a data node should
|
|
|
+ report its IP address.
|
|
|
+ </description>
|
|
|
+ </property>
|
|
|
+
|
|
|
+<property>
|
|
|
+ <name>dfs.datanode.dns.nameserver</name>
|
|
|
+ <value>default</value>
|
|
|
+ <description>The host name or IP address of the name server (DNS)
|
|
|
+ which a DataNode should use to determine the host name used by the
|
|
|
+ NameNode for communication and display purposes.
|
|
|
+ </description>
|
|
|
+ </property>
|
|
|
+
|
|
|
+<property>
|
|
|
+ <name>dfs.replication.considerLoad</name>
|
|
|
+ <value>true</value>
|
|
|
+ <description>Decide if chooseTarget considers the target's load or not
|
|
|
+ </description>
|
|
|
+</property>
|
|
|
+<property>
|
|
|
+ <name>dfs.default.chunk.view.size</name>
|
|
|
+ <value>32768</value>
|
|
|
+ <description>The number of bytes to view for a file on the browser.
|
|
|
+ </description>
|
|
|
+</property>
|
|
|
+
|
|
|
+<property>
|
|
|
+ <name>dfs.datanode.du.reserved</name>
|
|
|
+ <value>0</value>
|
|
|
+ <description>Reserved space in bytes per volume. Always leave this much space free for non dfs use.
|
|
|
+ </description>
|
|
|
+</property>
|
|
|
+
|
|
|
+<property>
|
|
|
+ <name>dfs.name.dir</name>
|
|
|
+ <value>${hadoop.tmp.dir}/dfs/name</value>
|
|
|
+ <description>Determines where on the local filesystem the DFS name node
|
|
|
+ should store the name table(fsimage). If this is a comma-delimited list
|
|
|
+ of directories then the name table is replicated in all of the
|
|
|
+ directories, for redundancy. </description>
|
|
|
+</property>
|
|
|
+
|
|
|
+<property>
|
|
|
+ <name>dfs.name.edits.dir</name>
|
|
|
+ <value>${dfs.name.dir}</value>
|
|
|
+ <description>Determines where on the local filesystem the DFS name node
|
|
|
+ should store the transaction (edits) file. If this is a comma-delimited list
|
|
|
+ of directories then the transaction file is replicated in all of the
|
|
|
+ directories, for redundancy. Default value is same as dfs.name.dir
|
|
|
+ </description>
|
|
|
+</property>
|
|
|
+<property>
|
|
|
+ <name>dfs.web.ugi</name>
|
|
|
+ <value>webuser,webgroup</value>
|
|
|
+ <description>The user account used by the web interface.
|
|
|
+ Syntax: USERNAME,GROUP1,GROUP2, ...
|
|
|
+ </description>
|
|
|
+</property>
|
|
|
+
|
|
|
+<property>
|
|
|
+ <name>dfs.permissions</name>
|
|
|
+ <value>true</value>
|
|
|
+ <description>
|
|
|
+ If "true", enable permission checking in HDFS.
|
|
|
+ If "false", permission checking is turned off,
|
|
|
+ but all other behavior is unchanged.
|
|
|
+ Switching from one parameter value to the other does not change the mode,
|
|
|
+ owner or group of files or directories.
|
|
|
+ </description>
|
|
|
+</property>
|
|
|
+
|
|
|
+<property>
|
|
|
+ <name>dfs.permissions.supergroup</name>
|
|
|
+ <value>supergroup</value>
|
|
|
+ <description>The name of the group of super-users.</description>
|
|
|
+</property>
|
|
|
+
|
|
|
+<property>
|
|
|
+ <name>dfs.data.dir</name>
|
|
|
+ <value>${hadoop.tmp.dir}/dfs/data</value>
|
|
|
+ <description>Determines where on the local filesystem an DFS data node
|
|
|
+ should store its blocks. If this is a comma-delimited
|
|
|
+ list of directories, then data will be stored in all named
|
|
|
+ directories, typically on different devices.
|
|
|
+ Directories that do not exist are ignored.
|
|
|
+ </description>
|
|
|
+</property>
|
|
|
+
|
|
|
+<property>
|
|
|
+ <name>dfs.replication</name>
|
|
|
+ <value>3</value>
|
|
|
+ <description>Default block replication.
|
|
|
+ The actual number of replications can be specified when the file is created.
|
|
|
+ The default is used if replication is not specified in create time.
|
|
|
+ </description>
|
|
|
+</property>
|
|
|
+
|
|
|
+<property>
|
|
|
+ <name>dfs.replication.max</name>
|
|
|
+ <value>512</value>
|
|
|
+ <description>Maximal block replication.
|
|
|
+ </description>
|
|
|
+</property>
|
|
|
+
|
|
|
+<property>
|
|
|
+ <name>dfs.replication.min</name>
|
|
|
+ <value>1</value>
|
|
|
+ <description>Minimal block replication.
|
|
|
+ </description>
|
|
|
+</property>
|
|
|
+
|
|
|
+<property>
|
|
|
+ <name>dfs.block.size</name>
|
|
|
+ <value>67108864</value>
|
|
|
+ <description>The default block size for new files.</description>
|
|
|
+</property>
|
|
|
+
|
|
|
+<property>
|
|
|
+ <name>dfs.df.interval</name>
|
|
|
+ <value>60000</value>
|
|
|
+ <description>Disk usage statistics refresh interval in msec.</description>
|
|
|
+</property>
|
|
|
+
|
|
|
+<property>
|
|
|
+ <name>dfs.client.block.write.retries</name>
|
|
|
+ <value>3</value>
|
|
|
+ <description>The number of retries for writing blocks to the data nodes,
|
|
|
+ before we signal failure to the application.
|
|
|
+ </description>
|
|
|
+</property>
|
|
|
+
|
|
|
+<property>
|
|
|
+ <name>dfs.blockreport.intervalMsec</name>
|
|
|
+ <value>3600000</value>
|
|
|
+ <description>Determines block reporting interval in milliseconds.</description>
|
|
|
+</property>
|
|
|
+
|
|
|
+<property>
|
|
|
+ <name>dfs.blockreport.initialDelay</name> <value>0</value>
|
|
|
+ <description>Delay for first block report in seconds.</description>
|
|
|
+</property>
|
|
|
+
|
|
|
+<property>
|
|
|
+ <name>dfs.heartbeat.interval</name>
|
|
|
+ <value>3</value>
|
|
|
+ <description>Determines datanode heartbeat interval in seconds.</description>
|
|
|
+</property>
|
|
|
+
|
|
|
+<property>
|
|
|
+ <name>dfs.namenode.handler.count</name>
|
|
|
+ <value>10</value>
|
|
|
+ <description>The number of server threads for the namenode.</description>
|
|
|
+</property>
|
|
|
+
|
|
|
+<property>
|
|
|
+ <name>dfs.safemode.threshold.pct</name>
|
|
|
+ <value>0.999f</value>
|
|
|
+ <description>
|
|
|
+ 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.
|
|
|
+ </description>
|
|
|
+</property>
|
|
|
+
|
|
|
+<property>
|
|
|
+ <name>dfs.safemode.extension</name>
|
|
|
+ <value>30000</value>
|
|
|
+ <description>
|
|
|
+ Determines extension of safe mode in milliseconds
|
|
|
+ after the threshold level is reached.
|
|
|
+ </description>
|
|
|
+</property>
|
|
|
+
|
|
|
+<property>
|
|
|
+ <name>dfs.balance.bandwidthPerSec</name>
|
|
|
+ <value>1048576</value>
|
|
|
+ <description>
|
|
|
+ Specifies the maximum amount of bandwidth that each datanode
|
|
|
+ can utilize for the balancing purpose in term of
|
|
|
+ the number of bytes per second.
|
|
|
+ </description>
|
|
|
+</property>
|
|
|
+
|
|
|
+<property>
|
|
|
+ <name>dfs.hosts</name>
|
|
|
+ <value></value>
|
|
|
+ <description>Names a file that contains a list of hosts that are
|
|
|
+ permitted to connect to the namenode. The full pathname of the file
|
|
|
+ must be specified. If the value is empty, all hosts are
|
|
|
+ permitted.</description>
|
|
|
+</property>
|
|
|
+
|
|
|
+<property>
|
|
|
+ <name>dfs.hosts.exclude</name>
|
|
|
+ <value></value>
|
|
|
+ <description>Names a file that contains a list of hosts that are
|
|
|
+ not permitted to connect to the namenode. The full pathname of the
|
|
|
+ file must be specified. If the value is empty, no hosts are
|
|
|
+ excluded.</description>
|
|
|
+</property>
|
|
|
+
|
|
|
+<property>
|
|
|
+ <name>dfs.max.objects</name>
|
|
|
+ <value>0</value>
|
|
|
+ <description>The maximum number of files, directories and blocks
|
|
|
+ dfs supports. A value of zero indicates no limit to the number
|
|
|
+ of objects that dfs supports.
|
|
|
+ </description>
|
|
|
+</property>
|
|
|
+
|
|
|
+<property>
|
|
|
+ <name>dfs.namenode.decommission.interval</name>
|
|
|
+ <value>30</value>
|
|
|
+ <description>Namenode periodicity in seconds to check if decommission is
|
|
|
+ complete.</description>
|
|
|
+</property>
|
|
|
+
|
|
|
+<property>
|
|
|
+ <name>dfs.namenode.decommission.nodes.per.interval</name>
|
|
|
+ <value>5</value>
|
|
|
+ <description>The number of nodes namenode checks if decommission is complete
|
|
|
+ in each dfs.namenode.decommission.interval.</description>
|
|
|
+</property>
|
|
|
+
|
|
|
+<property>
|
|
|
+ <name>dfs.replication.interval</name>
|
|
|
+ <value>3</value>
|
|
|
+ <description>The periodicity in seconds with which the namenode computes
|
|
|
+ repliaction work for datanodes. </description>
|
|
|
+</property>
|
|
|
+
|
|
|
+<property>
|
|
|
+ <name>dfs.access.time.precision</name>
|
|
|
+ <value>3600000</value>
|
|
|
+ <description>The access time for HDFS file is precise upto this value.
|
|
|
+ The default value is 1 hour. Setting a value of 0 disables
|
|
|
+ access times for HDFS.
|
|
|
+ </description>
|
|
|
+</property>
|
|
|
+
|
|
|
+<property>
|
|
|
+ <name>fs.s3.block.size</name>
|
|
|
+ <value>67108864</value>
|
|
|
+ <description>Block size to use when writing files to S3.</description>
|
|
|
+</property>
|
|
|
+
|
|
|
+<property>
|
|
|
+ <name>fs.s3.buffer.dir</name>
|
|
|
+ <value>${hadoop.tmp.dir}/s3</value>
|
|
|
+ <description>Determines where on the local filesystem the S3 filesystem
|
|
|
+ should store files before sending them to S3
|
|
|
+ (or after retrieving them from S3).
|
|
|
+ </description>
|
|
|
+</property>
|
|
|
+
|
|
|
+<property>
|
|
|
+ <name>fs.s3.maxRetries</name>
|
|
|
+ <value>4</value>
|
|
|
+ <description>The maximum number of retries for reading or writing files to S3,
|
|
|
+ before we signal failure to the application.
|
|
|
+ </description>
|
|
|
+</property>
|
|
|
+
|
|
|
+<property>
|
|
|
+ <name>fs.s3.sleepTimeSeconds</name>
|
|
|
+ <value>10</value>
|
|
|
+ <description>The number of seconds to sleep between each S3 retry.
|
|
|
+ </description>
|
|
|
+</property>
|
|
|
+
|
|
|
+<!-- map/reduce properties -->
|
|
|
+
|
|
|
<property>
|
|
|
<name>mapred.job.tracker</name>
|
|
|
<value>local</value>
|
|
|
@@ -115,6 +687,14 @@
|
|
|
</description>
|
|
|
</property>
|
|
|
|
|
|
+<property>
|
|
|
+ <name>local.cache.size</name>
|
|
|
+ <value>10737418240</value>
|
|
|
+ <description>The limit on the size of cache you want to keep, set by default
|
|
|
+ to 10GB. This will act as a soft limit on the cache directory for out of band data.
|
|
|
+ </description>
|
|
|
+</property>
|
|
|
+
|
|
|
<property>
|
|
|
<name>mapred.system.dir</name>
|
|
|
<value>${hadoop.tmp.dir}/mapred/system</value>
|
|
|
@@ -142,11 +722,11 @@
|
|
|
<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.
|
|
|
+ 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>
|
|
|
|
|
|
@@ -612,7 +1192,6 @@
|
|
|
from the reduce directory as they are consumed.</description>
|
|
|
</property>
|
|
|
|
|
|
-
|
|
|
<!--
|
|
|
<property>
|
|
|
<name>keep.task.files.pattern</name>
|
|
|
@@ -660,6 +1239,30 @@
|
|
|
</description>
|
|
|
</property>
|
|
|
|
|
|
+<property>
|
|
|
+ <name>io.seqfile.compress.blocksize</name>
|
|
|
+ <value>1000000</value>
|
|
|
+ <description>The minimum block size for compression in block compressed
|
|
|
+ SequenceFiles.
|
|
|
+ </description>
|
|
|
+</property>
|
|
|
+
|
|
|
+<property>
|
|
|
+ <name>io.seqfile.lazydecompress</name>
|
|
|
+ <value>true</value>
|
|
|
+ <description>Should values of block-compressed SequenceFiles be decompressed
|
|
|
+ only when necessary.
|
|
|
+ </description>
|
|
|
+</property>
|
|
|
+
|
|
|
+<property>
|
|
|
+ <name>io.seqfile.sorter.recordlimit</name>
|
|
|
+ <value>1000000</value>
|
|
|
+ <description>The limit on number of records to be kept in memory in a spill
|
|
|
+ in SequenceFiles.Sorter
|
|
|
+ </description>
|
|
|
+</property>
|
|
|
+
|
|
|
<property>
|
|
|
<name>map.sort.class</name>
|
|
|
<value>org.apache.hadoop.util.QuickSort</value>
|
|
|
@@ -678,7 +1281,7 @@
|
|
|
<name>mapred.userlog.retain.hours</name>
|
|
|
<value>24</value>
|
|
|
<description>The maximum time, in hours, for which the user-logs are to be
|
|
|
- retained.
|
|
|
+ retained.
|
|
|
</description>
|
|
|
</property>
|
|
|
|
|
|
@@ -696,18 +1299,18 @@
|
|
|
<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>
|
|
|
|
|
|
<property>
|
|
|
<name>mapred.max.tracker.blacklists</name>
|
|
|
<value>4</value>
|
|
|
- <description>The number of blacklists for a taskTracker by various jobs
|
|
|
+ <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.
|
|
|
+ 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>
|
|
|
+</property>
|
|
|
|
|
|
<property>
|
|
|
<name>mapred.max.tracker.failures</name>
|
|
|
@@ -860,7 +1463,66 @@
|
|
|
acceptable.
|
|
|
</description>
|
|
|
</property>
|
|
|
-
|
|
|
+
|
|
|
+<!-- ipc properties -->
|
|
|
+
|
|
|
+<property>
|
|
|
+ <name>ipc.client.idlethreshold</name>
|
|
|
+ <value>4000</value>
|
|
|
+ <description>Defines the threshold number of connections after which
|
|
|
+ connections will be inspected for idleness.
|
|
|
+ </description>
|
|
|
+</property>
|
|
|
+
|
|
|
+<property>
|
|
|
+ <name>ipc.client.kill.max</name>
|
|
|
+ <value>10</value>
|
|
|
+ <description>Defines the maximum number of clients to disconnect in one go.
|
|
|
+ </description>
|
|
|
+</property>
|
|
|
+
|
|
|
+<property>
|
|
|
+ <name>ipc.client.connection.maxidletime</name>
|
|
|
+ <value>10000</value>
|
|
|
+ <description>The maximum time in msec after which a client will bring down the
|
|
|
+ connection to the server.
|
|
|
+ </description>
|
|
|
+</property>
|
|
|
+
|
|
|
+<property>
|
|
|
+ <name>ipc.client.connect.max.retries</name>
|
|
|
+ <value>10</value>
|
|
|
+ <description>Indicates the number of retries a client will make to establish
|
|
|
+ a server connection.
|
|
|
+ </description>
|
|
|
+</property>
|
|
|
+
|
|
|
+<property>
|
|
|
+ <name>ipc.server.listen.queue.size</name>
|
|
|
+ <value>128</value>
|
|
|
+ <description>Indicates the length of the listen queue for servers accepting
|
|
|
+ client connections.
|
|
|
+ </description>
|
|
|
+</property>
|
|
|
+
|
|
|
+<property>
|
|
|
+ <name>ipc.server.tcpnodelay</name>
|
|
|
+ <value>false</value>
|
|
|
+ <description>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.
|
|
|
+ </description>
|
|
|
+</property>
|
|
|
+
|
|
|
+<property>
|
|
|
+ <name>ipc.client.tcpnodelay</name>
|
|
|
+ <value>false</value>
|
|
|
+ <description>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.
|
|
|
+ </description>
|
|
|
+</property>
|
|
|
+
|
|
|
<!-- Job Notification Configuration -->
|
|
|
|
|
|
<!--
|
|
|
@@ -889,8 +1551,38 @@
|
|
|
<description>Indicates time in milliseconds between notification URL retry
|
|
|
calls</description>
|
|
|
</property>
|
|
|
-
|
|
|
+
|
|
|
+<!-- Web Interface Configuration -->
|
|
|
+
|
|
|
+<property>
|
|
|
+ <name>webinterface.private.actions</name>
|
|
|
+ <value>false</value>
|
|
|
+ <description> 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.
|
|
|
+ </description>
|
|
|
+</property>
|
|
|
+
|
|
|
<!-- Proxy Configuration -->
|
|
|
+
|
|
|
+<property>
|
|
|
+ <name>hadoop.rpc.socket.factory.class.default</name>
|
|
|
+ <value>org.apache.hadoop.net.StandardSocketFactory</value>
|
|
|
+ <description> Default SocketFactory to use. This parameter is expected to be
|
|
|
+ formatted as "package.FactoryClassName".
|
|
|
+ </description>
|
|
|
+</property>
|
|
|
+
|
|
|
+<property>
|
|
|
+ <name>hadoop.rpc.socket.factory.class.ClientProtocol</name>
|
|
|
+ <value></value>
|
|
|
+ <description> 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.
|
|
|
+ </description>
|
|
|
+</property>
|
|
|
+
|
|
|
<property>
|
|
|
<name>hadoop.rpc.socket.factory.class.JobSubmissionProtocol</name>
|
|
|
<value></value>
|
|
|
@@ -899,6 +1591,44 @@
|
|
|
</description>
|
|
|
</property>
|
|
|
|
|
|
+<property>
|
|
|
+ <name>hadoop.socks.server</name>
|
|
|
+ <value></value>
|
|
|
+ <description> Address (host:port) of the SOCKS server to be used by the
|
|
|
+ SocksSocketFactory.
|
|
|
+ </description>
|
|
|
+</property>
|
|
|
+
|
|
|
+<!-- Rack Configuration -->
|
|
|
+
|
|
|
+<property>
|
|
|
+ <name>topology.node.switch.mapping.impl</name>
|
|
|
+ <value>org.apache.hadoop.net.ScriptBasedMapping</value>
|
|
|
+ <description> 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.
|
|
|
+ </description>
|
|
|
+</property>
|
|
|
+
|
|
|
+<property>
|
|
|
+ <name>topology.script.file.name</name>
|
|
|
+ <value></value>
|
|
|
+ <description> 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.
|
|
|
+ </description>
|
|
|
+</property>
|
|
|
+
|
|
|
+<property>
|
|
|
+ <name>topology.script.number.args</name>
|
|
|
+ <value>100</value>
|
|
|
+ <description> The max number of args that the script configured with
|
|
|
+ topology.script.file.name should be run with. Each arg is an
|
|
|
+ IP address.
|
|
|
+ </description>
|
|
|
+</property>
|
|
|
+
|
|
|
<property>
|
|
|
<name>mapred.task.cache.levels</name>
|
|
|
<value>2</value>
|
|
|
@@ -985,4 +1715,4 @@
|
|
|
</description>
|
|
|
</property>
|
|
|
|
|
|
-</configuration>
|
|
|
+</configuration>
|
Christopher Douglas