Hadoop_Configuration 博客分类： hadoop

    刚开始接触Hadoop的API时,首先第一个就是接触Configuration这个类,但是不知道为什么很多的其它方法都需要这个Configuration对象作为参数传入，今天好好的看了这个方法。其中最重要的莫过于它将用户对Hadoop所做的配置全部记录下来了。下面是我通过调用Configuration类中的Main方法而产生出来的xml数据。

<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<configuration>
<property><name>fs.s3n.impl</name><value>org.apache.hadoop.fs.s3native.NativeS3FileSystem</value></property>
<property><name>mapred.task.cache.levels</name><value>2</value></property>
<property><name>hadoop.tmp.dir</name><value>/tmp/hadoop-${user.name}</value></property>
<property><name>hadoop.native.lib</name><value>true</value></property>
<property><name>map.sort.class</name><value>org.apache.hadoop.util.QuickSort</value></property>
<property><name>ipc.client.idlethreshold</name><value>4000</value></property>
<property><name>mapred.system.dir</name><value>${hadoop.tmp.dir}/mapred/system</value></property>
<property><name>mapred.job.tracker.persist.jobstatus.hours</name><value>0</value></property>
<property><name>io.skip.checksum.errors</name><value>false</value></property>
<property><name>fs.default.name</name><value>hdfs://localhost:8020/</value></property>
<property><name>mapred.cluster.reduce.memory.mb</name><value>-1</value></property>
<property><name>mapred.child.tmp</name><value>./tmp</value></property>
<property><name>fs.har.impl.disable.cache</name><value>true</value></property>
<property><name>mapred.skip.reduce.max.skip.groups</name><value>0</value></property>
<property><name>mapred.heartbeats.in.second</name><value>100</value></property>
<property><name>mapred.tasktracker.dns.nameserver</name><value>default</value></property>
<property><name>io.sort.factor</name><value>10</value></property>
<property><name>mapred.task.timeout</name><value>600000</value></property>
<property><name>mapred.max.tracker.failures</name><value>4</value></property>
<property><name>hadoop.rpc.socket.factory.class.default</name><value>org.apache.hadoop.net.StandardSocketFactory</value></property>
<property><name>mapred.job.tracker.jobhistory.lru.cache.size</name><value>5</value></property>
<property><name>fs.hdfs.impl</name><value>org.apache.hadoop.hdfs.DistributedFileSystem</value></property>
<property><name>eclipse.plug-in.jobtracker.port</name><value>8021</value></property>
<property><name>mapred.skip.map.auto.incr.proc.count</name><value>true</value></property>
<property><name>mapreduce.job.complete.cancel.delegation.tokens</name><value>true</value></property>
<property><name>io.mapfile.bloom.size</name><value>1048576</value></property>
<property><name>mapreduce.reduce.shuffle.connect.timeout</name><value>180000</value></property>
<property><name>mapred.jobtracker.blacklist.fault-timeout-window</name><value>180</value></property>
<property><name>tasktracker.http.threads</name><value>40</value></property>
<property><name>mapred.job.shuffle.merge.percent</name><value>0.66</value></property>
<property><name>fs.ftp.impl</name><value>org.apache.hadoop.fs.ftp.FTPFileSystem</value></property>
<property><name>mapred.output.compress</name><value>false</value></property>
<property><name>io.bytes.per.checksum</name><value>512</value></property>
<property><name>mapred.healthChecker.script.timeout</name><value>600000</value></property>
<property><name>topology.node.switch.mapping.impl</name><value>org.apache.hadoop.net.ScriptBasedMapping</value></property>
<property><name>mapred.reduce.slowstart.completed.maps</name><value>0.05</value></property>
<property><name>mapred.reduce.max.attempts</name><value>4</value></property>
<property><name>fs.ramfs.impl</name><value>org.apache.hadoop.fs.InMemoryFileSystem</value></property>
<property><name>mapred.skip.map.max.skip.records</name><value>0</value></property>
<property><name>mapred.cluster.map.memory.mb</name><value>-1</value></property>
<property><name>hadoop.security.group.mapping</name><value>org.apache.hadoop.security.ShellBasedUnixGroupsMapping</value></property>
<property><name>mapred.job.tracker.persist.jobstatus.dir</name><value>/jobtracker/jobsInfo</value></property>
<property><name>mapred.jar</name><value>/home/hadoop/hadoop/.metadata/.plugins/org.apache.hadoop.eclipse/firstApp_CatURL.java-7377097405794968176.jar</value></property>
<property><name>fs.s3.buffer.dir</name><value>${hadoop.tmp.dir}/s3</value></property>
<property><name>job.end.retry.attempts</name><value>0</value></property>
<property><name>fs.file.impl</name><value>org.apache.hadoop.fs.LocalFileSystem</value></property>
<property><name>mapred.local.dir.minspacestart</name><value>0</value></property>
<property><name>mapred.output.compression.type</name><value>RECORD</value></property>
<property><name>topology.script.number.args</name><value>100</value></property>
<property><name>io.mapfile.bloom.error.rate</name><value>0.005</value></property>
<property><name>mapred.cluster.max.reduce.memory.mb</name><value>-1</value></property>
<property><name>mapred.max.tracker.blacklists</name><value>4</value></property>
<property><name>mapred.task.profile.maps</name><value>0-2</value></property>
<property><name>mapred.userlog.retain.hours</name><value>24</value></property>
<property><name>mapred.job.tracker.persist.jobstatus.active</name><value>false</value></property>
<property><name>hadoop.security.authorization</name><value>false</value></property>
<property><name>local.cache.size</name><value>10737418240</value></property>
<property><name>eclipse.plug-in.jobtracker.host</name><value>localhost</value></property>
<property><name>mapred.min.split.size</name><value>0</value></property>
<property><name>mapred.map.tasks</name><value>2</value></property>
<property><name>mapred.child.java.opts</name><value>-Xmx200m</value></property>
<property><name>mapreduce.job.counters.limit</name><value>120</value></property>
<property><name>eclipse.plug-in.user.name</name><value>hadoop</value></property>
<property><name>mapred.job.queue.name</name><value>default</value></property>
<property><name>mapred.job.tracker.retiredjobs.cache.size</name><value>1000</value></property>
<property><name>ipc.server.listen.queue.size</name><value>128</value></property>
<property><name>mapred.inmem.merge.threshold</name><value>1000</value></property>
<property><name>job.end.retry.interval</name><value>30000</value></property>
<property><name>mapred.skip.attempts.to.start.skipping</name><value>2</value></property>
<property><name>fs.checkpoint.dir</name><value>${hadoop.tmp.dir}/dfs/namesecondary</value></property>
<property><name>mapred.reduce.tasks</name><value>1</value></property>
<property><name>mapred.merge.recordsBeforeProgress</name><value>10000</value></property>
<property><name>mapred.userlog.limit.kb</name><value>0</value></property>
<property><name>mapred.job.reduce.memory.mb</name><value>-1</value></property>
<property><name>webinterface.private.actions</name><value>false</value></property>
<property><name>io.sort.spill.percent</name><value>0.80</value></property>
<property><name>mapred.job.shuffle.input.buffer.percent</name><value>0.70</value></property>
<property><name>eclipse.plug-in.socks.proxy.port</name><value>1080</value></property>
<property><name>mapred.map.tasks.speculative.execution</name><value>true</value></property>
<property><name>hadoop.util.hash.type</name><value>murmur</value></property>
<property><name>mapred.map.max.attempts</name><value>4</value></property>
<property><name>mapreduce.job.acl-view-job</name><value> </value></property>
<property><name>mapred.job.tracker.handler.count</name><value>10</value></property>
<property><name>mapreduce.reduce.shuffle.read.timeout</name><value>180000</value></property>
<property><name>mapred.tasktracker.expiry.interval</name><value>600000</value></property>
<property><name>mapred.jobtracker.maxtasks.per.job</name><value>-1</value></property>
<property><name>mapred.jobtracker.job.history.block.size</name><value>3145728</value></property>
<property><name>keep.failed.task.files</name><value>false</value></property>
<property><name>ipc.client.tcpnodelay</name><value>false</value></property>
<property><name>mapred.task.profile.reduces</name><value>0-2</value></property>
<property><name>mapred.output.compression.codec</name><value>org.apache.hadoop.io.compress.DefaultCodec</value></property>
<property><name>io.map.index.skip</name><value>0</value></property>
<property><name>ipc.server.tcpnodelay</name><value>false</value></property>
<property><name>mapred.jobtracker.blacklist.fault-bucket-width</name><value>15</value></property>
<property><name>mapred.used.genericoptionsparser</name><value>true</value></property>
<property><name>mapred.job.map.memory.mb</name><value>-1</value></property>
<property><name>hadoop.logfile.size</name><value>10000000</value></property>
<property><name>mapred.reduce.tasks.speculative.execution</name><value>true</value></property>
<property><name>mapreduce.tasktracker.outofband.heartbeat</name><value>false</value></property>
<property><name>mapreduce.reduce.input.limit</name><value>-1</value></property>
<property><name>hadoop.security.authentication</name><value>simple</value></property>
<property><name>eclipse.plug-in.socks.proxy.host</name><value>host</value></property>
<property><name>fs.checkpoint.period</name><value>3600</value></property>
<property><name>mapred.job.reuse.jvm.num.tasks</name><value>1</value></property>
<property><name>mapred.jobtracker.completeuserjobs.maximum</name><value>100</value></property>
<property><name>mapred.task.tracker.task-controller</name><value>org.apache.hadoop.mapred.DefaultTaskController</value></property>
<property><name>fs.s3.maxRetries</name><value>4</value></property>
<property><name>mapred.cluster.max.map.memory.mb</name><value>-1</value></property>
<property><name>mapreduce.job.acl-modify-job</name><value> </value></property>
<property><name>mapred.local.dir</name><value>${hadoop.tmp.dir}/mapred/local</value></property>
<property><name>fs.hftp.impl</name><value>org.apache.hadoop.hdfs.HftpFileSystem</value></property>
<property><name>fs.trash.interval</name><value>0</value></property>
<property><name>fs.s3.sleepTimeSeconds</name><value>10</value></property>
<property><name>mapred.submit.replication</name><value>10</value></property>
<property><name>fs.har.impl</name><value>org.apache.hadoop.fs.HarFileSystem</value></property>
<property><name>mapred.map.output.compression.codec</name><value>org.apache.hadoop.io.compress.DefaultCodec</value></property>
<property><name>mapred.tasktracker.dns.interface</name><value>default</value></property>
<property><name>eclipse.plug-in.namenode.port</name><value>8020</value></property>
<property><name>mapred.job.tracker</name><value>localhost:8021</value></property>
<property><name>io.seqfile.sorter.recordlimit</name><value>1000000</value></property>
<property><name>mapred.line.input.format.linespermap</name><value>1</value></property>
<property><name>mapred.jobtracker.taskScheduler</name><value>org.apache.hadoop.mapred.JobQueueTaskScheduler</value></property>
<property><name>eclipse.plug-in.masters.colocate</name><value>yes</value></property>
<property><name>mapred.local.dir.minspacekill</name><value>0</value></property>
<property><name>io.sort.record.percent</name><value>0.05</value></property>
<property><name>fs.kfs.impl</name><value>org.apache.hadoop.fs.kfs.KosmosFileSystem</value></property>
<property><name>mapred.temp.dir</name><value>${hadoop.tmp.dir}/mapred/temp</value></property>
<property><name>mapred.tasktracker.reduce.tasks.maximum</name><value>2</value></property>
<property><name>eclipse.plug-in.socks.proxy.enable</name><value>no</value></property>
<property><name>fs.checkpoint.edits.dir</name><value>${fs.checkpoint.dir}</value></property>
<property><name>mapred.tasktracker.tasks.sleeptime-before-sigkill</name><value>5000</value></property>
<property><name>eclipse.plug-in.location.name</name><value>localhost</value></property>
<property><name>mapred.job.reduce.input.buffer.percent</name><value>0.0</value></property>
<property><name>mapred.tasktracker.indexcache.mb</name><value>10</value></property>
<property><name>mapreduce.job.split.metainfo.maxsize</name><value>10000000</value></property>
<property><name>mapred.skip.reduce.auto.incr.proc.count</name><value>true</value></property>
<property><name>hadoop.logfile.count</name><value>10</value></property>
<property><name>io.seqfile.compress.blocksize</name><value>1000000</value></property>
<property><name>fs.s3.block.size</name><value>67108864</value></property>
<property><name>mapred.tasktracker.taskmemorymanager.monitoring-interval</name><value>5000</value></property>
<property><name>mapreduce.jobtracker.staging.root.dir</name><value>${hadoop.tmp.dir}/mapred/staging</value></property>
<property><name>mapred.acls.enabled</name><value>false</value></property>
<property><name>mapred.queue.default.state</name><value>RUNNING</value></property>
<property><name>mapred.queue.names</name><value>default</value></property>
<property><name>fs.hsftp.impl</name><value>org.apache.hadoop.hdfs.HsftpFileSystem</value></property>
<property><name>mapred.task.tracker.http.address</name><value>0.0.0.0:50060</value></property>
<property><name>mapred.reduce.parallel.copies</name><value>5</value></property>
<property><name>io.seqfile.lazydecompress</name><value>true</value></property>
<property><name>eclipse.plug-in.namenode.host</name><value>localhost</value></property>
<property><name>io.sort.mb</name><value>100</value></property>
<property><name>ipc.client.connection.maxidletime</name><value>10000</value></property>
<property><name>mapred.task.tracker.report.address</name><value>127.0.0.1:0</value></property>
<property><name>mapred.compress.map.output</name><value>false</value></property>
<property><name>hadoop.security.uid.cache.secs</name><value>14400</value></property>
<property><name>mapred.healthChecker.interval</name><value>60000</value></property>
<property><name>ipc.client.kill.max</name><value>10</value></property>
<property><name>ipc.client.connect.max.retries</name><value>10</value></property>
<property><name>fs.s3.impl</name><value>org.apache.hadoop.fs.s3.S3FileSystem</value></property>
<property><name>mapred.user.jobconf.limit</name><value>5242880</value></property>
<property><name>hadoop.socks.server</name><value>host:1080</value></property>
<property><name>mapred.job.tracker.http.address</name><value>0.0.0.0:50030</value></property>
<property><name>io.file.buffer.size</name><value>4096</value></property>
<property><name>mapred.jobtracker.restart.recover</name><value>false</value></property>
<property><name>io.serializations</name><value>org.apache.hadoop.io.serializer.WritableSerialization</value></property>
<property><name>mapred.task.profile</name><value>false</value></property>
<property><name>mapred.reduce.copy.backoff</name><value>300</value></property>
<property><name>jobclient.output.filter</name><value>FAILED</value></property>
<property><name>mapred.tasktracker.map.tasks.maximum</name><value>2</value></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></property>
<property><name>fs.checkpoint.size</name><value>67108864</value></property>
</configuration>

 

    根节点是configuration，也就代表了Configuration类了，至于里面的属性都是我们对Hadoop的配置参数，很多都是Hadoop默认的配置。所以其他的类如果想要对你配置的Hadoop做操作，当然离不开这些参数了。而如果你想往Hadoop中配置其他资源时，还可以通过Configuration中的set方法进行操作，而如果你想取里面的某些参数，同理也可以调用Configuration中的get方法。