> mapred.reduce.tasks 1
You've only got one reduce task, as Jason correctly surmised. Try
setting it using
-D mapred.reduce.tasks=2
when you run your job, or by calling JobConf#setNumReduceTasks()
Tom
On Fri, May 8, 2009 at 7:46 AM, Foss User <foss...@gmail.com> wrote:
> On Thu, May 7, 2009 at 9:45 PM, jason hadoop <jason.had...@gmail.com> wrote:
>> If you have it available still, via the job tracker web interface, attach
>> the per job xml configuration
>
> Job Configuration: JobId - job_200905071619_0003
>
> name value
> fs.s3n.impl org.apache.hadoop.fs.s3native.NativeS3FileSystem
> mapred.task.cache.levels 2
> hadoop.tmp.dir /tmp/hadoop-${user.name}
> hadoop.native.lib true
> map.sort.class org.apache.hadoop.util.QuickSort
> dfs.namenode.decommission.nodes.per.interval 5
> ipc.client.idlethreshold 4000
> mapred.system.dir ${hadoop.tmp.dir}/mapred/system
> mapred.job.tracker.persist.jobstatus.hours 0
> dfs.namenode.logging.level info
> dfs.datanode.address 0.0.0.0:50010
> io.skip.checksum.errors false
> fs.default.name hdfs://192.168.1.130:9000
> mapred.child.tmp ./tmp
> dfs.safemode.threshold.pct 0.999f
> mapred.skip.reduce.max.skip.groups 0
> dfs.namenode.handler.count 10
> dfs.blockreport.initialDelay 0
> mapred.jobtracker.instrumentation
> org.apache.hadoop.mapred.JobTrackerMetricsInst
> mapred.tasktracker.dns.nameserver default
> io.sort.factor 10
> mapred.task.timeout 600000
> mapred.max.tracker.failures 4
> hadoop.rpc.socket.factory.class.default
> org.apache.hadoop.net.StandardSocketFactory
> fs.hdfs.impl org.apache.hadoop.hdfs.DistributedFileSystem
> mapred.queue.default.acl-administer-jobs *
> mapred.queue.default.acl-submit-job *
> mapred.output.key.class org.apache.hadoop.io.Text
> mapred.skip.map.auto.incr.proc.count true
> dfs.safemode.extension 30000
> tasktracker.http.threads 40
> mapred.job.shuffle.merge.percent 0.66
> fs.ftp.impl org.apache.hadoop.fs.ftp.FTPFileSystem
> user.name fossist
> mapred.output.compress false
> io.bytes.per.checksum 512
> topology.node.switch.mapping.impl
> org.apache.hadoop.net.ScriptBasedMapping
> mapred.reduce.max.attempts 4
> fs.ramfs.impl org.apache.hadoop.fs.InMemoryFileSystem
> mapred.skip.map.max.skip.records 0
> dfs.name.edits.dir ${dfs.name.dir}
> hadoop.job.ugi fossist,fossist,dialout,cdrom,floppy,audio,video,plugdev
> mapred.job.tracker.persist.jobstatus.dir /jobtracker/jobsInfo
> mapred.jar
> /tmp/hadoop-hadoop/mapred/local/jobTracker/job_200905071619_0003.jar
> fs.s3.buffer.dir ${hadoop.tmp.dir}/s3
> dfs.block.size 67108864
> job.end.retry.attempts 0
> fs.file.impl org.apache.hadoop.fs.LocalFileSystem
> mapred.local.dir.minspacestart 0
> mapred.output.compression.type RECORD
> dfs.datanode.ipc.address 0.0.0.0:50020
> dfs.permissions true
> topology.script.number.args 100
> mapred.task.profile.maps 0-2
> dfs.datanode.https.address 0.0.0.0:50475
> mapred.userlog.retain.hours 24
> dfs.secondary.http.address 0.0.0.0:50090
> dfs.replication.max 512
> mapred.job.tracker.persist.jobstatus.active false
> local.cache.size 10737418240
> mapred.min.split.size 0
> mapred.map.tasks 3
> mapred.child.java.opts -Xmx200m
> mapred.output.value.class org.apache.hadoop.io.IntWritable
> mapred.job.queue.name default
> dfs.https.address 0.0.0.0:50470
> dfs.balance.bandwidthPerSec 1048576
> ipc.server.listen.queue.size 128
> group.name fossist
> job.end.retry.interval 30000
> mapred.inmem.merge.threshold 1000
> mapred.skip.attempts.to.start.skipping 2
> fs.checkpoint.dir ${hadoop.tmp.dir}/dfs/namesecondary
> mapred.reduce.tasks 1
> mapred.merge.recordsBeforeProgress 10000
> mapred.userlog.limit.kb 0
> webinterface.private.actions false
> dfs.max.objects 0
> io.sort.spill.percent 0.80
> mapred.job.shuffle.input.buffer.percent 0.70
> mapred.job.split.file
> hdfs://192.168.1.130:9000/tmp/hadoop-hadoop/mapred/system/job_200905071619_0003/job.split
> mapred.job.name wordcount
> mapred.map.tasks.speculative.execution true
> dfs.datanode.dns.nameserver default
> dfs.blockreport.intervalMsec 3600000
> mapred.map.max.attempts 4
> mapred.job.tracker.handler.count 10
> dfs.client.block.write.retries 3
> mapred.input.format.class org.apache.hadoop.mapred.TextInputFormat
> mapred.tasktracker.expiry.interval 600000
> mapred.jobtracker.maxtasks.per.job -1
> mapred.jobtracker.job.history.block.size 3145728
> keep.failed.task.files false
> mapred.output.format.class org.apache.hadoop.mapred.TextOutputFormat
> https.keystore.info.rsrc sslinfo.xml
> ipc.client.tcpnodelay false
> mapred.task.profile.reduces 0-2
> mapred.output.compression.codec org.apache.hadoop.io.compress.DefaultCodec
> io.map.index.skip 0
> mapred.working.dir hdfs://192.168.1.130:9000/user/fossist
> ipc.server.tcpnodelay false
> mapred.reducer.class in.fossist.examples.Reduce
> dfs.default.chunk.view.size 32768
> hadoop.logfile.size 10000000
> mapred.reduce.tasks.speculative.execution true
> dfs.datanode.du.reserved 0
> fs.checkpoint.period 3600
> mapred.combiner.class in.fossist.examples.Combine
> mapred.job.reuse.jvm.num.tasks 1
> dfs.web.ugi webuser,webgroup
> mapred.jobtracker.completeuserjobs.maximum 100
> dfs.df.interval 60000
> dfs.data.dir ${hadoop.tmp.dir}/dfs/data
> fs.s3.maxRetries 4
> dfs.datanode.dns.interface default
> mapred.local.dir ${hadoop.tmp.dir}/mapred/local
> fs.hftp.impl org.apache.hadoop.hdfs.HftpFileSystem
> dfs.permissions.supergroup supergroup
> mapred.mapper.class in.fossist.examples.Map
> fs.trash.interval 0
> fs.s3.sleepTimeSeconds 10
> dfs.replication.min 1
> mapred.submit.replication 10
> fs.har.impl org.apache.hadoop.fs.HarFileSystem
> mapred.map.output.compression.codec
> org.apache.hadoop.io.compress.DefaultCodec
> mapred.tasktracker.dns.interface default
> dfs.namenode.decommission.interval 30
> dfs.http.address 0.0.0.0:50070
> mapred.job.tracker 192.168.1.135:9001
> dfs.heartbeat.interval 3
> io.seqfile.sorter.recordlimit 1000000
> dfs.name.dir ${hadoop.tmp.dir}/dfs/name
> mapred.line.input.format.linespermap 1
> mapred.jobtracker.taskScheduler org.apache.hadoop.mapred.JobQueueTaskScheduler
> mapred.tasktracker.instrumentation
> org.apache.hadoop.mapred.TaskTrackerMetricsInst
> dfs.datanode.http.address 0.0.0.0:50075
> mapred.tasktracker.procfsbasedprocesstree.sleeptime-before-sigkill 5000
> mapred.local.dir.minspacekill 0
> dfs.replication.interval 3
> io.sort.record.percent 0.05
> fs.kfs.impl org.apache.hadoop.fs.kfs.KosmosFileSystem
> mapred.temp.dir ${hadoop.tmp.dir}/mapred/temp
> mapred.tasktracker.reduce.tasks.maximum 2
> dfs.replication 2
> fs.checkpoint.edits.dir ${fs.checkpoint.dir}
> mapred.job.reduce.input.buffer.percent 0.0
> mapred.tasktracker.indexcache.mb 10
> hadoop.logfile.count 10
> mapred.skip.reduce.auto.incr.proc.count true
> io.seqfile.compress.blocksize 1000000
> fs.s3.block.size 67108864
> mapred.tasktracker.taskmemorymanager.monitoring-interval 5000
> mapred.acls.enabled false
> mapred.queue.names default
> dfs.access.time.precision 3600000
> fs.hsftp.impl org.apache.hadoop.hdfs.HsftpFileSystem
> mapred.task.tracker.http.address 0.0.0.0:50060
> mapred.reduce.parallel.copies 5
> io.seqfile.lazydecompress true
> mapred.output.dir hdfs://192.168.1.130:9000/fossist/output5
> ipc.client.connection.maxidletime 10000
> io.sort.mb 100
> mapred.compress.map.output false
> mapred.task.tracker.report.address 127.0.0.1:0
> ipc.client.kill.max 10
> ipc.client.connect.max.retries 10
> fs.s3.impl org.apache.hadoop.fs.s3.S3FileSystem
> mapred.input.dir hdfs://192.168.1.130:9000/fossist/input
> mapred.job.tracker.http.address 0.0.0.0:50030
> io.file.buffer.size 4096
> mapred.jobtracker.restart.recover false
> io.serializations org.apache.hadoop.io.serializer.WritableSerialization
> dfs.datanode.handler.count 3
> mapred.reduce.copy.backoff 300
> mapred.task.profile false
> dfs.replication.considerLoad true
> jobclient.output.filter FAILED
> mapred.tasktracker.map.tasks.maximum 2
> io.compression.codecs
> org.apache.hadoop.io.compress.DefaultCodec,org.apache.hadoop.io.compress.GzipCodec,org.apache.hadoop.io.compress.BZip2Codec
> fs.checkpoint.size 67108864
>
