diff --git a/README b/README
index 6f3ad6e5..00912123 100644
--- a/README
+++ b/README
@@ -9,7 +9,7 @@ for the first edition at http://github.com/tomwhite/hadoop-book/tree/1e, and
for the second edition at http://github.com/tomwhite/hadoop-book/tree/2e.
This version of the code has been tested with:
- * Hadoop 1.1.1/0.22.0/0.23.0/2.0.2-alpha
+ * Hadoop 1.2.1/0.22.0/0.23.0/2.0.2-alpha
* Avro 1.5.4
* Pig 0.9.1
* Hive 0.8.0
@@ -25,7 +25,7 @@ You also need to install Maven.
Then you can build the code with:
-% mvn package -DskipTests -Dhadoop.version=1.1.1
+% mvn package -DskipTests -Dhadoop.version=1.2.1
(Note that only the Hadoop version numbers specified in hadoop-meta/pom.xml
can be used here, not any version of Hadoop.)
diff --git a/ch05/build/test/mapred/local/jobTracker/.job_20120528201803683_0001.xml.crc b/ch05/build/test/mapred/local/jobTracker/.job_20120528201803683_0001.xml.crc
deleted file mode 100644
index 0fd9a53a..00000000
Binary files a/ch05/build/test/mapred/local/jobTracker/.job_20120528201803683_0001.xml.crc and /dev/null differ
diff --git a/ch05/build/test/mapred/local/jobTracker/job_20120528201803683_0001.xml b/ch05/build/test/mapred/local/jobTracker/job_20120528201803683_0001.xml
deleted file mode 100755
index e2b25531..00000000
--- a/ch05/build/test/mapred/local/jobTracker/job_20120528201803683_0001.xml
+++ /dev/null
@@ -1,277 +0,0 @@
-
-fs.s3n.implorg.apache.hadoop.fs.s3native.NativeS3FileSystem
-mapreduce.tasktracker.tasks.sleeptimebeforesigkill5000
-dfs.datanode.data.dirfile://${hadoop.tmp.dir}/dfs/data
-dfs.namenode.checkpoint.size67108864
-mapreduce.reduce.speculativetrue
-map.sort.classorg.apache.hadoop.util.QuickSort
-hadoop.tmp.dir/tmp/hadoop-${user.name}
-dfs.namenode.decommission.nodes.per.interval5
-mapreduce.map.skip.proc.count.autoincrtrue
-ipc.client.idlethreshold4000
-mapreduce.map.maxattempts4
-mapreduce.jobtracker.heartbeats.in.second100
-dfs.datanode.data.dir.perm700
-mapreduce.tasktracker.http.address0.0.0.0:50060
-dfs.namenode.checkpoint.dirfile://${hadoop.tmp.dir}/dfs/namesecondary
-kfs.blocksize67108864
-dfs.bytes-per-checksum512
-dfs.namenode.support.allow.formattrue
-fs.trash.checkpoint.interval0
-dfs.namenode.https-address0.0.0.0:50470
-dfs.datanode.directoryscan.threads1
-dfs.datanode.address0.0.0.0:50010
-dfs.namenode.logging.levelinfo
-dfs.block.access.token.enablefalse
-io.skip.checksum.errorsfalse
-mapreduce.reduce.input.buffer.percent0.0
-mapreduce.tasktracker.instrumentationorg.apache.hadoop.mapred.TaskTrackerMetricsInst
-mapred.reducer.new-apitrue
-fs.har.impl.disable.cachetrue
-mapreduce.map.log.levelINFO
-dfs.namenode.handler.count10
-dfs.blockreport.initialDelay0
-fs.defaultFShdfs://localhost:60743
-mapreduce.job.map.classv3.MaxTemperatureMapper
-dfs.namenode.name.dirfile://${hadoop.tmp.dir}/dfs/name
-dfs.namenode.replication.interval3
-mapreduce.task.merge.progress.records10000
-hadoop.rpc.socket.factory.class.defaultorg.apache.hadoop.net.StandardSocketFactory
-dfs.namenode.http-address0.0.0.0:50070
-fs.hdfs.implorg.apache.hadoop.hdfs.DistributedFileSystem
-mapred.queue.default.acl-administer-jobs*
-mapreduce.tasktracker.healthchecker.script.timeout600000
-mapreduce.tasktracker.http.threads40
-mapreduce.job.jvm.numtasks1
-kfs.replication3
-dfs.block.access.key.update.interval600
-mapreduce.job.complete.cancel.delegation.tokenstrue
-io.mapfile.bloom.size1048576
-hadoop.rpc.protectionauthentication
-mapreduce.reduce.shuffle.connect.timeout180000
-dfs.namenode.replication.considerLoadtrue
-fs.ftp.implorg.apache.hadoop.fs.ftp.FTPFileSystem
-mapreduce.job.speculative.slownodethreshold1.0
-file.stream-buffer-size4096
-mapreduce.job.reduces1
-dfs.namenode.safemode.threshold-pct0.999f
-dfs.https.server.keystore.resourcessl-server.xml
-dfs.namenode.replication.min1
-mapreduce.job.combine.classv1.MaxTemperatureReducer
-dfs.namenode.safemode.min.datanodes0
-dfs.client.https.keystore.resourcessl-client.xml
-dfs.block.access.token.lifetime600
-mapreduce.job.speculative.slowtaskthreshold1.0
-fs.ftp.host.port21
-kfs.client-write-packet-size65536
-mapreduce.tasktracker.healthchecker.interval60000
-kfs.bytes-per-checksum512
-mapreduce.reduce.merge.inmem.threshold1000
-hadoop.security.group.mappingorg.apache.hadoop.security.ShellBasedUnixGroupsMapping
-mapreduce.client.output.filterALL
-mapreduce.job.maps1
-s3.replication3
-dfs.namenode.backup.address0.0.0.0:50100
-net.topology.node.switch.mapping.implorg.apache.hadoop.net.ScriptBasedMapping
-fs.s3.buffer.dir${hadoop.tmp.dir}/s3
-fs.file.implorg.apache.hadoop.fs.LocalFileSystem
-s3native.bytes-per-checksum512
-mapreduce.jobtracker.persist.jobstatus.hours1
-dfs.datanode.ipc.address0.0.0.0:50020
-dfs.namenode.checkpoint.edits.dir${dfs.namenode.checkpoint.dir}
-dfs.datanode.balance.bandwidthPerSec1048576
-s3.client-write-packet-size65536
-dfs.image.compression.codecorg.apache.hadoop.io.compress.DefaultCodec
-mapreduce.cluster.reducememory.mb-1
-mapreduce.reduce.shuffle.merge.percent0.66
-io.mapfile.bloom.error.rate0.005
-ftp.bytes-per-checksum512
-dfs.namenode.accesstime.precision3600000
-dfs.datanode.https.address0.0.0.0:50475
-mapreduce.map.sort.spill.percent0.80
-mapreduce.output.fileoutputformat.compression.typeRECORD
-mapreduce.job.committer.setup.cleanup.neededtrue
-dfs.replication.max512
-mapreduce.client.submit.file.replication10
-hadoop.security.authorizationfalse
-s3.bytes-per-checksum512
-dfs.namenode.checkpoint.period3600
-dfs.namenode.delegation.token.renew-interval86400000
-dfs.namenode.secondary.http-address0.0.0.0:50090
-mapreduce.jobtracker.tasktracker.maxblacklists4
-mapred.child.java.opts-Xmx200m
-mapreduce.jobtracker.persist.jobstatus.activetrue
-mapreduce.tasktracker.local.dir.minspacekill0
-mapreduce.jobtracker.webinterface.trustedfalse
-mapreduce.cluster.local.dir${hadoop.tmp.dir}/mapred/local
-ipc.server.listen.queue.size128
-dfs.permissions.enabledtrue
-mapreduce.job.queuenamedefault
-dfs.namenode.backup.http-address0.0.0.0:50105
-dfs.namenode.safemode.extension30000
-s3native.blocksize67108864
-mapreduce.jobtracker.retiredjobs.cache.size1000
-dfs.datanode.max.transfer.threads4096
-mapreduce.job.speculative.speculativecap0.1
-file.replication1
-mapreduce.map.skip.maxrecords0
-mapreduce.jobtracker.http.address127.0.0.1:60756
-ftp.client-write-packet-size65536
-hadoop.work.around.non.threadsafe.getpwuidfalse
-mapreduce.job.userlog.retain.hours24
-dfs.datanode.dns.nameserverdefault
-hadoop.util.hash.typemurmur
-mapreduce.tasktracker.taskmemorymanager.monitoringinterval5000
-dfs.blockreport.intervalMsec21600000
-dfs.client.https.need-authfalse
-mapreduce.job.acl-view-job
-mapreduce.map.speculativetrue
-io.map.index.interval128
-dfs.client.block.write.retries3
-mapreduce.reduce.shuffle.read.timeout180000
-mapreduce.input.fileinputformat.split.minsize0
-dfs.stream-buffer-size4096
-mapreduce.map.output.compressfalse
-dfs.https.enablefalse
-mapreduce.job.output.value.classorg.apache.hadoop.io.IntWritable
-mapreduce.tasktracker.dns.interfacedefault
-dfs.datanode.failed.volumes.tolerated0
-hadoop.kerberos.kinit.commandkinit
-mapreduce.output.fileoutputformat.compressfalse
-ipc.client.tcpnodelayfalse
-mapreduce.cluster.temp.dir${hadoop.tmp.dir}/mapred/temp
-fs.AbstractFileSystem.hdfs.implorg.apache.hadoop.fs.Hdfs
-mapreduce.tasktracker.local.dir.minspacestart0
-io.map.index.skip0
-ipc.server.tcpnodelayfalse
-ftp.replication3
-dfs.namenode.delegation.key.update-interval86400000
-mapreduce.job.working.dirhdfs://localhost:60743/user/tom
-mapred.mapper.new-apitrue
-mapreduce.reduce.markreset.buffer.percent0.0
-dfs.default.chunk.view.size32768
-hadoop.logfile.size10000000
-file.client-write-packet-size65536
-mapreduce.job.reduce.slowstart.completedmaps0.05
-mapreduce.job.dirhdfs://localhost:60743/tmp/hadoop-tom/mapred/staging/tom/.staging/job_20120528201803683_0001
-mapreduce.tasktracker.outofband.heartbeatfalse
-mapreduce.task.io.sort.factor10
-mapreduce.tasktracker.map.tasks.maximum2
-mapreduce.reduce.memory.mb-1
-fs.s3n.block.size67108864
-dfs.datanode.du.reserved0
-net.topology.script.number.args100
-mapreduce.client.progressmonitor.pollinterval1000
-hadoop.security.authenticationsimple
-mapreduce.jobtracker.system.dir${hadoop.tmp.dir}/mapred/system
-tfile.fs.output.buffer.size262144
-mapreduce.tasktracker.indexcache.mb10
-mapreduce.jobtracker.maxtasks.perjob-1
-dfs.web.ugiwebuser,webgroup
-hadoop.security.groups.cache.secs300
-mapreduce.jobtracker.jobhistory.lru.cache.size5
-mapreduce.map.memory.mb-1
-dfs.datanode.directoryscan.interval21600
-fs.AbstractFileSystem.file.implorg.apache.hadoop.fs.local.LocalFs
-mapreduce.reduce.skip.maxgroups0
-mapreduce.task.profilefalse
-kfs.stream-buffer-size4096
-fs.s3.maxRetries4
-dfs.datanode.dns.interfacedefault
-mapreduce.task.skip.start.attempts2
-mapreduce.task.tmp.dir./tmp
-file.blocksize67108864
-fs.ftp.host0.0.0.0
-file.bytes-per-checksum512
-dfs.image.compressfalse
-mapreduce.job.acl-modify-job
-fs.hftp.implorg.apache.hadoop.hdfs.HftpFileSystem
-mapreduce.job.submithostnameClouderas-MacBook-Pro-3.local
-mapreduce.task.profile.maps0-2
-mapreduce.jobtracker.expire.trackers.interval600000
-fs.trash.interval0
-fs.s3.sleepTimeSeconds10
-fs.har.implorg.apache.hadoop.fs.HarFileSystem
-mapreduce.cluster.mapmemory.mb-1
-mapreduce.reduce.maxattempts4
-mapreduce.client.completion.pollinterval5000
-mapreduce.tasktracker.report.address127.0.0.1:0
-dfs.namenode.decommission.interval30
-dfs.namenode.max.objects0
-ftp.stream-buffer-size4096
-mapreduce.job.output.key.classorg.apache.hadoop.io.Text
-dfs.heartbeat.interval3
-mapreduce.job.reduce.classv1.MaxTemperatureReducer
-mapreduce.tasktracker.taskcontrollerorg.apache.hadoop.mapred.DefaultTaskController
-io.seqfile.sorter.recordlimit1000000
-s3.blocksize67108864
-mapreduce.job.nameMax temperature
-dfs.datanode.http.address0.0.0.0:50075
-mapreduce.input.fileinputformat.inputdirhdfs://localhost:60743/user/tom/input
-mapreduce.jobtracker.restart.recoverfalse
-dfs.image.transfer.bandwidthPerSec0
-mapreduce.task.profile.reduces0-2
-s3native.stream-buffer-size4096
-dfs.namenode.edits.dir${dfs.namenode.name.dir}
-mapreduce.output.fileoutputformat.outputdiroutput
-mapreduce.output.fileoutputformat.compression.codecorg.apache.hadoop.io.compress.DefaultCodec
-mapreduce.job.end-notification.retry.attempts0
-fs.kfs.implorg.apache.hadoop.fs.kfs.KosmosFileSystem
-dfs.replication3
-mapreduce.jobtracker.jobhistory.block.size3145728
-mapreduce.jobtracker.addresslocalhost:60755
-mapreduce.task.timeout600000
-mapreduce.input.fileinputformat.numinputfiles1
-mapreduce.reduce.shuffle.input.buffer.percent0.70
-dfs.client-write-packet-size65536
-mapreduce.job.split.metainfo.maxsize10000000
-hadoop.logfile.count10
-fs.automatic.closetrue
-mapreduce.job.submithostaddress192.168.2.17
-s3.stream-buffer-size4096
-io.seqfile.compress.blocksize1000000
-mapreduce.jobtracker.maxmapmemory.mb-1
-fs.s3.block.size67108864
-mapreduce.jobtracker.taskcache.levels2
-mapreduce.jobtracker.staging.root.dir${hadoop.tmp.dir}/mapred/staging
-ftp.blocksize67108864
-fs.hsftp.implorg.apache.hadoop.hdfs.HsftpFileSystem
-mapreduce.job.maxtaskfailures.per.tracker4
-mapreduce.tasktracker.reduce.tasks.maximum2
-io.seqfile.lazydecompresstrue
-mapreduce.jobtracker.handler.count10
-mapreduce.jobtracker.persist.jobstatus.dir/jobtracker/jobsInfo
-hadoop.common.configuration.version0.22.0
-dfs.permissions.superusergroupsupergroup
-mapreduce.cluster.acls.enabledfalse
-mapreduce.reduce.skip.proc.count.autoincrtrue
-ipc.client.connection.maxidletime10000
-mapreduce.job.end-notification.retry.interval30000
-mapreduce.jobtracker.instrumentationorg.apache.hadoop.mapred.JobTrackerMetricsInst
-mapreduce.tasktracker.dns.nameserverdefault
-ipc.client.kill.max10
-ipc.client.connect.max.retries10
-hadoop.hdfs.configuration.version1
-fs.s3.implorg.apache.hadoop.fs.s3.S3FileSystem
-dfs.blocksize67108864
-io.seqfile.local.dir${hadoop.tmp.dir}/io/local
-mapreduce.jobtracker.maxreducememory.mb-1
-io.native.lib.availabletrue
-io.file.buffer.size4096
-io.serializationsorg.apache.hadoop.io.serializer.WritableSerialization,org.apache.hadoop.io.serializer.avro.AvroSpecificSerialization,org.apache.hadoop.io.serializer.avro.AvroReflectSerialization
-dfs.datanode.handler.count3
-mapreduce.task.userlog.limit.kb0
-tfile.fs.input.buffer.size262144
-mapreduce.reduce.shuffle.parallelcopies5
-mapreduce.task.io.sort.mb100
-mapreduce.reduce.log.levelINFO
-mapreduce.map.output.compress.codecorg.apache.hadoop.io.compress.DefaultCodec
-fs.df.interval60000
-dfs.namenode.delegation.token.max-lifetime604800000
-mapreduce.task.files.preserve.failedtasksfalse
-s3native.client-write-packet-size65536
-s3native.replication3
-io.compression.codecsorg.apache.hadoop.io.compress.DefaultCodec,org.apache.hadoop.io.compress.GzipCodec,org.apache.hadoop.io.compress.BZip2Codec
-mapreduce.jobtracker.taskschedulerorg.apache.hadoop.mapred.JobQueueTaskScheduler
-tfile.io.chunk.size1048576
-
\ No newline at end of file
diff --git a/hadoop-meta/pom.xml b/hadoop-meta/pom.xml
index 8ffdf457..36afa64e 100644
--- a/hadoop-meta/pom.xml
+++ b/hadoop-meta/pom.xml
@@ -32,11 +32,11 @@ A module which allows the Hadoop dependencies to be specified by a Maven profile
hadoop.version
- 1.1.2
+ 1.2.1
- 1.1.2
+ 1.2.1