You are viewing a plain text version of this content. The canonical link for it is here.
Posted to mapreduce-commits@hadoop.apache.org by su...@apache.org on 2012/10/12 02:15:43 UTC
svn commit: r1397387 [1/2] - in
/hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project: ./ bin/
conf/
hadoop-mapreduce-client/hadoop-mapreduce-client-app/src/main/java/org/apache/hadoop/mapreduce/v2/app/
hadoop-mapreduce-client/hadoop-mapred...
Author: suresh
Date: Fri Oct 12 00:15:22 2012
New Revision: 1397387
URL: http://svn.apache.org/viewvc?rev=1397387&view=rev
Log:
Merging all the changes from trunk
Added:
hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-jobclient/src/test/java/org/apache/hadoop/mapreduce/security/CredentialsTestJob.java
- copied unchanged from r1397380, hadoop/common/trunk/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-jobclient/src/test/java/org/apache/hadoop/mapreduce/security/CredentialsTestJob.java
hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-jobclient/src/test/java/org/apache/hadoop/mapreduce/security/TestMRCredentials.java
- copied unchanged from r1397380, hadoop/common/trunk/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-jobclient/src/test/java/org/apache/hadoop/mapreduce/security/TestMRCredentials.java
Modified:
hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/ (props changed)
hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/CHANGES.txt (contents, props changed)
hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/bin/mapred
hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/bin/mapred-config.sh
hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/bin/mr-jobhistory-daemon.sh
hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/conf/ (props changed)
hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-app/src/main/java/org/apache/hadoop/mapreduce/v2/app/MRAppMaster.java
hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-app/src/main/java/org/apache/hadoop/mapreduce/v2/app/client/MRClientService.java
hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-app/src/main/java/org/apache/hadoop/mapreduce/v2/app/job/impl/TaskAttemptImpl.java
hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-app/src/test/java/org/apache/hadoop/mapreduce/v2/app/TestStagingCleanup.java
hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/MapTask.java
hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/lib/TotalOrderPartitioner.java
hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/lib/output/LazyOutputFormat.java
hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/lib/output/MultipleOutputs.java
hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/lib/partition/TotalOrderPartitioner.java
hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/resources/mapred-default.xml (contents, props changed)
hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-hs/src/main/java/org/apache/hadoop/mapreduce/v2/hs/CompletedTask.java
hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-hs/src/main/java/org/apache/hadoop/mapreduce/v2/hs/HistoryFileManager.java
hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-hs/src/test/java/org/apache/hadoop/mapreduce/v2/hs/TestJobHistoryParsing.java
hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-jobclient/src/main/java/org/apache/hadoop/mapred/YARNRunner.java
hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-jobclient/src/test/java/org/apache/hadoop/mapreduce/lib/partition/TestTotalOrderPartitioner.java
hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/hadoop-mapreduce-examples/src/main/java/org/apache/hadoop/examples/dancing/DistributedPentomino.java
hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/pom.xml
hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/src/c++/ (props changed)
hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/src/contrib/ (props changed)
hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/src/contrib/block_forensics/ (props changed)
hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/src/contrib/build-contrib.xml (props changed)
hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/src/contrib/build.xml (props changed)
hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/src/contrib/data_join/ (props changed)
hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/src/contrib/eclipse-plugin/ (props changed)
hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/src/contrib/index/ (props changed)
hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/src/contrib/vaidya/ (props changed)
hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/src/examples/ (props changed)
hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/src/java/ (props changed)
hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/src/test/mapred/ (props changed)
hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/src/test/mapred/org/apache/hadoop/fs/ (props changed)
hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/src/test/mapred/org/apache/hadoop/hdfs/ (props changed)
hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/src/test/mapred/org/apache/hadoop/ipc/ (props changed)
hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/src/test/mapred/org/apache/hadoop/mapred/TestJobQueueInformation.java
hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/src/test/mapred/org/apache/hadoop/mapred/TestSetupAndCleanupFailure.java
hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/src/test/mapred/org/apache/hadoop/mapred/UtilsForTests.java
hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/src/webapps/job/ (props changed)
Propchange: hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/
------------------------------------------------------------------------------
Merged /hadoop/common/branches/HDFS-3077/hadoop-mapreduce-project:r1363593-1396941
Merged /hadoop/common/trunk/hadoop-mapreduce-project:r1390763-1397380
Modified: hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/CHANGES.txt
URL: http://svn.apache.org/viewvc/hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/CHANGES.txt?rev=1397387&r1=1397386&r2=1397387&view=diff
==============================================================================
--- hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/CHANGES.txt (original)
+++ hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/CHANGES.txt Fri Oct 12 00:15:22 2012
@@ -130,14 +130,34 @@ Trunk (Unreleased)
MAPREDUCE-4685. DBCount should not use ACCESS. (Viji via harsh)
+ MAPREDUCE-3223. Remove MR1 configs from mapred-default.xml (tlipcon via harsh)
+
+ MAPREDUCE-4678. Running the Pentomino example with defaults throws
+ java.lang.NegativeArraySizeException (Chris McConnell via harsh)
+
+ MAPREDUCE-4695. Fix LocalRunner on trunk after MAPREDUCE-3223 broke it
+ (harsh)
+
+ MAPREDUCE-4574. Fix TotalOrderParitioner to work with
+ non-WritableComparable key types. (harsh)
+
Release 2.0.3-alpha - Unreleased
INCOMPATIBLE CHANGES
+ MAPREDUCE-4123. Remove the 'mapred groups' command, which is no longer
+ supported. (Devaraj K via sseth)
+
NEW FEATURES
IMPROVEMENTS
+ MAPREDUCE-3678. The Map tasks logs should have the value of input
+ split it processed. (harsh)
+
+ MAPREDUCE-4616. Improve javadoc for MultipleOutputs. (Tony Burton via
+ acmurthy)
+
OPTIMIZATIONS
BUG FIXES
@@ -151,6 +171,13 @@ Release 2.0.3-alpha - Unreleased
MAPREDUCE-4674. Hadoop examples secondarysort has a typo
"secondarysrot" in the usage. (Robert Justice via eli)
+ MAPREDUCE-4681. Fix unit tests broken by HDFS-3910. (acmurthy)
+
+ MAPREDUCE-4712. mr-jobhistory-daemon.sh doesn't accept --config
+ (Vinod Kumar Vavilapalli via tgraves)
+
+ MAPREDUCE-4654. TestDistCp is ignored. (Sandy Ryza via tomwhite)
+
Release 2.0.2-alpha - 2012-09-07
INCOMPATIBLE CHANGES
@@ -527,6 +554,25 @@ Release 2.0.0-alpha - 05-23-2012
MAPREDUCE-4444. nodemanager fails to start when one of the local-dirs is
bad (Jason Lowe via bobby)
+Release 0.23.5 - UNRELEASED
+
+ INCOMPATIBLE CHANGES
+
+ NEW FEATURES
+
+ IMPROVEMENTS
+
+ OPTIMIZATIONS
+
+ BUG FIXES
+
+ MAPREDUCE-4554. Job Credentials are not transmitted if security is turned
+ off (Benoy Antony via bobby)
+
+ MAPREDUCE-4705. Fix a bug in job history lookup, which makes older jobs
+ inaccessible despite the presence of a valid history file. (Jason Lowe
+ via sseth)
+
Release 0.23.4 - UNRELEASED
INCOMPATIBLE CHANGES
@@ -550,7 +596,13 @@ Release 0.23.4 - UNRELEASED
MAPREDUCE-4647. We should only unjar jobjar if there is a lib directory
in it. (Robert Evans via tgraves)
-Release 0.23.3 - UNRELEASED
+ MAPREDUCE-4691. Historyserver can report "Unknown job" after RM says job
+ has completed (Robert Joseph Evans via jlowe)
+
+ MAPREDUCE-4689. JobClient.getMapTaskReports on failed job results in NPE
+ (jlowe via bobby)
+
+Release 0.23.3
INCOMPATIBLE CHANGES
Propchange: hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/CHANGES.txt
------------------------------------------------------------------------------
Merged /hadoop/common/branches/HDFS-3077/hadoop-mapreduce-project/CHANGES.txt:r1363593-1396941
Merged /hadoop/common/trunk/hadoop-mapreduce-project/CHANGES.txt:r1390763-1397380
Modified: hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/bin/mapred
URL: http://svn.apache.org/viewvc/hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/bin/mapred?rev=1397387&r1=1397386&r2=1397387&view=diff
==============================================================================
--- hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/bin/mapred (original)
+++ hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/bin/mapred Fri Oct 12 00:15:22 2012
@@ -17,7 +17,7 @@
bin=`which $0`
bin=`dirname ${bin}`
-bin=`cd "$bin"; pwd`
+bin=`cd "$bin" > /dev/null; pwd`
DEFAULT_LIBEXEC_DIR="$bin"/../libexec
HADOOP_LIBEXEC_DIR=${HADOOP_LIBEXEC_DIR:-$DEFAULT_LIBEXEC_DIR}
@@ -35,7 +35,6 @@ function print_usage(){
echo " queue get information regarding JobQueues"
echo " classpath prints the class path needed for running"
echo " mapreduce subcommands"
- echo " groups get the groups which users belong to"
echo " historyserver run job history servers as a standalone daemon"
echo " distcp <srcurl> <desturl> copy file or directories recursively"
echo " archive -archiveName NAME -p <parent path> <src>* <dest> create a hadoop archive"
@@ -63,9 +62,6 @@ elif [ "$COMMAND" = "sampler" ] ; then
HADOOP_OPTS="$HADOOP_OPTS $HADOOP_CLIENT_OPTS"
elif [ "$COMMAND" = "classpath" ] ; then
echo -n
-elif [ "$COMMAND" = "groups" ] ; then
- CLASS=org.apache.hadoop.mapred.tools.GetGroups
- HADOOP_OPTS="$HADOOP_OPTS $HADOOP_CLIENT_OPTS"
elif [ "$COMMAND" = "historyserver" ] ; then
CLASS=org.apache.hadoop.mapreduce.v2.hs.JobHistoryServer
HADOOP_OPTS="$HADOOP_OPTS -Dmapred.jobsummary.logger=${HADOOP_JHS_LOGGER:-INFO,console} $HADOOP_JOB_HISTORYSERVER_OPTS"
@@ -74,7 +70,8 @@ elif [ "$COMMAND" = "historyserver" ] ;
fi
elif [ "$COMMAND" = "mradmin" ] \
|| [ "$COMMAND" = "jobtracker" ] \
- || [ "$COMMAND" = "tasktracker" ] ; then
+ || [ "$COMMAND" = "tasktracker" ] \
+ || [ "$COMMAND" = "groups" ] ; then
echo "Sorry, the $COMMAND command is no longer supported."
echo "You may find similar functionality with the \"yarn\" shell command."
print_usage
Modified: hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/bin/mapred-config.sh
URL: http://svn.apache.org/viewvc/hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/bin/mapred-config.sh?rev=1397387&r1=1397386&r2=1397387&view=diff
==============================================================================
--- hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/bin/mapred-config.sh (original)
+++ hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/bin/mapred-config.sh Fri Oct 12 00:15:22 2012
@@ -39,11 +39,12 @@ else
exit
fi
-# some more specific variables
-export HADOOP_MAPRED_LOG_DIR=${HADOOP_MAPRED_LOG_DIR:-${HADOOP_MAPRED_HOME}/logs}
-export HADOOP_MAPRED_LOGFILE=${HADOOP_MAPRED_LOGFILE:-hadoop.log}
-
+# Only set locally to use in HADOOP_OPTS. No need to export.
+# The following defaults are useful when somebody directly invokes bin/mapred.
+HADOOP_MAPRED_LOG_DIR=${HADOOP_MAPRED_LOG_DIR:-${HADOOP_MAPRED_HOME}/logs}
+HADOOP_MAPRED_LOGFILE=${HADOOP_MAPRED_LOGFILE:-hadoop.log}
HADOOP_MAPRED_ROOT_LOGGER=${HADOOP_MAPRED_ROOT_LOGGER:-INFO,console}
+
HADOOP_OPTS="$HADOOP_OPTS -Dhadoop.log.dir=$HADOOP_MAPRED_LOG_DIR"
HADOOP_OPTS="$HADOOP_OPTS -Dhadoop.log.file=$HADOOP_MAPRED_LOGFILE"
export HADOOP_OPTS="$HADOOP_OPTS -Dhadoop.root.logger=${HADOOP_MAPRED_ROOT_LOGGER}"
Modified: hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/bin/mr-jobhistory-daemon.sh
URL: http://svn.apache.org/viewvc/hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/bin/mr-jobhistory-daemon.sh?rev=1397387&r1=1397386&r2=1397387&view=diff
==============================================================================
--- hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/bin/mr-jobhistory-daemon.sh (original)
+++ hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/bin/mr-jobhistory-daemon.sh Fri Oct 12 00:15:22 2012
@@ -36,6 +36,12 @@ fi
bin=`dirname "${BASH_SOURCE-$0}"`
bin=`cd "$bin"; pwd`
+DEFAULT_LIBEXEC_DIR="$bin"/../libexec
+HADOOP_LIBEXEC_DIR=${HADOOP_LIBEXEC_DIR:-$DEFAULT_LIBEXEC_DIR}
+if [ -e ${HADOOP_LIBEXEC_DIR}/mapred-config.sh ]; then
+ . $HADOOP_LIBEXEC_DIR/mapred-config.sh
+fi
+
# get arguments
startStop=$1
shift
@@ -68,10 +74,6 @@ export HADOOP_MAPRED_LOGFILE=mapred-$HAD
export HADOOP_MAPRED_ROOT_LOGGER=${HADOOP_MAPRED_ROOT_LOGGER:-INFO,RFA}
export HADOOP_JHS_LOGGER=${HADOOP_JHS_LOGGER:-INFO,JSA}
-DEFAULT_LIBEXEC_DIR="$bin"/../libexec
-HADOOP_LIBEXEC_DIR=${HADOOP_LIBEXEC_DIR:-$DEFAULT_LIBEXEC_DIR}
-. $HADOOP_LIBEXEC_DIR/mapred-config.sh
-
if [ -f "${HADOOP_CONF_DIR}/mapred-env.sh" ]; then
. "${HADOOP_CONF_DIR}/mapred-env.sh"
fi
Propchange: hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/conf/
------------------------------------------------------------------------------
Merged /hadoop/common/branches/HDFS-3077/hadoop-mapreduce-project/conf:r1363593-1396941
Merged /hadoop/common/trunk/hadoop-mapreduce-project/conf:r1390763-1397380
Modified: hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-app/src/main/java/org/apache/hadoop/mapreduce/v2/app/MRAppMaster.java
URL: http://svn.apache.org/viewvc/hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-app/src/main/java/org/apache/hadoop/mapreduce/v2/app/MRAppMaster.java?rev=1397387&r1=1397386&r2=1397387&view=diff
==============================================================================
--- hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-app/src/main/java/org/apache/hadoop/mapreduce/v2/app/MRAppMaster.java (original)
+++ hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-app/src/main/java/org/apache/hadoop/mapreduce/v2/app/MRAppMaster.java Fri Oct 12 00:15:22 2012
@@ -490,19 +490,17 @@ public class MRAppMaster extends Composi
try {
this.currentUser = UserGroupInformation.getCurrentUser();
- if (UserGroupInformation.isSecurityEnabled()) {
- // Read the file-system tokens from the localized tokens-file.
- Path jobSubmitDir =
- FileContext.getLocalFSFileContext().makeQualified(
- new Path(new File(MRJobConfig.JOB_SUBMIT_DIR)
- .getAbsolutePath()));
- Path jobTokenFile =
- new Path(jobSubmitDir, MRJobConfig.APPLICATION_TOKENS_FILE);
- fsTokens.addAll(Credentials.readTokenStorageFile(jobTokenFile, conf));
- LOG.info("jobSubmitDir=" + jobSubmitDir + " jobTokenFile="
- + jobTokenFile);
- currentUser.addCredentials(fsTokens); // For use by AppMaster itself.
- }
+ // Read the file-system tokens from the localized tokens-file.
+ Path jobSubmitDir =
+ FileContext.getLocalFSFileContext().makeQualified(
+ new Path(new File(MRJobConfig.JOB_SUBMIT_DIR)
+ .getAbsolutePath()));
+ Path jobTokenFile =
+ new Path(jobSubmitDir, MRJobConfig.APPLICATION_TOKENS_FILE);
+ fsTokens.addAll(Credentials.readTokenStorageFile(jobTokenFile, conf));
+ LOG.info("jobSubmitDir=" + jobSubmitDir + " jobTokenFile="
+ + jobTokenFile);
+ currentUser.addCredentials(fsTokens); // For use by AppMaster itself.
} catch (IOException e) {
throw new YarnException(e);
}
Modified: hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-app/src/main/java/org/apache/hadoop/mapreduce/v2/app/client/MRClientService.java
URL: http://svn.apache.org/viewvc/hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-app/src/main/java/org/apache/hadoop/mapreduce/v2/app/client/MRClientService.java?rev=1397387&r1=1397386&r2=1397387&view=diff
==============================================================================
--- hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-app/src/main/java/org/apache/hadoop/mapreduce/v2/app/client/MRClientService.java (original)
+++ hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-app/src/main/java/org/apache/hadoop/mapreduce/v2/app/client/MRClientService.java Fri Oct 12 00:15:22 2012
@@ -82,8 +82,7 @@ import org.apache.hadoop.yarn.factories.
import org.apache.hadoop.yarn.factory.providers.RecordFactoryProvider;
import org.apache.hadoop.yarn.ipc.RPCUtil;
import org.apache.hadoop.yarn.ipc.YarnRPC;
-import org.apache.hadoop.yarn.security.client.ClientToAMSecretManager;
-import org.apache.hadoop.yarn.security.client.ClientTokenIdentifier;
+import org.apache.hadoop.yarn.security.client.ClientToAMTokenSecretManager;
import org.apache.hadoop.yarn.service.AbstractService;
import org.apache.hadoop.yarn.webapp.WebApp;
import org.apache.hadoop.yarn.webapp.WebApps;
@@ -115,16 +114,15 @@ public class MRClientService extends Abs
YarnRPC rpc = YarnRPC.create(conf);
InetSocketAddress address = new InetSocketAddress(0);
- ClientToAMSecretManager secretManager = null;
+ ClientToAMTokenSecretManager secretManager = null;
if (UserGroupInformation.isSecurityEnabled()) {
- secretManager = new ClientToAMSecretManager();
String secretKeyStr =
System
.getenv(ApplicationConstants.APPLICATION_CLIENT_SECRET_ENV_NAME);
byte[] bytes = Base64.decodeBase64(secretKeyStr);
- ClientTokenIdentifier identifier = new ClientTokenIdentifier(
- this.appContext.getApplicationID());
- secretManager.setMasterKey(identifier, bytes);
+ secretManager =
+ new ClientToAMTokenSecretManager(this.appContext.getApplicationID(),
+ bytes);
}
server =
rpc.getServer(MRClientProtocol.class, protocolHandler, address,
Modified: hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-app/src/main/java/org/apache/hadoop/mapreduce/v2/app/job/impl/TaskAttemptImpl.java
URL: http://svn.apache.org/viewvc/hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-app/src/main/java/org/apache/hadoop/mapreduce/v2/app/job/impl/TaskAttemptImpl.java?rev=1397387&r1=1397386&r2=1397387&view=diff
==============================================================================
--- hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-app/src/main/java/org/apache/hadoop/mapreduce/v2/app/job/impl/TaskAttemptImpl.java (original)
+++ hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-app/src/main/java/org/apache/hadoop/mapreduce/v2/app/job/impl/TaskAttemptImpl.java Fri Oct 12 00:15:22 2012
@@ -647,14 +647,10 @@ public abstract class TaskAttemptImpl im
MRApps.setupDistributedCache(conf, localResources);
// Setup up task credentials buffer
- Credentials taskCredentials = new Credentials();
-
- if (UserGroupInformation.isSecurityEnabled()) {
- LOG.info("Adding #" + credentials.numberOfTokens()
- + " tokens and #" + credentials.numberOfSecretKeys()
- + " secret keys for NM use for launching container");
- taskCredentials.addAll(credentials);
- }
+ LOG.info("Adding #" + credentials.numberOfTokens()
+ + " tokens and #" + credentials.numberOfSecretKeys()
+ + " secret keys for NM use for launching container");
+ Credentials taskCredentials = new Credentials(credentials);
// LocalStorageToken is needed irrespective of whether security is enabled
// or not.
Modified: hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-app/src/test/java/org/apache/hadoop/mapreduce/v2/app/TestStagingCleanup.java
URL: http://svn.apache.org/viewvc/hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-app/src/test/java/org/apache/hadoop/mapreduce/v2/app/TestStagingCleanup.java?rev=1397387&r1=1397386&r2=1397387&view=diff
==============================================================================
--- hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-app/src/test/java/org/apache/hadoop/mapreduce/v2/app/TestStagingCleanup.java (original)
+++ hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-app/src/test/java/org/apache/hadoop/mapreduce/v2/app/TestStagingCleanup.java Fri Oct 12 00:15:22 2012
@@ -179,6 +179,10 @@ import org.junit.Test;
public Configuration getConfig() {
return conf;
}
+
+ @Override
+ protected void downloadTokensAndSetupUGI(Configuration conf) {
+ }
}
private final class MRAppTestCleanup extends MRApp {
@@ -266,4 +270,4 @@ import org.junit.Test;
Assert.assertTrue("Staging directory not cleaned before notifying RM",
app.cleanedBeforeContainerAllocatorStopped);
}
- }
\ No newline at end of file
+ }
Modified: hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/MapTask.java
URL: http://svn.apache.org/viewvc/hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/MapTask.java?rev=1397387&r1=1397386&r2=1397387&view=diff
==============================================================================
--- hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/MapTask.java (original)
+++ hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/MapTask.java Fri Oct 12 00:15:22 2012
@@ -424,6 +424,7 @@ class MapTask extends Task {
job.setLong(JobContext.MAP_INPUT_START, fileSplit.getStart());
job.setLong(JobContext.MAP_INPUT_PATH, fileSplit.getLength());
}
+ LOG.info("Processing split: " + inputSplit);
}
static class NewTrackingRecordReader<K,V>
@@ -694,6 +695,7 @@ class MapTask extends Task {
org.apache.hadoop.mapreduce.InputSplit split = null;
split = getSplitDetails(new Path(splitIndex.getSplitLocation()),
splitIndex.getStartOffset());
+ LOG.info("Processing split: " + split);
org.apache.hadoop.mapreduce.RecordReader<INKEY,INVALUE> input =
new NewTrackingRecordReader<INKEY,INVALUE>
Modified: hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/lib/TotalOrderPartitioner.java
URL: http://svn.apache.org/viewvc/hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/lib/TotalOrderPartitioner.java?rev=1397387&r1=1397386&r2=1397387&view=diff
==============================================================================
--- hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/lib/TotalOrderPartitioner.java (original)
+++ hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/lib/TotalOrderPartitioner.java Fri Oct 12 00:15:22 2012
@@ -31,7 +31,7 @@ import org.apache.hadoop.mapred.Partitio
*/
@InterfaceAudience.Public
@InterfaceStability.Stable
-public class TotalOrderPartitioner<K extends WritableComparable<?>,V>
+public class TotalOrderPartitioner<K ,V>
extends org.apache.hadoop.mapreduce.lib.partition.TotalOrderPartitioner<K, V>
implements Partitioner<K,V> {
Modified: hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/lib/output/LazyOutputFormat.java
URL: http://svn.apache.org/viewvc/hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/lib/output/LazyOutputFormat.java?rev=1397387&r1=1397386&r2=1397387&view=diff
==============================================================================
--- hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/lib/output/LazyOutputFormat.java (original)
+++ hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/lib/output/LazyOutputFormat.java Fri Oct 12 00:15:22 2012
@@ -32,7 +32,10 @@ import org.apache.hadoop.mapreduce.TaskA
import org.apache.hadoop.util.ReflectionUtils;
/**
- * A Convenience class that creates output lazily.
+ * A Convenience class that creates output lazily.
+ * Use in conjuction with org.apache.hadoop.mapreduce.lib.output.MultipleOutputs to recreate the
+ * behaviour of org.apache.hadoop.mapred.lib.MultipleTextOutputFormat (etc) of the old Hadoop API.
+ * See {@link MultipleOutputs} documentation for more information.
*/
@InterfaceAudience.Public
@InterfaceStability.Stable
Modified: hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/lib/output/MultipleOutputs.java
URL: http://svn.apache.org/viewvc/hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/lib/output/MultipleOutputs.java?rev=1397387&r1=1397386&r2=1397387&view=diff
==============================================================================
--- hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/lib/output/MultipleOutputs.java (original)
+++ hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/lib/output/MultipleOutputs.java Fri Oct 12 00:15:22 2012
@@ -20,7 +20,10 @@ package org.apache.hadoop.mapreduce.lib.
import org.apache.hadoop.classification.InterfaceAudience;
import org.apache.hadoop.classification.InterfaceStability;
import org.apache.hadoop.conf.Configuration;
+import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.*;
+import org.apache.hadoop.mapreduce.Reducer.Context;
+import org.apache.hadoop.mapreduce.lib.output.MultipleOutputs;
import org.apache.hadoop.mapreduce.task.TaskAttemptContextImpl;
import org.apache.hadoop.util.ReflectionUtils;
@@ -37,6 +40,7 @@ import java.util.*;
* Each additional output, or named output, may be configured with its own
* <code>OutputFormat</code>, with its own key class and with its own value
* class.
+ * </p>
*
* <p>
* Case two: to write data to different files provided by user
@@ -107,6 +111,64 @@ import java.util.*;
*
* }
* </pre>
+ *
+ * <p>
+ * When used in conjuction with org.apache.hadoop.mapreduce.lib.output.LazyOutputFormat,
+ * MultipleOutputs can mimic the behaviour of MultipleTextOutputFormat and MultipleSequenceFileOutputFormat
+ * from the old Hadoop API - ie, output can be written from the Reducer to more than one location.
+ * </p>
+ *
+ * <p>
+ * Use <code>MultipleOutputs.write(KEYOUT key, VALUEOUT value, String baseOutputPath)</code> to write key and
+ * value to a path specified by <code>baseOutputPath</code>, with no need to specify a named output:
+ * </p>
+ *
+ * <pre>
+ * private MultipleOutputs<Text, Text> out;
+ *
+ * public void setup(Context context) {
+ * out = new MultipleOutputs<Text, Text>(context);
+ * ...
+ * }
+ *
+ * public void reduce(Text key, Iterable<Text> values, Context context) throws IOException, InterruptedException {
+ * for (Text t : values) {
+ * out.write(key, t, generateFileName(<<i>parameter list...</i>>));
+ * }
+ * }
+ *
+ * protected void cleanup(Context context) throws IOException, InterruptedException {
+ * out.close();
+ * }
+ * </pre>
+ *
+ * <p>
+ * Use your own code in <code>generateFileName()</code> to create a custom path to your results.
+ * '/' characters in <code>baseOutputPath</code> will be translated into directory levels in your file system.
+ * Also, append your custom-generated path with "part" or similar, otherwise your output will be -00000, -00001 etc.
+ * No call to <code>context.write()</code> is necessary. See example <code>generateFileName()</code> code below.
+ * </p>
+ *
+ * <pre>
+ * private String generateFileName(Text k) {
+ * // expect Text k in format "Surname|Forename"
+ * String[] kStr = k.toString().split("\\|");
+ *
+ * String sName = kStr[0];
+ * String fName = kStr[1];
+ *
+ * // example for k = Smith|John
+ * // output written to /user/hadoop/path/to/output/Smith/John-r-00000 (etc)
+ * return sName + "/" + fName;
+ * }
+ * </pre>
+ *
+ * <p>
+ * Using MultipleOutputs in this way will still create zero-sized default output, eg part-00000.
+ * To prevent this use <code>LazyOutputFormat.setOutputFormatClass(job, TextOutputFormat.class);</code>
+ * instead of <code>job.setOutputFormatClass(TextOutputFormat.class);</code> in your Hadoop job configuration.
+ * </p>
+ *
*/
@InterfaceAudience.Public
@InterfaceStability.Stable
Modified: hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/lib/partition/TotalOrderPartitioner.java
URL: http://svn.apache.org/viewvc/hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/lib/partition/TotalOrderPartitioner.java?rev=1397387&r1=1397386&r2=1397387&view=diff
==============================================================================
--- hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/lib/partition/TotalOrderPartitioner.java (original)
+++ hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/lib/partition/TotalOrderPartitioner.java Fri Oct 12 00:15:22 2012
@@ -47,7 +47,7 @@ import org.apache.hadoop.util.Reflection
*/
@InterfaceAudience.Public
@InterfaceStability.Stable
-public class TotalOrderPartitioner<K extends WritableComparable<?>,V>
+public class TotalOrderPartitioner<K,V>
extends Partitioner<K,V> implements Configurable {
private Node partitions;
@@ -298,12 +298,13 @@ public class TotalOrderPartitioner<K ext
@SuppressWarnings("unchecked") // map output key class
private K[] readPartitions(FileSystem fs, Path p, Class<K> keyClass,
Configuration conf) throws IOException {
- SequenceFile.Reader reader = new SequenceFile.Reader(fs, p, conf);
+ SequenceFile.Reader reader = new SequenceFile.Reader(
+ conf,
+ SequenceFile.Reader.file(p));
ArrayList<K> parts = new ArrayList<K>();
K key = ReflectionUtils.newInstance(keyClass, conf);
- NullWritable value = NullWritable.get();
try {
- while (reader.next(key, value)) {
+ while ((key = (K) reader.next(key)) != null) {
parts.add(key);
key = ReflectionUtils.newInstance(keyClass, conf);
}
Modified: hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/resources/mapred-default.xml
URL: http://svn.apache.org/viewvc/hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/resources/mapred-default.xml?rev=1397387&r1=1397386&r2=1397387&view=diff
==============================================================================
--- hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/resources/mapred-default.xml (original)
+++ hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/resources/mapred-default.xml Fri Oct 12 00:15:22 2012
@@ -24,47 +24,6 @@
<configuration>
<property>
- <name>mapreduce.jobtracker.jobhistory.location</name>
- <value></value>
- <description> 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.
- </description>
-</property>
-
-<property>
- <name>mapreduce.jobtracker.jobhistory.task.numberprogresssplits</name>
- <value>12</value>
- <description> Every task attempt progresses from 0.0 to 1.0 [unless
- it fails or is killed]. We record, for each task attempt, certain
- statistics over each twelfth of the progress range. You can change
- the number of intervals we divide the entire range of progress into
- by setting this property. Higher values give more precision to the
- recorded data, but costs more memory in the job tracker at runtime.
- Each increment in this attribute costs 16 bytes per running task.
- </description>
-</property>
-
-<property>
- <name>mapreduce.job.userhistorylocation</name>
- <value></value>
- <description> 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".
- </description>
-</property>
-
-<property>
- <name>mapreduce.jobtracker.jobhistory.completed.location</name>
- <value></value>
- <description> The completed job history files are stored at this single well
- known location. If nothing is specified, the files are stored at
- ${mapreduce.jobtracker.jobhistory.location}/done.
- </description>
-</property>
-
-<property>
<name>mapreduce.job.committer.setup.cleanup.needed</name>
<value>true</value>
<description> true, if job needs job-setup and job-cleanup.
@@ -99,15 +58,6 @@
</property>
<property>
- <name>mapreduce.jobtracker.address</name>
- <value>local</value>
- <description>The host and port that the MapReduce job tracker runs
- at. If "local", then jobs are run in-process as a single map
- and reduce task.
- </description>
-</property>
-
-<property>
<name>mapreduce.local.clientfactory.class.name</name>
<value>org.apache.hadoop.mapred.LocalClientFactory</value>
<description>This the client factory that is responsible for
@@ -115,138 +65,10 @@
</property>
<property>
- <name>mapreduce.jobtracker.http.address</name>
- <value>0.0.0.0:50030</value>
- <description>
- The job tracker http server address and port the server will listen on.
- If the port is 0 then the server will start on a free port.
- </description>
-</property>
-
-<property>
- <name>mapreduce.jobtracker.handler.count</name>
- <value>10</value>
- <description>
- The number of server threads for the JobTracker. This should be roughly
- 4% of the number of tasktracker nodes.
- </description>
-</property>
-
-<property>
- <name>mapreduce.tasktracker.report.address</name>
- <value>127.0.0.1:0</value>
- <description>The interface and port that task tracker server listens on.
- Since it is only connected to by the tasks, it uses the local interface.
- EXPERT ONLY. Should only be changed if your host does not have the loopback
- interface.</description>
-</property>
-
-<property>
- <name>mapreduce.cluster.local.dir</name>
- <value>${hadoop.tmp.dir}/mapred/local</value>
- <description>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.
- </description>
-</property>
-
-<property>
- <name>mapreduce.jobtracker.system.dir</name>
- <value>${hadoop.tmp.dir}/mapred/system</value>
- <description>The directory where MapReduce stores control files.
- </description>
-</property>
-
-<property>
- <name>mapreduce.jobtracker.staging.root.dir</name>
- <value>${hadoop.tmp.dir}/mapred/staging</value>
- <description>The root of the staging area for users' job files
- In practice, this should be the directory where users' home
- directories are located (usually /user)
- </description>
-</property>
-
-<property>
- <name>mapreduce.cluster.temp.dir</name>
- <value>${hadoop.tmp.dir}/mapred/temp</value>
- <description>A shared directory for temporary files.
- </description>
-</property>
-
-<property>
- <name>mapreduce.tasktracker.local.dir.minspacestart</name>
- <value>0</value>
- <description>If the space in mapreduce.cluster.local.dir drops under this,
- do not ask for more tasks.
- Value in bytes.
- </description>
-</property>
-
-<property>
- <name>mapreduce.tasktracker.local.dir.minspacekill</name>
- <value>0</value>
- <description>If the space in mapreduce.cluster.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.
- </description>
-</property>
-
-<property>
- <name>mapreduce.jobtracker.expire.trackers.interval</name>
- <value>600000</value>
- <description>Expert: The time-interval, in miliseconds, after which
- a tasktracker is declared 'lost' if it doesn't send heartbeats.
- </description>
-</property>
-
-<property>
- <name>mapreduce.tasktracker.instrumentation</name>
- <value>org.apache.hadoop.mapred.TaskTrackerMetricsInst</value>
- <description>Expert: The instrumentation class to associate with each TaskTracker.
- </description>
-</property>
-
-<property>
- <name>mapreduce.tasktracker.resourcecalculatorplugin</name>
- <value></value>
- <description>
- Name of the class whose instance will be used to query resource information
- on the tasktracker.
-
- The class must be an instance of
- org.apache.hadoop.util.ResourceCalculatorPlugin. If the value is null, the
- tasktracker attempts to use a class appropriate to the platform.
- Currently, the only platform supported is Linux.
- </description>
-</property>
-
-<property>
- <name>mapreduce.tasktracker.taskmemorymanager.monitoringinterval</name>
- <value>5000</value>
- <description>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.
- </description>
-</property>
-
-<property>
- <name>mapreduce.tasktracker.tasks.sleeptimebeforesigkill</name>
- <value>5000</value>
- <description>The time, in milliseconds, the tasktracker waits for sending a
- SIGKILL to a task, after it has been sent a SIGTERM. This is currently
- not used on WINDOWS where tasks are just sent a SIGTERM.
- </description>
-</property>
-
-<property>
<name>mapreduce.job.maps</name>
<value>2</value>
<description>The default number of map tasks per job.
- Ignored when mapreduce.jobtracker.address is "local".
+ Ignored when mapreduce.framework.name is "local".
</description>
</property>
@@ -256,54 +78,21 @@
<description>The default number of reduce tasks per job. Typically set to 99%
of the cluster's reduce capacity, so that if a node fails the reduces can
still be executed in a single wave.
- Ignored when mapreduce.jobtracker.address is "local".
+ Ignored when mapreduce.framework.name is "local".
</description>
</property>
<property>
- <name>mapreduce.jobtracker.restart.recover</name>
- <value>false</value>
- <description>"true" to enable (job) recovery upon restart,
- "false" to start afresh
- </description>
-</property>
-
-<property>
- <name>mapreduce.jobtracker.jobhistory.block.size</name>
- <value>3145728</value>
- <description>The block size of the job history file. Since the job recovery
- uses job history, its important to dump job history to disk as
- soon as possible. Note that this is an expert level parameter.
- The default value is set to 3 MB.
- </description>
-</property>
-
-<property>
- <name>mapreduce.jobtracker.taskscheduler</name>
- <value>org.apache.hadoop.mapred.JobQueueTaskScheduler</value>
- <description>The class responsible for scheduling the tasks.</description>
-</property>
-
-
-<property>
<name>mapreduce.job.split.metainfo.maxsize</name>
<value>10000000</value>
<description>The maximum permissible size of the split metainfo file.
- The JobTracker won't attempt to read split metainfo files bigger than
- the configured value.
+ The MapReduce ApplicationMaster won't attempt to read submitted split metainfo
+ files bigger than this configured value.
No limits if set to -1.
</description>
</property>
<property>
- <name>mapreduce.jobtracker.taskscheduler.maxrunningtasks.perjob</name>
- <value></value>
- <description>The maximum number of running tasks for a job before
- it gets preempted. No limits if undefined.
- </description>
-</property>
-
-<property>
<name>mapreduce.map.maxattempts</name>
<value>4</value>
<description>Expert: The maximum number of attempts per map task.
@@ -333,7 +122,7 @@
<name>mapreduce.reduce.shuffle.connect.timeout</name>
<value>180000</value>
<description>Expert: The maximum amount of time (in milli seconds) reduce
- task spends in trying to connect to a tasktracker for getting map output.
+ task spends in trying to connect to a remote node for getting map output.
</description>
</property>
@@ -355,51 +144,6 @@
</description>
</property>
-<property>
- <name>mapreduce.tasktracker.map.tasks.maximum</name>
- <value>2</value>
- <description>The maximum number of map tasks that will be run
- simultaneously by a task tracker.
- </description>
-</property>
-
-<property>
- <name>mapreduce.tasktracker.reduce.tasks.maximum</name>
- <value>2</value>
- <description>The maximum number of reduce tasks that will be run
- simultaneously by a task tracker.
- </description>
-</property>
-
-<property>
- <name>mapreduce.jobtracker.retiredjobs.cache.size</name>
- <value>1000</value>
- <description>The number of retired job status to keep in the cache.
- </description>
-</property>
-
-<property>
- <name>mapreduce.tasktracker.outofband.heartbeat</name>
- <value>false</value>
- <description>Expert: Set this to true to let the tasktracker send an
- out-of-band heartbeat on task-completion for better latency.
- </description>
-</property>
-
-<property>
- <name>mapreduce.jobtracker.jobhistory.lru.cache.size</name>
- <value>5</value>
- <description>The number of job history files loaded in memory. The jobs are
- loaded when they are first accessed. The cache is cleared based on LRU.
- </description>
-</property>
-
-<property>
- <name>mapreduce.jobtracker.instrumentation</name>
- <value>org.apache.hadoop.mapred.JobTrackerMetricsInst</value>
- <description>Expert: The instrumentation class to associate with each JobTracker.
- </description>
-</property>
<property>
<name>mapred.child.java.opts</name>
@@ -424,7 +168,7 @@
<description>User added environment variables for the task tracker child
processes. Example :
1) A=foo This will set the env variable A to foo
- 2) B=$B:c This is inherit tasktracker's B env variable.
+ 2) B=$B:c This is inherit nodemanager's B env variable.
</description>
</property>
@@ -568,17 +312,9 @@
<name>mapreduce.job.speculative.slownodethreshold</name>
<value>1.0</value>
<description>The number of standard deviations by which a Task
- Tracker's ave map and reduce progress-rates (finishTime-dispatchTime)
+ Tracker's average map and reduce progress-rates (finishTime-dispatchTime)
must be lower than the average of all successful map/reduce task's for
- the TT to be considered too slow to give a speculative task to.
- </description>
-</property>
-
-<property>
- <name>mapreduce.job.jvm.numtasks</name>
- <value>1</value>
- <description>How many tasks to run per jvm. If set to -1, there is
- no limit.
+ the NodeManager to be considered too slow to give a speculative task to.
</description>
</property>
@@ -630,12 +366,6 @@
take priority over this setting.</description>
</property>
-<property>
- <name>mapreduce.jobtracker.maxtasks.perjob</name>
- <value>-1</value>
- <description>The maximum number of tasks for a single job.
- A value of -1 indicates that there is no maximum. </description>
-</property>
<property>
<name>mapreduce.client.submit.file.replication</name>
@@ -645,41 +375,6 @@
</description>
</property>
-
-<property>
- <name>mapreduce.tasktracker.dns.interface</name>
- <value>default</value>
- <description>The name of the Network Interface from which a task
- tracker should report its IP address.
- </description>
- </property>
-
-<property>
- <name>mapreduce.tasktracker.dns.nameserver</name>
- <value>default</value>
- <description>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.
- </description>
- </property>
-
-<property>
- <name>mapreduce.tasktracker.http.threads</name>
- <value>40</value>
- <description>The number of worker threads that for the http server. This is
- used for map output fetching
- </description>
-</property>
-
-<property>
- <name>mapreduce.tasktracker.http.address</name>
- <value>0.0.0.0:50060</value>
- <description>
- The task tracker http server address and port.
- If the port is 0 then the server will start on a free port.
- </description>
-</property>
-
<property>
<name>mapreduce.task.files.preserve.failedtasks</name>
<value>false</value>
@@ -752,53 +447,9 @@
</property>
<property>
- <name>mapreduce.job.userlog.retain.hours</name>
- <value>24</value>
- <description>The maximum time, in hours, for which the user-logs are to be
- retained after the job completion.
- </description>
-</property>
-
-<property>
- <name>mapreduce.jobtracker.hosts.filename</name>
- <value></value>
- <description>Names a file that contains the list of nodes that may
- connect to the jobtracker. If the value is empty, all hosts are
- permitted.</description>
-</property>
-
-<property>
- <name>mapreduce.jobtracker.hosts.exclude.filename</name>
- <value></value>
- <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>
- <name>mapreduce.jobtracker.heartbeats.in.second</name>
- <value>100</value>
- <description>Expert: Approximate number of heart-beats that could arrive
- at JobTracker in a second. Assuming each RPC can be processed
- in 10msec, the default value is made 100 RPCs in a second.
- </description>
-</property>
-
-<property>
- <name>mapreduce.jobtracker.tasktracker.maxblacklists</name>
- <value>4</value>
- <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.
- </description>
-</property>
-
-<property>
<name>mapreduce.job.maxtaskfailures.per.tracker</name>
<value>3</value>
- <description>The number of task-failures on a tasktracker of a given job
+ <description>The number of task-failures on a node manager of a given job
after which new tasks of that job aren't assigned to it. It
MUST be less than mapreduce.map.maxattempts and
mapreduce.reduce.maxattempts otherwise the failed task will
@@ -820,8 +471,8 @@
<name>mapreduce.client.completion.pollinterval</name>
<value>5000</value>
<description>The interval (in milliseconds) between which the JobClient
- polls the JobTracker for updates about job status. You may want to set this
- to a lower value to make tests run faster on a single node system. Adjusting
+ polls the MapReduce ApplicationMaster for updates about job status. You may want to
+ set this to a lower value to make tests run faster on a single node system. Adjusting
this value in production may lead to unwanted client-server traffic.
</description>
</property>
@@ -836,32 +487,6 @@
</description>
</property>
- <property>
- <name>mapreduce.jobtracker.persist.jobstatus.active</name>
- <value>true</value>
- <description>Indicates if persistency of job status information is
- active or not.
- </description>
- </property>
-
- <property>
- <name>mapreduce.jobtracker.persist.jobstatus.hours</name>
- <value>1</value>
- <description>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.
- </description>
-</property>
-
- <property>
- <name>mapreduce.jobtracker.persist.jobstatus.dir</name>
- <value>/jobtracker/jobsInfo</value>
- <description>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.
- </description>
- </property>
<property>
<name>mapreduce.task.profile</name>
@@ -894,8 +519,8 @@
<description> The number of Task attempts AFTER which skip mode
will be kicked off. When skip mode is kicked off, the
tasks reports the range of records which it will process
- next, to the TaskTracker. So that on failures, TT knows which
- ones are possibly the bad records. On further executions,
+ next, to the MR ApplicationMaster. So that on failures, the MR AM
+ knows which ones are possibly the bad records. On further executions,
those are skipped.
</description>
</property>
@@ -1006,15 +631,6 @@
calls</description>
</property>
-<!-- Proxy Configuration -->
-<property>
- <name>mapreduce.jobtracker.taskcache.levels</name>
- <value>2</value>
- <description> 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.
- </description>
-</property>
<property>
<name>mapreduce.job.queuename</name>
@@ -1028,18 +644,29 @@
</property>
<property>
+ <name>mapreduce.cluster.local.dir</name>
+ <value>${hadoop.tmp.dir}/mapred/local</value>
+ <description>
+ 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.
+ </description>
+</property>
+
+<property>
<name>mapreduce.cluster.acls.enabled</name>
<value>false</value>
<description> Specifies whether ACLs should be checked
for authorization of users for doing various queue and job level operations.
ACLs are disabled by default. If enabled, access control checks are made by
- JobTracker and TaskTracker when requests are made by users for queue
+ MapReduce ApplicationMaster when requests are made by users for queue
operations like submit job to a queue and kill a job in the queue and job
operations like viewing the job-details (See mapreduce.job.acl-view-job)
or for modifying the job (See mapreduce.job.acl-modify-job) using
Map/Reduce APIs, RPCs or via the console and web user interfaces.
- For enabling this flag(mapreduce.cluster.acls.enabled), this is to be set
- to true in mapred-site.xml on JobTracker node and on all TaskTracker nodes.
+ For enabling this flag, set to true in mapred-site.xml file of all
+ MapReduce clients (MR job submitting nodes).
</description>
</property>
@@ -1092,8 +719,8 @@
o job-level counters
o task-level counters
o tasks' diagnostic information
- o task-logs displayed on the TaskTracker web-UI and
- o job.xml showed by the JobTracker's web-UI
+ o task-logs displayed on the HistoryServer's web-UI and
+ o job.xml showed by the HistoryServer's web-UI
Every other piece of information of jobs is still accessible by any other
user, for e.g., JobStatus, JobProfile, list of jobs in the queue, etc.
@@ -1111,18 +738,10 @@
</property>
<property>
- <name>mapreduce.tasktracker.indexcache.mb</name>
- <value>10</value>
- <description> The maximum memory that a task tracker allows for the
- index cache that is used when serving map outputs to reducers.
- </description>
-</property>
-
-<property>
<name>mapreduce.task.merge.progress.records</name>
<value>10000</value>
<description> The number of records to process during merge before
- sending a progress notification to the TaskTracker.
+ sending a progress notification to the MR ApplicationMaster.
</description>
</property>
@@ -1143,22 +762,6 @@
</property>
<property>
- <name>mapreduce.tasktracker.taskcontroller</name>
- <value>org.apache.hadoop.mapred.DefaultTaskController</value>
- <description>TaskController which is used to launch and manage task execution
- </description>
-</property>
-
-<property>
- <name>mapreduce.tasktracker.group</name>
- <value></value>
- <description>Expert: Group to which TaskTracker belongs. If
- LinuxTaskController is configured via mapreduce.tasktracker.taskcontroller,
- the group owner of the task-controller binary should be same as this group.
- </description>
-</property>
-
-<property>
<name>mapreduce.shuffle.port</name>
<value>8080</value>
<description>Default port that the ShuffleHandler will run on. ShuffleHandler
@@ -1167,42 +770,6 @@
</description>
</property>
-<!-- Node health script variables -->
-
-<property>
- <name>mapreduce.tasktracker.healthchecker.script.path</name>
- <value></value>
- <description>Absolute path to the script which is
- periodicallyrun by the node health monitoring service to determine if
- the node is healthy or not. If the value of this key is empty or the
- file does not exist in the location configured here, the node health
- monitoring service is not started.</description>
-</property>
-
-<property>
- <name>mapreduce.tasktracker.healthchecker.interval</name>
- <value>60000</value>
- <description>Frequency of the node health script to be run,
- in milliseconds</description>
-</property>
-
-<property>
- <name>mapreduce.tasktracker.healthchecker.script.timeout</name>
- <value>600000</value>
- <description>Time after node health script should be killed if
- unresponsive and considered that the script has failed.</description>
-</property>
-
-<property>
- <name>mapreduce.tasktracker.healthchecker.script.args</name>
- <value></value>
- <description>List of arguments which are to be passed to
- node health script when it is being launched comma seperated.
- </description>
-</property>
-
-<!-- end of node health script variables -->
-
<!-- MR YARN Application properties -->
<property>
Propchange: hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/resources/mapred-default.xml
------------------------------------------------------------------------------
Merged /hadoop/common/branches/HDFS-3077/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/resources/mapred-default.xml:r1363593-1396941
Merged /hadoop/common/trunk/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/resources/mapred-default.xml:r1390763-1397380
Modified: hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-hs/src/main/java/org/apache/hadoop/mapreduce/v2/hs/CompletedTask.java
URL: http://svn.apache.org/viewvc/hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-hs/src/main/java/org/apache/hadoop/mapreduce/v2/hs/CompletedTask.java?rev=1397387&r1=1397386&r2=1397387&view=diff
==============================================================================
--- hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-hs/src/main/java/org/apache/hadoop/mapreduce/v2/hs/CompletedTask.java (original)
+++ hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-hs/src/main/java/org/apache/hadoop/mapreduce/v2/hs/CompletedTask.java Fri Oct 12 00:15:22 2012
@@ -42,6 +42,8 @@ import org.apache.hadoop.yarn.util.Recor
public class CompletedTask implements Task {
+ private static final Counters EMPTY_COUNTERS = new Counters();
+
private final TaskId taskId;
private final TaskInfo taskInfo;
private TaskReport report;
@@ -124,7 +126,11 @@ public class CompletedTask implements Ta
report.setFinishTime(taskInfo.getFinishTime());
report.setTaskState(getState());
report.setProgress(getProgress());
- report.setCounters(TypeConverter.toYarn(getCounters()));
+ Counters counters = getCounters();
+ if (counters == null) {
+ counters = EMPTY_COUNTERS;
+ }
+ report.setCounters(TypeConverter.toYarn(counters));
if (successfulAttempt != null) {
report.setSuccessfulAttempt(successfulAttempt);
}
Modified: hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-hs/src/main/java/org/apache/hadoop/mapreduce/v2/hs/HistoryFileManager.java
URL: http://svn.apache.org/viewvc/hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-hs/src/main/java/org/apache/hadoop/mapreduce/v2/hs/HistoryFileManager.java?rev=1397387&r1=1397386&r2=1397387&view=diff
==============================================================================
--- hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-hs/src/main/java/org/apache/hadoop/mapreduce/v2/hs/HistoryFileManager.java (original)
+++ hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-hs/src/main/java/org/apache/hadoop/mapreduce/v2/hs/HistoryFileManager.java Fri Oct 12 00:15:22 2012
@@ -23,14 +23,14 @@ import java.io.IOException;
import java.util.ArrayList;
import java.util.Collection;
import java.util.Collections;
-import java.util.HashMap;
import java.util.HashSet;
import java.util.Iterator;
import java.util.List;
-import java.util.Map;
import java.util.Set;
import java.util.SortedMap;
import java.util.TreeMap;
+import java.util.concurrent.ConcurrentHashMap;
+import java.util.concurrent.ConcurrentMap;
import java.util.concurrent.ConcurrentSkipListMap;
import java.util.concurrent.LinkedBlockingQueue;
import java.util.concurrent.ThreadFactory;
@@ -62,6 +62,7 @@ import org.apache.hadoop.mapreduce.v2.jo
import org.apache.hadoop.yarn.YarnException;
import org.apache.hadoop.yarn.service.AbstractService;
+import com.google.common.annotations.VisibleForTesting;
import com.google.common.util.concurrent.ThreadFactoryBuilder;
/**
@@ -77,7 +78,7 @@ public class HistoryFileManager extends
private static enum HistoryInfoState {
IN_INTERMEDIATE, IN_DONE, DELETED, MOVE_FAILED
};
-
+
private static String DONE_BEFORE_SERIAL_TAIL = JobHistoryUtils
.doneSubdirsBeforeSerialTail();
@@ -130,7 +131,7 @@ public class HistoryFileManager extends
}
}
- private static class JobListCache {
+ static class JobListCache {
private ConcurrentSkipListMap<JobId, HistoryFileInfo> cache;
private int maxSize;
private long maxAge;
@@ -199,6 +200,29 @@ public class HistoryFileManager extends
}
}
+ /**
+ * This class represents a user dir in the intermediate done directory. This
+ * is mostly for locking purposes.
+ */
+ private class UserLogDir {
+ long modTime = 0;
+
+ public synchronized void scanIfNeeded(FileStatus fs) {
+ long newModTime = fs.getModificationTime();
+ if (modTime != newModTime) {
+ Path p = fs.getPath();
+ try {
+ scanIntermediateDirectory(p);
+ //If scanning fails, we will scan again. We assume the failure is
+ // temporary.
+ modTime = newModTime;
+ } catch (IOException e) {
+ LOG.error("Error while trying to scan the directory " + p, e);
+ }
+ }
+ }
+ }
+
public class HistoryFileInfo {
private Path historyFile;
private Path confFile;
@@ -216,12 +240,14 @@ public class HistoryFileManager extends
: HistoryInfoState.IN_INTERMEDIATE;
}
- private synchronized boolean isMovePending() {
+ @VisibleForTesting
+ synchronized boolean isMovePending() {
return state == HistoryInfoState.IN_INTERMEDIATE
|| state == HistoryInfoState.MOVE_FAILED;
}
- private synchronized boolean didMoveFail() {
+ @VisibleForTesting
+ synchronized boolean didMoveFail() {
return state == HistoryInfoState.MOVE_FAILED;
}
@@ -342,7 +368,7 @@ public class HistoryFileManager extends
}
private SerialNumberIndex serialNumberIndex = null;
- private JobListCache jobListCache = null;
+ protected JobListCache jobListCache = null;
// Maintains a list of known done subdirectories.
private final Set<Path> existingDoneSubdirs = Collections
@@ -352,7 +378,8 @@ public class HistoryFileManager extends
* Maintains a mapping between intermediate user directories and the last
* known modification time.
*/
- private Map<String, Long> userDirModificationTimeMap = new HashMap<String, Long>();
+ private ConcurrentMap<String, UserLogDir> userDirModificationTimeMap =
+ new ConcurrentHashMap<String, UserLogDir>();
private JobACLsManager aclsMgr;
@@ -584,23 +611,15 @@ public class HistoryFileManager extends
for (FileStatus userDir : userDirList) {
String name = userDir.getPath().getName();
- long newModificationTime = userDir.getModificationTime();
- boolean shouldScan = false;
- synchronized (userDirModificationTimeMap) {
- if (!userDirModificationTimeMap.containsKey(name)
- || newModificationTime > userDirModificationTimeMap.get(name)) {
- shouldScan = true;
- userDirModificationTimeMap.put(name, newModificationTime);
- }
- }
- if (shouldScan) {
- try {
- scanIntermediateDirectory(userDir.getPath());
- } catch (IOException e) {
- LOG.error("Error while trying to scan the directory "
- + userDir.getPath(), e);
+ UserLogDir dir = userDirModificationTimeMap.get(name);
+ if(dir == null) {
+ dir = new UserLogDir();
+ UserLogDir old = userDirModificationTimeMap.putIfAbsent(name, dir);
+ if(old != null) {
+ dir = old;
}
}
+ dir.scanIfNeeded(userDir);
}
}
@@ -691,8 +710,8 @@ public class HistoryFileManager extends
* @throws IOException
*/
private HistoryFileInfo scanOldDirsForJob(JobId jobId) throws IOException {
- int jobSerialNumber = JobHistoryUtils.jobSerialNumber(jobId);
- String boxedSerialNumber = String.valueOf(jobSerialNumber);
+ String boxedSerialNumber = JobHistoryUtils.serialNumberDirectoryComponent(
+ jobId, serialNumberFormat);
Set<String> dateStringSet = serialNumberIndex.get(boxedSerialNumber);
if (dateStringSet == null) {
return null;
Modified: hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-hs/src/test/java/org/apache/hadoop/mapreduce/v2/hs/TestJobHistoryParsing.java
URL: http://svn.apache.org/viewvc/hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-hs/src/test/java/org/apache/hadoop/mapreduce/v2/hs/TestJobHistoryParsing.java?rev=1397387&r1=1397386&r2=1397387&view=diff
==============================================================================
--- hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-hs/src/test/java/org/apache/hadoop/mapreduce/v2/hs/TestJobHistoryParsing.java (original)
+++ hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-hs/src/test/java/org/apache/hadoop/mapreduce/v2/hs/TestJobHistoryParsing.java Fri Oct 12 00:15:22 2012
@@ -49,6 +49,7 @@ import org.apache.hadoop.mapreduce.jobhi
import org.apache.hadoop.mapreduce.v2.api.records.JobId;
import org.apache.hadoop.mapreduce.v2.api.records.JobState;
import org.apache.hadoop.mapreduce.v2.api.records.TaskAttemptId;
+import org.apache.hadoop.mapreduce.v2.api.records.TaskId;
import org.apache.hadoop.mapreduce.v2.api.records.TaskState;
import org.apache.hadoop.mapreduce.v2.app.MRApp;
import org.apache.hadoop.mapreduce.v2.app.job.Job;
@@ -59,6 +60,7 @@ import org.apache.hadoop.mapreduce.v2.ap
import org.apache.hadoop.mapreduce.v2.hs.HistoryFileManager.HistoryFileInfo;
import org.apache.hadoop.mapreduce.v2.hs.TestJobHistoryEvents.MRAppWithHistory;
import org.apache.hadoop.mapreduce.v2.jobhistory.FileNameIndexUtils;
+import org.apache.hadoop.mapreduce.v2.jobhistory.JHAdminConfig;
import org.apache.hadoop.mapreduce.v2.jobhistory.JobHistoryUtils;
import org.apache.hadoop.mapreduce.v2.jobhistory.JobIndexInfo;
import org.apache.hadoop.net.DNSToSwitchMapping;
@@ -402,6 +404,108 @@ public class TestJobHistoryParsing {
}
}
+ @Test
+ public void testCountersForFailedTask() throws Exception {
+ LOG.info("STARTING testCountersForFailedTask");
+ try {
+ Configuration conf = new Configuration();
+ conf
+ .setClass(
+ CommonConfigurationKeysPublic.NET_TOPOLOGY_NODE_SWITCH_MAPPING_IMPL_KEY,
+ MyResolver.class, DNSToSwitchMapping.class);
+ RackResolver.init(conf);
+ MRApp app = new MRAppWithHistoryWithFailedTask(2, 1, true,
+ this.getClass().getName(), true);
+ app.submit(conf);
+ Job job = app.getContext().getAllJobs().values().iterator().next();
+ JobId jobId = job.getID();
+ app.waitForState(job, JobState.FAILED);
+
+ // make sure all events are flushed
+ app.waitForState(Service.STATE.STOPPED);
+
+ String jobhistoryDir = JobHistoryUtils
+ .getHistoryIntermediateDoneDirForUser(conf);
+ JobHistory jobHistory = new JobHistory();
+ jobHistory.init(conf);
+
+ JobIndexInfo jobIndexInfo = jobHistory.getJobFileInfo(jobId)
+ .getJobIndexInfo();
+ String jobhistoryFileName = FileNameIndexUtils
+ .getDoneFileName(jobIndexInfo);
+
+ Path historyFilePath = new Path(jobhistoryDir, jobhistoryFileName);
+ FSDataInputStream in = null;
+ FileContext fc = null;
+ try {
+ fc = FileContext.getFileContext(conf);
+ in = fc.open(fc.makeQualified(historyFilePath));
+ } catch (IOException ioe) {
+ LOG.info("Can not open history file: " + historyFilePath, ioe);
+ throw (new Exception("Can not open History File"));
+ }
+
+ JobHistoryParser parser = new JobHistoryParser(in);
+ JobInfo jobInfo = parser.parse();
+ Exception parseException = parser.getParseException();
+ Assert.assertNull("Caught an expected exception " + parseException,
+ parseException);
+ for (Map.Entry<TaskID,TaskInfo> entry : jobInfo.getAllTasks().entrySet()) {
+ TaskId yarnTaskID = TypeConverter.toYarn(entry.getKey());
+ CompletedTask ct = new CompletedTask(yarnTaskID, entry.getValue());
+ Assert.assertNotNull("completed task report has null counters",
+ ct.getReport().getCounters());
+ }
+ } finally {
+ LOG.info("FINISHED testCountersForFailedTask");
+ }
+ }
+
+ @Test
+ public void testScanningOldDirs() throws Exception {
+ LOG.info("STARTING testScanningOldDirs");
+ try {
+ Configuration conf = new Configuration();
+ conf
+ .setClass(
+ CommonConfigurationKeysPublic.NET_TOPOLOGY_NODE_SWITCH_MAPPING_IMPL_KEY,
+ MyResolver.class, DNSToSwitchMapping.class);
+ RackResolver.init(conf);
+ MRApp app =
+ new MRAppWithHistory(1, 1, true,
+ this.getClass().getName(), true);
+ app.submit(conf);
+ Job job = app.getContext().getAllJobs().values().iterator().next();
+ JobId jobId = job.getID();
+ LOG.info("JOBID is " + TypeConverter.fromYarn(jobId).toString());
+ app.waitForState(job, JobState.SUCCEEDED);
+
+ // make sure all events are flushed
+ app.waitForState(Service.STATE.STOPPED);
+
+ HistoryFileManagerForTest hfm = new HistoryFileManagerForTest();
+ hfm.init(conf);
+ HistoryFileInfo fileInfo = hfm.getFileInfo(jobId);
+ Assert.assertNotNull("Unable to locate job history", fileInfo);
+
+ // force the manager to "forget" the job
+ hfm.deleteJobFromJobListCache(fileInfo);
+ final int msecPerSleep = 10;
+ int msecToSleep = 10 * 1000;
+ while (fileInfo.isMovePending() && msecToSleep > 0) {
+ Assert.assertTrue(!fileInfo.didMoveFail());
+ msecToSleep -= msecPerSleep;
+ Thread.sleep(msecPerSleep);
+ }
+ Assert.assertTrue("Timeout waiting for history move", msecToSleep > 0);
+
+ fileInfo = hfm.getFileInfo(jobId);
+ Assert.assertNotNull("Unable to locate old job history", fileInfo);
+ } finally {
+ LOG.info("FINISHED testScanningOldDirs");
+ }
+ }
+
static class MRAppWithHistoryWithFailedAttempt extends MRAppWithHistory {
public MRAppWithHistoryWithFailedAttempt(int maps, int reduces, boolean autoComplete,
@@ -422,6 +526,32 @@ public class TestJobHistoryParsing {
}
}
+ static class MRAppWithHistoryWithFailedTask extends MRAppWithHistory {
+
+ public MRAppWithHistoryWithFailedTask(int maps, int reduces, boolean autoComplete,
+ String testName, boolean cleanOnStart) {
+ super(maps, reduces, autoComplete, testName, cleanOnStart);
+ }
+
+ @SuppressWarnings("unchecked")
+ @Override
+ protected void attemptLaunched(TaskAttemptId attemptID) {
+ if (attemptID.getTaskId().getId() == 0) {
+ getContext().getEventHandler().handle(
+ new TaskAttemptEvent(attemptID, TaskAttemptEventType.TA_FAILMSG));
+ } else {
+ getContext().getEventHandler().handle(
+ new TaskAttemptEvent(attemptID, TaskAttemptEventType.TA_DONE));
+ }
+ }
+ }
+
+ static class HistoryFileManagerForTest extends HistoryFileManager {
+ void deleteJobFromJobListCache(HistoryFileInfo fileInfo) {
+ jobListCache.delete(fileInfo);
+ }
+ }
+
public static void main(String[] args) throws Exception {
TestJobHistoryParsing t = new TestJobHistoryParsing();
t.testHistoryParsing();
Modified: hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-jobclient/src/main/java/org/apache/hadoop/mapred/YARNRunner.java
URL: http://svn.apache.org/viewvc/hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-jobclient/src/main/java/org/apache/hadoop/mapred/YARNRunner.java?rev=1397387&r1=1397386&r2=1397387&view=diff
==============================================================================
--- hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-jobclient/src/main/java/org/apache/hadoop/mapred/YARNRunner.java (original)
+++ hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-jobclient/src/main/java/org/apache/hadoop/mapred/YARNRunner.java Fri Oct 12 00:15:22 2012
@@ -372,12 +372,9 @@ public class YARNRunner implements Clien
}
// Setup security tokens
- ByteBuffer securityTokens = null;
- if (UserGroupInformation.isSecurityEnabled()) {
- DataOutputBuffer dob = new DataOutputBuffer();
- ts.writeTokenStorageToStream(dob);
- securityTokens = ByteBuffer.wrap(dob.getData(), 0, dob.getLength());
- }
+ DataOutputBuffer dob = new DataOutputBuffer();
+ ts.writeTokenStorageToStream(dob);
+ ByteBuffer securityTokens = ByteBuffer.wrap(dob.getData(), 0, dob.getLength());
// Setup the command to run the AM
List<String> vargs = new ArrayList<String>(8);
Modified: hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-jobclient/src/test/java/org/apache/hadoop/mapreduce/lib/partition/TestTotalOrderPartitioner.java
URL: http://svn.apache.org/viewvc/hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-jobclient/src/test/java/org/apache/hadoop/mapreduce/lib/partition/TestTotalOrderPartitioner.java?rev=1397387&r1=1397386&r2=1397387&view=diff
==============================================================================
--- hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-jobclient/src/test/java/org/apache/hadoop/mapreduce/lib/partition/TestTotalOrderPartitioner.java (original)
+++ hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-jobclient/src/test/java/org/apache/hadoop/mapreduce/lib/partition/TestTotalOrderPartitioner.java Fri Oct 12 00:15:22 2012
@@ -21,19 +21,25 @@ package org.apache.hadoop.mapreduce.lib.
import java.io.IOException;
import java.util.ArrayList;
import java.util.Arrays;
+import java.util.Comparator;
import junit.framework.TestCase;
import org.apache.hadoop.conf.Configuration;
+import org.apache.hadoop.fs.CommonConfigurationKeys;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.RawComparator;
import org.apache.hadoop.io.SequenceFile;
import org.apache.hadoop.io.Text;
-import org.apache.hadoop.io.WritableComparable;
import org.apache.hadoop.io.WritableComparator;
import org.apache.hadoop.io.WritableUtils;
+import org.apache.hadoop.io.SequenceFile.CompressionType;
+import org.apache.hadoop.io.serializer.JavaSerialization;
+import org.apache.hadoop.io.serializer.JavaSerializationComparator;
+import org.apache.hadoop.io.serializer.Serialization;
+import org.apache.hadoop.io.serializer.WritableSerialization;
import org.apache.hadoop.mapreduce.MRJobConfig;
public class TestTotalOrderPartitioner extends TestCase {
@@ -51,6 +57,19 @@ public class TestTotalOrderPartitioner e
new Text("yak"), // 9
};
+ private static final String[] splitJavaStrings = new String[] {
+ // -inf // 0
+ new String("aabbb"), // 1
+ new String("babbb"), // 2
+ new String("daddd"), // 3
+ new String("dddee"), // 4
+ new String("ddhee"), // 5
+ new String("dingo"), // 6
+ new String("hijjj"), // 7
+ new String("n"), // 8
+ new String("yak"), // 9
+ };
+
static class Check<T> {
T data;
int part;
@@ -76,19 +95,41 @@ public class TestTotalOrderPartitioner e
testStrings.add(new Check<Text>(new Text("hi"), 6));
};
- private static <T extends WritableComparable<?>> Path writePartitionFile(
+ private static final ArrayList<Check<String>> testJavaStrings =
+ new ArrayList<Check<String>>();
+ static {
+ testJavaStrings.add(new Check<String>(new String("aaaaa"), 0));
+ testJavaStrings.add(new Check<String>(new String("aaabb"), 0));
+ testJavaStrings.add(new Check<String>(new String("aabbb"), 1));
+ testJavaStrings.add(new Check<String>(new String("aaaaa"), 0));
+ testJavaStrings.add(new Check<String>(new String("babbb"), 2));
+ testJavaStrings.add(new Check<String>(new String("baabb"), 1));
+ testJavaStrings.add(new Check<String>(new String("yai"), 8));
+ testJavaStrings.add(new Check<String>(new String("yak"), 9));
+ testJavaStrings.add(new Check<String>(new String("z"), 9));
+ testJavaStrings.add(new Check<String>(new String("ddngo"), 5));
+ testJavaStrings.add(new Check<String>(new String("hi"), 6));
+ };
+
+
+ private static <T> Path writePartitionFile(
String testname, Configuration conf, T[] splits) throws IOException {
final FileSystem fs = FileSystem.getLocal(conf);
final Path testdir = new Path(System.getProperty("test.build.data", "/tmp")
- ).makeQualified(fs);
+ ).makeQualified(
+ fs.getUri(),
+ fs.getWorkingDirectory());
Path p = new Path(testdir, testname + "/_partition.lst");
TotalOrderPartitioner.setPartitionFile(conf, p);
conf.setInt(MRJobConfig.NUM_REDUCES, splits.length + 1);
SequenceFile.Writer w = null;
try {
- w = SequenceFile.createWriter(fs, conf, p,
- splits[0].getClass(), NullWritable.class,
- SequenceFile.CompressionType.NONE);
+ w = SequenceFile.createWriter(
+ conf,
+ SequenceFile.Writer.file(p),
+ SequenceFile.Writer.keyClass(splits[0].getClass()),
+ SequenceFile.Writer.valueClass(NullWritable.class),
+ SequenceFile.Writer.compression(CompressionType.NONE));
for (int i = 0; i < splits.length; ++i) {
w.append(splits[i], NullWritable.get());
}
@@ -99,6 +140,31 @@ public class TestTotalOrderPartitioner e
return p;
}
+ public void testTotalOrderWithCustomSerialization() throws Exception {
+ TotalOrderPartitioner<String, NullWritable> partitioner =
+ new TotalOrderPartitioner<String, NullWritable>();
+ Configuration conf = new Configuration();
+ conf.setStrings(CommonConfigurationKeys.IO_SERIALIZATIONS_KEY,
+ JavaSerialization.class.getName(),
+ WritableSerialization.class.getName());
+ conf.setClass(MRJobConfig.KEY_COMPARATOR,
+ JavaSerializationComparator.class,
+ Comparator.class);
+ Path p = TestTotalOrderPartitioner.<String>writePartitionFile(
+ "totalordercustomserialization", conf, splitJavaStrings);
+ conf.setClass(MRJobConfig.MAP_OUTPUT_KEY_CLASS, String.class, Object.class);
+ try {
+ partitioner.setConf(conf);
+ NullWritable nw = NullWritable.get();
+ for (Check<String> chk : testJavaStrings) {
+ assertEquals(chk.data.toString(), chk.part,
+ partitioner.getPartition(chk.data, nw, splitJavaStrings.length + 1));
+ }
+ } finally {
+ p.getFileSystem(conf).delete(p, true);
+ }
+ }
+
public void testTotalOrderMemCmp() throws Exception {
TotalOrderPartitioner<Text,NullWritable> partitioner =
new TotalOrderPartitioner<Text,NullWritable>();
Modified: hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/hadoop-mapreduce-examples/src/main/java/org/apache/hadoop/examples/dancing/DistributedPentomino.java
URL: http://svn.apache.org/viewvc/hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/hadoop-mapreduce-examples/src/main/java/org/apache/hadoop/examples/dancing/DistributedPentomino.java?rev=1397387&r1=1397386&r2=1397387&view=diff
==============================================================================
--- hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/hadoop-mapreduce-examples/src/main/java/org/apache/hadoop/examples/dancing/DistributedPentomino.java (original)
+++ hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/hadoop-mapreduce-examples/src/main/java/org/apache/hadoop/examples/dancing/DistributedPentomino.java Fri Oct 12 00:15:22 2012
@@ -165,16 +165,30 @@ public class DistributedPentomino extend
}
public int run(String[] args) throws Exception {
+ Configuration conf = getConf();
if (args.length == 0) {
- System.out.println("pentomino <output>");
+ System.out.println("Usage: pentomino <output> [-depth #] [-height #] [-width #]");
ToolRunner.printGenericCommandUsage(System.out);
return 2;
}
-
- Configuration conf = getConf();
- int width = conf.getInt(Pentomino.WIDTH, PENT_WIDTH);
- int height = conf.getInt(Pentomino.HEIGHT, PENT_HEIGHT);
- int depth = conf.getInt(Pentomino.DEPTH, PENT_DEPTH);
+ // check for passed parameters, otherwise use defaults
+ int width = PENT_WIDTH;
+ int height = PENT_HEIGHT;
+ int depth = PENT_DEPTH;
+ for (int i = 0; i < args.length; i++) {
+ if (args[i].equalsIgnoreCase("-depth")) {
+ depth = Integer.parseInt(args[i++].trim());
+ } else if (args[i].equalsIgnoreCase("-height")) {
+ height = Integer.parseInt(args[i++].trim());
+ } else if (args[i].equalsIgnoreCase("-width") ) {
+ width = Integer.parseInt(args[i++].trim());
+ }
+ }
+ // now set the values within conf for M/R tasks to read, this
+ // will ensure values are set preventing MAPREDUCE-4678
+ conf.setInt(Pentomino.WIDTH, width);
+ conf.setInt(Pentomino.HEIGHT, height);
+ conf.setInt(Pentomino.DEPTH, depth);
Class<? extends Pentomino> pentClass = conf.getClass(Pentomino.CLASS,
OneSidedPentomino.class, Pentomino.class);
int numMaps = conf.getInt(MRJobConfig.NUM_MAPS, DEFAULT_MAPS);
Modified: hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/pom.xml
URL: http://svn.apache.org/viewvc/hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/pom.xml?rev=1397387&r1=1397386&r2=1397387&view=diff
==============================================================================
--- hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/pom.xml (original)
+++ hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/pom.xml Fri Oct 12 00:15:22 2012
@@ -149,7 +149,6 @@
<dependency>
<groupId>junit</groupId>
<artifactId>junit</artifactId>
- <scope>test</scope>
</dependency>
<dependency>
<groupId>org.jboss.netty</groupId>
Propchange: hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/src/c++/
------------------------------------------------------------------------------
Merged /hadoop/common/trunk/hadoop-mapreduce-project/src/c++:r1390763-1397380
Merged /hadoop/common/branches/HDFS-3077/hadoop-mapreduce-project/src/c++:r1363593-1396941
Propchange: hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/src/contrib/
------------------------------------------------------------------------------
Merged /hadoop/common/branches/HDFS-3077/hadoop-mapreduce-project/src/contrib:r1363593-1396941
Merged /hadoop/common/trunk/hadoop-mapreduce-project/src/contrib:r1390763-1397380
Propchange: hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/src/contrib/block_forensics/
------------------------------------------------------------------------------
Merged /hadoop/common/branches/HDFS-3077/hadoop-mapreduce-project/src/contrib/block_forensics:r1363593-1396941
Merged /hadoop/common/trunk/hadoop-mapreduce-project/src/contrib/block_forensics:r1390763-1397380
Propchange: hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/src/contrib/build-contrib.xml
------------------------------------------------------------------------------
Merged /hadoop/common/trunk/hadoop-mapreduce-project/src/contrib/build-contrib.xml:r1390763-1397380
Merged /hadoop/common/branches/HDFS-3077/hadoop-mapreduce-project/src/contrib/build-contrib.xml:r1363593-1396941
Propchange: hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/src/contrib/build.xml
------------------------------------------------------------------------------
Merged /hadoop/common/trunk/hadoop-mapreduce-project/src/contrib/build.xml:r1390763-1397380
Merged /hadoop/common/branches/HDFS-3077/hadoop-mapreduce-project/src/contrib/build.xml:r1363593-1396941
Propchange: hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/src/contrib/data_join/
------------------------------------------------------------------------------
Merged /hadoop/common/branches/HDFS-3077/hadoop-mapreduce-project/src/contrib/data_join:r1363593-1396941
Merged /hadoop/common/trunk/hadoop-mapreduce-project/src/contrib/data_join:r1390763-1397380
Propchange: hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/src/contrib/eclipse-plugin/
------------------------------------------------------------------------------
Merged /hadoop/common/branches/HDFS-3077/hadoop-mapreduce-project/src/contrib/eclipse-plugin:r1363593-1396941
Merged /hadoop/common/trunk/hadoop-mapreduce-project/src/contrib/eclipse-plugin:r1390763-1397380
Propchange: hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/src/contrib/index/
------------------------------------------------------------------------------
Merged /hadoop/common/trunk/hadoop-mapreduce-project/src/contrib/index:r1390763-1397380
Merged /hadoop/common/branches/HDFS-3077/hadoop-mapreduce-project/src/contrib/index:r1363593-1396941
Propchange: hadoop/common/branches/branch-trunk-win/hadoop-mapreduce-project/src/contrib/vaidya/
------------------------------------------------------------------------------
Merged /hadoop/common/branches/HDFS-3077/hadoop-mapreduce-project/src/contrib/vaidya:r1363593-1396941
Merged /hadoop/common/trunk/hadoop-mapreduce-project/src/contrib/vaidya:r1390763-1397380