svn commit: r1603670 - in /hadoop/common/trunk/hadoop-mapreduce-project: ./ hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/ hadoop-mapreduce-client/hadoop-
Author: kasha Date: Wed Jun 18 23:28:50 2014 New Revision: 1603670 URL: http://svn.apache.org/r1603670 Log: MAPREDUCE-5896. InputSplits should indicate which locations have the block cached in memory. (Sandy Ryza via kasha) Added: hadoop/common/trunk/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/InputSplitWithLocationInfo.java hadoop/common/trunk/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/SplitLocationInfo.java Modified: hadoop/common/trunk/hadoop-mapreduce-project/CHANGES.txt hadoop/common/trunk/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/FileInputFormat.java hadoop/common/trunk/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/FileSplit.java hadoop/common/trunk/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/InputSplit.java hadoop/common/trunk/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/lib/input/FileInputFormat.java hadoop/common/trunk/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/lib/input/FileSplit.java hadoop/common/trunk/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/test/java/org/apache/hadoop/mapred/TestFileInputFormat.java hadoop/common/trunk/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/test/java/org/apache/hadoop/mapreduce/lib/input/TestFileInputFormat.java Modified: hadoop/common/trunk/hadoop-mapreduce-project/CHANGES.txt URL: http://svn.apache.org/viewvc/hadoop/common/trunk/hadoop-mapreduce-project/CHANGES.txt?rev=1603670r1=1603669r2=1603670view=diff == --- hadoop/common/trunk/hadoop-mapreduce-project/CHANGES.txt (original) +++ hadoop/common/trunk/hadoop-mapreduce-project/CHANGES.txt Wed Jun 18 23:28:50 2014 @@ -213,6 +213,9 @@ Release 2.5.0 - UNRELEASED MAPREDUCE-5834. Increased test-timeouts in TestGridMixClasses to avoid occassional failures. (Mit Desai via vinodkv) +MAPREDUCE-5896. InputSplits should indicate which locations have the block +cached in memory. (Sandy Ryza via kasha) + OPTIMIZATIONS BUG FIXES Modified: hadoop/common/trunk/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/FileInputFormat.java URL: http://svn.apache.org/viewvc/hadoop/common/trunk/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/FileInputFormat.java?rev=1603670r1=1603669r2=1603670view=diff == --- hadoop/common/trunk/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/FileInputFormat.java (original) +++ hadoop/common/trunk/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/FileInputFormat.java Wed Jun 18 23:28:50 2014 @@ -295,6 +295,15 @@ public abstract class FileInputFormatK, String[] hosts) { return new FileSplit(file, start, length, hosts); } + + /** + * A factory that makes the split for this class. It can be overridden + * by sub-classes to make sub-types + */ + protected FileSplit makeSplit(Path file, long start, long length, +String[] hosts, String[] inMemoryHosts) { +return new FileSplit(file, start, length, hosts, inMemoryHosts); + } /** Splits files returned by {@link #listStatus(JobConf)} when * they're too big.*/ @@ -337,22 +346,22 @@ public abstract class FileInputFormatK, long bytesRemaining = length; while (((double) bytesRemaining)/splitSize SPLIT_SLOP) { -String[] splitHosts = getSplitHosts(blkLocations, +String[][] splitHosts = getSplitHostsAndCachedHosts(blkLocations, length-bytesRemaining, splitSize, clusterMap); splits.add(makeSplit(path, length-bytesRemaining, splitSize, -splitHosts)); +splitHosts[0], splitHosts[1])); bytesRemaining -= splitSize; } if (bytesRemaining != 0) { -String[] splitHosts = getSplitHosts(blkLocations, length +String[][] splitHosts = getSplitHostsAndCachedHosts(blkLocations, length - bytesRemaining, bytesRemaining, clusterMap); splits.add(makeSplit(path, length - bytesRemaining, bytesRemaining, -
svn commit: r1603694 - in /hadoop/common/branches/branch-0.23.11/hadoop-mapreduce-project: ./ hadoop-mapreduce-client/ hadoop-mapreduce-client/hadoop-mapreduce-client-app/ hadoop-mapreduce-client/hado
Author: tgraves Date: Thu Jun 19 01:17:43 2014 New Revision: 1603694 URL: http://svn.apache.org/r1603694 Log: Preparing for release 0.23.11 Modified: hadoop/common/branches/branch-0.23.11/hadoop-mapreduce-project/CHANGES.txt hadoop/common/branches/branch-0.23.11/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-app/pom.xml hadoop/common/branches/branch-0.23.11/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-common/pom.xml hadoop/common/branches/branch-0.23.11/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/pom.xml hadoop/common/branches/branch-0.23.11/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-hs-plugins/pom.xml hadoop/common/branches/branch-0.23.11/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-hs/pom.xml hadoop/common/branches/branch-0.23.11/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-jobclient/pom.xml hadoop/common/branches/branch-0.23.11/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-shuffle/pom.xml hadoop/common/branches/branch-0.23.11/hadoop-mapreduce-project/hadoop-mapreduce-client/pom.xml hadoop/common/branches/branch-0.23.11/hadoop-mapreduce-project/hadoop-mapreduce-examples/pom.xml hadoop/common/branches/branch-0.23.11/hadoop-mapreduce-project/pom.xml Modified: hadoop/common/branches/branch-0.23.11/hadoop-mapreduce-project/CHANGES.txt URL: http://svn.apache.org/viewvc/hadoop/common/branches/branch-0.23.11/hadoop-mapreduce-project/CHANGES.txt?rev=1603694r1=1603693r2=1603694view=diff == --- hadoop/common/branches/branch-0.23.11/hadoop-mapreduce-project/CHANGES.txt (original) +++ hadoop/common/branches/branch-0.23.11/hadoop-mapreduce-project/CHANGES.txt Thu Jun 19 01:17:43 2014 @@ -1,6 +1,6 @@ Hadoop MapReduce Change Log -Release 0.23.11 - UNRELEASED +Release 0.23.11 - 2014-06-26 INCOMPATIBLE CHANGES Modified: hadoop/common/branches/branch-0.23.11/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-app/pom.xml URL: http://svn.apache.org/viewvc/hadoop/common/branches/branch-0.23.11/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-app/pom.xml?rev=1603694r1=1603693r2=1603694view=diff == --- hadoop/common/branches/branch-0.23.11/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-app/pom.xml (original) +++ hadoop/common/branches/branch-0.23.11/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-app/pom.xml Thu Jun 19 01:17:43 2014 @@ -19,12 +19,12 @@ parent artifactIdhadoop-mapreduce-client/artifactId groupIdorg.apache.hadoop/groupId -version0.23.11-SNAPSHOT/version +version0.23.11/version /parent modelVersion4.0.0/modelVersion groupIdorg.apache.hadoop/groupId artifactIdhadoop-mapreduce-client-app/artifactId - version0.23.11-SNAPSHOT/version + version0.23.11/version namehadoop-mapreduce-client-app/name properties Modified: hadoop/common/branches/branch-0.23.11/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-common/pom.xml URL: http://svn.apache.org/viewvc/hadoop/common/branches/branch-0.23.11/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-common/pom.xml?rev=1603694r1=1603693r2=1603694view=diff == --- hadoop/common/branches/branch-0.23.11/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-common/pom.xml (original) +++ hadoop/common/branches/branch-0.23.11/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-common/pom.xml Thu Jun 19 01:17:43 2014 @@ -19,12 +19,12 @@ parent artifactIdhadoop-mapreduce-client/artifactId groupIdorg.apache.hadoop/groupId -version0.23.11-SNAPSHOT/version +version0.23.11/version /parent modelVersion4.0.0/modelVersion groupIdorg.apache.hadoop/groupId artifactIdhadoop-mapreduce-client-common/artifactId - version0.23.11-SNAPSHOT/version + version0.23.11/version namehadoop-mapreduce-client-common/name properties Modified: hadoop/common/branches/branch-0.23.11/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/pom.xml URL: http://svn.apache.org/viewvc/hadoop/common/branches/branch-0.23.11/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/pom.xml?rev=1603694r1=1603693r2=1603694view=diff == --- hadoop/common/branches/branch-0.23.11/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/pom.xml (original) +++