Author: vinodkv
Date: Tue Mar 11 01:30:20 2014
New Revision: 1576171
URL: http://svn.apache.org/r1576171
Log:
MAPREDUCE-5028. Fixed a bug in MapTask that was causing mappers to fail when a
large value of io.sort.mb is set. Contributed by Karthik Kambatla.
svn merge --ignore-ancestry -c 1576170 ../../trunk/
Added:
hadoop/common/branches/branch-2/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-jobclient/src/test/java/org/apache/hadoop/mapreduce/LargeSorter.java
- copied unchanged from r1576170,
hadoop/common/trunk/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-jobclient/src/test/java/org/apache/hadoop/mapreduce/LargeSorter.java
hadoop/common/branches/branch-2/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-jobclient/src/test/java/org/apache/hadoop/mapreduce/TestLargeSort.java
- copied unchanged from r1576170,
hadoop/common/trunk/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-jobclient/src/test/java/org/apache/hadoop/mapreduce/TestLargeSort.java
Modified:
hadoop/common/branches/branch-2/hadoop-mapreduce-project/CHANGES.txt
hadoop/common/branches/branch-2/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/MapTask.java
hadoop/common/branches/branch-2/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/task/ReduceContextImpl.java
hadoop/common/branches/branch-2/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/task/reduce/InMemoryReader.java
hadoop/common/branches/branch-2/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-jobclient/src/test/java/org/apache/hadoop/test/MapredTestDriver.java
Modified: hadoop/common/branches/branch-2/hadoop-mapreduce-project/CHANGES.txt
URL:
http://svn.apache.org/viewvc/hadoop/common/branches/branch-2/hadoop-mapreduce-project/CHANGES.txt?rev=1576171&r1=1576170&r2=1576171&view=diff
==============================================================================
--- hadoop/common/branches/branch-2/hadoop-mapreduce-project/CHANGES.txt
(original)
+++ hadoop/common/branches/branch-2/hadoop-mapreduce-project/CHANGES.txt Tue
Mar 11 01:30:20 2014
@@ -69,6 +69,9 @@ Release 2.4.0 - UNRELEASED
MAPREDUCE-5780. SliveTest should use the specified path to get the
particular FileSystem instead of using the default FileSystem. (szetszwo)
+ MAPREDUCE-5028. Fixed a bug in MapTask that was causing mappers to fail
+ when a large value of io.sort.mb is set. (Karthik Kambatla via vinodkv)
+
Release 2.3.1 - UNRELEASED
INCOMPATIBLE CHANGES
Modified:
hadoop/common/branches/branch-2/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-2/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/MapTask.java?rev=1576171&r1=1576170&r2=1576171&view=diff
==============================================================================
---
hadoop/common/branches/branch-2/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/MapTask.java
(original)
+++
hadoop/common/branches/branch-2/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/MapTask.java
Tue Mar 11 01:30:20 2014
@@ -1176,8 +1176,9 @@ public class MapTask extends Task {
equator = pos;
// set index prior to first entry, aligned at meta boundary
final int aligned = pos - (pos % METASIZE);
- kvindex =
- ((aligned - METASIZE + kvbuffer.length) % kvbuffer.length) / 4;
+ // Cast one of the operands to long to avoid integer overflow
+ kvindex = (int)
+ (((long)aligned - METASIZE + kvbuffer.length) % kvbuffer.length) / 4;
LOG.info("(EQUATOR) " + pos + " kvi " + kvindex +
"(" + (kvindex * 4) + ")");
}
@@ -1192,8 +1193,9 @@ public class MapTask extends Task {
bufstart = bufend = e;
final int aligned = e - (e % METASIZE);
// set start/end to point to first meta record
- kvstart = kvend =
- ((aligned - METASIZE + kvbuffer.length) % kvbuffer.length) / 4;
+ // Cast one of the operands to long to avoid integer overflow
+ kvstart = kvend = (int)
+ (((long)aligned - METASIZE + kvbuffer.length) % kvbuffer.length) / 4;
LOG.info("(RESET) equator " + e + " kv " + kvstart + "(" +
(kvstart * 4) + ")" + " kvi " + kvindex + "(" + (kvindex * 4) + ")");
}
Modified:
hadoop/common/branches/branch-2/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/task/ReduceContextImpl.java
URL:
http://svn.apache.org/viewvc/hadoop/common/branches/branch-2/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/task/ReduceContextImpl.java?rev=1576171&r1=1576170&r2=1576171&view=diff
==============================================================================
---
hadoop/common/branches/branch-2/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/task/ReduceContextImpl.java
(original)
+++
hadoop/common/branches/branch-2/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/task/ReduceContextImpl.java
Tue Mar 11 01:30:20 2014
@@ -141,7 +141,8 @@ public class ReduceContextImpl<KEYIN,VAL
buffer.reset(currentRawKey.getBytes(), 0, currentRawKey.getLength());
key = keyDeserializer.deserialize(key);
DataInputBuffer nextVal = input.getValue();
- buffer.reset(nextVal.getData(), nextVal.getPosition(),
nextVal.getLength());
+ buffer.reset(nextVal.getData(), nextVal.getPosition(), nextVal.getLength()
+ - nextVal.getPosition());
value = valueDeserializer.deserialize(value);
currentKeyLength = nextKey.getLength() - nextKey.getPosition();
@@ -205,7 +206,8 @@ public class ReduceContextImpl<KEYIN,VAL
if (backupStore.hasNext()) {
backupStore.next();
DataInputBuffer next = backupStore.nextValue();
- buffer.reset(next.getData(), next.getPosition(), next.getLength());
+ buffer.reset(next.getData(), next.getPosition(), next.getLength()
+ - next.getPosition());
value = valueDeserializer.deserialize(value);
return value;
} else {
Modified:
hadoop/common/branches/branch-2/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/task/reduce/InMemoryReader.java
URL:
http://svn.apache.org/viewvc/hadoop/common/branches/branch-2/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/task/reduce/InMemoryReader.java?rev=1576171&r1=1576170&r2=1576171&view=diff
==============================================================================
---
hadoop/common/branches/branch-2/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/task/reduce/InMemoryReader.java
(original)
+++
hadoop/common/branches/branch-2/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/task/reduce/InMemoryReader.java
Tue Mar 11 01:30:20 2014
@@ -37,9 +37,9 @@ import org.apache.hadoop.mapreduce.TaskA
public class InMemoryReader<K, V> extends Reader<K, V> {
private final TaskAttemptID taskAttemptId;
private final MergeManagerImpl<K,V> merger;
- DataInputBuffer memDataIn = new DataInputBuffer();
- private int start;
- private int length;
+ private final DataInputBuffer memDataIn = new DataInputBuffer();
+ private final int start;
+ private final int length;
public InMemoryReader(MergeManagerImpl<K,V> merger, TaskAttemptID
taskAttemptId,
byte[] data, int start, int length, Configuration conf)
@@ -50,14 +50,14 @@ public class InMemoryReader<K, V> extend
buffer = data;
bufferSize = (int)fileLength;
- memDataIn.reset(buffer, start, length);
+ memDataIn.reset(buffer, start, length - start);
this.start = start;
this.length = length;
}
@Override
public void reset(int offset) {
- memDataIn.reset(buffer, start + offset, length);
+ memDataIn.reset(buffer, start + offset, length - start - offset);
bytesRead = offset;
eof = false;
}
Modified:
hadoop/common/branches/branch-2/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-jobclient/src/test/java/org/apache/hadoop/test/MapredTestDriver.java
URL:
http://svn.apache.org/viewvc/hadoop/common/branches/branch-2/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-jobclient/src/test/java/org/apache/hadoop/test/MapredTestDriver.java?rev=1576171&r1=1576170&r2=1576171&view=diff
==============================================================================
---
hadoop/common/branches/branch-2/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-jobclient/src/test/java/org/apache/hadoop/test/MapredTestDriver.java
(original)
+++
hadoop/common/branches/branch-2/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-jobclient/src/test/java/org/apache/hadoop/test/MapredTestDriver.java
Tue Mar 11 01:30:20 2014
@@ -29,6 +29,7 @@ import org.apache.hadoop.mapred.TestSequ
import org.apache.hadoop.mapred.TestTextInputFormat;
import org.apache.hadoop.mapred.ThreadedMapBenchmark;
import org.apache.hadoop.mapreduce.FailJob;
+import org.apache.hadoop.mapreduce.LargeSorter;
import org.apache.hadoop.mapreduce.MiniHadoopClusterManager;
import org.apache.hadoop.mapreduce.SleepJob;
import org.apache.hadoop.util.ProgramDriver;
@@ -104,6 +105,8 @@ public class MapredTestDriver {
"HDFS Stress Test and Live Data Verification.");
pgd.addClass("minicluster", MiniHadoopClusterManager.class,
"Single process HDFS and MR cluster.");
+ pgd.addClass("largesorter", LargeSorter.class,
+ "Large-Sort tester");
} catch(Throwable e) {
e.printStackTrace();
}
