@Override
public long[] writePartitionedFile(BlockId blockId, TaskContext context, File outputFile)
throws IOException {
// Track location of the partition starts in the output file
final long[] lengths = new long[numPartitions];
if (partitionWriters == null) {
// We were passed an empty iterator
return lengths;
}
final FileOutputStream out = new FileOutputStream(outputFile, true);
final long writeStartTime = System.nanoTime();
boolean threwException = true;
try {
for (int i = 0; i < numPartitions; i++) {
final FileInputStream in = new FileInputStream(partitionWriters[i].fileSegment().file());
boolean copyThrewException = true;
try {
lengths[i] = Utils.copyStream(in, out, false, transferToEnabled);
copyThrewException = false;
} finally {
Closeables.close(in, copyThrewException);
}
if (!partitionWriters[i].fileSegment().file().delete()) {
logger.error("Unable to delete file for partition {}", i);
}
}
threwException = false;
} finally {
Closeables.close(out, threwException);
writeMetrics.incShuffleWriteTime(System.nanoTime() - writeStartTime);
}
partitionWriters = null;
return lengths;
}
@Override
public void insertAll(Iterator<Product2<K, V>> records) throws IOException {
assert (partitionWriters == null);
if (!records.hasNext()) {
return;
}
final SerializerInstance serInstance = serializer.newInstance();
final long openStartTime = System.nanoTime();
partitionWriters = new DiskBlockObjectWriter[numPartitions];
for (int i = 0; i < numPartitions; i++) {
final Tuple2<TempShuffleBlockId, File> tempShuffleBlockIdPlusFile =
blockManager.diskBlockManager().createTempShuffleBlock();
final File file = tempShuffleBlockIdPlusFile._2();
final BlockId blockId = tempShuffleBlockIdPlusFile._1();
partitionWriters[i] =
blockManager
.getDiskWriter(blockId, file, serInstance, fileBufferSize, writeMetrics)
.open();
}
// Creating the file to write to and creating a disk writer both involve interacting with
// the disk, and can take a long time in aggregate when we open many files, so should be
// included in the shuffle write time.
writeMetrics.incShuffleWriteTime(System.nanoTime() - openStartTime);
while (records.hasNext()) {
final Product2<K, V> record = records.next();
final K key = record._1();
partitionWriters[partitioner.getPartition(key)].write(key, record._2());
}
for (DiskBlockObjectWriter writer : partitionWriters) {
writer.commitAndClose();
}
}
/**
* Merges spill files by using NIO's transferTo to concatenate spill partitions' bytes. This is
* only safe when the IO compression codec and serializer support concatenation of serialized
* streams.
*
* @return the partition lengths in the merged file.
*/
private long[] mergeSpillsWithTransferTo(SpillInfo[] spills, File outputFile) throws IOException {
assert (spills.length >= 2);
final int numPartitions = partitioner.numPartitions();
final long[] partitionLengths = new long[numPartitions];
final FileChannel[] spillInputChannels = new FileChannel[spills.length];
final long[] spillInputChannelPositions = new long[spills.length];
FileChannel mergedFileOutputChannel = null;
boolean threwException = true;
try {
for (int i = 0; i < spills.length; i++) {
spillInputChannels[i] = new FileInputStream(spills[i].file).getChannel();
}
// This file needs to opened in append mode in order to work around a Linux kernel bug that
// affects transferTo; see SPARK-3948 for more details.
mergedFileOutputChannel = new FileOutputStream(outputFile, true).getChannel();
long bytesWrittenToMergedFile = 0;
for (int partition = 0; partition < numPartitions; partition++) {
for (int i = 0; i < spills.length; i++) {
final long partitionLengthInSpill = spills[i].partitionLengths[partition];
long bytesToTransfer = partitionLengthInSpill;
final FileChannel spillInputChannel = spillInputChannels[i];
final long writeStartTime = System.nanoTime();
while (bytesToTransfer > 0) {
final long actualBytesTransferred =
spillInputChannel.transferTo(
spillInputChannelPositions[i], bytesToTransfer, mergedFileOutputChannel);
spillInputChannelPositions[i] += actualBytesTransferred;
bytesToTransfer -= actualBytesTransferred;
}
writeMetrics.incShuffleWriteTime(System.nanoTime() - writeStartTime);
bytesWrittenToMergedFile += partitionLengthInSpill;
partitionLengths[partition] += partitionLengthInSpill;
}
}
// Check the position after transferTo loop to see if it is in the right position and raise an
// exception if it is incorrect. The position will not be increased to the expected length
// after calling transferTo in kernel version 2.6.32. This issue is described at
// https://bugs.openjdk.java.net/browse/JDK-7052359 and SPARK-3948.
if (mergedFileOutputChannel.position() != bytesWrittenToMergedFile) {
throw new IOException(
"Current position "
+ mergedFileOutputChannel.position()
+ " does not equal expected "
+ "position "
+ bytesWrittenToMergedFile
+ " after transferTo. Please check your kernel"
+ " version to see if it is 2.6.32, as there is a kernel bug which will lead to "
+ "unexpected behavior when using transferTo. You can set spark.file.transferTo=false "
+ "to disable this NIO feature.");
}
threwException = false;
} finally {
// To avoid masking exceptions that caused us to prematurely enter the finally block, only
// throw exceptions during cleanup if threwException == false.
for (int i = 0; i < spills.length; i++) {
assert (spillInputChannelPositions[i] == spills[i].file.length());
Closeables.close(spillInputChannels[i], threwException);
}
Closeables.close(mergedFileOutputChannel, threwException);
}
return partitionLengths;
}
