private ValuesIterator createEmptyIterator(boolean inMemory)
throws IOException, InterruptedException {
if (!inMemory) {
streamPaths = new Path[0];
// This will return EmptyIterator
rawKeyValueIterator =
TezMerger.merge(
conf,
fs,
keyClass,
valClass,
null,
false,
-1,
1024,
streamPaths,
false,
mergeFactor,
tmpDir,
comparator,
new ProgressReporter(),
null,
null,
null,
null);
} else {
List<TezMerger.Segment> segments = Lists.newLinkedList();
// This will return EmptyIterator
rawKeyValueIterator =
TezMerger.merge(
conf,
fs,
keyClass,
valClass,
segments,
mergeFactor,
tmpDir,
comparator,
new ProgressReporter(),
new GenericCounter("readsCounter", "y"),
new GenericCounter("writesCounter", "y1"),
new GenericCounter("bytesReadCounter", "y2"),
new Progress());
}
return new ValuesIterator(
rawKeyValueIterator,
comparator,
keyClass,
valClass,
conf,
(TezCounter) new GenericCounter("inputKeyCounter", "y3"),
(TezCounter) new GenericCounter("inputValueCounter", "y4"));
}
/**
* Create sample data (in memory), with an attached counter and return ValuesIterator
*
* @param inMemory
* @param keyCounter
* @param tupleCounter
* @return ValuesIterator
* @throws IOException
*/
private ValuesIterator createCountedIterator(
boolean inMemory, TezCounter keyCounter, TezCounter tupleCounter)
throws IOException, InterruptedException {
if (!inMemory) {
streamPaths = createFiles();
// Merge all files to get KeyValueIterator
rawKeyValueIterator =
TezMerger.merge(
conf,
fs,
keyClass,
valClass,
null,
false,
-1,
1024,
streamPaths,
false,
mergeFactor,
tmpDir,
comparator,
new ProgressReporter(),
null,
null,
null,
null);
} else {
List<TezMerger.Segment> segments = createInMemStreams();
rawKeyValueIterator =
TezMerger.merge(
conf,
fs,
keyClass,
valClass,
segments,
mergeFactor,
tmpDir,
comparator,
new ProgressReporter(),
new GenericCounter("readsCounter", "y"),
new GenericCounter("writesCounter", "y1"),
new GenericCounter("bytesReadCounter", "y2"),
new Progress());
}
return new ValuesIterator(
rawKeyValueIterator, comparator, keyClass, valClass, conf, keyCounter, tupleCounter);
}
private void mergeParts() throws IOException {
// get the approximate size of the final output/index files
long finalOutFileSize = 0;
long finalIndexFileSize = 0;
final Path[] filename = new Path[numSpills];
final String taskIdentifier = outputContext.getUniqueIdentifier();
for (int i = 0; i < numSpills; i++) {
filename[i] = mapOutputFile.getSpillFile(i);
finalOutFileSize += rfs.getFileStatus(filename[i]).getLen();
}
if (numSpills == 1) { // the spill is the final output
sameVolRename(filename[0], mapOutputFile.getOutputFileForWriteInVolume(filename[0]));
if (indexCacheList.size() == 0) {
sameVolRename(
mapOutputFile.getSpillIndexFile(0),
mapOutputFile.getOutputIndexFileForWriteInVolume(filename[0]));
} else {
indexCacheList
.get(0)
.writeToFile(mapOutputFile.getOutputIndexFileForWriteInVolume(filename[0]), conf);
}
return;
}
// read in paged indices
for (int i = indexCacheList.size(); i < numSpills; ++i) {
Path indexFileName = mapOutputFile.getSpillIndexFile(i);
indexCacheList.add(new TezSpillRecord(indexFileName, conf));
}
// make correction in the length to include the sequence file header
// lengths for each partition
finalOutFileSize += partitions * APPROX_HEADER_LENGTH;
finalIndexFileSize = partitions * MAP_OUTPUT_INDEX_RECORD_LENGTH;
Path finalOutputFile = mapOutputFile.getOutputFileForWrite(finalOutFileSize);
Path finalIndexFile = mapOutputFile.getOutputIndexFileForWrite(finalIndexFileSize);
// The output stream for the final single output file
FSDataOutputStream finalOut = rfs.create(finalOutputFile, true, 4096);
if (numSpills == 0) {
// TODO Change event generation to say there is no data rather than generating a dummy file
// create dummy files
TezSpillRecord sr = new TezSpillRecord(partitions);
try {
for (int i = 0; i < partitions; i++) {
long segmentStart = finalOut.getPos();
Writer writer = new Writer(conf, finalOut, keyClass, valClass, codec, null, null);
writer.close();
TezIndexRecord rec =
new TezIndexRecord(segmentStart, writer.getRawLength(), writer.getCompressedLength());
// Covers the case of multiple spills.
outputBytesWithOverheadCounter.increment(writer.getRawLength());
sr.putIndex(rec, i);
}
sr.writeToFile(finalIndexFile, conf);
} finally {
finalOut.close();
}
return;
} else {
final TezSpillRecord spillRec = new TezSpillRecord(partitions);
for (int parts = 0; parts < partitions; parts++) {
// create the segments to be merged
List<Segment> segmentList = new ArrayList<Segment>(numSpills);
for (int i = 0; i < numSpills; i++) {
TezIndexRecord indexRecord = indexCacheList.get(i).getIndex(parts);
Segment s =
new Segment(
conf,
rfs,
filename[i],
indexRecord.getStartOffset(),
indexRecord.getPartLength(),
codec,
ifileReadAhead,
ifileReadAheadLength,
ifileBufferSize,
true);
segmentList.add(i, s);
if (LOG.isDebugEnabled()) {
LOG.debug(
"TaskIdentifier="
+ taskIdentifier
+ " Partition="
+ parts
+ "Spill ="
+ i
+ "("
+ indexRecord.getStartOffset()
+ ","
+ indexRecord.getRawLength()
+ ", "
+ indexRecord.getPartLength()
+ ")");
}
}
int mergeFactor =
this.conf.getInt(
TezRuntimeConfiguration.TEZ_RUNTIME_IO_SORT_FACTOR,
TezRuntimeConfiguration.TEZ_RUNTIME_IO_SORT_FACTOR_DEFAULT);
// sort the segments only if there are intermediate merges
boolean sortSegments = segmentList.size() > mergeFactor;
// merge
TezRawKeyValueIterator kvIter =
TezMerger.merge(
conf,
rfs,
keyClass,
valClass,
codec,
segmentList,
mergeFactor,
new Path(taskIdentifier),
(RawComparator) ConfigUtils.getIntermediateOutputKeyComparator(conf),
nullProgressable,
sortSegments,
true,
null,
spilledRecordsCounter,
additionalSpillBytesRead,
null); // Not using any Progress in TezMerger. Should just work.
// write merged output to disk
long segmentStart = finalOut.getPos();
Writer writer =
new Writer(conf, finalOut, keyClass, valClass, codec, spilledRecordsCounter, null);
if (combiner == null || numSpills < minSpillsForCombine) {
TezMerger.writeFile(
kvIter,
writer,
nullProgressable,
TezRuntimeConfiguration.TEZ_RUNTIME_RECORDS_BEFORE_PROGRESS_DEFAULT);
} else {
runCombineProcessor(kvIter, writer);
}
writer.close();
// record offsets
final TezIndexRecord rec =
new TezIndexRecord(segmentStart, writer.getRawLength(), writer.getCompressedLength());
spillRec.putIndex(rec, parts);
}
spillRec.writeToFile(finalIndexFile, conf);
finalOut.close();
for (int i = 0; i < numSpills; i++) {
rfs.delete(filename[i], true);
}
}
}