use of org.apache.hadoop.mapred.Merger.Segment in project hadoop by apache.
the class MergeManagerImpl method finalMerge.
private RawKeyValueIterator finalMerge(JobConf job, FileSystem fs, List<InMemoryMapOutput<K, V>> inMemoryMapOutputs, List<CompressAwarePath> onDiskMapOutputs) throws IOException {
LOG.info("finalMerge called with " + inMemoryMapOutputs.size() + " in-memory map-outputs and " + onDiskMapOutputs.size() + " on-disk map-outputs");
final long maxInMemReduce = getMaxInMemReduceLimit();
// merge config params
Class<K> keyClass = (Class<K>) job.getMapOutputKeyClass();
Class<V> valueClass = (Class<V>) job.getMapOutputValueClass();
boolean keepInputs = job.getKeepFailedTaskFiles();
final Path tmpDir = new Path(reduceId.toString());
final RawComparator<K> comparator = (RawComparator<K>) job.getOutputKeyComparator();
// segments required to vacate memory
List<Segment<K, V>> memDiskSegments = new ArrayList<Segment<K, V>>();
long inMemToDiskBytes = 0;
boolean mergePhaseFinished = false;
if (inMemoryMapOutputs.size() > 0) {
TaskID mapId = inMemoryMapOutputs.get(0).getMapId().getTaskID();
inMemToDiskBytes = createInMemorySegments(inMemoryMapOutputs, memDiskSegments, maxInMemReduce);
final int numMemDiskSegments = memDiskSegments.size();
if (numMemDiskSegments > 0 && ioSortFactor > onDiskMapOutputs.size()) {
// If we reach here, it implies that we have less than io.sort.factor
// disk segments and this will be incremented by 1 (result of the
// memory segments merge). Since this total would still be
// <= io.sort.factor, we will not do any more intermediate merges,
// the merge of all these disk segments would be directly fed to the
// reduce method
mergePhaseFinished = true;
// must spill to disk, but can't retain in-mem for intermediate merge
final Path outputPath = mapOutputFile.getInputFileForWrite(mapId, inMemToDiskBytes).suffix(Task.MERGED_OUTPUT_PREFIX);
final RawKeyValueIterator rIter = Merger.merge(job, fs, keyClass, valueClass, memDiskSegments, numMemDiskSegments, tmpDir, comparator, reporter, spilledRecordsCounter, null, mergePhase);
FSDataOutputStream out = CryptoUtils.wrapIfNecessary(job, fs.create(outputPath));
Writer<K, V> writer = new Writer<K, V>(job, out, keyClass, valueClass, codec, null, true);
try {
Merger.writeFile(rIter, writer, reporter, job);
writer.close();
onDiskMapOutputs.add(new CompressAwarePath(outputPath, writer.getRawLength(), writer.getCompressedLength()));
writer = null;
// add to list of final disk outputs.
} catch (IOException e) {
if (null != outputPath) {
try {
fs.delete(outputPath, true);
} catch (IOException ie) {
// NOTHING
}
}
throw e;
} finally {
if (null != writer) {
writer.close();
}
}
LOG.info("Merged " + numMemDiskSegments + " segments, " + inMemToDiskBytes + " bytes to disk to satisfy " + "reduce memory limit");
inMemToDiskBytes = 0;
memDiskSegments.clear();
} else if (inMemToDiskBytes != 0) {
LOG.info("Keeping " + numMemDiskSegments + " segments, " + inMemToDiskBytes + " bytes in memory for " + "intermediate, on-disk merge");
}
}
// segments on disk
List<Segment<K, V>> diskSegments = new ArrayList<Segment<K, V>>();
long onDiskBytes = inMemToDiskBytes;
long rawBytes = inMemToDiskBytes;
CompressAwarePath[] onDisk = onDiskMapOutputs.toArray(new CompressAwarePath[onDiskMapOutputs.size()]);
for (CompressAwarePath file : onDisk) {
long fileLength = fs.getFileStatus(file).getLen();
onDiskBytes += fileLength;
rawBytes += (file.getRawDataLength() > 0) ? file.getRawDataLength() : fileLength;
LOG.debug("Disk file: " + file + " Length is " + fileLength);
diskSegments.add(new Segment<K, V>(job, fs, file, codec, keepInputs, (file.toString().endsWith(Task.MERGED_OUTPUT_PREFIX) ? null : mergedMapOutputsCounter), file.getRawDataLength()));
}
LOG.info("Merging " + onDisk.length + " files, " + onDiskBytes + " bytes from disk");
Collections.sort(diskSegments, new Comparator<Segment<K, V>>() {
public int compare(Segment<K, V> o1, Segment<K, V> o2) {
if (o1.getLength() == o2.getLength()) {
return 0;
}
return o1.getLength() < o2.getLength() ? -1 : 1;
}
});
// build final list of segments from merged backed by disk + in-mem
List<Segment<K, V>> finalSegments = new ArrayList<Segment<K, V>>();
long inMemBytes = createInMemorySegments(inMemoryMapOutputs, finalSegments, 0);
LOG.info("Merging " + finalSegments.size() + " segments, " + inMemBytes + " bytes from memory into reduce");
if (0 != onDiskBytes) {
final int numInMemSegments = memDiskSegments.size();
diskSegments.addAll(0, memDiskSegments);
memDiskSegments.clear();
// Pass mergePhase only if there is a going to be intermediate
// merges. See comment where mergePhaseFinished is being set
Progress thisPhase = (mergePhaseFinished) ? null : mergePhase;
RawKeyValueIterator diskMerge = Merger.merge(job, fs, keyClass, valueClass, codec, diskSegments, ioSortFactor, numInMemSegments, tmpDir, comparator, reporter, false, spilledRecordsCounter, null, thisPhase);
diskSegments.clear();
if (0 == finalSegments.size()) {
return diskMerge;
}
finalSegments.add(new Segment<K, V>(new RawKVIteratorReader(diskMerge, onDiskBytes), true, rawBytes));
}
return Merger.merge(job, fs, keyClass, valueClass, finalSegments, finalSegments.size(), tmpDir, comparator, reporter, spilledRecordsCounter, null, null);
}
Aggregations