MapTask.java

  @SuppressWarnings("unchecked")
  private <INKEY,INVALUE,OUTKEY,OUTVALUE>
  void runNewMapper(final JobConf job,
                    final TaskSplitIndex splitIndex,
                    final TaskUmbilicalProtocol umbilical,
                    TaskReporter reporter
                    ) throws IOException, ClassNotFoundException,
                             InterruptedException {
    // make a task context so we can get the classes
    org.apache.hadoop.mapreduce.TaskAttemptContext taskContext =
      new org.apache.hadoop.mapreduce.task.TaskAttemptContextImpl(job, 
                                                                  getTaskID(),
                                                                  reporter);
    // make a mapper
    org.apache.hadoop.mapreduce.Mapper<INKEY,INVALUE,OUTKEY,OUTVALUE> mapper =
      (org.apache.hadoop.mapreduce.Mapper<INKEY,INVALUE,OUTKEY,OUTVALUE>)
        ReflectionUtils.newInstance(taskContext.getMapperClass(), job);
    // make the input format
    org.apache.hadoop.mapreduce.InputFormat<INKEY,INVALUE> inputFormat =
      (org.apache.hadoop.mapreduce.InputFormat<INKEY,INVALUE>)
        ReflectionUtils.newInstance(taskContext.getInputFormatClass(), job);
    // rebuild the input split
    org.apache.hadoop.mapreduce.InputSplit split = null;
    split = getSplitDetails(new Path(splitIndex.getSplitLocation()),
        splitIndex.getStartOffset());
    LOG.info("Processing split: " + split);

    org.apache.hadoop.mapreduce.RecordReader<INKEY,INVALUE> input =
      new NewTrackingRecordReader<INKEY,INVALUE>
        (split, inputFormat, reporter, taskContext);
    
    job.setBoolean(JobContext.SKIP_RECORDS, isSkipping());
    org.apache.hadoop.mapreduce.RecordWriter output = null;
    
    // get an output object
    if (job.getNumReduceTasks() == 0) {
      output = 
        new NewDirectOutputCollector(taskContext, job, umbilical, reporter);
    } else {
      output = new NewOutputCollector(taskContext, job, umbilical, reporter);
    }

    org.apache.hadoop.mapreduce.MapContext<INKEY, INVALUE, OUTKEY, OUTVALUE> 
    mapContext = 
      new MapContextImpl<INKEY, INVALUE, OUTKEY, OUTVALUE>(job, getTaskID(), 
          input, output, 
          committer, 
          reporter, split);

    org.apache.hadoop.mapreduce.Mapper<INKEY,INVALUE,OUTKEY,OUTVALUE>.Context 
        mapperContext = 
          new WrappedMapper<INKEY, INVALUE, OUTKEY, OUTVALUE>().getMapContext(
              mapContext);

    try {
      input.initialize(split, mapperContext);
      mapper.run(mapperContext);
      mapPhase.complete();
      setPhase(TaskStatus.Phase.SORT);
      statusUpdate(umbilical);
      input.close();
      input = null;
      output.close(mapperContext);
      output = null;
    } finally {
      closeQuietly(input);
      closeQuietly(output, mapperContext);
    }
  }

MapOutputBuffer.class

    private void sortAndSpill() throws IOException, ClassNotFoundException,
                                       InterruptedException {
      //approximate the length of the output file to be the length of the
      //buffer + header lengths for the partitions
      final long size = distanceTo(bufstart, bufend, bufvoid) +
                  partitions * APPROX_HEADER_LENGTH;
      FSDataOutputStream out = null;
      try {
        // create spill file
        final SpillRecord spillRec = new SpillRecord(partitions);
        final Path filename =
            mapOutputFile.getSpillFileForWrite(numSpills, size);
        out = rfs.create(filename);

        final int mstart = kvend / NMETA;
        final int mend = 1 + // kvend is a valid record
          (kvstart >= kvend
          ? kvstart
          : kvmeta.capacity() + kvstart) / NMETA;
        sorter.sort(MapOutputBuffer.this, mstart, mend, reporter);
        int spindex = mstart;
        final IndexRecord rec = new IndexRecord();
        final InMemValBytes value = new InMemValBytes();
        for (int i = 0; i < partitions; ++i) {
          IFile.Writer<K, V> writer = null;
          try {
            long segmentStart = out.getPos();
            FSDataOutputStream partitionOut = CryptoUtils.wrapIfNecessary(job, out);
            writer = new Writer<K, V>(job, partitionOut, keyClass, valClass, codec,
                                      spilledRecordsCounter);
            if (combinerRunner == null) {
              // spill directly
              DataInputBuffer key = new DataInputBuffer();
              while (spindex < mend &&
                  kvmeta.get(offsetFor(spindex % maxRec) + PARTITION) == i) {
                final int kvoff = offsetFor(spindex % maxRec);
                int keystart = kvmeta.get(kvoff + KEYSTART);
                int valstart = kvmeta.get(kvoff + VALSTART);
                key.reset(kvbuffer, keystart, valstart - keystart);
                getVBytesForOffset(kvoff, value);
                writer.append(key, value);
                ++spindex;
              }
            } else {
              int spstart = spindex;
              while (spindex < mend &&
                  kvmeta.get(offsetFor(spindex % maxRec)
                            + PARTITION) == i) {
                ++spindex;
              }
              // Note: we would like to avoid the combiner if we've fewer
              // than some threshold of records for a partition
              if (spstart != spindex) {
                combineCollector.setWriter(writer);
                RawKeyValueIterator kvIter =
                  new MRResultIterator(spstart, spindex);
                combinerRunner.combine(kvIter, combineCollector);
              }
            }

            // close the writer
            writer.close();

            // record offsets
            rec.startOffset = segmentStart;
            rec.rawLength = writer.getRawLength() + CryptoUtils.cryptoPadding(job);
            rec.partLength = writer.getCompressedLength() + CryptoUtils.cryptoPadding(job);
            spillRec.putIndex(rec, i);

            writer = null;
          } finally {
            if (null != writer) writer.close();
          }
        }

        if (totalIndexCacheMemory >= indexCacheMemoryLimit) {
          // create spill index file
          Path indexFilename =
              mapOutputFile.getSpillIndexFileForWrite(numSpills, partitions
                  * MAP_OUTPUT_INDEX_RECORD_LENGTH);
          spillRec.writeToFile(indexFilename, job);
        } else {
          indexCacheList.add(spillRec);
          totalIndexCacheMemory +=
            spillRec.size() * MAP_OUTPUT_INDEX_RECORD_LENGTH;
        }
        LOG.info("Finished spill " + numSpills);
        ++numSpills;
      } finally {
        if (out != null) out.close();
      }
    }

 /**
     * Compare logical range, st i, j MOD offset capacity.
     * Compare by partition, then by key.
     * @see IndexedSortable#compare
     */
    public int compare(final int mi, final int mj) {
      final int kvi = offsetFor(mi % maxRec);
      final int kvj = offsetFor(mj % maxRec);
      final int kvip = kvmeta.get(kvi + PARTITION);
      final int kvjp = kvmeta.get(kvj + PARTITION);
      // sort by partition
      if (kvip != kvjp) {
        return kvip - kvjp;
      }
      // sort by key
      return comparator.compare(kvbuffer,
          kvmeta.get(kvi + KEYSTART),
          kvmeta.get(kvi + VALSTART) - kvmeta.get(kvi + KEYSTART),
          kvbuffer,
          kvmeta.get(kvj + KEYSTART),
          kvmeta.get(kvj + VALSTART) - kvmeta.get(kvj + KEYSTART));
    }

  @SuppressWarnings("unchecked")
    public void init(MapOutputCollector.Context context
                    ) throws IOException, ClassNotFoundException {
      job = context.getJobConf();
      reporter = context.getReporter();
      mapTask = context.getMapTask();
      mapOutputFile = mapTask.getMapOutputFile();
      sortPhase = mapTask.getSortPhase();
      spilledRecordsCounter = reporter.getCounter(TaskCounter.SPILLED_RECORDS);
      partitions = job.getNumReduceTasks();
      rfs = ((LocalFileSystem)FileSystem.getLocal(job)).getRaw();

      //sanity checks
      final float spillper =
        job.getFloat(JobContext.MAP_SORT_SPILL_PERCENT, (float)0.8);
      final int sortmb = job.getInt(JobContext.IO_SORT_MB, 100);
      indexCacheMemoryLimit = job.getInt(JobContext.INDEX_CACHE_MEMORY_LIMIT,
                                         INDEX_CACHE_MEMORY_LIMIT_DEFAULT);
      if (spillper > (float)1.0 || spillper <= (float)0.0) {
        throw new IOException("Invalid \"" + JobContext.MAP_SORT_SPILL_PERCENT +
            "\": " + spillper);
      }
      if ((sortmb & 0x7FF) != sortmb) {
        throw new IOException(
            "Invalid \"" + JobContext.IO_SORT_MB + "\": " + sortmb);
      }
      sorter = ReflectionUtils.newInstance(job.getClass("map.sort.class",
            QuickSort.class, IndexedSorter.class), job);
      // buffers and accounting
      int maxMemUsage = sortmb << 20;
      maxMemUsage -= maxMemUsage % METASIZE;
      kvbuffer = new byte[maxMemUsage];
      bufvoid = kvbuffer.length;
      kvmeta = ByteBuffer.wrap(kvbuffer)
         .order(ByteOrder.nativeOrder())
         .asIntBuffer();
      setEquator(0);
      bufstart = bufend = bufindex = equator;
      kvstart = kvend = kvindex;

      maxRec = kvmeta.capacity() / NMETA;
      softLimit = (int)(kvbuffer.length * spillper);
      bufferRemaining = softLimit;
      LOG.info(JobContext.IO_SORT_MB + ": " + sortmb);
      LOG.info("soft limit at " + softLimit);
      LOG.info("bufstart = " + bufstart + "; bufvoid = " + bufvoid);
      LOG.info("kvstart = " + kvstart + "; length = " + maxRec);

      // k/v serialization
      comparator = job.getOutputKeyComparator();
      keyClass = (Class<K>)job.getMapOutputKeyClass();
      valClass = (Class<V>)job.getMapOutputValueClass();
      serializationFactory = new SerializationFactory(job);
      keySerializer = serializationFactory.getSerializer(keyClass);
      keySerializer.open(bb);
      valSerializer = serializationFactory.getSerializer(valClass);
      valSerializer.open(bb);

      // output counters
      mapOutputByteCounter = reporter.getCounter(TaskCounter.MAP_OUTPUT_BYTES);
      mapOutputRecordCounter =
        reporter.getCounter(TaskCounter.MAP_OUTPUT_RECORDS);
      fileOutputByteCounter = reporter
          .getCounter(TaskCounter.MAP_OUTPUT_MATERIALIZED_BYTES);

      // compression
      if (job.getCompressMapOutput()) {
        Class<? extends CompressionCodec> codecClass =
          job.getMapOutputCompressorClass(DefaultCodec.class);
        codec = ReflectionUtils.newInstance(codecClass, job);
      } else {
        codec = null;
      }

      // combiner
      final Counters.Counter combineInputCounter =
        reporter.getCounter(TaskCounter.COMBINE_INPUT_RECORDS);
      combinerRunner = CombinerRunner.create(job, getTaskID(), 
                                             combineInputCounter,
                                             reporter, null);
      if (combinerRunner != null) {
        final Counters.Counter combineOutputCounter =
          reporter.getCounter(TaskCounter.COMBINE_OUTPUT_RECORDS);
        combineCollector= new CombineOutputCollector<K,V>(combineOutputCounter, reporter, job);
      } else {
        combineCollector = null;
      }
      spillInProgress = false;
      minSpillsForCombine = job.getInt(JobContext.MAP_COMBINE_MIN_SPILLS, 3);
      spillThread.setDaemon(true);
      spillThread.setName("SpillThread");
      spillLock.lock();
      try {
        spillThread.start();
        while (!spillThreadRunning) {
          spillDone.await();
        }
      } catch (InterruptedException e) {
        throw new IOException("Spill thread failed to initialize", e);
      } finally {
        spillLock.unlock();
      }
      if (sortSpillException != null) {
        throw new IOException("Spill thread failed to initialize",
            sortSpillException);
      }
    }

jobConf.java

  /**
   * Get the {@link RawComparator} comparator used to compare keys.
   * 
   * @return the {@link RawComparator} comparator used to compare keys.
   */
  public RawComparator getOutputKeyComparator() {
    Class<? extends RawComparator> theClass = getClass(
      JobContext.KEY_COMPARATOR, null, RawComparator.class);
    if (theClass != null)
      return ReflectionUtils.newInstance(theClass, this);
    return WritableComparator.get(getMapOutputKeyClass().asSubclass(WritableComparable.class), this);
  }

WritableComparator.java

  /** Get a comparator for a {@link WritableComparable} implementation. */
  public static WritableComparator get(
      Class<? extends WritableComparable> c, Configuration conf) {
    WritableComparator comparator = comparators.get(c);
    if (comparator == null) {
      // force the static initializers to run
      forceInit(c);
      // look to see if it is defined now
      comparator = comparators.get(c);
      // if not, use the generic one
      if (comparator == null) {
        comparator = new WritableComparator(c, conf, true);
      }
    }
    // Newly passed Configuration objects should be used.
    ReflectionUtils.setConf(comparator, conf);
    return comparator;
  }

  /** Compare two WritableComparables.
   *
   * <p> The default implementation uses the natural ordering, calling {@link
   * Comparable#compareTo(Object)}. */
  @SuppressWarnings("unchecked")
  public int compare(WritableComparable a, WritableComparable b) {
    return a.compareTo(b);
  }