hdfs MapTask类

maptask这个类是很复杂的,如图,有很多内部类.内部类中又包含内部类.

先看Mapoutbuffer类,MapOutputBuffer是一个用来暂时存储map输出的缓冲区，它的缓冲区大小是有限的，当写入的数据超过缓冲区的设定的阀值时，需要将缓冲区的数据溢出写入到磁盘，这个过程称之为spill，spill的动作会通过Condition通知给SpillThread，由SpillThread完成具体的处理过程。

MapOutputBuffer有个初始化方法,部分代码如下
其中spiller 0.8 是说内存buf用到这个比例就会flush
sortmb,内存buf大小,默认100MB
sorter:对mapper输出的key排序,用的quicksort算法.

//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;

然后数据写入环形缓冲区,一侧写kv对,一侧写meta信息
partition，keystart，valuestart
既然meta中包含分区信息,这时候已经分区了.
其中有个sortAndSpill()方法. 负责Spill的线程在拿到一段内存buf后会调用QuickSort的sort方法进行内存中的快排

  sorter.sort(MapOutputBuffer.this, mstart, mend, reporter);

mapper输出的keyvalue首先是按partition聚合。而我们如果指定key的compare方法会在这里生效并进行排序. 搞完后就会写文件.如果有combiner,执行combiner

 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();
      }
    }
    ```

merger方法
```java
private void mergeParts() throws IOException, InterruptedException, 
                                     ClassNotFoundException {
      // get the approximate size of the final output/index files
      long finalOutFileSize = 0;
      long finalIndexFileSize = 0;
      final Path[] filename = new Path[numSpills];
      final TaskAttemptID mapId = getTaskID();

      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]), job);
        }
        sortPhase.complete();
        return;
      }

      // read in paged indices
      for (int i = indexCacheList.size(); i < numSpills; ++i) {
        Path indexFileName = mapOutputFile.getSpillIndexFile(i);
        indexCacheList.add(new SpillRecord(indexFileName, job));
      }

      //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) {
        //create dummy files
        IndexRecord rec = new IndexRecord();
        SpillRecord sr = new SpillRecord(partitions);
        try {
          for (int i = 0; i < partitions; i++) {
            long segmentStart = finalOut.getPos();
            FSDataOutputStream finalPartitionOut = CryptoUtils.wrapIfNecessary(job, finalOut);
            Writer<K, V> writer =
              new Writer<K, V>(job, finalPartitionOut, keyClass, valClass, codec, null);
            writer.close();
            rec.startOffset = segmentStart;
            rec.rawLength = writer.getRawLength() + CryptoUtils.cryptoPadding(job);
            rec.partLength = writer.getCompressedLength() + CryptoUtils.cryptoPadding(job);
            sr.putIndex(rec, i);
          }
          sr.writeToFile(finalIndexFile, job);
        } finally {
          finalOut.close();
        }
        sortPhase.complete();
        return;
      }
      {
        sortPhase.addPhases(partitions); // Divide sort phase into sub-phases
        
        IndexRecord rec = new IndexRecord();
        final SpillRecord spillRec = new SpillRecord(partitions);
        for (int parts = 0; parts < partitions; parts++) {
          //create the segments to be merged
          List<Segment<K,V>> segmentList =
            new ArrayList<Segment<K, V>>(numSpills);
          for(int i = 0; i < numSpills; i++) {
            IndexRecord indexRecord = indexCacheList.get(i).getIndex(parts);

            Segment<K,V> s =
              new Segment<K,V>(job, rfs, filename[i], indexRecord.startOffset,
                               indexRecord.partLength, codec, true);
            segmentList.add(i, s);

            if (LOG.isDebugEnabled()) {
              LOG.debug("MapId=" + mapId + " Reducer=" + parts +
                  "Spill =" + i + "(" + indexRecord.startOffset + "," +
                  indexRecord.rawLength + ", " + indexRecord.partLength + ")");
            }
          }

          int mergeFactor = job.getInt(JobContext.IO_SORT_FACTOR, 100);
          // sort the segments only if there are intermediate merges
          boolean sortSegments = segmentList.size() > mergeFactor;
          //merge
          @SuppressWarnings("unchecked")
          RawKeyValueIterator kvIter = Merger.merge(job, rfs,
                         keyClass, valClass, codec,
                         segmentList, mergeFactor,
                         new Path(mapId.toString()),
                         job.getOutputKeyComparator(), reporter, sortSegments,
                         null, spilledRecordsCounter, sortPhase.phase(),
                         TaskType.MAP);

          //write merged output to disk
          long segmentStart = finalOut.getPos();
          FSDataOutputStream finalPartitionOut = CryptoUtils.wrapIfNecessary(job, finalOut);
          Writer<K, V> writer =
              new Writer<K, V>(job, finalPartitionOut, keyClass, valClass, codec,
                               spilledRecordsCounter);
          if (combinerRunner == null || numSpills < minSpillsForCombine) {
            Merger.writeFile(kvIter, writer, reporter, job);
          } else {
            combineCollector.setWriter(writer);
            combinerRunner.combine(kvIter, combineCollector);
          }

          //close
          writer.close();

          sortPhase.startNextPhase();
          
          // record offsets
          rec.startOffset = segmentStart;
          rec.rawLength = writer.getRawLength() + CryptoUtils.cryptoPadding(job);
          rec.partLength = writer.getCompressedLength() + CryptoUtils.cryptoPadding(job);
          spillRec.putIndex(rec, parts);
        }
        spillRec.writeToFile(finalIndexFile, job);
        finalOut.close();
        for(int i = 0; i < numSpills; i++) {
          rfs.delete(filename[i],true);
        }
      }
    }
    
    ```