1.hadoop map源码在maptask.class文件中

 @Override
  public void run(final JobConf job, final TaskUmbilicalProtocol umbilical)
    throws IOException, ClassNotFoundException, InterruptedException {
    this.umbilical = umbilical;

    if (isMapTask()) {
      // If there are no reducers then there won't be any sort. Hence the map 
      // phase will govern the entire attempt's progress.
      //如果没有reduce,则只进行map,否则在map后进行排序以提高reduce效率
      if (conf.getNumReduceTasks() == 0) {
        mapPhase = getProgress().addPhase("map", 1.0f);
      } else {
        // If there are reducers then the entire attempt's progress will be 
        // split between the map phase (67%) and the sort phase (33%).
        mapPhase = getProgress().addPhase("map", 0.667f);
        sortPhase  = getProgress().addPhase("sort", 0.333f);
      }
    }
    TaskReporter reporter = startReporter(umbilical);
 
    boolean useNewApi = job.getUseNewMapper();
    initialize(job, getJobID(), reporter, useNewApi);

    // check if it is a cleanupJobTask
    if (jobCleanup) {
      runJobCleanupTask(umbilical, reporter);
      return;
    }
    if (jobSetup) {
      runJobSetupTask(umbilical, reporter);
      return;
    }
    if (taskCleanup) {
      runTaskCleanupTask(umbilical, reporter);
      return;
    }
    //跟进
    if (useNewApi) {
      runNewMapper(job, splitMetaInfo, umbilical, reporter);
    } else {
      runOldMapper(job, splitMetaInfo, umbilical, reporter);
    }
    done(umbilical, reporter);
  }

2.跟进runNewMapper

通过反射获取用户定义的map和input类

    // 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);

将input赋值为 NewTrackingRecordReader类

   org.apache.hadoop.mapreduce.RecordReader<INKEY,INVALUE> input =
      new NewTrackingRecordReader<INKEY,INVALUE>
        (split, inputFormat, reporter, taskContext);

    NewTrackingRecordReader(org.apache.hadoop.mapreduce.InputSplit split,
        org.apache.hadoop.mapreduce.InputFormat<K, V> inputFormat,
        TaskReporter reporter,
        org.apache.hadoop.mapreduce.TaskAttemptContext taskContext)
        throws InterruptedException, IOException {
      //real赋值为LineRecordReaer,inputFormat调用的方法来自父类TextInputFormat
      this.real = inputFormat.createRecordReader(split, taskContext);
    }

  @Override
  public RecordReader<LongWritable, Text> 
    createRecordReader(InputSplit split,
                       TaskAttemptContext context) {
    String delimiter = context.getConfiguration().get(
        "textinputformat.record.delimiter");
    byte[] recordDelimiterBytes = null;
    if (null != delimiter)
      recordDelimiterBytes = delimiter.getBytes(Charsets.UTF_8);
    return new LineRecordReader(recordDelimiterBytes);
  }

继续回到MapTask类runNewMapper方法

    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);

mapperContext返回mapContext类，而mapContext类为MapContextImpl实现。

//将input赋值给reader
  public MapContextImpl(Configuration conf, TaskAttemptID taskid,
                        RecordReader<KEYIN,VALUEIN> reader,
                        RecordWriter<KEYOUT,VALUEOUT> writer,
                        OutputCommitter committer,
                        StatusReporter reporter,
                        InputSplit split) {
    super(conf, taskid, writer, committer, reporter);
    this.reader = reader;
    this.split = split;
  }
//mapContext的getCurrentValue和nextKeyValue()是由reader来实现
//所以调用的是LineRecordReader类的方法
  @Override
  public VALUEIN getCurrentValue() throws IOException, InterruptedException {
    return reader.getCurrentValue();
  }

  @Override
  public boolean nextKeyValue() throws IOException, InterruptedException {
    return reader.nextKeyValue();
  }

3.hadoop map 输入主要逻辑

继续回到runNewMapper方法中

    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;
    } 

首先对input进行初始化，初始化方法如下:

  public void initialize(InputSplit genericSplit,
                         TaskAttemptContext context) throws IOException {
    FileSplit split = (FileSplit) genericSplit;
    Configuration job = context.getConfiguration();
    this.maxLineLength = job.getInt(MAX_LINE_LENGTH, Integer.MAX_VALUE);
    start = split.getStart();
    end = start + split.getLength();
    final Path file = split.getPath();

    // open the file and seek to the start of the split
    final FileSystem fs = file.getFileSystem(job);
    fileIn = fs.open(file);
    
    CompressionCodec codec = new CompressionCodecFactory(job).getCodec(file);
    if (null!=codec) {
      isCompressedInput = true;
      decompressor = CodecPool.getDecompressor(codec);
//如果是压缩文件，不能分割
      if (codec instanceof SplittableCompressionCodec) {
        final SplitCompressionInputStream cIn =
          ((SplittableCompressionCodec)codec).createInputStream(
            fileIn, decompressor, start, end,
            SplittableCompressionCodec.READ_MODE.BYBLOCK);
        in = new CompressedSplitLineReader(cIn, job,
            this.recordDelimiterBytes);
        start = cIn.getAdjustedStart();
        end = cIn.getAdjustedEnd();
        filePosition = cIn;
      } else {
        if (start != 0) {
          // So we have a split that is only part of a file stored using
          // a Compression codec that cannot be split.
          throw new IOException("Cannot seek in " +
              codec.getClass().getSimpleName() + " compressed stream");
        }

        in = new SplitLineReader(codec.createInputStream(fileIn,
            decompressor), job, this.recordDelimiterBytes);
        filePosition = fileIn;
      }
    } else {
//否则，文件寻址到块的开始位置
      fileIn.seek(start);
      in = new UncompressedSplitLineReader(
          fileIn, job, this.recordDelimiterBytes, split.getLength());
      filePosition = fileIn;
    }
    // If this is not the first split, we always throw away first record
    // because we always (except the last split) read one extra line in
    // next() method.
//如果不是文件开始，则第一行留给上一个split读，保证读取到的是完整的一行
    if (start != 0) {
      start += in.readLine(new Text(), 0, maxBytesToConsume(start));
    }
//设置pos
    this.pos = start;
  }

其次执行mapper.run(mapperContext)方法，即执行

  public void run(Context context) throws IOException, InterruptedException {
    setup(context);
    try {
//上面说过，执行的是linerecordreader的方法
      while (context.nextKeyValue()) {
        map(context.getCurrentKey(), context.getCurrentValue(), context);
      }
    } finally {
      cleanup(context);
    }
  }

看看linerecordreader类的nextKeyValue方法

  public boolean nextKeyValue() throws IOException {
//输入key默认为longwritable类型
    if (key == null) {
      key = new LongWritable();
    }
//设置key为pos位置，即当前读取文件中的位置
    key.set(pos);
    if (value == null) {
      value = new Text();
    }
    int newSize = 0;
//额外读取一行
    // We always read one extra line, which lies outside the upper
    // split limit i.e. (end - 1)
    while (getFilePosition() <= end || in.needAdditionalRecordAfterSplit()) {
      if (pos == 0) {
        newSize = skipUtfByteOrderMark();
      } else {
        newSize = in.readLine(value, maxLineLength, maxBytesToConsume(pos));
        pos += newSize;
      }

      if ((newSize == 0) || (newSize < maxLineLength)) {
        break;
      }

      // line too long. try again
      LOG.info("Skipped line of size " + newSize + " at pos " + 
               (pos - newSize));
    }
    if (newSize == 0) {
      key = null;
      value = null;
      return false;
    } else {
      return true;
    }
  }

4. hadoop map 输出主要逻辑

    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 {
//跟进
      output = new NewOutputCollector(taskContext, job, umbilical, reporter);
    }

    NewOutputCollector(org.apache.hadoop.mapreduce.JobContext jobContext,
                       JobConf job,
                       TaskUmbilicalProtocol umbilical,
                       TaskReporter reporter
                       ) throws IOException, ClassNotFoundException {
      collector = createSortingCollector(job, reporter);
      partitions = jobContext.getNumReduceTasks();
//如果reduce数为1，则分区函数直接返回0，否则返回getPartitionerClass
      if (partitions > 1) {
        partitioner = (org.apache.hadoop.mapreduce.Partitioner<K,V>)
          ReflectionUtils.newInstance(jobContext.getPartitionerClass(), job);
      } else {
        partitioner = new org.apache.hadoop.mapreduce.Partitioner<K,V>() {
          @Override
          public int getPartition(K key, V value, int numPartitions) {
            return partitions - 1;
          }
        };
      }
    }

跟进getPartitionerClass,如果用户未定义，返回HashPartitioner.class，否则返回用户定义的类

  public Class<? extends Partitioner<?,?>> getPartitionerClass() 
     throws ClassNotFoundException {
    return (Class<? extends Partitioner<?,?>>) 
      conf.getClass(PARTITIONER_CLASS_ATTR, HashPartitioner.class);
  }

跟进HashPartitioner.class

public class HashPartitioner<K, V> extends Partitioner<K, V> {

  /** Use {@link Object#hashCode()} to partition. */
//跟进key的hash值映射到reduce上
  public int getPartition(K key, V value,
                          int numReduceTasks) {
    return (key.hashCode() & Integer.MAX_VALUE) % numReduceTasks;
  }

}

当用户定义类调用write方法时候，会调用NewOutputCollector.class的write方法，
跟进看下write方法

    @Override
    public void write(K key, V value) throws IOException, InterruptedException {
      collector.collect(key, value,
                        partitioner.getPartition(key, value, partitions));
    }

可以看出，会将key,value和根据key得到的分区值，这三个参数来调用collector.collect方法。collector在上面定义过了，跟进collector。

collector = createSortingCollector(job, reporter);

  @SuppressWarnings("unchecked")
  private <KEY, VALUE> MapOutputCollector<KEY, VALUE>
          createSortingCollector(JobConf job, TaskReporter reporter)
    throws IOException, ClassNotFoundException {
    MapOutputCollector.Context context =
      new MapOutputCollector.Context(this, job, reporter);

    Class<?>[] collectorClasses = job.getClasses(
      JobContext.MAP_OUTPUT_COLLECTOR_CLASS_ATTR, MapOutputBuffer.class);
    int remainingCollectors = collectorClasses.length;
    Exception lastException = null;
    for (Class clazz : collectorClasses) {
      try {
        if (!MapOutputCollector.class.isAssignableFrom(clazz)) {
          throw new IOException("Invalid output collector class: " + clazz.getName() +
            " (does not implement MapOutputCollector)");
        }
        Class<? extends MapOutputCollector> subclazz =
          clazz.asSubclass(MapOutputCollector.class);
        LOG.debug("Trying map output collector class: " + subclazz.getName());
        MapOutputCollector<KEY, VALUE> collector =
          ReflectionUtils.newInstance(subclazz, job);
        collector.init(context);
        LOG.info("Map output collector class = " + collector.getClass().getName());
        return collector;
      } catch (Exception e) {
        String msg = "Unable to initialize MapOutputCollector " + clazz.getName();
        if (--remainingCollectors > 0) {
          msg += " (" + remainingCollectors + " more collector(s) to try)";
        }
        lastException = e;
        LOG.warn(msg, e);
      }
    }

    if (lastException != null) {
      throw new IOException("Initialization of all the collectors failed. " +
          "Error in last collector was:" + lastException.toString(),
          lastException);
    } else {
      throw new IOException("Initialization of all the collectors failed.");
    }
  }

return的collector默认为MapOutputBuffer.class，跟进MapOutputBuffer.class的init方法。

    @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
      //public static final int DEFAULT_IO_SORT_MB = 100;
      //所以map之后要输入到内存缓冲区中，内存缓冲区大小默认为100M,写硬盘阈值为0.8
      final float spillper =
        job.getFloat(JobContext.MAP_SORT_SPILL_PERCENT, (float)0.8);
      final int sortmb = job.getInt(MRJobConfig.IO_SORT_MB,
          MRJobConfig.DEFAULT_IO_SORT_MB);
      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(
                   MRJobConfig.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);
      }
    }

5.collector init方法主体部分

//内存缓冲区大小100M,写硬盘阈值为0.8

      //sanity checks
      final float spillper =
        job.getFloat(JobContext.MAP_SORT_SPILL_PERCENT, (float)0.8);
      final int sortmb = job.getInt(MRJobConfig.IO_SORT_MB,
          MRJobConfig.DEFAULT_IO_SORT_MB);

排序类如果用户指定则使用用户指定的，否则用快排

     sorter = ReflectionUtils.newInstance(job.getClass(
                   MRJobConfig.MAP_SORT_CLASS, QuickSort.class,
                   IndexedSorter.class), job);

排序会用到比较器，所以如果没定义比较器，则取key默认的比较器，否则取定义的比较器。

comparator = job.getOutputKeyComparator();
  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);
  }

如果用户设置了combiner,则在内存排序之后进行combiner，并且在本地文件多于默认值3个时候，再次进行combiner.

      // 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);

6.collector初始化后操作

collector初始化后，在用户自定义context.write（key,value）时调用write方法时，会执行

    @Override
    public void write(K key, V value) throws IOException, InterruptedException {
      collector.collect(key, value,
                        partitioner.getPartition(key, value, partitions));
    }

跟进collect方法

      try {
        // serialize key bytes into buffer
        int keystart = bufindex;
        keySerializer.serialize(key);
        if (bufindex < keystart) {
          // wrapped the key; must make contiguous
          bb.shiftBufferedKey();
          keystart = 0;
        }
        // serialize value bytes into buffer
        final int valstart = bufindex;
        valSerializer.serialize(value);
        // It's possible for records to have zero length, i.e. the serializer
        // will perform no writes. To ensure that the boundary conditions are
        // checked and that the kvindex invariant is maintained, perform a
        // zero-length write into the buffer. The logic monitoring this could be
        // moved into collect, but this is cleaner and inexpensive. For now, it
        // is acceptable.
        bb.write(b0, 0, 0);

        // the record must be marked after the preceding write, as the metadata
        // for this record are not yet written
        int valend = bb.markRecord();

        mapOutputRecordCounter.increment(1);
        mapOutputByteCounter.increment(
            distanceTo(keystart, valend, bufvoid));

        // write accounting info
        kvmeta.put(kvindex + 2, partition);
        kvmeta.put(kvindex + 1, keystart);
        kvmeta.put(kvindex, valstart);
        kvmeta.put(kvindex + 3, distanceTo(valstart, valend));
        // advance kvindex
        kvindex = (kvindex - 4 + kvmeta.capacity()) % kvmeta.capacity();
      }

    private static final int VALSTART = 0;         // val offset in acct
    private static final int KEYSTART = 1;         // key offset in acct
    private static final int PARTITION = 2;        // partition offset in acct
    private static final int VALLEN = 3;           // length of value
    private static final int NMETA = 4;            // num meta ints
    private static final int METASIZE = NMETA * 4; // size in bytes

具体细节待补充

7.output.close

最后结束后，会调用close方法，跟进

output.close(mapperContext);

    @Override
    public void close(TaskAttemptContext context
                      ) throws IOException,InterruptedException {
      try {
        collector.flush();
      } catch (ClassNotFoundException cnf) {
        throw new IOException("can't find class ", cnf);
      }
      collector.close();
    }

    public void flush() throws IOException, ClassNotFoundException,
           InterruptedException {
...
          sortAndSpill();
...     
}

          if (combinerRunner == null || numSpills < minSpillsForCombine) {
            Merger.writeFile(kvIter, writer, reporter, job);
          } else {
            combineCollector.setWriter(writer);
            combinerRunner.combine(kvIter, combineCollector);
          }

8.整体流程

map从不同切块逐行读取数据，<k,v>,根据k的hash值得到partition，然后将<k,v,p>传入output，在内存中排序combiner后写入本地文件，然后当本地文件大于阈值再次combiner.