hadoop maptask

hadoop MapTask

1.通过Job的inputFormmat获得对应InputFormat然后获得RecordReader

2.numReduceTasks从前面conf计算的得到，numReduceTasks>0就有n个partition来做shuffle，说明partition的个数是由reduceNum决定的。numReduceTasks为0，则明显是map直接输出的任务。 

 

 private <INKEY,INVALUE,OUTKEY,OUTVALUE>
  void runOldMapper(final JobConf job,
                    final TaskSplitIndex splitIndex,
                    final TaskUmbilicalProtocol umbilical,
                    TaskReporter reporter
                    ) throws IOException, InterruptedException,
                             ClassNotFoundException {
    InputSplit inputSplit = getSplitDetails(new Path(splitIndex.getSplitLocation()),
           splitIndex.getStartOffset());

    updateJobWithSplit(job, inputSplit);
    reporter.setInputSplit(inputSplit);

    RecordReader<INKEY,INVALUE> rawIn =                  // open input
      job.getInputFormat().getRecordReader(inputSplit, job, reporter);
    RecordReader<INKEY,INVALUE> in = isSkipping() ? 
        new SkippingRecordReader<INKEY,INVALUE>(rawIn, umbilical, reporter) :
        new TrackedRecordReader<INKEY,INVALUE>(rawIn, reporter);
    job.setBoolean("mapred.skip.on", isSkipping());


    int numReduceTasks = conf.getNumReduceTasks();
    LOG.info("numReduceTasks: " + numReduceTasks);
    MapOutputCollector collector = null;
    if (numReduceTasks > 0) {
      collector = new MapOutputBuffer(umbilical, job, reporter);
    } else { 
      collector = new DirectMapOutputCollector(umbilical, job, reporter);
    }
    MapRunnable<INKEY,INVALUE,OUTKEY,OUTVALUE> runner =
      ReflectionUtils.newInstance(job.getMapRunnerClass(), job);

    try {
      runner.run(in, new OldOutputCollector(collector, conf), reporter);
      collector.flush();
    } finally {
      //close
      in.close();                               // close input
      collector.close();
    }
  }

 

Q.前面方法调用getSplitDetail是为了获得InputSplit，这里有点看不懂

private <T> T getSplitDetails(Path file, long offset)
   throws IOException {
    FileSystem fs = file.getFileSystem(conf);
    FSDataInputStream inFile = fs.open(file);
    inFile.seek(offset);
    String className = Text.readString(inFile);
    Class<T> cls;
    try {
      cls = (Class<T>) conf.getClassByName(className);
    } catch (ClassNotFoundException ce) {
      IOException wrap = new IOException("Split class " + className +
                                          " not found");
      wrap.initCause(ce);
      throw wrap;
    }
    SerializationFactory factory = new SerializationFactory(conf);
    Deserializer<T> deserializer = (Deserializer<T>) factory.getDeserializer(cls);
    deserializer.open(inFile);
    T split = deserializer.deserialize(null);
    long pos = inFile.getPos();
    getCounters().findCounter(Task.Counter.SPLIT_RAW_BYTES).increment(pos - offset);
    inFile.close();
    return split;
  }

 

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

    // start thread that will handle communication with parent
    TaskReporter reporter = new TaskReporter(getProgress(), umbilical,
        jvmContext);
    reporter.startCommunicationThread();
    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;
    }

    if (useNewApi) {
      runNewMapper(job, splitMetaInfo, umbilical, reporter);
    } else {
      runOldMapper(job, splitMetaInfo, umbilical, reporter);
    }
    done(umbilical, reporter);
  }

 

新api下的runMapper，将各种自定义的class信息都保存到conf里了，用动态代理的方式new mapper出来。

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.TaskAttemptContext(job, getTaskID());
    // 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());

    org.apache.hadoop.mapreduce.RecordReader<INKEY,INVALUE> input =
      new NewTrackingRecordReader<INKEY,INVALUE>
          (inputFormat.createRecordReader(split, taskContext), reporter);
    
    job.setBoolean("mapred.skip.on", isSkipping());
    org.apache.hadoop.mapreduce.RecordWriter output = null;
    org.apache.hadoop.mapreduce.Mapper<INKEY,INVALUE,OUTKEY,OUTVALUE>.Context 
         mapperContext = null;
    try {
      Constructor<org.apache.hadoop.mapreduce.Mapper.Context> contextConstructor =
        org.apache.hadoop.mapreduce.Mapper.Context.class.getConstructor
        (new Class[]{org.apache.hadoop.mapreduce.Mapper.class,
                     Configuration.class,
                     org.apache.hadoop.mapreduce.TaskAttemptID.class,
                     org.apache.hadoop.mapreduce.RecordReader.class,
                     org.apache.hadoop.mapreduce.RecordWriter.class,
                     org.apache.hadoop.mapreduce.OutputCommitter.class,
                     org.apache.hadoop.mapreduce.StatusReporter.class,
                     org.apache.hadoop.mapreduce.InputSplit.class});

      // get an output object
      if (job.getNumReduceTasks() == 0) {
         output =
           new NewDirectOutputCollector(taskContext, job, umbilical, reporter);
      } else {
        output = new NewOutputCollector(taskContext, job, umbilical, reporter);
      }

      mapperContext = contextConstructor.newInstance(mapper, job, getTaskID(),
                                                     input, output, committer,
                                                     reporter, split);

      input.initialize(split, mapperContext);
      mapper.run(mapperContext);
      input.close();
      output.close(mapperContext);
    } catch (NoSuchMethodException e) {
      throw new IOException("Can't find Context constructor", e);
    } catch (InstantiationException e) {
      throw new IOException("Can't create Context", e);
    } catch (InvocationTargetException e) {
      throw new IOException("Can't invoke Context constructor", e);
    } catch (IllegalAccessException e) {
      throw new IOException("Can't invoke Context constructor", e);
    }
  }