ReduceTask工作机制源码解析

1.  在LocalJobRunner$Job中的run()方法中
    try {
          if (numReduceTasks > 0) {
        //根据reduceTask的个数，创建对应个数的LocalJobRunner$Job$ReduceTaskRunnable
            List<RunnableWithThrowable> reduceRunnables = getReduceTaskRunnables(
                jobId, mapOutputFiles);
       // 线程池
            ExecutorService reduceService = createReduceExecutor();
        //将 ReduceTaskRunnable提交给线程池执行
            runTasks(reduceRunnables, reduceService, "reduce");
          }
    
     1) . 执行    LocalJobRunner$Job$ReduceTaskRunnable 中的run方法
        
    (1) . ReduceTask reduce = new ReduceTask(systemJobFile.toString(),
              reduceId, taskId, mapIds.size(), 1);
          //创建ReduceTask对象
        (2) . reduce.run(localConf, Job.this); // 执行ReduceTask的run方法
          <1> . runNewReducer(job, umbilical, reporter, rIter, comparator,
                    keyClass, valueClass);
            [1] . org.apache.hadoop.mapreduce.TaskAttemptContext taskContext = TaskAttemptContextImpl
            [2] . org.apache.hadoop.mapreduce.Reducer<INKEY,INVALUE,OUTKEY,OUTVALUE> reducer = WordCountReducer
            [3] . org.apache.hadoop.mapreduce.RecordWriter<OUTKEY,OUTVALUE> trackedRW = ReduceTask$NewTrackingRecordWriter
            [4] . reducer.run(reducerContext);
                  //执行WordCountReducer的run方法 ，实际执行的是WordCountReducer继承的Reducer类中的run方法.
              {1} .reduce(context.getCurrentKey(), context.getValues(), context);
                   //执行到WordCountReducer中的 reduce方法.
                          {2} . context.write(k,v) 将处理完的kv写出.
                >>1 . reduceContext.write(key, value);
                >>2 . output.write(key, value);
                >>3 . real.write(key,value);  // 通过RecordWriter将kv写出
                >>4 . out.write(NEWLINE);  //通过输出流将数据写到结果文件中