【Hadoop篇】YARN源码分析（三）

0、回顾【Hadoop篇】YARN源码分析（二）

NodeManager启动了YarnChild

1、YarnChild分析

1.YarnChild执行提交的MapTask或ReduceTask
2.TaskUmbilicalProtocol将MapTask和ReduceTask处理结果反馈给MRAppMaster

class YarnChild {
    public static void main(String[] args) throws Throwable {
        final JobConf job = new JobConf(MRJobConfig.JOB_CONF_FILE);
        configureTask(job, task, credentials, jt);
        
        //TaskUmbilicalProtocol协议启动
        final InetSocketAddress address = NetUtils.createSocketAddrForHost(host, port);
        final TaskUmbilicalProtocol umbilical = taskOwner.doAs(new PrivilegedExceptionAction<TaskUmbilicalProtocol>() {
            @Override
           public TaskUmbilicalProtocol run() throws Exception {
              return (TaskUmbilicalProtocol)RPC.getProxy(TaskUmbilicalProtocol.class, TaskUmbilicalProtocol.versionID, address, job);
           }
       });
        
        //获取需要执行的任务
        Task task = null;
        myTask = umbilical.getTask(context);
        task = myTask.getTask();
        YarnChild.taskid = task.getTaskID();
        configureTask(job, task, credentials, jt);
        
        //执行任务
        MRApps.setJobClassLoader(job);
        taskFinal.run(job, umbilical);
    }
}

public class MapTask extends Task {
    public void run(final JobConf job, final TaskUmbilicalProtocol umbilical) throws IOException, ClassNotFoundException, InterruptedException {
        TaskReporter reporter = startReporter(umbilical);
        initialize(job, getJobID(), reporter, useNewApi);
        runNewMapper(job, splitMetaInfo, umbilical, reporter);
        done(umbilical, reporter);
    }
    
    private <INKEY,INVALUE,OUTKEY,OUTVALUE> void runNewMapper(final JobConf job, final TaskSplitIndex splitIndex, final TaskUmbilicalProtocol umbilical, TaskReporter reporter ) {
       TaskAttemptContext taskContext = new 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
       split = getSplitDetails(new Path(splitIndex.getSplitLocation()), splitIndex.getStartOffset());
       org.apache.hadoop.mapreduce.RecordReader<INKEY,INVALUE> input = new NewTrackingRecordReader<INKEY,INVALUE>(split, inputFormat, reporter, taskContext);
       
       org.apache.hadoop.mapreduce.RecordWriter output = null;
       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);
       
       input.initialize(split, mapperContext);
       mapper.run(mapperContext);
       ->setup(context);
       ->while (context.nextKeyValue()) {  --context和MapContextImpl有关系
         ->map(context.getCurrentKey(), context.getCurrentValue(), context);
           ->业务处理...
           ->context.write(new Text(word), new IntWritable(1));   --业务代码
       mapPhase.complete();
       statusUpdate(umbilical);
       input.close();
       output.close(mapperContext);
       closeQuietly(input);
   }
   
   public void done(TaskUmbilicalProtocol umbilical, TaskReporter reporter) throws IOException, InterruptedException {
       sendDone(umbilical);
       ->umbilical.done(getTaskID());   --umbilical是TaskUmbilicalProtocol
   }
}