Hadoop中Job的源代码和过程分析以及实现了什么功能？

这个Job定义的就是我们的MapReduce任务了，在hadoop中每个任务都要定义一个Job，在Job中设定任务的输入输出、任务名字和运行逻辑等东西，DISTCP工具的Job在createAndSubmitJob()方法中的job = createJob()实现。实现源码如下：





 
private Job createJob() throws IOException {

    String    jobName = "distcp";

    String    userChosenName = getConf().get(JobContext.JOB_NAME);

    if    (userChosenName != null)

      jobName    += ": " + userChosenName;

    Job    job = Job.getInstance(getConf());

       job.setJobName(jobName);

       job.setInputFormatClass(DistCpUtils.getStrategy(getConf(),    inputOptions)); 

       job.setJarByClass(CopyMapper.class);

       configureOutputFormat(job);                                                    

 

       job.setMapperClass(CopyMapper.class);

       job.setNumReduceTasks(0);

       job.setMapOutputKeyClass(Text.class);

       job.setMapOutputValueClass(Text.class);

       job.setOutputFormatClass(CopyOutputFormat.class);                             

       job.getConfiguration().set(JobContext.MAP_SPECULATIVE,    "false");              

       job.getConfiguration().set(JobContext.NUM_MAPS,   

                     String.valueOf(inputOptions.getMaxMaps()));                      

 

    if    (inputOptions.getSslConfigurationFile() != null) {

         setupSSLConfig(job);

    }

 

       inputOptions.appendToConf(job.getConfiguration());

    return    job;

}