MapReduce原理（1）：Job从创建到提交到集群获取所需资源进行运行的过程 源码解析 + 图解

1、Job的创建

Job类中重载了3个getInstance(),这个方法是唯一暴露给外部的方法

Configuration conf = new Configuration();
conf.set("fs.defaultFS", "hdfs://192.168.116.117:8020/");
Job job = Job.getInstance(conf,"wordCount");

Job中getInstance()部分的源码

public class Job extends JobContextImpl implements JobContext {
    
	//无参的实例，实际会调用一个默认的配置文件
  public static Job getInstance() throws IOException {
   
    // create with a null Cluster
    return getInstance(new Configuration());
  }
   //传入一个配置文件
  public static Job getInstance(Configuration conf) throws IOException {
   
    // create with a null Cluster
    JobConf jobConf = new JobConf(conf);
    return new Job(jobConf);
  }
	//传入配置文件，jobName是job的名字，默认是jar包的名字
  public static Job getInstance(Configuration conf, String jobName)
           throws IOException {
   
    // create with a null Cluster
    Job result = getInstance(conf);
    result.setJobName(jobName);
    return result;
  }
	//没有特定的culster
  @Deprecated
  public static Job getInstance(Cluster ignored) throws IOException {
   
    return getInstance();
  }
  	//没有特定的culster,只有在需要时才会从conf参数创建群集
  @Deprecated
  public static Job getInstance(Cluster ignored, Configuration conf) 
      throws IOException {
   
    return getInstance(conf);
  }
  
 	//传入集群对象和job状态
  @Private
  public static Job getInstance(Cluster cluster, JobStatus status, 
      Configuration conf) throws IOException {
   
    Job job = getInstance(status, conf);
    job.setCluster(cluster);
    return job;
  }
  ...
  }

2、作业的提交

job.waitForCompletion(true)

waitForCompletion()源码

  /**
  * Submit the job to the cluster and wait for it to finish.
  * @param verbose print the progress to the user
  * @return true if the job succeeded
  * @throws IOException thrown if the communication with the 
  *         <code>JobTracker</code> is lost
  */
 public boolean waitForCompletion(boolean verbose
                                  ) throws IOException<