hadoop2.7之Mapper/reducer源码分析

package org.apache.hadoop.examples;

import java.io.IOException;
import java.util.StringTokenizer;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.GenericOptionsParser;

public class WordCount {
    //继承泛型类Mapper
  public static class TokenizerMapper 
       extends Mapper<Object, Text, Text, IntWritable>{
    //定义hadoop数据类型IntWritable实例one，并且赋值为1
    private final static IntWritable one = new IntWritable(1);
    //定义hadoop数据类型Text实例word
    private Text word = new Text();
    //实现map函数    
    public void map(Object key, Text value, Context context
                    ) throws IOException, InterruptedException {
        //Java的字符串分解类，默认分隔符“空格”、“制表符(‘\t’)”、“换行符(‘\n’)”、“回车符(‘\r’)”
      StringTokenizer itr = new StringTokenizer(value.toString());
      //循环条件表示返回是否还有分隔符。
      while (itr.hasMoreTokens()) {
       /*
　　　　nextToken()：返回从当前位置到下一个分隔符的字符串
　　　　word.set()Java数据类型与hadoop数据类型转换
　　　　*/
        word.set(itr.nextToken());
        //hadoop全局类context输出函数write;
        context.write(word, one);
      }
    }
  }
  
  //继承泛型类Reducer
  public static class IntSumReducer 
       extends Reducer<Text,IntWritable,Text,IntWritable> {

    //实例化IntWritable
    private IntWritable result = new IntWritable();
    //实现reduce
    public void reduce(Text key, Iterable<IntWritable> values, 
                       Context context
                       ) throws IOException, InterruptedException {
      int sum = 0;
      //循环values，并记录单词个数
      for (IntWritable val : values) {
        sum += val.get();
      }
      //Java数据类型sum，转换为hadoop数据类型result
      result.set(sum);
      //输出结果到hdfs
      context.write(key, result);
    }
  }

  public static void main(String[] args) throws Exception {
    //实例化Configuration
    Configuration conf = new Configuration();
    /*
　　    GenericOptionsParser是hadoop框架中解析命令行参数的基本类。
　　    getRemainingArgs();返回数组【一组路径】
　　    */
    /*
　　    函数实现
　　    public String[] getRemainingArgs() {
        return (commandLine == null) ? new String[]{} : commandLine.getArgs();
　　    }*/
    String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
    //如果只有一个路径，则输出需要有输入路径和输出路径
    if (otherArgs.length < 2) {
      System.err.println("Usage: wordcount <in> [<in>...] <out>");
      System.exit(2);
    }
    //实例化job
    Job job = Job.getInstance(conf, "word count");
    job.setJarByClass(WordCount.class);
    job.setMapperClass(TokenizerMapper.class);
    /*
　　    指定CombinerClass类
　　    这里很多人对CombinerClass不理解
　　    */
    job.setCombinerClass(IntSumReducer.class);
    job.setReducerClass(IntSumReducer.class);
    //rduce输出Key的类型，是Text
    job.setOutputKeyClass(Text.class);
    // rduce输出Value的类型
    job.setOutputValueClass(IntWritable.class);
    //添加输入路径
    for (int i = 0; i < otherArgs.length - 1; ++i) {
      FileInputFormat.addInputPath(job, new Path(otherArgs[i]));
    }
    //添加输出路径
    FileOutputFormat.setOutputPath(job,
      new Path(otherArgs[otherArgs.length - 1]));
    //提交job
    System.exit(job.waitForCompletion(true) ? 0 : 1);
  }
}

     public class MyMapper<K extends WritableComparable, V extends Writable> 
      extends MapReduceBase implements Mapper<K, V, K, V> {
      
        static enum MyCounters { NUM_RECORDS }
        
        private String mapTaskId;
        private String inputFile;
        private int noRecords = 0;
        
        public void configure(JobConf job) {
          mapTaskId = job.get(JobContext.TASK_ATTEMPT_ID);
          inputFile = job.get(JobContext.MAP_INPUT_FILE);
        }
        
        public void map(K key, V val,
                        OutputCollector<K, V> output, Reporter reporter)
        throws IOException {
          // Process the <key, value> pair (assume this takes a while)
          // ...
          // ...
          
          // Let the framework know that we are alive, and kicking!
          // reporter.progress();
          
          // Process some more
          // ...
          // ...
          
          // Increment the no. of <key, value> pairs processed
          ++noRecords;
 
          // Increment counters
          reporter.incrCounter(NUM_RECORDS, 1);
         
          // Every 100 records update application-level status
          if ((noRecords%100) == 0) {
            reporter.setStatus(mapTaskId + " processed " + noRecords + 
                               " from input-file: " + inputFile); 
          }
          
          // Output the result
          output.collect(key, val);
        }
      }

 public class TokenCounterMapper 
     extends Mapper<Object, Text, Text, IntWritable>{
    
   private final static IntWritable one = new IntWritable(1);
   private Text word = new Text();
   
   public void map(Object key, Text value, Context context) throws IOException, InterruptedException {
     StringTokenizer itr = new StringTokenizer(value.toString());
     while (itr.hasMoreTokens()) {
       word.set(itr.nextToken());
       context.write(word, one);
     }
   }
 }

  void map(K1 key, V1 value, OutputCollector<K2, V2> output, Reporter reporter)
  throws IOException;

     public class MyReducer<K extends WritableComparable, V extends Writable> 
      extends MapReduceBase implements Reducer<K, V, K, V> {
      
        static enum MyCounters { NUM_RECORDS }
         
        private String reduceTaskId;
        private int noKeys = 0;
        
        public void configure(JobConf job) {
          reduceTaskId = job.get(JobContext.TASK_ATTEMPT_ID);
        }
        
        public void reduce(K key, Iterator<V> values,
                           OutputCollector<K, V> output, 
                           Reporter reporter)
        throws IOException {
        
          // Process
          int noValues = 0;
          while (values.hasNext()) {
            V value = values.next();
            
            // Increment the no. of values for this key
            ++noValues;
            
            // Process the <key, value> pair (assume this takes a while)
            // ...
            // ...
            
            // Let the framework know that we are alive, and kicking!
            if ((noValues%10) == 0) {
              reporter.progress();
            }
          
            // Process some more
            // ...
            // ...
            
            // Output the <key, value> 
            output.collect(key, value);
          }
          
          // Increment the no. of <key, list of values> pairs processed
          ++noKeys;
          
          // Increment counters
          reporter.incrCounter(NUM_RECORDS, 1);
          
          // Every 100 keys update application-level status
          if ((noKeys%100) == 0) {
            reporter.setStatus(reduceTaskId + " processed " + noKeys);
          }
        }
      }

 /**
   * 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, InterruptedException,
                                            ClassNotFoundException {
    if (state == JobState.DEFINE) {
      submit();
    }
    if (verbose) {
      monitorAndPrintJob();
    } else {
      // get the completion poll interval from the client.
      int completionPollIntervalMillis = 
        Job.getCompletionPollInterval(cluster.getConf());
      while (!isComplete()) {
        try {
          Thread.sleep(completionPollIntervalMillis);
        } catch (InterruptedException ie) {
        }
      }
    }
    return isSuccessful();
  }

/**
   * Submit the job to the cluster and return immediately.
   * @throws IOException
   */
  public void submit() 
         throws IOException, InterruptedException, ClassNotFoundException {
    ensureState(JobState.DEFINE);
    setUseNewAPI();
    connect();
    final JobSubmitter submitter = 
        getJobSubmitter(cluster.getFileSystem(), cluster.getClient());
    status = ugi.doAs(new PrivilegedExceptionAction<JobStatus>() {
      public JobStatus run() throws IOException, InterruptedException, 
      ClassNotFoundException {
        return submitter.submitJobInternal(Job.this, cluster);
      }
    });
    state = JobState.RUNNING;
    LOG.info("The url to track the job: " + getTrackingURL());
   }

  private synchronized void connect()
          throws IOException, InterruptedException, ClassNotFoundException {
    if (cluster == null) {
      cluster = 
        ugi.doAs(new PrivilegedExceptionAction<Cluster>() {
                   public Cluster run()
                          throws IOException, InterruptedException, 
                                 ClassNotFoundException {
                     return new Cluster(getConfiguration());
                   }
                 });
    }
  }

public static enum JobTrackerStatus {INITIALIZING, RUNNING};
  
  private ClientProtocolProvider clientProtocolProvider;
  private ClientProtocol client;
  private UserGroupInformation ugi;
  private Configuration conf;
  private FileSystem fs = null;
  private Path sysDir = null;
  private Path stagingAreaDir = null;
  private Path jobHistoryDir = null;

/**
   * Internal method for submitting jobs to the system.
   * 
   * <p>The job submission process involves:
   * <ol>
   *   <li>
   *   Checking the input and output specifications of the job.
   *   </li>
   *   <li>
   *   Computing the {@link InputSplit}s for the job.
   *   </li>
   *   <li>
   *   Setup the requisite accounting information for the 
   *   {@link DistributedCache} of the job, if necessary.
   *   </li>
   *   <li>
   *   Copying the job‘s jar and configuration to the map-reduce system
   *   directory on the distributed file-system. 
   *   </li>
   *   <li>
   *   Submitting the job to the <code>JobTracker</code> and optionally
   *   monitoring it‘s status.
   *   </li>
   * </ol></p>
   * @param job the configuration to submit
   * @param cluster the handle to the Cluster
   * @throws ClassNotFoundException
   * @throws InterruptedException
   * @throws IOException
   */
  JobStatus submitJobInternal(Job job, Cluster cluster) 
  throws ClassNotFoundException, InterruptedException, IOException {

    //validate the jobs output specs 
    checkSpecs(job);

    Configuration conf = job.getConfiguration();
    addMRFrameworkToDistributedCache(conf);

    Path jobStagingArea = JobSubmissionFiles.getStagingDir(cluster, conf);
    //configure the command line options correctly on the submitting dfs
    InetAddress ip = InetAddress.getLocalHost();
    if (ip != null) {
      submitHostAddress = ip.getHostAddress();
      submitHostName = ip.getHostName();
      conf.set(MRJobConfig.JOB_SUBMITHOST,submitHostName);
      conf.set(MRJobConfig.JOB_SUBMITHOSTADDR,submitHostAddress);
    }
    JobID jobId = submitClient.getNewJobID();
    job.setJobID(jobId);
    Path submitJobDir = new Path(jobStagingArea, jobId.toString());
    JobStatus status = null;
    try {
      conf.set(MRJobConfig.USER_NAME,
          UserGroupInformation.getCurrentUser().getShortUserName());
      conf.set("hadoop.http.filter.initializers", 
          "org.apache.hadoop.yarn.server.webproxy.amfilter.AmFilterInitializer");
      conf.set(MRJobConfig.MAPREDUCE_JOB_DIR, submitJobDir.toString());
      LOG.debug("Configuring job " + jobId + " with " + submitJobDir 
          + " as the submit dir");
      // get delegation token for the dir
      TokenCache.obtainTokensForNamenodes(job.getCredentials(),
          new Path[] { submitJobDir }, conf);
      
      populateTokenCache(conf, job.getCredentials());

      // generate a secret to authenticate shuffle transfers
      if (TokenCache.getShuffleSecretKey(job.getCredentials()) == null) {
        KeyGenerator keyGen;
        try {
         
          int keyLen = CryptoUtils.isShuffleEncrypted(conf) 
              ? conf.getInt(MRJobConfig.MR_ENCRYPTED_INTERMEDIATE_DATA_KEY_SIZE_BITS, 
                  MRJobConfig.DEFAULT_MR_ENCRYPTED_INTERMEDIATE_DATA_KEY_SIZE_BITS)
              : SHUFFLE_KEY_LENGTH;
          keyGen = KeyGenerator.getInstance(SHUFFLE_KEYGEN_ALGORITHM);
          keyGen.init(keyLen);
        } catch (NoSuchAlgorithmException e) {
          throw new IOException("Error generating shuffle secret key", e);
        }
        SecretKey shuffleKey = keyGen.generateKey();
        TokenCache.setShuffleSecretKey(shuffleKey.getEncoded(),
            job.getCredentials());
      }

      copyAndConfigureFiles(job, submitJobDir);

      Path submitJobFile = JobSubmissionFiles.getJobConfPath(submitJobDir);
      
      // Create the splits for the job
      LOG.debug("Creating splits at " + jtFs.makeQualified(submitJobDir));
      int maps = writeSplits(job, submitJobDir);
      conf.setInt(MRJobConfig.NUM_MAPS, maps);
      LOG.info("number of splits:" + maps);

      // write "queue admins of the queue to which job is being submitted"
      // to job file.
      String queue = conf.get(MRJobConfig.QUEUE_NAME,
          JobConf.DEFAULT_QUEUE_NAME);
      AccessControlList acl = submitClient.getQueueAdmins(queue);
      conf.set(toFullPropertyName(queue,
          QueueACL.ADMINISTER_JOBS.getAclName()), acl.getAclString());

      // removing jobtoken referrals before copying the jobconf to HDFS
      // as the tasks don‘t need this setting, actually they may break
      // because of it if present as the referral will point to a
      // different job.
      TokenCache.cleanUpTokenReferral(conf);

      if (conf.getBoolean(
          MRJobConfig.JOB_TOKEN_TRACKING_IDS_ENABLED,
          MRJobConfig.DEFAULT_JOB_TOKEN_TRACKING_IDS_ENABLED)) {
        // Add HDFS tracking ids
        ArrayList<String> trackingIds = new ArrayList<String>();
        for (Token<? extends TokenIdentifier> t :
            job.getCredentials().getAllTokens()) {
          trackingIds.add(t.decodeIdentifier().getTrackingId());
        }
        conf.setStrings(MRJobConfig.JOB_TOKEN_TRACKING_IDS,
            trackingIds.toArray(new String[trackingIds.size()]));
      }

      // Set reservation info if it exists
      ReservationId reservationId = job.getReservationId();
      if (reservationId != null) {
        conf.set(MRJobConfig.RESERVATION_ID, reservationId.toString());
      }

      // Write job file to submit dir
      writeConf(conf, submitJobFile);
      
      //
      // Now, actually submit the job (using the submit name)
      //
      printTokens(jobId, job.getCredentials());
      status = submitClient.submitJob(
          jobId, submitJobDir.toString(), job.getCredentials());
      if (status != null) {
        return status;
      } else {
        throw new IOException("Could not launch job");
      }
    } finally {
      if (status == null) {
        LOG.info("Cleaning up the staging area " + submitJobDir);
        if (jtFs != null && submitJobDir != null)
          jtFs.delete(submitJobDir, true);

      }
    }
  }

 @Override
  public JobStatus submitJob(JobID jobId, String jobSubmitDir, Credentials ts)
  throws IOException, InterruptedException {
    
    addHistoryToken(ts);
    
    // Construct necessary information to start the MR AM
    ApplicationSubmissionContext appContext =
      createApplicationSubmissionContext(conf, jobSubmitDir, ts);

    // Submit to ResourceManager
    try {
      ApplicationId applicationId =
          resMgrDelegate.submitApplication(appContext);

      ApplicationReport appMaster = resMgrDelegate
          .getApplicationReport(applicationId);
      String diagnostics =
          (appMaster == null ?
              "application report is null" : appMaster.getDiagnostics());
      if (appMaster == null
          || appMaster.getYarnApplicationState() == YarnApplicationState.FAILED
          || appMaster.getYarnApplicationState() == YarnApplicationState.KILLED) {
        throw new IOException("Failed to run job : " +
            diagnostics);
      }
      return clientCache.getClient(jobId).getJobStatus(jobId);
    } catch (YarnException e) {
      throw new IOException(e);
    }
  }

@Override
  public ApplicationId
      submitApplication(ApplicationSubmissionContext appContext)
          throws YarnException, IOException {
    ApplicationId applicationId = appContext.getApplicationId();
    if (applicationId == null) {
      throw new ApplicationIdNotProvidedException(
          "ApplicationId is not provided in ApplicationSubmissionContext");
    }
    SubmitApplicationRequest request =
        Records.newRecord(SubmitApplicationRequest.class);
    request.setApplicationSubmissionContext(appContext);

    // Automatically add the timeline DT into the CLC
    // Only when the security and the timeline service are both enabled
    if (isSecurityEnabled() && timelineServiceEnabled) {
      addTimelineDelegationToken(appContext.getAMContainerSpec());
    }

    //TODO: YARN-1763:Handle RM failovers during the submitApplication call.
    rmClient.submitApplication(request);

    int pollCount = 0;
    long startTime = System.currentTimeMillis();
    EnumSet<YarnApplicationState> waitingStates = 
                                 EnumSet.of(YarnApplicationState.NEW,
                                 YarnApplicationState.NEW_SAVING,
                                 YarnApplicationState.SUBMITTED);
    EnumSet<YarnApplicationState> failToSubmitStates = 
                                  EnumSet.of(YarnApplicationState.FAILED,
                                  YarnApplicationState.KILLED);        
    while (true) {
      try {
        ApplicationReport appReport = getApplicationReport(applicationId);
        YarnApplicationState state = appReport.getYarnApplicationState();
        if (!waitingStates.contains(state)) {
          if(failToSubmitStates.contains(state)) {
            throw new YarnException("Failed to submit " + applicationId + 
                " to YARN : " + appReport.getDiagnostics());
          }
          LOG.info("Submitted application " + applicationId);
          break;
        }

        long elapsedMillis = System.currentTimeMillis() - startTime;
        if (enforceAsyncAPITimeout() &&
            elapsedMillis >= asyncApiPollTimeoutMillis) {
          throw new YarnException("Timed out while waiting for application " +
              applicationId + " to be submitted successfully");
        }

        // Notify the client through the log every 10 poll, in case the client
        // is blocked here too long.
        if (++pollCount % 10 == 0) {
          LOG.info("Application submission is not finished, " +
              "submitted application " + applicationId +
              " is still in " + state);
        }
        try {
          Thread.sleep(submitPollIntervalMillis);
        } catch (InterruptedException ie) {
          LOG.error("Interrupted while waiting for application "
              + applicationId
              + " to be successfully submitted.");
        }
      } catch (ApplicationNotFoundException ex) {
        // FailOver or RM restart happens before RMStateStore saves
        // ApplicationState
        LOG.info("Re-submit application " + applicationId + "with the " +
            "same ApplicationSubmissionContext");
        rmClient.submitApplication(request);
      }
    }

    return applicationId;
  }

 @Override
  public SubmitApplicationResponse submitApplication(
      SubmitApplicationRequest request) throws YarnException {
    ApplicationSubmissionContext submissionContext = request
        .getApplicationSubmissionContext();
    ApplicationId applicationId = submissionContext.getApplicationId();

    // ApplicationSubmissionContext needs to be validated for safety - only
    // those fields that are independent of the RM‘s configuration will be
    // checked here, those that are dependent on RM configuration are validated
    // in RMAppManager.

    String user = null;
    try {
      // Safety
      user = UserGroupInformation.getCurrentUser().getShortUserName();
    } catch (IOException ie) {
      LOG.warn("Unable to get the current user.", ie);
      RMAuditLogger.logFailure(user, AuditConstants.SUBMIT_APP_REQUEST,
          ie.getMessage(), "ClientRMService",
          "Exception in submitting application", applicationId);
      throw RPCUtil.getRemoteException(ie);
    }

    // Check whether app has already been put into rmContext,
    // If it is, simply return the response
    if (rmContext.getRMApps().get(applicationId) != null) {
      LOG.info("This is an earlier submitted application: " + applicationId);
      return SubmitApplicationResponse.newInstance();
    }

    if (submissionContext.getQueue() == null) {
      submissionContext.setQueue(YarnConfiguration.DEFAULT_QUEUE_NAME);
    }
    if (submissionContext.getApplicationName() == null) {
      submissionContext.setApplicationName(
          YarnConfiguration.DEFAULT_APPLICATION_NAME);
    }
    if (submissionContext.getApplicationType() == null) {
      submissionContext
        .setApplicationType(YarnConfiguration.DEFAULT_APPLICATION_TYPE);
    } else {
      if (submissionContext.getApplicationType().length() > YarnConfiguration.APPLICATION_TYPE_LENGTH) {
        submissionContext.setApplicationType(submissionContext
          .getApplicationType().substring(0,
            YarnConfiguration.APPLICATION_TYPE_LENGTH));
      }
    }

    try {
      // call RMAppManager to submit application directly
      rmAppManager.submitApplication(submissionContext,
          System.currentTimeMillis(), user);

      LOG.info("Application with id " + applicationId.getId() + 
          " submitted by user " + user);
      RMAuditLogger.logSuccess(user, AuditConstants.SUBMIT_APP_REQUEST,
          "ClientRMService", applicationId);
    } catch (YarnException e) {
      LOG.info("Exception in submitting application with id " +
          applicationId.getId(), e);
      RMAuditLogger.logFailure(user, AuditConstants.SUBMIT_APP_REQUEST,
          e.getMessage(), "ClientRMService",
          "Exception in submitting application", applicationId);
      throw e;
    }

    SubmitApplicationResponse response = recordFactory
        .newRecordInstance(SubmitApplicationResponse.class);
    return response;
  }

 @SuppressWarnings("unchecked")
  protected void submitApplication(
      ApplicationSubmissionContext submissionContext, long submitTime,
      String user) throws YarnException {
    ApplicationId applicationId = submissionContext.getApplicationId();

    RMAppImpl application =
        createAndPopulateNewRMApp(submissionContext, submitTime, user);
    ApplicationId appId = submissionContext.getApplicationId();

    if (UserGroupInformation.isSecurityEnabled()) {
      try {
        this.rmContext.getDelegationTokenRenewer().addApplicationAsync(appId,
            parseCredentials(submissionContext),
            submissionContext.getCancelTokensWhenComplete(),
            application.getUser());
      } catch (Exception e) {
        LOG.warn("Unable to parse credentials.", e);
        // Sending APP_REJECTED is fine, since we assume that the
        // RMApp is in NEW state and thus we haven‘t yet informed the
        // scheduler about the existence of the application
        assert application.getState() == RMAppState.NEW;
        this.rmContext.getDispatcher().getEventHandler()
          .handle(new RMAppRejectedEvent(applicationId, e.getMessage()));
        throw RPCUtil.getRemoteException(e);
      }
    } else {
      // Dispatcher is not yet started at this time, so these START events
      // enqueued should be guaranteed to be first processed when dispatcher
      // gets started.
      this.rmContext.getDispatcher().getEventHandler()
        .handle(new RMAppEvent(applicationId, RMAppEventType.START));
    }
  }

 @SuppressWarnings("unchecked")
  protected void submitApplication(
      ApplicationSubmissionContext submissionContext, long submitTime,
      String user) throws YarnException {
    ApplicationId applicationId = submissionContext.getApplicationId();

    RMAppImpl application =
        createAndPopulateNewRMApp(submissionContext, submitTime, user);
    ApplicationId appId = submissionContext.getApplicationId();

    if (UserGroupInformation.isSecurityEnabled()) {
      try {
        this.rmContext.getDelegationTokenRenewer().addApplicationAsync(appId,
            parseCredentials(submissionContext),
            submissionContext.getCancelTokensWhenComplete(),
            application.getUser());
      } catch (Exception e) {
        LOG.warn("Unable to parse credentials.", e);
        // Sending APP_REJECTED is fine, since we assume that the
        // RMApp is in NEW state and thus we haven‘t yet informed the
        // scheduler about the existence of the application
        assert application.getState() == RMAppState.NEW;
        this.rmContext.getDispatcher().getEventHandler()
          .handle(new RMAppRejectedEvent(applicationId, e.getMessage()));
        throw RPCUtil.getRemoteException(e);
      }
    } else {
      // Dispatcher is not yet started at this time, so these START events
      // enqueued should be guaranteed to be first processed when dispatcher
      // gets started.
      this.rmContext.getDispatcher().getEventHandler()
        .handle(new RMAppEvent(applicationId, RMAppEventType.START));
    }
  }

  /**
   * Asynchronously add application tokens for renewal.
   * @param applicationId added application
   * @param ts tokens
   * @param shouldCancelAtEnd true if tokens should be canceled when the app is
   * done else false. 
   * @param user user
   */
  public void addApplicationAsync(ApplicationId applicationId, Credentials ts,
      boolean shouldCancelAtEnd, String user) {
    processDelegationTokenRenewerEvent(new DelegationTokenRenewerAppSubmitEvent(
      applicationId, ts, shouldCancelAtEnd, user));
  }

  private void processDelegationTokenRenewerEvent(
      DelegationTokenRenewerEvent evt) {
    serviceStateLock.readLock().lock();
    try {
      if (isServiceStarted) {
        renewerService.execute(new DelegationTokenRenewerRunnable(evt));
      } else {
        pendingEventQueue.add(evt);
      }
    } finally {
      serviceStateLock.readLock().unlock();
    }
  }

 @Override
    public void run() {
      if (evt instanceof DelegationTokenRenewerAppSubmitEvent) {
        DelegationTokenRenewerAppSubmitEvent appSubmitEvt =
            (DelegationTokenRenewerAppSubmitEvent) evt;
        handleDTRenewerAppSubmitEvent(appSubmitEvt);
      } else if (evt.getType().equals(
          DelegationTokenRenewerEventType.FINISH_APPLICATION)) {
        DelegationTokenRenewer.this.handleAppFinishEvent(evt);
      }
    }

 @SuppressWarnings("unchecked")
    private void handleDTRenewerAppSubmitEvent(
        DelegationTokenRenewerAppSubmitEvent event) {
      /*
       * For applications submitted with delegation tokens we are not submitting
       * the application to scheduler from RMAppManager. Instead we are doing
       * it from here. The primary goal is to make token renewal as a part of
       * application submission asynchronous so that client thread is not
       * blocked during app submission.
       */
      try {
        // Setup tokens for renewal
        DelegationTokenRenewer.this.handleAppSubmitEvent(event);
        rmContext.getDispatcher().getEventHandler()
            .handle(new RMAppEvent(event.getApplicationId(), RMAppEventType.START));
      } catch (Throwable t) {
        LOG.warn(
            "Unable to add the application to the delegation token renewer.",
            t);
        // Sending APP_REJECTED is fine, since we assume that the
        // RMApp is in NEW state and thus we havne‘t yet informed the
        // Scheduler about the existence of the application
        rmContext.getDispatcher().getEventHandler().handle(
            new RMAppRejectedEvent(event.getApplicationId(), t.getMessage()));
      }
    }
  }

private void handleAppSubmitEvent(DelegationTokenRenewerAppSubmitEvent evt)
      throws IOException, InterruptedException {
    ApplicationId applicationId = evt.getApplicationId();
    Credentials ts = evt.getCredentials();
    boolean shouldCancelAtEnd = evt.shouldCancelAtEnd();
    if (ts == null) {
      return; // nothing to add
    }

    if (LOG.isDebugEnabled()) {
      LOG.debug("Registering tokens for renewal for:" +
          " appId = " + applicationId);
    }

    Collection<Token<?>> tokens = ts.getAllTokens();
    long now = System.currentTimeMillis();

    // find tokens for renewal, but don‘t add timers until we know
    // all renewable tokens are valid
    // At RM restart it is safe to assume that all the previously added tokens
    // are valid
    appTokens.put(applicationId,
      Collections.synchronizedSet(new HashSet<DelegationTokenToRenew>()));
    Set<DelegationTokenToRenew> tokenList = new HashSet<DelegationTokenToRenew>();
    boolean hasHdfsToken = false;
    for (Token<?> token : tokens) {
      if (token.isManaged()) {
        if (token.getKind().equals(new Text("HDFS_DELEGATION_TOKEN"))) {
          LOG.info(applicationId + " found existing hdfs token " + token);
          hasHdfsToken = true;
        }

        DelegationTokenToRenew dttr = allTokens.get(token);
        if (dttr == null) {
          dttr = new DelegationTokenToRenew(Arrays.asList(applicationId), token,
              getConfig(), now, shouldCancelAtEnd, evt.getUser());
          try {
            renewToken(dttr);
          } catch (IOException ioe) {
            throw new IOException("Failed to renew token: " + dttr.token, ioe);
          }
        }
        tokenList.add(dttr);
      }
    }

    if (!tokenList.isEmpty()) {
      // Renewing token and adding it to timer calls are separated purposefully
      // If user provides incorrect token then it should not be added for
      // renewal.
      for (DelegationTokenToRenew dtr : tokenList) {
        DelegationTokenToRenew currentDtr =
            allTokens.putIfAbsent(dtr.token, dtr);
        if (currentDtr != null) {
          // another job beat us
          currentDtr.referringAppIds.add(applicationId);
          appTokens.get(applicationId).add(currentDtr);
        } else {
          appTokens.get(applicationId).add(dtr);
          setTimerForTokenRenewal(dtr);
        }
      }
    }

    if (!hasHdfsToken) {
      requestNewHdfsDelegationToken(Arrays.asList(applicationId), evt.getUser(),
        shouldCancelAtEnd);
    }
  }