Java 类org.apache.hadoop.mapreduce.OutputCommitter 实例源码

public ReduceContextImpl(Configuration conf, TaskAttemptID taskid,
                         RawKeyValueIterator input, 
                         Counter inputKeyCounter,
                         Counter inputValueCounter,
                         RecordWriter<KEYOUT,VALUEOUT> output,
                         OutputCommitter committer,
                         StatusReporter reporter,
                         RawComparator<KEYIN> comparator,
                         Class<KEYIN> keyClass,
                         Class<VALUEIN> valueClass
                        ) throws InterruptedException, IOException{
  super(conf, taskid, output, committer, reporter);
  this.input = input;
  this.inputKeyCounter = inputKeyCounter;
  this.inputValueCounter = inputValueCounter;
  this.comparator = comparator;
  this.serializationFactory = new SerializationFactory(conf);
  this.keyDeserializer = serializationFactory.getDeserializer(keyClass);
  this.keyDeserializer.open(buffer);
  this.valueDeserializer = serializationFactory.getDeserializer(valueClass);
  this.valueDeserializer.open(buffer);
  hasMore = input.next();
  this.keyClass = keyClass;
  this.valueClass = valueClass;
  this.conf = conf;
  this.taskid = taskid;
}

private void writeBadOutput(TaskAttempt attempt, Configuration conf)
  throws Exception {
  TaskAttemptContext tContext = new TaskAttemptContextImpl(conf, 
      TypeConverter.fromYarn(attempt.getID()));

  TextOutputFormat<?, ?> theOutputFormat = new TextOutputFormat();
  RecordWriter theRecordWriter = theOutputFormat
      .getRecordWriter(tContext);

  NullWritable nullWritable = NullWritable.get();
  try {
    theRecordWriter.write(key2, val2);
    theRecordWriter.write(null, nullWritable);
    theRecordWriter.write(null, val2);
    theRecordWriter.write(nullWritable, val1);
    theRecordWriter.write(key1, nullWritable);
    theRecordWriter.write(key2, null);
    theRecordWriter.write(null, null);
    theRecordWriter.write(key1, val1);
  } finally {
    theRecordWriter.close(tContext);
  }

  OutputFormat outputFormat = ReflectionUtils.newInstance(
      tContext.getOutputFormatClass(), conf);
  OutputCommitter committer = outputFormat.getOutputCommitter(tContext);
  committer.commitTask(tContext);
}

private void writeOutput(TaskAttempt attempt, Configuration conf)
  throws Exception {
  TaskAttemptContext tContext = new TaskAttemptContextImpl(conf, 
      TypeConverter.fromYarn(attempt.getID()));

  TextOutputFormat<?, ?> theOutputFormat = new TextOutputFormat();
  RecordWriter theRecordWriter = theOutputFormat
      .getRecordWriter(tContext);

  NullWritable nullWritable = NullWritable.get();
  try {
    theRecordWriter.write(key1, val1);
    theRecordWriter.write(null, nullWritable);
    theRecordWriter.write(null, val1);
    theRecordWriter.write(nullWritable, val2);
    theRecordWriter.write(key2, nullWritable);
    theRecordWriter.write(key1, null);
    theRecordWriter.write(null, null);
    theRecordWriter.write(key2, val2);
  } finally {
    theRecordWriter.close(tContext);
  }

  OutputFormat outputFormat = ReflectionUtils.newInstance(
      tContext.getOutputFormatClass(), conf);
  OutputCommitter committer = outputFormat.getOutputCommitter(tContext);
  committer.commitTask(tContext);
}

@Test(timeout=20000)
public void testCommitJobFailsJob() throws Exception {
  Configuration conf = new Configuration();
  conf.set(MRJobConfig.MR_AM_STAGING_DIR, stagingDir);
  AsyncDispatcher dispatcher = new AsyncDispatcher();
  dispatcher.init(conf);
  dispatcher.start();
  CyclicBarrier syncBarrier = new CyclicBarrier(2);
  OutputCommitter committer = new TestingOutputCommitter(syncBarrier, false);
  CommitterEventHandler commitHandler =
      createCommitterEventHandler(dispatcher, committer);
  commitHandler.init(conf);
  commitHandler.start();

  JobImpl job = createRunningStubbedJob(conf, dispatcher, 2, null);
  completeJobTasks(job);
  assertJobState(job, JobStateInternal.COMMITTING);

  // let the committer fail and verify the job fails
  syncBarrier.await();
  assertJobState(job, JobStateInternal.FAILED);
  dispatcher.stop();
  commitHandler.stop();
}

@Test(timeout=20000)
public void testKilledDuringCommit() throws Exception {
  Configuration conf = new Configuration();
  conf.set(MRJobConfig.MR_AM_STAGING_DIR, stagingDir);
  AsyncDispatcher dispatcher = new AsyncDispatcher();
  dispatcher.init(conf);
  dispatcher.start();
  CyclicBarrier syncBarrier = new CyclicBarrier(2);
  OutputCommitter committer = new WaitingOutputCommitter(syncBarrier, true);
  CommitterEventHandler commitHandler =
      createCommitterEventHandler(dispatcher, committer);
  commitHandler.init(conf);
  commitHandler.start();

  JobImpl job = createRunningStubbedJob(conf, dispatcher, 2, null);
  completeJobTasks(job);
  assertJobState(job, JobStateInternal.COMMITTING);

  syncBarrier.await();
  job.handle(new JobEvent(job.getID(), JobEventType.JOB_KILL));
  assertJobState(job, JobStateInternal.KILLED);
  dispatcher.stop();
  commitHandler.stop();
}

@Test
public void testTransitionsAtFailed() throws IOException {
  Configuration conf = new Configuration();
  AsyncDispatcher dispatcher = new AsyncDispatcher();
  dispatcher.init(conf);
  dispatcher.start();

  OutputCommitter committer = mock(OutputCommitter.class);
  doThrow(new IOException("forcefail"))
    .when(committer).setupJob(any(JobContext.class));
  CommitterEventHandler commitHandler =
      createCommitterEventHandler(dispatcher, committer);
  commitHandler.init(conf);
  commitHandler.start();

  AppContext mockContext = mock(AppContext.class);
  when(mockContext.hasSuccessfullyUnregistered()).thenReturn(false);
  JobImpl job = createStubbedJob(conf, dispatcher, 2, mockContext);
  JobId jobId = job.getID();
  job.handle(new JobEvent(jobId, JobEventType.JOB_INIT));
  assertJobState(job, JobStateInternal.INITED);
  job.handle(new JobStartEvent(jobId));
  assertJobState(job, JobStateInternal.FAILED);

  job.handle(new JobEvent(jobId, JobEventType.JOB_TASK_COMPLETED));
  assertJobState(job, JobStateInternal.FAILED);
  job.handle(new JobEvent(jobId, JobEventType.JOB_TASK_ATTEMPT_COMPLETED));
  assertJobState(job, JobStateInternal.FAILED);
  job.handle(new JobEvent(jobId, JobEventType.JOB_MAP_TASK_RESCHEDULED));
  assertJobState(job, JobStateInternal.FAILED);
  job.handle(new JobEvent(jobId, JobEventType.JOB_TASK_ATTEMPT_FETCH_FAILURE));
  assertJobState(job, JobStateInternal.FAILED);
  Assert.assertEquals(JobState.RUNNING, job.getState());
  when(mockContext.hasSuccessfullyUnregistered()).thenReturn(true);
  Assert.assertEquals(JobState.FAILED, job.getState());

  dispatcher.stop();
  commitHandler.stop();
}

private static CommitterEventHandler createCommitterEventHandler(
    Dispatcher dispatcher, OutputCommitter committer) {
  final SystemClock clock = new SystemClock();
  AppContext appContext = mock(AppContext.class);
  when(appContext.getEventHandler()).thenReturn(
      dispatcher.getEventHandler());
  when(appContext.getClock()).thenReturn(clock);
  RMHeartbeatHandler heartbeatHandler = new RMHeartbeatHandler() {
    @Override
    public long getLastHeartbeatTime() {
      return clock.getTime();
    }
    @Override
    public void runOnNextHeartbeat(Runnable callback) {
      callback.run();
    }
  };
  ApplicationAttemptId id = 
    ConverterUtils.toApplicationAttemptId("appattempt_1234567890000_0001_0");
  when(appContext.getApplicationID()).thenReturn(id.getApplicationId());
  when(appContext.getApplicationAttemptId()).thenReturn(id);
  CommitterEventHandler handler =
      new CommitterEventHandler(appContext, committer, heartbeatHandler);
  dispatcher.register(CommitterEventType.class, handler);
  return handler;
}

@SuppressWarnings("rawtypes")
public TestJob(JobId jobId, ApplicationAttemptId applicationAttemptId,
    Configuration conf, EventHandler eventHandler,
    TaskAttemptListener taskAttemptListener, Clock clock,
    OutputCommitter committer, boolean newApiCommitter,
    String user, AppContext appContext,
    JobStateInternal forcedState, String diagnostic) {
  super(jobId, getApplicationAttemptId(applicationId, getStartCount()),
      conf, eventHandler, taskAttemptListener,
      new JobTokenSecretManager(), new Credentials(), clock,
      getCompletedTaskFromPreviousRun(), metrics, committer,
      newApiCommitter, user, System.currentTimeMillis(), getAllAMInfos(),
      appContext, forcedState, diagnostic);

  // This "this leak" is okay because the retained pointer is in an
  //  instance variable.
  localStateMachine = localFactory.make(this);
}

@SuppressWarnings("unchecked")
public static <K,V> 
CombinerRunner<K,V> create(JobConf job,
                           TaskAttemptID taskId,
                           Counters.Counter inputCounter,
                           TaskReporter reporter,
                           org.apache.hadoop.mapreduce.OutputCommitter committer
                          ) throws ClassNotFoundException {
  Class<? extends Reducer<K,V,K,V>> cls = 
    (Class<? extends Reducer<K,V,K,V>>) job.getCombinerClass();

  if (cls != null) {
    return new OldCombinerRunner(cls, job, inputCounter, reporter);
  }
  // make a task context so we can get the classes
  org.apache.hadoop.mapreduce.TaskAttemptContext taskContext =
    new org.apache.hadoop.mapreduce.task.TaskAttemptContextImpl(job, taskId,
        reporter);
  Class<? extends org.apache.hadoop.mapreduce.Reducer<K,V,K,V>> newcls = 
    (Class<? extends org.apache.hadoop.mapreduce.Reducer<K,V,K,V>>)
       taskContext.getCombinerClass();
  if (newcls != null) {
    return new NewCombinerRunner<K,V>(newcls, job, taskId, taskContext, 
                                      inputCounter, reporter, committer);
  }

  return null;
}

@SuppressWarnings("unchecked")
NewCombinerRunner(Class reducerClass,
                  JobConf job,
                  org.apache.hadoop.mapreduce.TaskAttemptID taskId,
                  org.apache.hadoop.mapreduce.TaskAttemptContext context,
                  Counters.Counter inputCounter,
                  TaskReporter reporter,
                  org.apache.hadoop.mapreduce.OutputCommitter committer) {
  super(inputCounter, job, reporter);
  this.reducerClass = reducerClass;
  this.taskId = taskId;
  keyClass = (Class<K>) context.getMapOutputKeyClass();
  valueClass = (Class<V>) context.getMapOutputValueClass();
  comparator = (RawComparator<K>) context.getCombinerKeyGroupingComparator();
  this.committer = committer;
}

@SuppressWarnings({"rawtypes", "unchecked"})
@Test (timeout=10000)
public void testLoadMapper() throws Exception {

  Configuration conf = new Configuration();
  conf.setInt(JobContext.NUM_REDUCES, 2);

  CompressionEmulationUtil.setCompressionEmulationEnabled(conf, true);
  conf.setBoolean(MRJobConfig.MAP_OUTPUT_COMPRESS, true);

  TaskAttemptID taskId = new TaskAttemptID();
  RecordReader<NullWritable, GridmixRecord> reader = new FakeRecordReader();

  LoadRecordGkGrWriter writer = new LoadRecordGkGrWriter();

  OutputCommitter committer = new CustomOutputCommitter();
  StatusReporter reporter = new TaskAttemptContextImpl.DummyReporter();
  LoadSplit split = getLoadSplit();

  MapContext<NullWritable, GridmixRecord, GridmixKey, GridmixRecord> mapContext = new MapContextImpl<NullWritable, GridmixRecord, GridmixKey, GridmixRecord>(
          conf, taskId, reader, writer, committer, reporter, split);
  // context
  Context ctx = new WrappedMapper<NullWritable, GridmixRecord, GridmixKey, GridmixRecord>()
          .getMapContext(mapContext);

  reader.initialize(split, ctx);
  ctx.getConfiguration().setBoolean(MRJobConfig.MAP_OUTPUT_COMPRESS, true);
  CompressionEmulationUtil.setCompressionEmulationEnabled(
          ctx.getConfiguration(), true);

  LoadJob.LoadMapper mapper = new LoadJob.LoadMapper();
  // setup, map, clean
  mapper.run(ctx);

  Map<GridmixKey, GridmixRecord> data = writer.getData();
  // check result
  assertEquals(2, data.size());

}

private void writeBadOutput(TaskAttempt attempt, Configuration conf)
  throws Exception {
  TaskAttemptContext tContext = new TaskAttemptContextImpl(conf, 
      TypeConverter.fromYarn(attempt.getID()));

  TextOutputFormat<?, ?> theOutputFormat = new TextOutputFormat();
  RecordWriter theRecordWriter = theOutputFormat
      .getRecordWriter(tContext);

  NullWritable nullWritable = NullWritable.get();
  try {
    theRecordWriter.write(key2, val2);
    theRecordWriter.write(null, nullWritable);
    theRecordWriter.write(null, val2);
    theRecordWriter.write(nullWritable, val1);
    theRecordWriter.write(key1, nullWritable);
    theRecordWriter.write(key2, null);
    theRecordWriter.write(null, null);
    theRecordWriter.write(key1, val1);
  } finally {
    theRecordWriter.close(tContext);
  }

  OutputFormat outputFormat = ReflectionUtils.newInstance(
      tContext.getOutputFormatClass(), conf);
  OutputCommitter committer = outputFormat.getOutputCommitter(tContext);
  committer.commitTask(tContext);
}

@Test(timeout=20000)
public void testCommitJobFailsJob() throws Exception {
  Configuration conf = new Configuration();
  conf.set(MRJobConfig.MR_AM_STAGING_DIR, stagingDir);
  AsyncDispatcher dispatcher = new AsyncDispatcher();
  dispatcher.init(conf);
  dispatcher.start();
  CyclicBarrier syncBarrier = new CyclicBarrier(2);
  OutputCommitter committer = new TestingOutputCommitter(syncBarrier, false);
  CommitterEventHandler commitHandler =
      createCommitterEventHandler(dispatcher, committer);
  commitHandler.init(conf);
  commitHandler.start();

  JobImpl job = createRunningStubbedJob(conf, dispatcher, 2, null);
  completeJobTasks(job);
  assertJobState(job, JobStateInternal.COMMITTING);

  // let the committer fail and verify the job fails
  syncBarrier.await();
  assertJobState(job, JobStateInternal.FAILED);
  dispatcher.stop();
  commitHandler.stop();
}

@Test(timeout=20000)
public void testKilledDuringCommit() throws Exception {
  Configuration conf = new Configuration();
  conf.set(MRJobConfig.MR_AM_STAGING_DIR, stagingDir);
  AsyncDispatcher dispatcher = new AsyncDispatcher();
  dispatcher.init(conf);
  dispatcher.start();
  CyclicBarrier syncBarrier = new CyclicBarrier(2);
  OutputCommitter committer = new WaitingOutputCommitter(syncBarrier, true);
  CommitterEventHandler commitHandler =
      createCommitterEventHandler(dispatcher, committer);
  commitHandler.init(conf);
  commitHandler.start();

  JobImpl job = createRunningStubbedJob(conf, dispatcher, 2, null);
  completeJobTasks(job);
  assertJobState(job, JobStateInternal.COMMITTING);

  syncBarrier.await();
  job.handle(new JobEvent(job.getID(), JobEventType.JOB_KILL));
  assertJobState(job, JobStateInternal.KILLED);
  dispatcher.stop();
  commitHandler.stop();
}

private static CommitterEventHandler createCommitterEventHandler(
    Dispatcher dispatcher, OutputCommitter committer) {
  final SystemClock clock = new SystemClock();
  AppContext appContext = mock(AppContext.class);
  when(appContext.getEventHandler()).thenReturn(
      dispatcher.getEventHandler());
  when(appContext.getClock()).thenReturn(clock);
  RMHeartbeatHandler heartbeatHandler = new RMHeartbeatHandler() {
    @Override
    public long getLastHeartbeatTime() {
      return clock.getTime();
    }
    @Override
    public void runOnNextHeartbeat(Runnable callback) {
      callback.run();
    }
  };
  ApplicationAttemptId id = 
    ConverterUtils.toApplicationAttemptId("appattempt_1234567890000_0001_0");
  when(appContext.getApplicationID()).thenReturn(id.getApplicationId());
  when(appContext.getApplicationAttemptId()).thenReturn(id);
  CommitterEventHandler handler =
      new CommitterEventHandler(appContext, committer, heartbeatHandler);
  dispatcher.register(CommitterEventType.class, handler);
  return handler;
}

@SuppressWarnings("unchecked")
NewCombinerRunner(Class reducerClass,
                  JobConf job,
                  org.apache.hadoop.mapreduce.TaskAttemptID taskId,
                  org.apache.hadoop.mapreduce.TaskAttemptContext context,
                  Counters.Counter inputCounter,
                  TaskReporter reporter,
                  org.apache.hadoop.mapreduce.OutputCommitter committer) {
  super(inputCounter, job, reporter);
  this.reducerClass = reducerClass;
  this.taskId = taskId;
  keyClass = (Class<K>) context.getMapOutputKeyClass();
  valueClass = (Class<V>) context.getMapOutputValueClass();
  comparator = (RawComparator<K>) context.getCombinerKeyGroupingComparator();
  this.committer = committer;
}

@Override
@Deprecated
public void cleanupJob(org.apache.hadoop.mapred.JobContext context) throws IOException {
    // no-op
    // added for compatibility with hadoop 0.20.x (used by old tools, such as Cascalog)
    for (OutputCommitter committer : committers) {
        committer.cleanupJob(context);
    }
}

private void writeBadOutput(TaskAttempt attempt, Configuration conf)
  throws Exception {
  TaskAttemptContext tContext = new TaskAttemptContextImpl(conf, 
      TypeConverter.fromYarn(attempt.getID()));

  TextOutputFormat<?, ?> theOutputFormat = new TextOutputFormat();
  RecordWriter theRecordWriter = theOutputFormat
      .getRecordWriter(tContext);

  NullWritable nullWritable = NullWritable.get();
  try {
    theRecordWriter.write(key2, val2);
    theRecordWriter.write(null, nullWritable);
    theRecordWriter.write(null, val2);
    theRecordWriter.write(nullWritable, val1);
    theRecordWriter.write(key1, nullWritable);
    theRecordWriter.write(key2, null);
    theRecordWriter.write(null, null);
    theRecordWriter.write(key1, val1);
  } finally {
    theRecordWriter.close(tContext);
  }

  OutputFormat outputFormat = ReflectionUtils.newInstance(
      tContext.getOutputFormatClass(), conf);
  OutputCommitter committer = outputFormat.getOutputCommitter(tContext);
  committer.commitTask(tContext);
}

@Test(timeout=20000)
public void testCommitJobFailsJob() throws Exception {
  Configuration conf = new Configuration();
  conf.set(MRJobConfig.MR_AM_STAGING_DIR, stagingDir);
  AsyncDispatcher dispatcher = new AsyncDispatcher();
  dispatcher.init(conf);
  dispatcher.start();
  CyclicBarrier syncBarrier = new CyclicBarrier(2);
  OutputCommitter committer = new TestingOutputCommitter(syncBarrier, false);
  CommitterEventHandler commitHandler =
      createCommitterEventHandler(dispatcher, committer);
  commitHandler.init(conf);
  commitHandler.start();

  JobImpl job = createRunningStubbedJob(conf, dispatcher, 2, null);
  completeJobTasks(job);
  assertJobState(job, JobStateInternal.COMMITTING);

  // let the committer fail and verify the job fails
  syncBarrier.await();
  assertJobState(job, JobStateInternal.FAILED);
  dispatcher.stop();
  commitHandler.stop();
}

@Test(timeout=20000)
public void testKilledDuringCommit() throws Exception {
  Configuration conf = new Configuration();
  conf.set(MRJobConfig.MR_AM_STAGING_DIR, stagingDir);
  AsyncDispatcher dispatcher = new AsyncDispatcher();
  dispatcher.init(conf);
  dispatcher.start();
  CyclicBarrier syncBarrier = new CyclicBarrier(2);
  OutputCommitter committer = new WaitingOutputCommitter(syncBarrier, true);
  CommitterEventHandler commitHandler =
      createCommitterEventHandler(dispatcher, committer);
  commitHandler.init(conf);
  commitHandler.start();

  JobImpl job = createRunningStubbedJob(conf, dispatcher, 2, null);
  completeJobTasks(job);
  assertJobState(job, JobStateInternal.COMMITTING);

  syncBarrier.await();
  job.handle(new JobEvent(job.getID(), JobEventType.JOB_KILL));
  assertJobState(job, JobStateInternal.KILLED);
  dispatcher.stop();
  commitHandler.stop();
}

@SuppressWarnings("rawtypes")
public TestJob(JobId jobId, ApplicationAttemptId applicationAttemptId,
    Configuration conf, EventHandler eventHandler,
    TaskAttemptListener taskAttemptListener, Clock clock,
    OutputCommitter committer, boolean newApiCommitter,
    String user, AppContext appContext,
    JobStateInternal forcedState, String diagnostic) {
  super(jobId, getApplicationAttemptId(applicationId, getStartCount()),
      conf, eventHandler, taskAttemptListener,
      new JobTokenSecretManager(), new Credentials(), clock,
      getCompletedTaskFromPreviousRun(), metrics, committer,
      newApiCommitter, user, System.currentTimeMillis(), getAllAMInfos(),
      appContext, forcedState, diagnostic);

  // This "this leak" is okay because the retained pointer is in an
  //  instance variable.
  localStateMachine = localFactory.make(this);
}

@SuppressWarnings("unchecked")
NewCombinerRunner(Class reducerClass,
                  JobConf job,
                  org.apache.hadoop.mapreduce.TaskAttemptID taskId,
                  org.apache.hadoop.mapreduce.TaskAttemptContext context,
                  Counters.Counter inputCounter,
                  TaskReporter reporter,
                  org.apache.hadoop.mapreduce.OutputCommitter committer) {
  super(inputCounter, job, reporter);
  this.reducerClass = reducerClass;
  this.taskId = taskId;
  keyClass = (Class<K>) context.getMapOutputKeyClass();
  valueClass = (Class<V>) context.getMapOutputValueClass();
  comparator = (RawComparator<K>) context.getCombinerKeyGroupingComparator();
  this.committer = committer;
}

public CommitterEventHandler(AppContext context, OutputCommitter committer,
    RMHeartbeatHandler rmHeartbeatHandler, ClassLoader jobClassLoader) {
  super("CommitterEventHandler");
  this.context = context;
  this.committer = committer;
  this.rmHeartbeatHandler = rmHeartbeatHandler;
  this.stopped = new AtomicBoolean(false);
  this.jobClassLoader = jobClassLoader;
}

public TaskAttemptRecoverEvent(TaskAttemptId id, TaskAttemptInfo taInfo,
    OutputCommitter committer, boolean recoverOutput) {
  super(id, TaskAttemptEventType.TA_RECOVER);
  this.taInfo = taInfo;
  this.committer = committer;
  this.recoverAttemptOutput = recoverOutput;
}

public TaskRecoverEvent(TaskId taskID, TaskInfo taskInfo,
    OutputCommitter committer, boolean recoverTaskOutput) {
  super(taskID, TaskEventType.T_RECOVER);
  this.taskInfo = taskInfo;
  this.committer = committer;
  this.recoverTaskOutput = recoverTaskOutput;
}

@Test
public void testJobNoTasks() {
  Configuration conf = new Configuration();
  conf.setInt(MRJobConfig.NUM_REDUCES, 0);
  conf.set(MRJobConfig.MR_AM_STAGING_DIR, stagingDir);
  conf.set(MRJobConfig.WORKFLOW_ID, "testId");
  conf.set(MRJobConfig.WORKFLOW_NAME, "testName");
  conf.set(MRJobConfig.WORKFLOW_NODE_NAME, "testNodeName");
  conf.set(MRJobConfig.WORKFLOW_ADJACENCY_PREFIX_STRING + "key1", "value1");
  conf.set(MRJobConfig.WORKFLOW_ADJACENCY_PREFIX_STRING + "key2", "value2");
  conf.set(MRJobConfig.WORKFLOW_TAGS, "tag1,tag2");


  AsyncDispatcher dispatcher = new AsyncDispatcher();
  dispatcher.init(conf);
  dispatcher.start();
  OutputCommitter committer = mock(OutputCommitter.class);
  CommitterEventHandler commitHandler =
      createCommitterEventHandler(dispatcher, committer);
  commitHandler.init(conf);
  commitHandler.start();

  JobSubmittedEventHandler jseHandler = new JobSubmittedEventHandler("testId",
      "testName", "testNodeName", "\"key2\"=\"value2\" \"key1\"=\"value1\" ",
      "tag1,tag2");
  dispatcher.register(EventType.class, jseHandler);
  JobImpl job = createStubbedJob(conf, dispatcher, 0, null);
  job.handle(new JobEvent(job.getID(), JobEventType.JOB_INIT));
  assertJobState(job, JobStateInternal.INITED);
  job.handle(new JobStartEvent(job.getID()));
  assertJobState(job, JobStateInternal.SUCCEEDED);
  dispatcher.stop();
  commitHandler.stop();
  try {
    Assert.assertTrue(jseHandler.getAssertValue());
  } catch (InterruptedException e) {
    Assert.fail("Workflow related attributes are not tested properly");
  }
}

@Test(timeout=20000)
public void testCheckJobCompleteSuccess() throws Exception {
  Configuration conf = new Configuration();
  conf.set(MRJobConfig.MR_AM_STAGING_DIR, stagingDir);
  AsyncDispatcher dispatcher = new AsyncDispatcher();
  dispatcher.init(conf);
  dispatcher.start();
  CyclicBarrier syncBarrier = new CyclicBarrier(2);
  OutputCommitter committer = new TestingOutputCommitter(syncBarrier, true);
  CommitterEventHandler commitHandler =
      createCommitterEventHandler(dispatcher, committer);
  commitHandler.init(conf);
  commitHandler.start();

  JobImpl job = createRunningStubbedJob(conf, dispatcher, 2, null);
  completeJobTasks(job);
  assertJobState(job, JobStateInternal.COMMITTING);

  // let the committer complete and verify the job succeeds
  syncBarrier.await();
  assertJobState(job, JobStateInternal.SUCCEEDED);

  job.handle(new JobEvent(job.getID(),
      JobEventType.JOB_TASK_ATTEMPT_COMPLETED));
  assertJobState(job, JobStateInternal.SUCCEEDED);

  job.handle(new JobEvent(job.getID(), 
      JobEventType.JOB_MAP_TASK_RESCHEDULED));
  assertJobState(job, JobStateInternal.SUCCEEDED);

  dispatcher.stop();
  commitHandler.stop();
}

@Test(timeout=20000)
public void testRebootedDuringCommit() throws Exception {
  Configuration conf = new Configuration();
  conf.set(MRJobConfig.MR_AM_STAGING_DIR, stagingDir);
  conf.setInt(MRJobConfig.MR_AM_MAX_ATTEMPTS, 2);
  AsyncDispatcher dispatcher = new AsyncDispatcher();
  dispatcher.init(conf);
  dispatcher.start();
  CyclicBarrier syncBarrier = new CyclicBarrier(2);
  OutputCommitter committer = new WaitingOutputCommitter(syncBarrier, true);
  CommitterEventHandler commitHandler =
      createCommitterEventHandler(dispatcher, committer);
  commitHandler.init(conf);
  commitHandler.start();

  AppContext mockContext = mock(AppContext.class);
  when(mockContext.isLastAMRetry()).thenReturn(true);
  when(mockContext.hasSuccessfullyUnregistered()).thenReturn(false);
  JobImpl job = createRunningStubbedJob(conf, dispatcher, 2, mockContext);
  completeJobTasks(job);
  assertJobState(job, JobStateInternal.COMMITTING);

  syncBarrier.await();
  job.handle(new JobEvent(job.getID(), JobEventType.JOB_AM_REBOOT));
  assertJobState(job, JobStateInternal.REBOOT);
  // return the external state as ERROR since this is last retry.
  Assert.assertEquals(JobState.RUNNING, job.getState());
  when(mockContext.hasSuccessfullyUnregistered()).thenReturn(true);
  Assert.assertEquals(JobState.ERROR, job.getState());

  dispatcher.stop();
  commitHandler.stop();
}

@Test(timeout=20000)
public void testKilledDuringSetup() throws Exception {
  Configuration conf = new Configuration();
  conf.set(MRJobConfig.MR_AM_STAGING_DIR, stagingDir);
  AsyncDispatcher dispatcher = new AsyncDispatcher();
  dispatcher.init(conf);
  dispatcher.start();
  OutputCommitter committer = new StubbedOutputCommitter() {
    @Override
    public synchronized void setupJob(JobContext jobContext)
        throws IOException {
      while (!Thread.interrupted()) {
        try {
          wait();
        } catch (InterruptedException e) {
        }
      }
    }
  };
  CommitterEventHandler commitHandler =
      createCommitterEventHandler(dispatcher, committer);
  commitHandler.init(conf);
  commitHandler.start();

  JobImpl job = createStubbedJob(conf, dispatcher, 2, null);
  JobId jobId = job.getID();
  job.handle(new JobEvent(jobId, JobEventType.JOB_INIT));
  assertJobState(job, JobStateInternal.INITED);
  job.handle(new JobStartEvent(jobId));
  assertJobState(job, JobStateInternal.SETUP);

  job.handle(new JobEvent(job.getID(), JobEventType.JOB_KILL));
  assertJobState(job, JobStateInternal.KILLED);
  dispatcher.stop();
  commitHandler.stop();
}

@Test
public void testAbortJobCalledAfterKillingTasks() throws IOException {
  Configuration conf = new Configuration();
  conf.set(MRJobConfig.MR_AM_STAGING_DIR, stagingDir);
  conf.set(MRJobConfig.MR_AM_COMMITTER_CANCEL_TIMEOUT_MS, "1000");
  InlineDispatcher dispatcher = new InlineDispatcher();
  dispatcher.init(conf);
  dispatcher.start();
  OutputCommitter committer = Mockito.mock(OutputCommitter.class);
  CommitterEventHandler commitHandler =
      createCommitterEventHandler(dispatcher, committer);
  commitHandler.init(conf);
  commitHandler.start();
  JobImpl job = createRunningStubbedJob(conf, dispatcher, 2, null);

  //Fail one task. This should land the JobImpl in the FAIL_WAIT state
  job.handle(new JobTaskEvent(
    MRBuilderUtils.newTaskId(job.getID(), 1, TaskType.MAP),
    TaskState.FAILED));
  //Verify abort job hasn't been called
  Mockito.verify(committer, Mockito.never())
    .abortJob((JobContext) Mockito.any(), (State) Mockito.any());
  assertJobState(job, JobStateInternal.FAIL_WAIT);

  //Verify abortJob is called once and the job failed
  Mockito.verify(committer, Mockito.timeout(2000).times(1))
    .abortJob((JobContext) Mockito.any(), (State) Mockito.any());
  assertJobState(job, JobStateInternal.FAILED);

  dispatcher.stop();
}

@Test (timeout=10000)
public void testFailAbortDoesntHang() throws IOException {
  Configuration conf = new Configuration();
  conf.set(MRJobConfig.MR_AM_STAGING_DIR, stagingDir);
  conf.set(MRJobConfig.MR_AM_COMMITTER_CANCEL_TIMEOUT_MS, "1000");

  DrainDispatcher dispatcher = new DrainDispatcher();
  dispatcher.init(conf);
  dispatcher.start();
  OutputCommitter committer = Mockito.mock(OutputCommitter.class);
  CommitterEventHandler commitHandler =
      createCommitterEventHandler(dispatcher, committer);
  commitHandler.init(conf);
  commitHandler.start();
  //Job has only 1 mapper task. No reducers
  conf.setInt(MRJobConfig.NUM_REDUCES, 0);
  conf.setInt(MRJobConfig.MAP_MAX_ATTEMPTS, 1);
  JobImpl job = createRunningStubbedJob(conf, dispatcher, 1, null);

  //Fail / finish all the tasks. This should land the JobImpl directly in the
  //FAIL_ABORT state
  for(Task t: job.tasks.values()) {
    TaskImpl task = (TaskImpl) t;
    task.handle(new TaskEvent(task.getID(), TaskEventType.T_SCHEDULE));
    for(TaskAttempt ta: task.getAttempts().values()) {
      task.handle(new TaskTAttemptEvent(ta.getID(),
        TaskEventType.T_ATTEMPT_FAILED));
    }
  }

  dispatcher.await();
  //Verify abortJob is called once and the job failed
  Mockito.verify(committer, Mockito.timeout(2000).times(1))
    .abortJob((JobContext) Mockito.any(), (State) Mockito.any());
  assertJobState(job, JobStateInternal.FAILED);

  dispatcher.stop();
}

@Test(timeout=20000)
public void testKilledDuringKillAbort() throws Exception {
  Configuration conf = new Configuration();
  conf.set(MRJobConfig.MR_AM_STAGING_DIR, stagingDir);
  AsyncDispatcher dispatcher = new AsyncDispatcher();
  dispatcher.init(conf);
  dispatcher.start();
  OutputCommitter committer = new StubbedOutputCommitter() {
    @Override
    public synchronized void abortJob(JobContext jobContext, State state)
        throws IOException {
      while (!Thread.interrupted()) {
        try {
          wait();
        } catch (InterruptedException e) {
        }
      }
    }
  };
  CommitterEventHandler commitHandler =
      createCommitterEventHandler(dispatcher, committer);
  commitHandler.init(conf);
  commitHandler.start();

  JobImpl job = createStubbedJob(conf, dispatcher, 2, null);
  JobId jobId = job.getID();
  job.handle(new JobEvent(jobId, JobEventType.JOB_INIT));
  assertJobState(job, JobStateInternal.INITED);
  job.handle(new JobStartEvent(jobId));
  assertJobState(job, JobStateInternal.SETUP);

  job.handle(new JobEvent(jobId, JobEventType.JOB_KILL));
  assertJobState(job, JobStateInternal.KILL_ABORT);

  job.handle(new JobEvent(jobId, JobEventType.JOB_KILL));
  assertJobState(job, JobStateInternal.KILLED);
  dispatcher.stop();
  commitHandler.stop();
}

public synchronized OutputCommitter getOutputCommitter(
    TaskAttemptContext context) throws IOException {
  if (committer == null) {
    Path output = getOutputPath(context);
    committer = new CommitterWithCustomAbort(output, context);
  }
  return committer;
}

public synchronized OutputCommitter getOutputCommitter(
    TaskAttemptContext context) throws IOException {
  if (committer == null) {
    Path output = getOutputPath(context);
    committer = new CommitterWithCustomDeprecatedCleanup(output, context);
  }
  return committer;
}

@SuppressWarnings("unchecked")
protected static <INKEY,INVALUE,OUTKEY,OUTVALUE> 
org.apache.hadoop.mapreduce.Reducer<INKEY,INVALUE,OUTKEY,OUTVALUE>.Context
createReduceContext(org.apache.hadoop.mapreduce.Reducer
                      <INKEY,INVALUE,OUTKEY,OUTVALUE> reducer,
                    Configuration job,
                    org.apache.hadoop.mapreduce.TaskAttemptID taskId, 
                    RawKeyValueIterator rIter,
                    org.apache.hadoop.mapreduce.Counter inputKeyCounter,
                    org.apache.hadoop.mapreduce.Counter inputValueCounter,
                    org.apache.hadoop.mapreduce.RecordWriter<OUTKEY,OUTVALUE> output, 
                    org.apache.hadoop.mapreduce.OutputCommitter committer,
                    org.apache.hadoop.mapreduce.StatusReporter reporter,
                    RawComparator<INKEY> comparator,
                    Class<INKEY> keyClass, Class<INVALUE> valueClass
) throws IOException, InterruptedException {
  org.apache.hadoop.mapreduce.ReduceContext<INKEY, INVALUE, OUTKEY, OUTVALUE> 
  reduceContext = 
    new ReduceContextImpl<INKEY, INVALUE, OUTKEY, OUTVALUE>(job, taskId, 
                                                            rIter, 
                                                            inputKeyCounter, 
                                                            inputValueCounter, 
                                                            output, 
                                                            committer, 
                                                            reporter, 
                                                            comparator, 
                                                            keyClass, 
                                                            valueClass);

  org.apache.hadoop.mapreduce.Reducer<INKEY,INVALUE,OUTKEY,OUTVALUE>.Context 
      reducerContext = 
        new WrappedReducer<INKEY, INVALUE, OUTKEY, OUTVALUE>().getReducerContext(
            reduceContext);

  return reducerContext;
}

@Override
public OutputCommitter getOutputCommitter(TaskAttemptContext context) 
throws IOException, InterruptedException {
  if (baseOut == null) {
    getBaseOutputFormat(context.getConfiguration());
  }
  return super.getOutputCommitter(context);
}

public TaskInputOutputContextImpl(Configuration conf, TaskAttemptID taskid,
                                  RecordWriter<KEYOUT,VALUEOUT> output,
                                  OutputCommitter committer,
                                  StatusReporter reporter) {
  super(conf, taskid, reporter);
  this.output = output;
  this.committer = committer;
}

@SuppressWarnings({"rawtypes", "unchecked"})
@Test (timeout=10000)
public void testLoadMapper() throws Exception {

  Configuration conf = new Configuration();
  conf.setInt(JobContext.NUM_REDUCES, 2);

  CompressionEmulationUtil.setCompressionEmulationEnabled(conf, true);
  conf.setBoolean(MRJobConfig.MAP_OUTPUT_COMPRESS, true);

  TaskAttemptID taskId = new TaskAttemptID();
  RecordReader<NullWritable, GridmixRecord> reader = new FakeRecordReader();

  LoadRecordGkGrWriter writer = new LoadRecordGkGrWriter();

  OutputCommitter committer = new CustomOutputCommitter();
  StatusReporter reporter = new TaskAttemptContextImpl.DummyReporter();
  LoadSplit split = getLoadSplit();

  MapContext<NullWritable, GridmixRecord, GridmixKey, GridmixRecord> mapContext = new MapContextImpl<NullWritable, GridmixRecord, GridmixKey, GridmixRecord>(
          conf, taskId, reader, writer, committer, reporter, split);
  // context
  Context ctx = new WrappedMapper<NullWritable, GridmixRecord, GridmixKey, GridmixRecord>()
          .getMapContext(mapContext);

  reader.initialize(split, ctx);
  ctx.getConfiguration().setBoolean(MRJobConfig.MAP_OUTPUT_COMPRESS, true);
  CompressionEmulationUtil.setCompressionEmulationEnabled(
          ctx.getConfiguration(), true);

  LoadJob.LoadMapper mapper = new LoadJob.LoadMapper();
  // setup, map, clean
  mapper.run(ctx);

  Map<GridmixKey, GridmixRecord> data = writer.getData();
  // check result
  assertEquals(2, data.size());

}

@SuppressWarnings({"unchecked", "rawtypes"})
@Test (timeout=30000)
public void testSleepMapper() throws Exception {
  SleepJob.SleepMapper test = new SleepJob.SleepMapper();

  Configuration conf = new Configuration();
  conf.setInt(JobContext.NUM_REDUCES, 2);

  CompressionEmulationUtil.setCompressionEmulationEnabled(conf, true);
  conf.setBoolean(MRJobConfig.MAP_OUTPUT_COMPRESS, true);
  TaskAttemptID taskId = new TaskAttemptID();
  FakeRecordLLReader reader = new FakeRecordLLReader();
  LoadRecordGkNullWriter writer = new LoadRecordGkNullWriter();
  OutputCommitter committer = new CustomOutputCommitter();
  StatusReporter reporter = new TaskAttemptContextImpl.DummyReporter();
  SleepSplit split = getSleepSplit();
  MapContext<LongWritable, LongWritable, GridmixKey, NullWritable> mapcontext = new MapContextImpl<LongWritable, LongWritable, GridmixKey, NullWritable>(
          conf, taskId, reader, writer, committer, reporter, split);
  Context context = new WrappedMapper<LongWritable, LongWritable, GridmixKey, NullWritable>()
          .getMapContext(mapcontext);

  long start = System.currentTimeMillis();
  LOG.info("start:" + start);
  LongWritable key = new LongWritable(start + 2000);
  LongWritable value = new LongWritable(start + 2000);
  // should slip 2 sec
  test.map(key, value, context);
  LOG.info("finish:" + System.currentTimeMillis());
  assertTrue(System.currentTimeMillis() >= (start + 2000));

  test.cleanup(context);
  assertEquals(1, writer.getData().size());
}

public TaskAttemptRecoverEvent(TaskAttemptId id, TaskAttemptInfo taInfo,
    OutputCommitter committer, boolean recoverOutput) {
  super(id, TaskAttemptEventType.TA_RECOVER);
  this.taInfo = taInfo;
  this.committer = committer;
  this.recoverAttemptOutput = recoverOutput;
}