Java TaskID类代码示例

import org.apache.hadoop.mapreduce.TaskID; //导入依赖的package包/类
public void setDatum(Object odatum) {
  this.datum = (TaskFailed)odatum;
  this.id =
      TaskID.forName(datum.taskid.toString());
  this.taskType =
      TaskType.valueOf(datum.taskType.toString());
  this.finishTime = datum.finishTime;
  this.error = datum.error.toString();
  this.failedDueToAttempt =
      datum.failedDueToAttempt == null
      ? null
      : TaskAttemptID.forName(
          datum.failedDueToAttempt.toString());
  this.status = datum.status.toString();
  this.counters =
      EventReader.fromAvro(datum.counters);
}
 

import org.apache.hadoop.mapreduce.TaskID; //导入依赖的package包/类
private List<InputSplit> createSplits(JobContext jobContext, List<DynamicInputChunk> chunks) throws IOException {
  int numMaps = getNumMapTasks(jobContext.getConfiguration());

  final int nSplits = Math.min(numMaps, chunks.size());
  List<InputSplit> splits = new ArrayList<>(nSplits);

  for (int i = 0; i < nSplits; ++i) {
    TaskID taskId = new TaskID(jobContext.getJobID(), TaskType.MAP, i);
    chunks.get(i).assignTo(taskId);
    splits.add(new FileSplit(chunks.get(i).getPath(), 0,
        // Setting non-zero length for FileSplit size, to avoid a possible
        // future when 0-sized file-splits are considered "empty" and skipped
        // over.
        getMinRecordsPerChunk(jobContext.getConfiguration()), null));
  }
  ConfigurationUtil.publish(jobContext.getConfiguration(), CONF_LABEL_NUM_SPLITS, splits.size());
  return splits;
}
 

import org.apache.hadoop.mapreduce.TaskID; //导入依赖的package包/类
/**
 * test a getters of TaskAttemptFinishedEvent and TaskAttemptFinished
 * 
 * @throws Exception
 */
@Test(timeout = 10000)
public void testTaskAttemptFinishedEvent() throws Exception {

  JobID jid = new JobID("001", 1);
  TaskID tid = new TaskID(jid, TaskType.REDUCE, 2);
  TaskAttemptID taskAttemptId = new TaskAttemptID(tid, 3);
  Counters counters = new Counters();
  TaskAttemptFinishedEvent test = new TaskAttemptFinishedEvent(taskAttemptId,
      TaskType.REDUCE, "TEST", 123L, "RAKNAME", "HOSTNAME", "STATUS",
      counters);
  assertEquals(test.getAttemptId().toString(), taskAttemptId.toString());

  assertEquals(test.getCounters(), counters);
  assertEquals(test.getFinishTime(), 123L);
  assertEquals(test.getHostname(), "HOSTNAME");
  assertEquals(test.getRackName(), "RAKNAME");
  assertEquals(test.getState(), "STATUS");
  assertEquals(test.getTaskId(), tid);
  assertEquals(test.getTaskStatus(), "TEST");
  assertEquals(test.getTaskType(), TaskType.REDUCE);

}
 

import org.apache.hadoop.mapreduce.TaskID; //导入依赖的package包/类
@Override
public void cleanUpPartialOutputForTask(TaskAttemptContext context)
    throws IOException {

  // we double check this is never invoked from a non-preemptable subclass.
  // This should never happen, since the invoking codes is checking it too,
  // but it is safer to double check. Errors handling this would produce
  // inconsistent output.

  if (!this.getClass().isAnnotationPresent(Checkpointable.class)) {
    throw new IllegalStateException("Invoking cleanUpPartialOutputForTask() " +
        "from non @Preemptable class");
  }
  FileSystem fs =
    fsFor(getTaskAttemptPath(context), context.getConfiguration());

  LOG.info("cleanUpPartialOutputForTask: removing everything belonging to " +
      context.getTaskAttemptID().getTaskID() + " in: " +
      getCommittedTaskPath(context).getParent());

  final TaskAttemptID taid = context.getTaskAttemptID();
  final TaskID tid = taid.getTaskID();
  Path pCommit = getCommittedTaskPath(context).getParent();
  // remove any committed output
  for (int i = 0; i < taid.getId(); ++i) {
    TaskAttemptID oldId = new TaskAttemptID(tid, i);
    Path pTask = new Path(pCommit, oldId.toString());
    if (fs.exists(pTask) && !fs.delete(pTask, true)) {
      throw new IOException("Failed to delete " + pTask);
    }
  }
}
 

import org.apache.hadoop.mapreduce.TaskID; //导入依赖的package包/类
/**
 * Generate a unique filename, based on the task id, name, and extension
 * @param context the task that is calling this
 * @param name the base filename
 * @param extension the filename extension
 * @return a string like $name-[mrsct]-$id$extension
 */
public synchronized static String getUniqueFile(TaskAttemptContext context,
                                                String name,
                                                String extension) {
  TaskID taskId = context.getTaskAttemptID().getTaskID();
  int partition = taskId.getId();
  StringBuilder result = new StringBuilder();
  result.append(name);
  result.append('-');
  result.append(
      TaskID.getRepresentingCharacter(taskId.getTaskType()));
  result.append('-');
  result.append(NUMBER_FORMAT.format(partition));
  result.append(extension);
  return result.toString();
}
 

import org.apache.hadoop.mapreduce.TaskID; //导入依赖的package包/类
public void setDatum(Object oDatum) {
  this.datum = (TaskFinished)oDatum;
  this.taskid = TaskID.forName(datum.taskid.toString());
  if (datum.successfulAttemptId != null) {
    this.successfulAttemptId = TaskAttemptID
        .forName(datum.successfulAttemptId.toString());
  }
  this.finishTime = datum.finishTime;
  this.taskType = TaskType.valueOf(datum.taskType.toString());
  this.status = datum.status.toString();
  this.counters = EventReader.fromAvro(datum.counters);
}
 

import org.apache.hadoop.mapreduce.TaskID; //导入依赖的package包/类
private void printFailedAttempts(FilteredJob filteredJob) {
    Map<String, Set<TaskID>> badNodes = filteredJob.getFilteredMap();
    StringBuffer attempts = new StringBuffer();
    if (badNodes.size() > 0) {
      attempts.append("\n").append(filteredJob.getFilter());
      attempts.append(" task attempts by nodes");
      attempts.append("\nHostname\tFailedTasks");
      attempts.append("\n===============================");
      System.out.println(attempts.toString());
      for (Map.Entry<String, 
          Set<TaskID>> entry : badNodes.entrySet()) {
        String node = entry.getKey();
        Set<TaskID> failedTasks = entry.getValue();
        attempts.setLength(0);
        attempts.append(node).append("\t");
        for (TaskID t : failedTasks) {
          attempts.append(t).append(", ");
        }
        System.out.println(attempts.toString());
      }
    }
}
 

import org.apache.hadoop.mapreduce.TaskID; //导入依赖的package包/类
private void loadAllTasks() {
  if (tasksLoaded.get()) {
    return;
  }
  tasksLock.lock();
  try {
    if (tasksLoaded.get()) {
      return;
    }
    for (Map.Entry<TaskID, TaskInfo> entry : jobInfo.getAllTasks().entrySet()) {
      TaskId yarnTaskID = TypeConverter.toYarn(entry.getKey());
      TaskInfo taskInfo = entry.getValue();
      Task task = new CompletedTask(yarnTaskID, taskInfo);
      tasks.put(yarnTaskID, task);
      if (task.getType() == TaskType.MAP) {
        mapTasks.put(task.getID(), task);
      } else if (task.getType() == TaskType.REDUCE) {
        reduceTasks.put(task.getID(), task);
      }
    }
    tasksLoaded.set(true);
  } finally {
    tasksLock.unlock();
  }
}
 

import org.apache.hadoop.mapreduce.TaskID; //导入依赖的package包/类
private long computeFinishedMaps(JobInfo jobInfo, int numMaps,
    int numSuccessfulMaps) {
  if (numMaps == numSuccessfulMaps) {
    return jobInfo.getFinishedMaps();
  }

  long numFinishedMaps = 0;
  Map<org.apache.hadoop.mapreduce.TaskID, TaskInfo> taskInfos = jobInfo
      .getAllTasks();
  for (TaskInfo taskInfo : taskInfos.values()) {
    if (TaskState.SUCCEEDED.toString().equals(taskInfo.getTaskStatus())) {
      ++numFinishedMaps;
    }
  }
  return numFinishedMaps;
}
 

import org.apache.hadoop.mapreduce.TaskID; //导入依赖的package包/类
/**
 * test some methods of CompletedTaskAttempt
 */
@Test (timeout=5000)
public void testCompletedTaskAttempt(){
  
  TaskAttemptInfo attemptInfo= mock(TaskAttemptInfo.class);
  when(attemptInfo.getRackname()).thenReturn("Rackname");
  when(attemptInfo.getShuffleFinishTime()).thenReturn(11L);
  when(attemptInfo.getSortFinishTime()).thenReturn(12L);
  when(attemptInfo.getShufflePort()).thenReturn(10);
  
  JobID jobId= new JobID("12345",0);
  TaskID taskId =new TaskID(jobId,TaskType.REDUCE, 0);
  TaskAttemptID taskAttemptId= new TaskAttemptID(taskId, 0);
  when(attemptInfo.getAttemptId()).thenReturn(taskAttemptId);
  
  
  CompletedTaskAttempt taskAttemt= new CompletedTaskAttempt(null,attemptInfo);
  assertEquals( "Rackname",   taskAttemt.getNodeRackName());
  assertEquals( Phase.CLEANUP,   taskAttemt.getPhase());
  assertTrue(  taskAttemt.isFinished());
  assertEquals( 11L,   taskAttemt.getShuffleFinishTime());
  assertEquals( 12L,   taskAttemt.getSortFinishTime());
  assertEquals( 10,   taskAttemt.getShufflePort());
}
 

import org.apache.hadoop.mapreduce.TaskID; //导入依赖的package包/类
HistoryEvent maybeEmitEvent(ParsedLine line, String taskIDName,
    HistoryEventEmitter thatg) {
  if (taskIDName == null) {
    return null;
  }

  TaskID taskID = TaskID.forName(taskIDName);

  String taskType = line.get("TASK_TYPE");
  String startTime = line.get("START_TIME");
  String splits = line.get("SPLITS");

  if (startTime != null && taskType != null) {
    Task20LineHistoryEventEmitter that =
        (Task20LineHistoryEventEmitter) thatg;

    that.originalStartTime = Long.parseLong(startTime);
    that.originalTaskType =
        Version20LogInterfaceUtils.get20TaskType(taskType);

    return new TaskStartedEvent(taskID, that.originalStartTime,
        that.originalTaskType, splits);
  }

  return null;
}
 

import org.apache.hadoop.mapreduce.TaskID; //导入依赖的package包/类
/**
 * Mask the job ID part in a {@link TaskAttemptID}.
 * 
 * @param attemptId
 *          raw {@link TaskAttemptID} read from trace
 * @return masked {@link TaskAttemptID} with empty {@link JobID}.
 */
private TaskAttemptID maskAttemptID(TaskAttemptID attemptId) {
  JobID jobId = new JobID();
  TaskType taskType = attemptId.getTaskType();
  TaskID taskId = attemptId.getTaskID();
  return new TaskAttemptID(jobId.getJtIdentifier(), jobId.getId(), taskType,
      taskId.getId(), attemptId.getId());
}
 

import org.apache.hadoop.mapreduce.TaskID; //导入依赖的package包/类
public void setDatum(Object odatum) {
  this.datum = (TaskFailed)odatum;
  this.id =
      TaskID.forName(datum.getTaskid().toString());
  this.taskType =
      TaskType.valueOf(datum.getTaskType().toString());
  this.finishTime = datum.getFinishTime();
  this.error = datum.getError().toString();
  this.failedDueToAttempt =
      datum.getFailedDueToAttempt() == null
      ? null
      : TaskAttemptID.forName(
          datum.getFailedDueToAttempt().toString());
  this.status = datum.getStatus().toString();
  this.counters =
      EventReader.fromAvro(datum.getCounters());
}
 

import org.apache.hadoop.mapreduce.TaskID; //导入依赖的package包/类
HistoryEvent maybeEmitEvent(ParsedLine line, String taskIDName,
    HistoryEventEmitter thatg) {
  if (taskIDName == null) {
    return null;
  }

  TaskID taskID = TaskID.forName(taskIDName);

  String finishTime = line.get("FINISH_TIME");

  if (finishTime != null) {
    return new TaskUpdatedEvent(taskID, Long.parseLong(finishTime));
  }

  return null;
}
 

import org.apache.hadoop.mapreduce.TaskID; //导入依赖的package包/类
/**
 * Reassigns the chunk to a specified Map-Task, for consumption.
 *
 * @param taskId The Map-Task to which a the chunk is to be reassigned.
 * @throws IOException Exception on failure to reassign.
 */
public void assignTo(TaskID taskId) throws IOException {
  Path newPath = new Path(chunkRootPath, taskId.toString());
  if (!fs.rename(chunkFilePath, newPath)) {
    LOG.warn("{} could not be assigned to {}", chunkFilePath, taskId);
  }
}