/**
* Submit the job to the cluster and return immediately.
*
* @throws IOException
*/
public void submit() throws IOException, InterruptedException, ClassNotFoundException {
ensureState(JobState.DEFINE);
setUseNewAPI();
// Connect to the JobTracker and submit the job
connect();
info = jobClient.submitJobInternal(conf);
state = JobState.RUNNING;
}
/**
* Sets the flag that will allow the JobTracker to cancel the HDFS delegation tokens upon job
* completion. Defaults to true.
*/
public void setCancelDelegationTokenUponJobCompletion(boolean value) {
ensureState(JobState.DEFINE);
conf.setBoolean(JOB_CANCEL_DELEGATION_TOKEN, value);
}
/**
* Gets the counters for this job.
*
* @return the counters for this job.
* @throws IOException
*/
public Counters getCounters() throws IOException {
ensureState(JobState.RUNNING);
return new Counters(info.getCounters());
}
/**
* Fail indicated task attempt.
*
* @param taskId the id of the task to be terminated.
* @throws IOException
*/
public void failTask(TaskAttemptID taskId) throws IOException {
ensureState(JobState.RUNNING);
info.killTask(org.apache.hadoop.mapred.TaskAttemptID.downgrade(taskId), true);
}
/**
* Get events indicating completion (success/failure) of component tasks.
*
* @param startFrom index to start fetching events from
* @return an array of {@link TaskCompletionEvent}s
* @throws IOException
*/
public TaskCompletionEvent[] getTaskCompletionEvents(int startFrom) throws IOException {
ensureState(JobState.RUNNING);
return info.getTaskCompletionEvents(startFrom);
}
/**
* Kill the running job. Blocks until all job tasks have been killed as well. If the job is no
* longer running, it simply returns.
*
* @throws IOException
*/
public void killJob() throws IOException {
ensureState(JobState.RUNNING);
info.killJob();
}
/**
* Set the {@link Reducer} for the job.
*
* @param cls the <code>Reducer</code> to use
* @throws IllegalStateException if the job is submitted
*/
public void setReducerClass(Class<? extends Reducer> cls) throws IllegalStateException {
ensureState(JobState.DEFINE);
conf.setClass(REDUCE_CLASS_ATTR, cls, Reducer.class);
}
/**
* Set the current working directory for the default file system.
*
* @param dir the new current working directory.
* @throws IllegalStateException if the job is submitted
*/
public void setWorkingDirectory(Path dir) throws IOException {
ensureState(JobState.DEFINE);
conf.setWorkingDirectory(dir);
}
/**
* Get the <i>progress</i> of the job's reduce-tasks, as a float between 0.0 and 1.0. When all
* reduce tasks have completed, the function returns 1.0.
*
* @return the progress of the job's reduce-tasks.
* @throws IOException
*/
public float reduceProgress() throws IOException {
ensureState(JobState.RUNNING);
return info.reduceProgress();
}
/**
* Get the URL where some job progress information will be displayed.
*
* @return the URL where some job progress information will be displayed.
*/
public String getTrackingURL() {
ensureState(JobState.RUNNING);
return info.getTrackingURL();
}
/**
* Set the user-specified job name.
*
* @param name the job's new name.
* @throws IllegalStateException if the job is submitted
*/
public void setJobName(String name) throws IllegalStateException {
ensureState(JobState.DEFINE);
conf.setJobName(name);
}
/**
* Define the comparator that controls which keys are grouped together for a single call to {@link
* Reducer#reduce(Object, Iterable, org.apache.hadoop.mapreduce.Reducer.Context)}
*
* @param cls the raw comparator to use
* @throws IllegalStateException if the job is submitted
*/
public void setGroupingComparatorClass(Class<? extends RawComparator> cls)
throws IllegalStateException {
ensureState(JobState.DEFINE);
conf.setOutputValueGroupingComparator(cls);
}
/**
* Define the comparator that controls how the keys are sorted before they are passed to the
* {@link Reducer}.
*
* @param cls the raw comparator
* @throws IllegalStateException if the job is submitted
*/
public void setSortComparatorClass(Class<? extends RawComparator> cls)
throws IllegalStateException {
ensureState(JobState.DEFINE);
conf.setOutputKeyComparatorClass(cls);
}
/**
* Set the value class for job outputs.
*
* @param theClass the value class for job outputs.
* @throws IllegalStateException if the job is submitted
*/
public void setOutputValueClass(Class<?> theClass) throws IllegalStateException {
ensureState(JobState.DEFINE);
conf.setOutputValueClass(theClass);
}
/**
* Set the {@link Partitioner} for the job.
*
* @param cls the <code>Partitioner</code> to use
* @throws IllegalStateException if the job is submitted
*/
public void setPartitionerClass(Class<? extends Partitioner> cls) throws IllegalStateException {
ensureState(JobState.DEFINE);
conf.setClass(PARTITIONER_CLASS_ATTR, cls, Partitioner.class);
}
/**
* Check if the job is finished or not. This is a non-blocking call.
*
* @return <code>true</code> if the job is complete, else <code>false</code>.
* @throws IOException
*/
public boolean isComplete() throws IOException {
ensureState(JobState.RUNNING);
return info.isComplete();
}
/**
* Set the number of reduce tasks for the job.
*
* @param tasks the number of reduce tasks
* @throws IllegalStateException if the job is submitted
*/
public void setNumReduceTasks(int tasks) throws IllegalStateException {
ensureState(JobState.DEFINE);
conf.setNumReduceTasks(tasks);
}
/**
* Check if the job completed successfully.
*
* @return <code>true</code> if the job succeeded, else <code>false</code>.
* @throws IOException
*/
public boolean isSuccessful() throws IOException {
ensureState(JobState.RUNNING);
return info.isSuccessful();
}
/**
* Set the {@link InputFormat} for the job.
*
* @param cls the <code>InputFormat</code> to use
* @throws IllegalStateException if the job is submitted
*/
public void setInputFormatClass(Class<? extends InputFormat> cls) throws IllegalStateException {
ensureState(JobState.DEFINE);
conf.setClass(INPUT_FORMAT_CLASS_ATTR, cls, InputFormat.class);
}
/**
* Set the {@link Mapper} for the job.
*
* @param cls the <code>Mapper</code> to use
* @throws IllegalStateException if the job is submitted
*/
public void setMapperClass(Class<? extends Mapper> cls) throws IllegalStateException {
ensureState(JobState.DEFINE);
conf.setClass(MAP_CLASS_ATTR, cls, Mapper.class);
}