Examples with TimeoutException java.util.concurrent.TimeoutException used on opensource projects

Example 6 with TimeoutException

use of java.util.concurrent.TimeoutException in project flink by apache.

the class TaskExecutor method offerSlotsToJobManager.

// ------------------------------------------------------------------------
//  Internal job manager connection methods
// ------------------------------------------------------------------------
private void offerSlotsToJobManager(final JobID jobId) {
    final JobManagerConnection jobManagerConnection = jobManagerTable.get(jobId);
    if (jobManagerConnection == null) {
        log.debug("There is no job manager connection to the leader of job {}.", jobId);
    } else {
        if (taskSlotTable.hasAllocatedSlots(jobId)) {
            log.info("Offer reserved slots to the leader of job {}.", jobId);
            final JobMasterGateway jobMasterGateway = jobManagerConnection.getJobManagerGateway();
            final Iterator<TaskSlot> reservedSlotsIterator = taskSlotTable.getAllocatedSlots(jobId);
            final UUID leaderId = jobManagerConnection.getLeaderId();
            final Collection<SlotOffer> reservedSlots = new HashSet<>(2);
            while (reservedSlotsIterator.hasNext()) {
                SlotOffer offer = reservedSlotsIterator.next().generateSlotOffer();
                try {
                    if (!taskSlotTable.markSlotActive(offer.getAllocationId())) {
                        // the slot is either free or releasing at the moment
                        final String message = "Could not mark slot " + jobId + " active.";
                        log.debug(message);
                        jobMasterGateway.failSlot(getResourceID(), offer.getAllocationId(), leaderId, new Exception(message));
                    }
                } catch (SlotNotFoundException e) {
                    final String message = "Could not mark slot " + jobId + " active.";
                    jobMasterGateway.failSlot(getResourceID(), offer.getAllocationId(), leaderId, new Exception(message));
                    continue;
                }
                reservedSlots.add(offer);
            }
            Future<Iterable<SlotOffer>> acceptedSlotsFuture = jobMasterGateway.offerSlots(getResourceID(), reservedSlots, leaderId, taskManagerConfiguration.getTimeout());
            acceptedSlotsFuture.thenAcceptAsync(new AcceptFunction<Iterable<SlotOffer>>() {

                @Override
                public void accept(Iterable<SlotOffer> acceptedSlots) {
                    // check if the response is still valid
                    if (isJobManagerConnectionValid(jobId, leaderId)) {
                        // mark accepted slots active
                        for (SlotOffer acceptedSlot : acceptedSlots) {
                            reservedSlots.remove(acceptedSlot);
                        }
                        final Exception e = new Exception("The slot was rejected by the JobManager.");
                        for (SlotOffer rejectedSlot : reservedSlots) {
                            freeSlot(rejectedSlot.getAllocationId(), e);
                        }
                    } else {
                        // discard the response since there is a new leader for the job
                        log.debug("Discard offer slot response since there is a new leader " + "for the job {}.", jobId);
                    }
                }
            }, getMainThreadExecutor());
            acceptedSlotsFuture.exceptionallyAsync(new ApplyFunction<Throwable, Void>() {

                @Override
                public Void apply(Throwable throwable) {
                    if (throwable instanceof TimeoutException) {
                        // We ran into a timeout. Try again.
                        offerSlotsToJobManager(jobId);
                    } else {
                        // We encountered an exception. Free the slots and return them to the RM.
                        for (SlotOffer reservedSlot : reservedSlots) {
                            freeSlot(reservedSlot.getAllocationId(), throwable);
                        }
                    }
                    return null;
                }
            }, getMainThreadExecutor());
        } else {
            log.debug("There are no unassigned slots for the job {}.", jobId);
        }
    }
}

Example 7 with TimeoutException

use of java.util.concurrent.TimeoutException in project flink by apache.

the class TestingListener method waitForNewLeader.

public String waitForNewLeader(long timeout) throws Exception {
    long start = System.currentTimeMillis();
    long curTimeout;
    while (exception == null && (address == null || address.equals(oldAddress)) && (curTimeout = timeout - System.currentTimeMillis() + start) > 0) {
        synchronized (lock) {
            try {
                lock.wait(curTimeout);
            } catch (InterruptedException e) {
            // we got interrupted so check again for the condition
            }
        }
    }
    if (exception != null) {
        throw exception;
    } else if (address == null || address.equals(oldAddress)) {
        throw new TimeoutException("Listener was not notified about a leader within " + timeout + "ms");
    }
    oldAddress = address;
    return address;
}

Example 8 with TimeoutException

use of java.util.concurrent.TimeoutException in project flink by apache.

the class JobClient method submitJobDetached.

/**
	 * Submits a job in detached mode. The method sends the JobGraph to the
	 * JobManager and waits for the answer whether the job could be started or not.
	 *
	 * @param jobManagerGateway Gateway to the JobManager which will execute the jobs
	 * @param config The cluster wide configuration.
	 * @param jobGraph The job
	 * @param timeout  Timeout in which the JobManager must have responded.
	 */
public static void submitJobDetached(ActorGateway jobManagerGateway, Configuration config, JobGraph jobGraph, FiniteDuration timeout, ClassLoader classLoader) throws JobExecutionException {
    checkNotNull(jobManagerGateway, "The jobManagerGateway must not be null.");
    checkNotNull(jobGraph, "The jobGraph must not be null.");
    checkNotNull(timeout, "The timeout must not be null.");
    LOG.info("Checking and uploading JAR files");
    try {
        jobGraph.uploadUserJars(jobManagerGateway, timeout, config);
    } catch (IOException e) {
        throw new JobSubmissionException(jobGraph.getJobID(), "Could not upload the program's JAR files to the JobManager.", e);
    }
    Object result;
    try {
        Future<Object> future = jobManagerGateway.ask(new JobManagerMessages.SubmitJob(jobGraph, // only receive the Acknowledge for the job submission message
        ListeningBehaviour.DETACHED), timeout);
        result = Await.result(future, timeout);
    } catch (TimeoutException e) {
        throw new JobTimeoutException(jobGraph.getJobID(), "JobManager did not respond within " + timeout.toString(), e);
    } catch (Throwable t) {
        throw new JobSubmissionException(jobGraph.getJobID(), "Failed to send job to JobManager: " + t.getMessage(), t.getCause());
    }
    if (result instanceof JobManagerMessages.JobSubmitSuccess) {
        JobID respondedID = ((JobManagerMessages.JobSubmitSuccess) result).jobId();
        // validate response
        if (!respondedID.equals(jobGraph.getJobID())) {
            throw new JobExecutionException(jobGraph.getJobID(), "JobManager responded for wrong Job. This Job: " + jobGraph.getJobID() + ", response: " + respondedID);
        }
    } else if (result instanceof JobManagerMessages.JobResultFailure) {
        try {
            SerializedThrowable t = ((JobManagerMessages.JobResultFailure) result).cause();
            throw t.deserializeError(classLoader);
        } catch (JobExecutionException e) {
            throw e;
        } catch (Throwable t) {
            throw new JobExecutionException(jobGraph.getJobID(), "JobSubmission failed: " + t.getMessage(), t);
        }
    } else {
        throw new JobExecutionException(jobGraph.getJobID(), "Unexpected response from JobManager: " + result);
    }
}

Example 9 with TimeoutException

use of java.util.concurrent.TimeoutException in project flink by apache.

the class JobClient method awaitJobResult.

/**
	 * Given a JobListeningContext, awaits the result of the job execution that this context is bound to
	 * @param listeningContext The listening context of the job execution
	 * @return The result of the execution
	 * @throws JobExecutionException if anything goes wrong while monitoring the job
	 */
public static JobExecutionResult awaitJobResult(JobListeningContext listeningContext) throws JobExecutionException {
    final JobID jobID = listeningContext.getJobID();
    final ActorRef jobClientActor = listeningContext.getJobClientActor();
    final Future<Object> jobSubmissionFuture = listeningContext.getJobResultFuture();
    final FiniteDuration askTimeout = listeningContext.getTimeout();
    // retrieves class loader if necessary
    final ClassLoader classLoader = listeningContext.getClassLoader();
    // ping the JobClientActor from time to time to check if it is still running
    while (!jobSubmissionFuture.isCompleted()) {
        try {
            Await.ready(jobSubmissionFuture, askTimeout);
        } catch (InterruptedException e) {
            throw new JobExecutionException(jobID, "Interrupted while waiting for job completion.");
        } catch (TimeoutException e) {
            try {
                Await.result(Patterns.ask(jobClientActor, // Ping the Actor to see if it is alive
                new Identify(true), Timeout.durationToTimeout(askTimeout)), askTimeout);
            // we got a reply, continue waiting for the job result
            } catch (Exception eInner) {
                // thus the health check failed
                if (!jobSubmissionFuture.isCompleted()) {
                    throw new JobExecutionException(jobID, "JobClientActor seems to have died before the JobExecutionResult could be retrieved.", eInner);
                }
            }
        }
    }
    final Object answer;
    try {
        // we have already awaited the result, zero time to wait here
        answer = Await.result(jobSubmissionFuture, Duration.Zero());
    } catch (Throwable throwable) {
        throw new JobExecutionException(jobID, "Couldn't retrieve the JobExecutionResult from the JobManager.", throwable);
    } finally {
        // failsafe shutdown of the client actor
        jobClientActor.tell(PoisonPill.getInstance(), ActorRef.noSender());
    }
    // second block handles the actual response
    if (answer instanceof JobManagerMessages.JobResultSuccess) {
        LOG.info("Job execution complete");
        SerializedJobExecutionResult result = ((JobManagerMessages.JobResultSuccess) answer).result();
        if (result != null) {
            try {
                return result.toJobExecutionResult(classLoader);
            } catch (Throwable t) {
                throw new JobExecutionException(jobID, "Job was successfully executed but JobExecutionResult could not be deserialized.");
            }
        } else {
            throw new JobExecutionException(jobID, "Job was successfully executed but result contained a null JobExecutionResult.");
        }
    } else if (answer instanceof JobManagerMessages.JobResultFailure) {
        LOG.info("Job execution failed");
        SerializedThrowable serThrowable = ((JobManagerMessages.JobResultFailure) answer).cause();
        if (serThrowable != null) {
            Throwable cause = serThrowable.deserializeError(classLoader);
            if (cause instanceof JobExecutionException) {
                throw (JobExecutionException) cause;
            } else {
                throw new JobExecutionException(jobID, "Job execution failed", cause);
            }
        } else {
            throw new JobExecutionException(jobID, "Job execution failed with null as failure cause.");
        }
    } else if (answer instanceof JobManagerMessages.JobNotFound) {
        throw new JobRetrievalException(((JobManagerMessages.JobNotFound) answer).jobID(), "Couldn't retrieve Job " + jobID + " because it was not running.");
    } else {
        throw new JobExecutionException(jobID, "Unknown answer from JobManager after submitting the job: " + answer);
    }
}

Example 10 with TimeoutException

use of java.util.concurrent.TimeoutException in project flink by apache.

the class Execution method deployToSlot.

public void deployToSlot(final SimpleSlot slot) throws JobException {
    checkNotNull(slot);
    // The more general check is the timeout of the deployment call
    if (!slot.isAlive()) {
        throw new JobException("Target slot (TaskManager) for deployment is no longer alive.");
    }
    // make sure exactly one deployment call happens from the correct state
    // note: the transition from CREATED to DEPLOYING is for testing purposes only
    ExecutionState previous = this.state;
    if (previous == SCHEDULED || previous == CREATED) {
        if (!transitionState(previous, DEPLOYING)) {
            // this should actually not happen and indicates a race somewhere else
            throw new IllegalStateException("Cannot deploy task: Concurrent deployment call race.");
        }
    } else {
        // vertex may have been cancelled, or it was already scheduled
        throw new IllegalStateException("The vertex must be in CREATED or SCHEDULED state to be deployed. Found state " + previous);
    }
    try {
        // good, we are allowed to deploy
        if (!slot.setExecutedVertex(this)) {
            throw new JobException("Could not assign the ExecutionVertex to the slot " + slot);
        }
        this.assignedResource = slot;
        // race double check, did we fail/cancel and do we need to release the slot?
        if (this.state != DEPLOYING) {
            slot.releaseSlot();
            return;
        }
        if (LOG.isInfoEnabled()) {
            LOG.info(String.format("Deploying %s (attempt #%d) to %s", vertex.getSimpleName(), attemptNumber, getAssignedResourceLocation().getHostname()));
        }
        final TaskDeploymentDescriptor deployment = vertex.createDeploymentDescriptor(attemptId, slot, taskState, attemptNumber);
        // register this execution at the execution graph, to receive call backs
        vertex.getExecutionGraph().registerExecution(this);
        final TaskManagerGateway taskManagerGateway = slot.getTaskManagerGateway();
        final Future<Acknowledge> submitResultFuture = taskManagerGateway.submitTask(deployment, timeout);
        submitResultFuture.exceptionallyAsync(new ApplyFunction<Throwable, Void>() {

            @Override
            public Void apply(Throwable failure) {
                if (failure instanceof TimeoutException) {
                    String taskname = vertex.getTaskNameWithSubtaskIndex() + " (" + attemptId + ')';
                    markFailed(new Exception("Cannot deploy task " + taskname + " - TaskManager (" + getAssignedResourceLocation() + ") not responding after a timeout of " + timeout, failure));
                } else {
                    markFailed(failure);
                }
                return null;
            }
        }, executor);
    } catch (Throwable t) {
        markFailed(t);
        ExceptionUtils.rethrow(t);
    }
}