Search in sources :

Example 11 with StatefulTask

use of org.apache.flink.runtime.jobgraph.tasks.StatefulTask in project flink by apache.

the class Task method run.

/**
	 * The core work method that bootstraps the task and executes it code
	 */
@Override
public void run() {
    // ----------------------------
    while (true) {
        ExecutionState current = this.executionState;
        if (current == ExecutionState.CREATED) {
            if (transitionState(ExecutionState.CREATED, ExecutionState.DEPLOYING)) {
                // success, we can start our work
                break;
            }
        } else if (current == ExecutionState.FAILED) {
            // we were immediately failed. tell the TaskManager that we reached our final state
            notifyFinalState();
            return;
        } else if (current == ExecutionState.CANCELING) {
            if (transitionState(ExecutionState.CANCELING, ExecutionState.CANCELED)) {
                // we were immediately canceled. tell the TaskManager that we reached our final state
                notifyFinalState();
                return;
            }
        } else {
            throw new IllegalStateException("Invalid state for beginning of operation of task " + this + '.');
        }
    }
    // all resource acquisitions and registrations from here on
    // need to be undone in the end
    Map<String, Future<Path>> distributedCacheEntries = new HashMap<String, Future<Path>>();
    AbstractInvokable invokable = null;
    ClassLoader userCodeClassLoader;
    try {
        // ----------------------------
        //  Task Bootstrap - We periodically
        //  check for canceling as a shortcut
        // ----------------------------
        // activate safety net for task thread
        LOG.info("Creating FileSystem stream leak safety net for task {}", this);
        FileSystemSafetyNet.initializeSafetyNetForThread();
        // first of all, get a user-code classloader
        // this may involve downloading the job's JAR files and/or classes
        LOG.info("Loading JAR files for task {}.", this);
        userCodeClassLoader = createUserCodeClassloader(libraryCache);
        final ExecutionConfig executionConfig = serializedExecutionConfig.deserializeValue(userCodeClassLoader);
        if (executionConfig.getTaskCancellationInterval() >= 0) {
            // override task cancellation interval from Flink config if set in ExecutionConfig
            taskCancellationInterval = executionConfig.getTaskCancellationInterval();
        }
        if (executionConfig.getTaskCancellationTimeout() >= 0) {
            // override task cancellation timeout from Flink config if set in ExecutionConfig
            taskCancellationTimeout = executionConfig.getTaskCancellationTimeout();
        }
        // now load the task's invokable code
        invokable = loadAndInstantiateInvokable(userCodeClassLoader, nameOfInvokableClass);
        if (isCanceledOrFailed()) {
            throw new CancelTaskException();
        }
        // ----------------------------------------------------------------
        // register the task with the network stack
        // this operation may fail if the system does not have enough
        // memory to run the necessary data exchanges
        // the registration must also strictly be undone
        // ----------------------------------------------------------------
        LOG.info("Registering task at network: {}.", this);
        network.registerTask(this);
        // next, kick off the background copying of files for the distributed cache
        try {
            for (Map.Entry<String, DistributedCache.DistributedCacheEntry> entry : DistributedCache.readFileInfoFromConfig(jobConfiguration)) {
                LOG.info("Obtaining local cache file for '{}'.", entry.getKey());
                Future<Path> cp = fileCache.createTmpFile(entry.getKey(), entry.getValue(), jobId);
                distributedCacheEntries.put(entry.getKey(), cp);
            }
        } catch (Exception e) {
            throw new Exception(String.format("Exception while adding files to distributed cache of task %s (%s).", taskNameWithSubtask, executionId), e);
        }
        if (isCanceledOrFailed()) {
            throw new CancelTaskException();
        }
        // ----------------------------------------------------------------
        //  call the user code initialization methods
        // ----------------------------------------------------------------
        TaskKvStateRegistry kvStateRegistry = network.createKvStateTaskRegistry(jobId, getJobVertexId());
        Environment env = new RuntimeEnvironment(jobId, vertexId, executionId, executionConfig, taskInfo, jobConfiguration, taskConfiguration, userCodeClassLoader, memoryManager, ioManager, broadcastVariableManager, accumulatorRegistry, kvStateRegistry, inputSplitProvider, distributedCacheEntries, writers, inputGates, checkpointResponder, taskManagerConfig, metrics, this);
        // let the task code create its readers and writers
        invokable.setEnvironment(env);
        if (null != taskStateHandles) {
            if (invokable instanceof StatefulTask) {
                StatefulTask op = (StatefulTask) invokable;
                op.setInitialState(taskStateHandles);
            } else {
                throw new IllegalStateException("Found operator state for a non-stateful task invokable");
            }
            // be memory and GC friendly - since the code stays in invoke() for a potentially long time,
            // we clear the reference to the state handle
            //noinspection UnusedAssignment
            taskStateHandles = null;
        }
        // ----------------------------------------------------------------
        //  actual task core work
        // ----------------------------------------------------------------
        // we must make strictly sure that the invokable is accessible to the cancel() call
        // by the time we switched to running.
        this.invokable = invokable;
        // switch to the RUNNING state, if that fails, we have been canceled/failed in the meantime
        if (!transitionState(ExecutionState.DEPLOYING, ExecutionState.RUNNING)) {
            throw new CancelTaskException();
        }
        // notify everyone that we switched to running
        notifyObservers(ExecutionState.RUNNING, null);
        taskManagerActions.updateTaskExecutionState(new TaskExecutionState(jobId, executionId, ExecutionState.RUNNING));
        // make sure the user code classloader is accessible thread-locally
        executingThread.setContextClassLoader(userCodeClassLoader);
        // run the invokable
        invokable.invoke();
        // to the fact that it has been canceled
        if (isCanceledOrFailed()) {
            throw new CancelTaskException();
        }
        // finish the produced partitions. if this fails, we consider the execution failed.
        for (ResultPartition partition : producedPartitions) {
            if (partition != null) {
                partition.finish();
            }
        }
        // if that fails, the task was canceled/failed in the meantime
        if (transitionState(ExecutionState.RUNNING, ExecutionState.FINISHED)) {
            notifyObservers(ExecutionState.FINISHED, null);
        } else {
            throw new CancelTaskException();
        }
    } catch (Throwable t) {
        try {
            // check if the exception is unrecoverable
            if (ExceptionUtils.isJvmFatalError(t) || (t instanceof OutOfMemoryError && taskManagerConfig.shouldExitJvmOnOutOfMemoryError())) {
                // don't attempt a clean shutdown, because we cannot expect the clean shutdown to complete
                try {
                    LOG.error("Encountered fatal error {} - terminating the JVM", t.getClass().getName(), t);
                } finally {
                    Runtime.getRuntime().halt(-1);
                }
            }
            // to failExternally()
            while (true) {
                ExecutionState current = this.executionState;
                if (current == ExecutionState.RUNNING || current == ExecutionState.DEPLOYING) {
                    if (t instanceof CancelTaskException) {
                        if (transitionState(current, ExecutionState.CANCELED)) {
                            cancelInvokable();
                            notifyObservers(ExecutionState.CANCELED, null);
                            break;
                        }
                    } else {
                        if (transitionState(current, ExecutionState.FAILED, t)) {
                            // proper failure of the task. record the exception as the root cause
                            String errorMessage = String.format("Execution of %s (%s) failed.", taskNameWithSubtask, executionId);
                            failureCause = t;
                            cancelInvokable();
                            notifyObservers(ExecutionState.FAILED, new Exception(errorMessage, t));
                            break;
                        }
                    }
                } else if (current == ExecutionState.CANCELING) {
                    if (transitionState(current, ExecutionState.CANCELED)) {
                        notifyObservers(ExecutionState.CANCELED, null);
                        break;
                    }
                } else if (current == ExecutionState.FAILED) {
                    // in state failed already, no transition necessary any more
                    break;
                } else // unexpected state, go to failed
                if (transitionState(current, ExecutionState.FAILED, t)) {
                    LOG.error("Unexpected state in task {} ({}) during an exception: {}.", taskNameWithSubtask, executionId, current);
                    break;
                }
            // else fall through the loop and
            }
        } catch (Throwable tt) {
            String message = String.format("FATAL - exception in exception handler of task %s (%s).", taskNameWithSubtask, executionId);
            LOG.error(message, tt);
            notifyFatalError(message, tt);
        }
    } finally {
        try {
            LOG.info("Freeing task resources for {} ({}).", taskNameWithSubtask, executionId);
            // stop the async dispatcher.
            // copy dispatcher reference to stack, against concurrent release
            ExecutorService dispatcher = this.asyncCallDispatcher;
            if (dispatcher != null && !dispatcher.isShutdown()) {
                dispatcher.shutdownNow();
            }
            // free the network resources
            network.unregisterTask(this);
            // free memory resources
            if (invokable != null) {
                memoryManager.releaseAll(invokable);
            }
            // remove all of the tasks library resources
            libraryCache.unregisterTask(jobId, executionId);
            // remove all files in the distributed cache
            removeCachedFiles(distributedCacheEntries, fileCache);
            // close and de-activate safety net for task thread
            LOG.info("Ensuring all FileSystem streams are closed for task {}", this);
            FileSystemSafetyNet.closeSafetyNetAndGuardedResourcesForThread();
            notifyFinalState();
        } catch (Throwable t) {
            // an error in the resource cleanup is fatal
            String message = String.format("FATAL - exception in resource cleanup of task %s (%s).", taskNameWithSubtask, executionId);
            LOG.error(message, t);
            notifyFatalError(message, t);
        }
        // errors here will only be logged
        try {
            metrics.close();
        } catch (Throwable t) {
            LOG.error("Error during metrics de-registration of task {} ({}).", taskNameWithSubtask, executionId, t);
        }
    }
}
Also used : ExecutionState(org.apache.flink.runtime.execution.ExecutionState) HashMap(java.util.HashMap) TaskKvStateRegistry(org.apache.flink.runtime.query.TaskKvStateRegistry) ExecutionConfig(org.apache.flink.api.common.ExecutionConfig) AbstractInvokable(org.apache.flink.runtime.jobgraph.tasks.AbstractInvokable) Path(org.apache.flink.core.fs.Path) CheckpointDeclineTaskNotCheckpointingException(org.apache.flink.runtime.checkpoint.decline.CheckpointDeclineTaskNotCheckpointingException) TimeoutException(java.util.concurrent.TimeoutException) CancelTaskException(org.apache.flink.runtime.execution.CancelTaskException) RejectedExecutionException(java.util.concurrent.RejectedExecutionException) PartitionProducerDisposedException(org.apache.flink.runtime.jobmanager.PartitionProducerDisposedException) CheckpointDeclineTaskNotReadyException(org.apache.flink.runtime.checkpoint.decline.CheckpointDeclineTaskNotReadyException) IOException(java.io.IOException) ResultPartition(org.apache.flink.runtime.io.network.partition.ResultPartition) StatefulTask(org.apache.flink.runtime.jobgraph.tasks.StatefulTask) CancelTaskException(org.apache.flink.runtime.execution.CancelTaskException) ExecutorService(java.util.concurrent.ExecutorService) Future(java.util.concurrent.Future) Environment(org.apache.flink.runtime.execution.Environment) NetworkEnvironment(org.apache.flink.runtime.io.network.NetworkEnvironment) Map(java.util.Map) HashMap(java.util.HashMap)

Example 12 with StatefulTask

use of org.apache.flink.runtime.jobgraph.tasks.StatefulTask in project flink by apache.

the class Task method triggerCheckpointBarrier.

// ------------------------------------------------------------------------
//  Notifications on the invokable
// ------------------------------------------------------------------------
/**
	 * Calls the invokable to trigger a checkpoint, if the invokable implements the interface
	 * {@link StatefulTask}.
	 * 
	 * @param checkpointID The ID identifying the checkpoint.
	 * @param checkpointTimestamp The timestamp associated with the checkpoint.
	 * @param checkpointOptions Options for performing this checkpoint.
	 */
public void triggerCheckpointBarrier(final long checkpointID, long checkpointTimestamp, final CheckpointOptions checkpointOptions) {
    final AbstractInvokable invokable = this.invokable;
    final CheckpointMetaData checkpointMetaData = new CheckpointMetaData(checkpointID, checkpointTimestamp);
    if (executionState == ExecutionState.RUNNING && invokable != null) {
        if (invokable instanceof StatefulTask) {
            // build a local closure
            final StatefulTask statefulTask = (StatefulTask) invokable;
            final String taskName = taskNameWithSubtask;
            Runnable runnable = new Runnable() {

                @Override
                public void run() {
                    // activate safety net for checkpointing thread
                    LOG.debug("Creating FileSystem stream leak safety net for {}", Thread.currentThread().getName());
                    FileSystemSafetyNet.initializeSafetyNetForThread();
                    try {
                        boolean success = statefulTask.triggerCheckpoint(checkpointMetaData, checkpointOptions);
                        if (!success) {
                            checkpointResponder.declineCheckpoint(getJobID(), getExecutionId(), checkpointID, new CheckpointDeclineTaskNotReadyException(taskName));
                        }
                    } catch (Throwable t) {
                        if (getExecutionState() == ExecutionState.RUNNING) {
                            failExternally(new Exception("Error while triggering checkpoint " + checkpointID + " for " + taskNameWithSubtask, t));
                        } else {
                            LOG.debug("Encountered error while triggering checkpoint {} for " + "{} ({}) while being not in state running.", checkpointID, taskNameWithSubtask, executionId, t);
                        }
                    } finally {
                        // close and de-activate safety net for checkpointing thread
                        LOG.debug("Ensuring all FileSystem streams are closed for {}", Thread.currentThread().getName());
                        FileSystemSafetyNet.closeSafetyNetAndGuardedResourcesForThread();
                    }
                }
            };
            executeAsyncCallRunnable(runnable, String.format("Checkpoint Trigger for %s (%s).", taskNameWithSubtask, executionId));
        } else {
            checkpointResponder.declineCheckpoint(jobId, executionId, checkpointID, new CheckpointDeclineTaskNotCheckpointingException(taskNameWithSubtask));
            LOG.error("Task received a checkpoint request, but is not a checkpointing task - {} ({}).", taskNameWithSubtask, executionId);
        }
    } else {
        LOG.debug("Declining checkpoint request for non-running task {} ({}).", taskNameWithSubtask, executionId);
        // send back a message that we did not do the checkpoint
        checkpointResponder.declineCheckpoint(jobId, executionId, checkpointID, new CheckpointDeclineTaskNotReadyException(taskNameWithSubtask));
    }
}
Also used : StatefulTask(org.apache.flink.runtime.jobgraph.tasks.StatefulTask) CheckpointDeclineTaskNotCheckpointingException(org.apache.flink.runtime.checkpoint.decline.CheckpointDeclineTaskNotCheckpointingException) CheckpointDeclineTaskNotReadyException(org.apache.flink.runtime.checkpoint.decline.CheckpointDeclineTaskNotReadyException) CheckpointMetaData(org.apache.flink.runtime.checkpoint.CheckpointMetaData) AbstractInvokable(org.apache.flink.runtime.jobgraph.tasks.AbstractInvokable) CheckpointDeclineTaskNotCheckpointingException(org.apache.flink.runtime.checkpoint.decline.CheckpointDeclineTaskNotCheckpointingException) TimeoutException(java.util.concurrent.TimeoutException) CancelTaskException(org.apache.flink.runtime.execution.CancelTaskException) RejectedExecutionException(java.util.concurrent.RejectedExecutionException) PartitionProducerDisposedException(org.apache.flink.runtime.jobmanager.PartitionProducerDisposedException) CheckpointDeclineTaskNotReadyException(org.apache.flink.runtime.checkpoint.decline.CheckpointDeclineTaskNotReadyException) IOException(java.io.IOException)

Aggregations

StatefulTask (org.apache.flink.runtime.jobgraph.tasks.StatefulTask)12 BufferOrEvent (org.apache.flink.runtime.io.network.partition.consumer.BufferOrEvent)9 Test (org.junit.Test)9 CheckpointMetrics (org.apache.flink.runtime.checkpoint.CheckpointMetrics)8 CheckpointOptions (org.apache.flink.runtime.checkpoint.CheckpointOptions)8 CheckpointMetaData (org.apache.flink.runtime.checkpoint.CheckpointMetaData)5 CheckpointDeclineOnCancellationBarrierException (org.apache.flink.runtime.checkpoint.decline.CheckpointDeclineOnCancellationBarrierException)5 AbstractInvokable (org.apache.flink.runtime.jobgraph.tasks.AbstractInvokable)3 IOException (java.io.IOException)2 RejectedExecutionException (java.util.concurrent.RejectedExecutionException)2 TimeoutException (java.util.concurrent.TimeoutException)2 AlignmentLimitExceededException (org.apache.flink.runtime.checkpoint.decline.AlignmentLimitExceededException)2 CheckpointDeclineSubsumedException (org.apache.flink.runtime.checkpoint.decline.CheckpointDeclineSubsumedException)2 CheckpointDeclineTaskNotCheckpointingException (org.apache.flink.runtime.checkpoint.decline.CheckpointDeclineTaskNotCheckpointingException)2 CheckpointDeclineTaskNotReadyException (org.apache.flink.runtime.checkpoint.decline.CheckpointDeclineTaskNotReadyException)2 CancelTaskException (org.apache.flink.runtime.execution.CancelTaskException)2 PartitionProducerDisposedException (org.apache.flink.runtime.jobmanager.PartitionProducerDisposedException)2 HashMap (java.util.HashMap)1 Map (java.util.Map)1 ExecutorService (java.util.concurrent.ExecutorService)1