Examples with InputSplitProvider org.apache.flink.runtime.jobgraph.tasks.InputSplitProvider used on opensource projects

Example 1 with InputSplitProvider

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

the class DataSourceTask method getInputSplits.

private Iterator<InputSplit> getInputSplits() {
    final InputSplitProvider provider = getEnvironment().getInputSplitProvider();
    return new Iterator<InputSplit>() {

        private InputSplit nextSplit;

        private boolean exhausted;

        @Override
        public boolean hasNext() {
            if (exhausted) {
                return false;
            }
            if (nextSplit != null) {
                return true;
            }
            final InputSplit split;
            try {
                split = provider.getNextInputSplit(getUserCodeClassLoader());
            } catch (InputSplitProviderException e) {
                throw new RuntimeException("Could not retrieve next input split.", e);
            }
            if (split != null) {
                this.nextSplit = split;
                return true;
            } else {
                exhausted = true;
                return false;
            }
        }

        @Override
        public InputSplit next() {
            if (this.nextSplit == null && !hasNext()) {
                throw new NoSuchElementException();
            }
            final InputSplit tmp = this.nextSplit;
            this.nextSplit = null;
            return tmp;
        }

        @Override
        public void remove() {
            throw new UnsupportedOperationException();
        }
    };
}

Example 2 with InputSplitProvider

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

the class TaskExecutor method submitTask.

// ----------------------------------------------------------------------
// Task lifecycle RPCs
// ----------------------------------------------------------------------
@Override
public CompletableFuture<Acknowledge> submitTask(TaskDeploymentDescriptor tdd, JobMasterId jobMasterId, Time timeout) {
    try {
        final JobID jobId = tdd.getJobId();
        final ExecutionAttemptID executionAttemptID = tdd.getExecutionAttemptId();
        final JobTable.Connection jobManagerConnection = jobTable.getConnection(jobId).orElseThrow(() -> {
            final String message = "Could not submit task because there is no JobManager " + "associated for the job " + jobId + '.';
            log.debug(message);
            return new TaskSubmissionException(message);
        });
        if (!Objects.equals(jobManagerConnection.getJobMasterId(), jobMasterId)) {
            final String message = "Rejecting the task submission because the job manager leader id " + jobMasterId + " does not match the expected job manager leader id " + jobManagerConnection.getJobMasterId() + '.';
            log.debug(message);
            throw new TaskSubmissionException(message);
        }
        if (!taskSlotTable.tryMarkSlotActive(jobId, tdd.getAllocationId())) {
            final String message = "No task slot allocated for job ID " + jobId + " and allocation ID " + tdd.getAllocationId() + '.';
            log.debug(message);
            throw new TaskSubmissionException(message);
        }
        // re-integrate offloaded data:
        try {
            tdd.loadBigData(taskExecutorBlobService.getPermanentBlobService());
        } catch (IOException | ClassNotFoundException e) {
            throw new TaskSubmissionException("Could not re-integrate offloaded TaskDeploymentDescriptor data.", e);
        }
        // deserialize the pre-serialized information
        final JobInformation jobInformation;
        final TaskInformation taskInformation;
        try {
            jobInformation = tdd.getSerializedJobInformation().deserializeValue(getClass().getClassLoader());
            taskInformation = tdd.getSerializedTaskInformation().deserializeValue(getClass().getClassLoader());
        } catch (IOException | ClassNotFoundException e) {
            throw new TaskSubmissionException("Could not deserialize the job or task information.", e);
        }
        if (!jobId.equals(jobInformation.getJobId())) {
            throw new TaskSubmissionException("Inconsistent job ID information inside TaskDeploymentDescriptor (" + tdd.getJobId() + " vs. " + jobInformation.getJobId() + ")");
        }
        TaskManagerJobMetricGroup jobGroup = taskManagerMetricGroup.addJob(jobInformation.getJobId(), jobInformation.getJobName());
        // note that a pre-existing job group can NOT be closed concurrently - this is done by
        // the same TM thread in removeJobMetricsGroup
        TaskMetricGroup taskMetricGroup = jobGroup.addTask(taskInformation.getJobVertexId(), tdd.getExecutionAttemptId(), taskInformation.getTaskName(), tdd.getSubtaskIndex(), tdd.getAttemptNumber());
        InputSplitProvider inputSplitProvider = new RpcInputSplitProvider(jobManagerConnection.getJobManagerGateway(), taskInformation.getJobVertexId(), tdd.getExecutionAttemptId(), taskManagerConfiguration.getRpcTimeout());
        final TaskOperatorEventGateway taskOperatorEventGateway = new RpcTaskOperatorEventGateway(jobManagerConnection.getJobManagerGateway(), executionAttemptID, (t) -> runAsync(() -> failTask(executionAttemptID, t)));
        TaskManagerActions taskManagerActions = jobManagerConnection.getTaskManagerActions();
        CheckpointResponder checkpointResponder = jobManagerConnection.getCheckpointResponder();
        GlobalAggregateManager aggregateManager = jobManagerConnection.getGlobalAggregateManager();
        LibraryCacheManager.ClassLoaderHandle classLoaderHandle = jobManagerConnection.getClassLoaderHandle();
        ResultPartitionConsumableNotifier resultPartitionConsumableNotifier = jobManagerConnection.getResultPartitionConsumableNotifier();
        PartitionProducerStateChecker partitionStateChecker = jobManagerConnection.getPartitionStateChecker();
        final TaskLocalStateStore localStateStore = localStateStoresManager.localStateStoreForSubtask(jobId, tdd.getAllocationId(), taskInformation.getJobVertexId(), tdd.getSubtaskIndex());
        // TODO: Pass config value from user program and do overriding here.
        final StateChangelogStorage<?> changelogStorage;
        try {
            changelogStorage = changelogStoragesManager.stateChangelogStorageForJob(jobId, taskManagerConfiguration.getConfiguration(), jobGroup);
        } catch (IOException e) {
            throw new TaskSubmissionException(e);
        }
        final JobManagerTaskRestore taskRestore = tdd.getTaskRestore();
        final TaskStateManager taskStateManager = new TaskStateManagerImpl(jobId, tdd.getExecutionAttemptId(), localStateStore, changelogStorage, taskRestore, checkpointResponder);
        MemoryManager memoryManager;
        try {
            memoryManager = taskSlotTable.getTaskMemoryManager(tdd.getAllocationId());
        } catch (SlotNotFoundException e) {
            throw new TaskSubmissionException("Could not submit task.", e);
        }
        Task task = new Task(jobInformation, taskInformation, tdd.getExecutionAttemptId(), tdd.getAllocationId(), tdd.getSubtaskIndex(), tdd.getAttemptNumber(), tdd.getProducedPartitions(), tdd.getInputGates(), memoryManager, taskExecutorServices.getIOManager(), taskExecutorServices.getShuffleEnvironment(), taskExecutorServices.getKvStateService(), taskExecutorServices.getBroadcastVariableManager(), taskExecutorServices.getTaskEventDispatcher(), externalResourceInfoProvider, taskStateManager, taskManagerActions, inputSplitProvider, checkpointResponder, taskOperatorEventGateway, aggregateManager, classLoaderHandle, fileCache, taskManagerConfiguration, taskMetricGroup, resultPartitionConsumableNotifier, partitionStateChecker, getRpcService().getScheduledExecutor());
        taskMetricGroup.gauge(MetricNames.IS_BACK_PRESSURED, task::isBackPressured);
        log.info("Received task {} ({}), deploy into slot with allocation id {}.", task.getTaskInfo().getTaskNameWithSubtasks(), tdd.getExecutionAttemptId(), tdd.getAllocationId());
        boolean taskAdded;
        try {
            taskAdded = taskSlotTable.addTask(task);
        } catch (SlotNotFoundException | SlotNotActiveException e) {
            throw new TaskSubmissionException("Could not submit task.", e);
        }
        if (taskAdded) {
            task.startTaskThread();
            setupResultPartitionBookkeeping(tdd.getJobId(), tdd.getProducedPartitions(), task.getTerminationFuture());
            return CompletableFuture.completedFuture(Acknowledge.get());
        } else {
            final String message = "TaskManager already contains a task for id " + task.getExecutionId() + '.';
            log.debug(message);
            throw new TaskSubmissionException(message);
        }
    } catch (TaskSubmissionException e) {
        return FutureUtils.completedExceptionally(e);
    }
}

Example 3 with InputSplitProvider

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

the class TaskTest method createTask.

private Task createTask(Class<? extends AbstractInvokable> invokable, LibraryCacheManager libCache, NetworkEnvironment networkEnvironment, ResultPartitionConsumableNotifier consumableNotifier, PartitionProducerStateChecker partitionProducerStateChecker, Executor executor, Configuration taskManagerConfig, ExecutionConfig execConfig) throws IOException {
    JobID jobId = new JobID();
    JobVertexID jobVertexId = new JobVertexID();
    ExecutionAttemptID executionAttemptId = new ExecutionAttemptID();
    InputSplitProvider inputSplitProvider = new TaskInputSplitProvider(jobManagerGateway, jobId, jobVertexId, executionAttemptId, new FiniteDuration(60, TimeUnit.SECONDS));
    CheckpointResponder checkpointResponder = new ActorGatewayCheckpointResponder(jobManagerGateway);
    SerializedValue<ExecutionConfig> serializedExecutionConfig = new SerializedValue<>(execConfig);
    JobInformation jobInformation = new JobInformation(jobId, "Test Job", serializedExecutionConfig, new Configuration(), Collections.<BlobKey>emptyList(), Collections.<URL>emptyList());
    TaskInformation taskInformation = new TaskInformation(jobVertexId, "Test Task", 1, 1, invokable.getName(), new Configuration());
    return new Task(jobInformation, taskInformation, executionAttemptId, new AllocationID(), 0, 0, Collections.<ResultPartitionDeploymentDescriptor>emptyList(), Collections.<InputGateDeploymentDescriptor>emptyList(), 0, null, mock(MemoryManager.class), mock(IOManager.class), networkEnvironment, mock(BroadcastVariableManager.class), taskManagerConnection, inputSplitProvider, checkpointResponder, libCache, mock(FileCache.class), new TestingTaskManagerRuntimeInfo(taskManagerConfig), mock(TaskMetricGroup.class), consumableNotifier, partitionProducerStateChecker, executor);
}

Example 4 with InputSplitProvider

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

the class TaskExecutor method submitTask.

// ======================================================================
//  RPC methods
// ======================================================================
// ----------------------------------------------------------------------
// Task lifecycle RPCs
// ----------------------------------------------------------------------
@RpcMethod
public Acknowledge submitTask(TaskDeploymentDescriptor tdd, UUID jobManagerLeaderId) throws TaskSubmissionException {
    // first, deserialize the pre-serialized information
    final JobInformation jobInformation;
    final TaskInformation taskInformation;
    try {
        jobInformation = tdd.getSerializedJobInformation().deserializeValue(getClass().getClassLoader());
        taskInformation = tdd.getSerializedTaskInformation().deserializeValue(getClass().getClassLoader());
    } catch (IOException | ClassNotFoundException e) {
        throw new TaskSubmissionException("Could not deserialize the job or task information.", e);
    }
    final JobID jobId = jobInformation.getJobId();
    final JobManagerConnection jobManagerConnection = jobManagerTable.get(jobId);
    if (jobManagerConnection == null) {
        final String message = "Could not submit task because there is no JobManager " + "associated for the job " + jobId + '.';
        log.debug(message);
        throw new TaskSubmissionException(message);
    }
    if (!jobManagerConnection.getLeaderId().equals(jobManagerLeaderId)) {
        final String message = "Rejecting the task submission because the job manager leader id " + jobManagerLeaderId + " does not match the expected job manager leader id " + jobManagerConnection.getLeaderId() + '.';
        log.debug(message);
        throw new TaskSubmissionException(message);
    }
    if (!taskSlotTable.existsActiveSlot(jobId, tdd.getAllocationId())) {
        final String message = "No task slot allocated for job ID " + jobId + " and allocation ID " + tdd.getAllocationId() + '.';
        log.debug(message);
        throw new TaskSubmissionException(message);
    }
    TaskMetricGroup taskMetricGroup = taskManagerMetricGroup.addTaskForJob(jobInformation.getJobId(), jobInformation.getJobName(), taskInformation.getJobVertexId(), tdd.getExecutionAttemptId(), taskInformation.getTaskName(), tdd.getSubtaskIndex(), tdd.getAttemptNumber());
    InputSplitProvider inputSplitProvider = new RpcInputSplitProvider(jobManagerConnection.getLeaderId(), jobManagerConnection.getJobManagerGateway(), jobInformation.getJobId(), taskInformation.getJobVertexId(), tdd.getExecutionAttemptId(), taskManagerConfiguration.getTimeout());
    TaskManagerActions taskManagerActions = jobManagerConnection.getTaskManagerActions();
    CheckpointResponder checkpointResponder = jobManagerConnection.getCheckpointResponder();
    LibraryCacheManager libraryCache = jobManagerConnection.getLibraryCacheManager();
    ResultPartitionConsumableNotifier resultPartitionConsumableNotifier = jobManagerConnection.getResultPartitionConsumableNotifier();
    PartitionProducerStateChecker partitionStateChecker = jobManagerConnection.getPartitionStateChecker();
    Task task = new Task(jobInformation, taskInformation, tdd.getExecutionAttemptId(), tdd.getAllocationId(), tdd.getSubtaskIndex(), tdd.getAttemptNumber(), tdd.getProducedPartitions(), tdd.getInputGates(), tdd.getTargetSlotNumber(), tdd.getTaskStateHandles(), memoryManager, ioManager, networkEnvironment, broadcastVariableManager, taskManagerActions, inputSplitProvider, checkpointResponder, libraryCache, fileCache, taskManagerConfiguration, taskMetricGroup, resultPartitionConsumableNotifier, partitionStateChecker, getRpcService().getExecutor());
    log.info("Received task {}.", task.getTaskInfo().getTaskNameWithSubtasks());
    boolean taskAdded;
    try {
        taskAdded = taskSlotTable.addTask(task);
    } catch (SlotNotFoundException | SlotNotActiveException e) {
        throw new TaskSubmissionException("Could not submit task.", e);
    }
    if (taskAdded) {
        task.startTaskThread();
        return Acknowledge.get();
    } else {
        final String message = "TaskManager already contains a task for id " + task.getExecutionId() + '.';
        log.debug(message);
        throw new TaskSubmissionException(message);
    }
}