Examples with JobBundleFactory org.apache.beam.runners.fnexecution.control.JobBundleFactory used on opensource projects

Example 1 with JobBundleFactory

use of org.apache.beam.runners.fnexecution.control.JobBundleFactory in project flink by apache.

the class PythonTestUtils method createMockJobBundleFactory.

public static JobBundleFactory createMockJobBundleFactory() {
    JobBundleFactory jobBundleFactorySpy = spy(JobBundleFactory.class);
    StageBundleFactory stageBundleFactorySpy = spy(StageBundleFactory.class);
    when(jobBundleFactorySpy.forStage(any())).thenReturn(stageBundleFactorySpy);
    ProcessBundleDescriptors.ExecutableProcessBundleDescriptor processBundleDescriptor = spy(ProcessBundleDescriptors.ExecutableProcessBundleDescriptor.class);
    when(stageBundleFactorySpy.getProcessBundleDescriptor()).thenReturn(processBundleDescriptor);
    RemoteBundle remoteBundleSpy = spy(RemoteBundle.class);
    try {
        when(stageBundleFactorySpy.getBundle(any(OutputReceiverFactory.class), any(TimerReceiverFactory.class), any(StateRequestHandler.class), any(BundleProgressHandler.class))).thenReturn(remoteBundleSpy);
    } catch (Exception e) {
    // ignore
    }
    Map<String, FnDataReceiver> inputReceivers = new HashMap<>();
    FnDataReceiver<WindowedValue<?>> windowedValueReceiverSpy = spy(FnDataReceiver.class);
    inputReceivers.put("input", windowedValueReceiverSpy);
    when(remoteBundleSpy.getInputReceivers()).thenReturn(inputReceivers);
    return jobBundleFactorySpy;
}

Example 2 with JobBundleFactory

use of org.apache.beam.runners.fnexecution.control.JobBundleFactory in project beam by apache.

the class BeamFnMapTaskExecutorFactory method create.

/**
 * Creates a new {@link DataflowMapTaskExecutor} from the given {@link MapTask} definition using
 * the provided {@link ReaderFactory}.
 */
@Override
public DataflowMapTaskExecutor create(InstructionRequestHandler instructionRequestHandler, GrpcFnServer<GrpcDataService> grpcDataFnServer, Endpoints.ApiServiceDescriptor dataApiServiceDescriptor, GrpcFnServer<GrpcStateService> grpcStateFnServer, MutableNetwork<Node, Edge> network, PipelineOptions options, String stageName, ReaderFactory readerFactory, SinkFactory sinkFactory, DataflowExecutionContext<?> executionContext, CounterSet counterSet, IdGenerator idGenerator) {
    // TODO: remove this once we trust the code paths
    checkArgument(DataflowRunner.hasExperiment(options.as(DataflowPipelineDebugOptions.class), "beam_fn_api"), "%s should only be used when beam_fn_api is enabled", getClass().getSimpleName());
    // Swap out all the InstructionOutput nodes with OutputReceiver nodes
    Networks.replaceDirectedNetworkNodes(network, createOutputReceiversTransform(stageName, counterSet));
    if (DataflowRunner.hasExperiment(options.as(DataflowPipelineDebugOptions.class), "use_executable_stage_bundle_execution")) {
        LOG.debug("Using SingleEnvironmentInstanceJobBundleFactory");
        JobBundleFactory jobBundleFactory = SingleEnvironmentInstanceJobBundleFactory.create(StaticRemoteEnvironmentFactory.forService(instructionRequestHandler), grpcDataFnServer, grpcStateFnServer, idGenerator);
        // If the use_executable_stage_bundle_execution is enabled, use ExecutableStage instead.
        Networks.replaceDirectedNetworkNodes(network, createOperationTransformForExecutableStageNode(network, stageName, executionContext, jobBundleFactory));
    } else {
        // Swap out all the RegisterFnRequest nodes with Operation nodes
        Networks.replaceDirectedNetworkNodes(network, createOperationTransformForRegisterFnNodes(idGenerator, instructionRequestHandler, grpcStateFnServer.getService(), stageName, executionContext));
        // Swap out all the RemoteGrpcPort nodes with Operation nodes, note that it is expected
        // that the RegisterFnRequest nodes have already been replaced.
        Networks.replaceDirectedNetworkNodes(network, createOperationTransformForGrpcPortNodes(network, grpcDataFnServer.getService(), // TODO: Set NameContext properly for these operations.
        executionContext.createOperationContext(NameContext.create(stageName, stageName, stageName, stageName))));
    }
    // Swap out all the FetchAndFilterStreamingSideInput nodes with operation nodes
    Networks.replaceDirectedNetworkNodes(network, createOperationTransformForFetchAndFilterStreamingSideInputNodes(network, idGenerator, instructionRequestHandler, grpcDataFnServer.getService(), dataApiServiceDescriptor, executionContext, stageName));
    // Swap out all the ParallelInstruction nodes with Operation nodes
    Networks.replaceDirectedNetworkNodes(network, createOperationTransformForParallelInstructionNodes(stageName, network, options, readerFactory, sinkFactory, executionContext));
    // Collect all the operations within the network and attach all the operations as receivers
    // to preceding output receivers.
    List<Operation> topoSortedOperations = new ArrayList<>();
    for (OperationNode node : Iterables.filter(Networks.topologicalOrder(network), OperationNode.class)) {
        topoSortedOperations.add(node.getOperation());
        for (Node predecessor : Iterables.filter(network.predecessors(node), OutputReceiverNode.class)) {
            ((OutputReceiverNode) predecessor).getOutputReceiver().addOutput((Receiver) node.getOperation());
        }
    }
    if (LOG.isDebugEnabled()) {
        LOG.info("Map task network: {}", Networks.toDot(network));
    }
    return BeamFnMapTaskExecutor.withSharedCounterSet(topoSortedOperations, counterSet, executionContext.getExecutionStateTracker());
}

Example 3 with JobBundleFactory

use of org.apache.beam.runners.fnexecution.control.JobBundleFactory in project flink by apache.

the class BeamPythonFunctionRunner method open.

// ------------------------------------------------------------------------
@Override
public void open(PythonConfig config) throws Exception {
    this.bundleStarted = false;
    this.resultBuffer = new LinkedBlockingQueue<>();
    this.reusableResultTuple = new Tuple2<>();
    // The creation of stageBundleFactory depends on the initialized environment manager.
    environmentManager.open();
    PortablePipelineOptions portableOptions = PipelineOptionsFactory.as(PortablePipelineOptions.class);
    if (jobOptions.containsKey(PythonOptions.STATE_CACHE_SIZE.key())) {
        portableOptions.as(ExperimentalOptions.class).setExperiments(Collections.singletonList(ExperimentalOptions.STATE_CACHE_SIZE + "=" + jobOptions.get(PythonOptions.STATE_CACHE_SIZE.key())));
    }
    Struct pipelineOptions = PipelineOptionsTranslation.toProto(portableOptions);
    if (memoryManager != null && config.isUsingManagedMemory()) {
        Preconditions.checkArgument(managedMemoryFraction > 0 && managedMemoryFraction <= 1.0, "The configured managed memory fraction for Python worker process must be within (0, 1], was: %s. " + "It may be because the consumer type \"Python\" was missing or set to 0 for the config option \"taskmanager.memory.managed.consumer-weights\"." + managedMemoryFraction);
        final LongFunctionWithException<PythonSharedResources, Exception> initializer = (size) -> new PythonSharedResources(createJobBundleFactory(pipelineOptions), createPythonExecutionEnvironment(size));
        sharedResources = memoryManager.getSharedMemoryResourceForManagedMemory(MANAGED_MEMORY_RESOURCE_ID, initializer, managedMemoryFraction);
        LOG.info("Obtained shared Python process of size {} bytes", sharedResources.getSize());
        sharedResources.getResourceHandle().addPythonEnvironmentManager(environmentManager);
        JobBundleFactory jobBundleFactory = sharedResources.getResourceHandle().getJobBundleFactory();
        RunnerApi.Environment environment = sharedResources.getResourceHandle().getEnvironment();
        stageBundleFactory = createStageBundleFactory(jobBundleFactory, environment);
    } else {
        // there is no way to access the MemoryManager for the batch job of old planner,
        // fallback to the way that spawning a Python process for each Python operator
        jobBundleFactory = createJobBundleFactory(pipelineOptions);
        stageBundleFactory = createStageBundleFactory(jobBundleFactory, createPythonExecutionEnvironment(-1));
    }
    progressHandler = getProgressHandler(flinkMetricContainer);
}