Examples with TestingHighAvailabilityServices org.apache.flink.runtime.highavailability.TestingHighAvailabilityServices used on opensource projects

Example 11 with TestingHighAvailabilityServices

use of org.apache.flink.runtime.highavailability.TestingHighAvailabilityServices in project flink by apache.

the class TaskManagerRunnerStartupTest method setupTest.

@Before
public void setupTest() {
    highAvailabilityServices = new TestingHighAvailabilityServices();
    highAvailabilityServices.setResourceManagerLeaderRetriever(new SettableLeaderRetrievalService());
}

Example 12 with TestingHighAvailabilityServices

use of org.apache.flink.runtime.highavailability.TestingHighAvailabilityServices in project flink by apache.

the class TaskExecutorRecoveryTest method testRecoveredTaskExecutorWillRestoreAllocationState.

@Test
public void testRecoveredTaskExecutorWillRestoreAllocationState(@TempDir File tempDir) throws Exception {
    final ResourceID resourceId = ResourceID.generate();
    final Configuration configuration = new Configuration();
    configuration.set(TaskManagerOptions.NUM_TASK_SLOTS, 2);
    configuration.set(CheckpointingOptions.LOCAL_RECOVERY, true);
    final TestingResourceManagerGateway testingResourceManagerGateway = new TestingResourceManagerGateway();
    final ArrayBlockingQueue<TaskExecutorSlotReport> queue = new ArrayBlockingQueue<>(2);
    testingResourceManagerGateway.setSendSlotReportFunction(slotReportInformation -> {
        queue.offer(TaskExecutorSlotReport.create(slotReportInformation.f0, slotReportInformation.f2));
        return CompletableFuture.completedFuture(Acknowledge.get());
    });
    final TestingRpcService rpcService = rpcServiceExtension.getTestingRpcService();
    rpcService.registerGateway(testingResourceManagerGateway.getAddress(), testingResourceManagerGateway);
    final JobID jobId = new JobID();
    final TestingHighAvailabilityServices highAvailabilityServices = new TestingHighAvailabilityServices();
    highAvailabilityServices.setResourceManagerLeaderRetriever(new SettableLeaderRetrievalService(testingResourceManagerGateway.getAddress(), testingResourceManagerGateway.getFencingToken().toUUID()));
    final SettableLeaderRetrievalService jobMasterLeaderRetriever = new SettableLeaderRetrievalService();
    highAvailabilityServices.setJobMasterLeaderRetriever(jobId, jobMasterLeaderRetriever);
    final WorkingDirectory workingDirectory = WorkingDirectory.create(tempDir);
    final TaskExecutor taskExecutor = TaskExecutorBuilder.newBuilder(rpcService, highAvailabilityServices, workingDirectory).setConfiguration(configuration).setResourceId(resourceId).build();
    taskExecutor.start();
    final TaskExecutorGateway taskExecutorGateway = taskExecutor.getSelfGateway(TaskExecutorGateway.class);
    final TaskExecutorSlotReport taskExecutorSlotReport = queue.take();
    final SlotReport slotReport = taskExecutorSlotReport.getSlotReport();
    assertThat(slotReport.getNumSlotStatus(), is(2));
    final SlotStatus slotStatus = slotReport.iterator().next();
    final SlotID allocatedSlotID = slotStatus.getSlotID();
    final AllocationID allocationId = new AllocationID();
    taskExecutorGateway.requestSlot(allocatedSlotID, jobId, allocationId, slotStatus.getResourceProfile(), "localhost", testingResourceManagerGateway.getFencingToken(), Time.seconds(10L)).join();
    taskExecutor.close();
    final BlockingQueue<Collection<SlotOffer>> offeredSlots = new ArrayBlockingQueue<>(1);
    final TestingJobMasterGateway jobMasterGateway = new TestingJobMasterGatewayBuilder().setOfferSlotsFunction((resourceID, slotOffers) -> {
        offeredSlots.offer(new HashSet<>(slotOffers));
        return CompletableFuture.completedFuture(slotOffers);
    }).build();
    rpcService.registerGateway(jobMasterGateway.getAddress(), jobMasterGateway);
    jobMasterLeaderRetriever.notifyListener(jobMasterGateway.getAddress(), jobMasterGateway.getFencingToken().toUUID());
    // recover the TaskExecutor
    final TaskExecutor recoveredTaskExecutor = TaskExecutorBuilder.newBuilder(rpcService, highAvailabilityServices, workingDirectory).setConfiguration(configuration).setResourceId(resourceId).build();
    recoveredTaskExecutor.start();
    final TaskExecutorSlotReport recoveredSlotReport = queue.take();
    for (SlotStatus status : recoveredSlotReport.getSlotReport()) {
        if (status.getSlotID().equals(allocatedSlotID)) {
            assertThat(status.getJobID(), is(jobId));
            assertThat(status.getAllocationID(), is(allocationId));
        } else {
            assertThat(status.getJobID(), is(nullValue()));
        }
    }
    final Collection<SlotOffer> take = offeredSlots.take();
    assertThat(take, hasSize(1));
    final SlotOffer offeredSlot = take.iterator().next();
    assertThat(offeredSlot.getAllocationId(), is(allocationId));
}

Example 13 with TestingHighAvailabilityServices

use of org.apache.flink.runtime.highavailability.TestingHighAvailabilityServices in project flink by apache.

the class TaskExecutorSlotLifetimeTest method testUserCodeClassLoaderIsBoundToSlot.

/**
 * Tests that the user code class loader is bound to the lifetime of the slot. This means that
 * it is being reused across a failover, for example. See FLINK-16408.
 */
@Test
public void testUserCodeClassLoaderIsBoundToSlot() throws Exception {
    final Configuration configuration = new Configuration();
    final TestingRpcService rpcService = TESTING_RPC_SERVICE_RESOURCE.getTestingRpcService();
    final TestingResourceManagerGateway resourceManagerGateway = new TestingResourceManagerGateway();
    final CompletableFuture<SlotReport> firstSlotReportFuture = new CompletableFuture<>();
    resourceManagerGateway.setSendSlotReportFunction(resourceIDInstanceIDSlotReportTuple3 -> {
        firstSlotReportFuture.complete(resourceIDInstanceIDSlotReportTuple3.f2);
        return CompletableFuture.completedFuture(Acknowledge.get());
    });
    final BlockingQueue<TaskExecutionState> taskExecutionStates = new ArrayBlockingQueue<>(3);
    final OneShotLatch slotsOfferedLatch = new OneShotLatch();
    final TestingJobMasterGateway jobMasterGateway = new TestingJobMasterGatewayBuilder().setOfferSlotsFunction((resourceID, slotOffers) -> {
        slotsOfferedLatch.trigger();
        return CompletableFuture.completedFuture(slotOffers);
    }).setUpdateTaskExecutionStateFunction(FunctionUtils.uncheckedFunction(taskExecutionState -> {
        taskExecutionStates.put(taskExecutionState);
        return CompletableFuture.completedFuture(Acknowledge.get());
    })).build();
    final LeaderRetrievalService resourceManagerLeaderRetriever = new SettableLeaderRetrievalService(resourceManagerGateway.getAddress(), resourceManagerGateway.getFencingToken().toUUID());
    final LeaderRetrievalService jobMasterLeaderRetriever = new SettableLeaderRetrievalService(jobMasterGateway.getAddress(), jobMasterGateway.getFencingToken().toUUID());
    final TestingHighAvailabilityServices haServices = new TestingHighAvailabilityServicesBuilder().setResourceManagerLeaderRetriever(resourceManagerLeaderRetriever).setJobMasterLeaderRetrieverFunction(ignored -> jobMasterLeaderRetriever).build();
    rpcService.registerGateway(resourceManagerGateway.getAddress(), resourceManagerGateway);
    rpcService.registerGateway(jobMasterGateway.getAddress(), jobMasterGateway);
    final LocalUnresolvedTaskManagerLocation unresolvedTaskManagerLocation = new LocalUnresolvedTaskManagerLocation();
    try (final TaskExecutor taskExecutor = createTaskExecutor(configuration, rpcService, haServices, unresolvedTaskManagerLocation)) {
        taskExecutor.start();
        final SlotReport slotReport = firstSlotReportFuture.join();
        final SlotID firstSlotId = slotReport.iterator().next().getSlotID();
        final TaskExecutorGateway taskExecutorGateway = taskExecutor.getSelfGateway(TaskExecutorGateway.class);
        final JobID jobId = new JobID();
        final AllocationID allocationId = new AllocationID();
        taskExecutorGateway.requestSlot(firstSlotId, jobId, allocationId, ResourceProfile.ZERO, jobMasterGateway.getAddress(), resourceManagerGateway.getFencingToken(), RpcUtils.INF_TIMEOUT).join();
        final TaskDeploymentDescriptor tdd = TaskDeploymentDescriptorBuilder.newBuilder(jobId, UserClassLoaderExtractingInvokable.class).setAllocationId(allocationId).build();
        slotsOfferedLatch.await();
        taskExecutorGateway.submitTask(tdd, jobMasterGateway.getFencingToken(), RpcUtils.INF_TIMEOUT).join();
        final ClassLoader firstClassLoader = UserClassLoaderExtractingInvokable.take();
        // wait for the first task to finish
        TaskExecutionState taskExecutionState;
        do {
            taskExecutionState = taskExecutionStates.take();
        } while (!taskExecutionState.getExecutionState().isTerminal());
        // check that a second task will re-use the same class loader
        taskExecutorGateway.submitTask(tdd, jobMasterGateway.getFencingToken(), RpcUtils.INF_TIMEOUT).join();
        final ClassLoader secondClassLoader = UserClassLoaderExtractingInvokable.take();
        assertThat(firstClassLoader, sameInstance(secondClassLoader));
    }
}

Example 14 with TestingHighAvailabilityServices

use of org.apache.flink.runtime.highavailability.TestingHighAvailabilityServices in project flink by apache.

the class TaskExecutorTest method setup.

@Before
public void setup() throws IOException {
    rpc = new TestingRpcService();
    configuration = new Configuration();
    TaskExecutorResourceUtils.adjustForLocalExecution(configuration);
    unresolvedTaskManagerLocation = new LocalUnresolvedTaskManagerLocation();
    jobId = new JobID();
    jobId2 = new JobID();
    testingFatalErrorHandler = new TestingFatalErrorHandler();
    haServices = new TestingHighAvailabilityServices();
    resourceManagerLeaderRetriever = new SettableLeaderRetrievalService();
    jobManagerLeaderRetriever = new SettableLeaderRetrievalService();
    jobManagerLeaderRetriever2 = new SettableLeaderRetrievalService();
    haServices.setResourceManagerLeaderRetriever(resourceManagerLeaderRetriever);
    haServices.setJobMasterLeaderRetriever(jobId, jobManagerLeaderRetriever);
    haServices.setJobMasterLeaderRetriever(jobId2, jobManagerLeaderRetriever2);
    nettyShuffleEnvironment = new NettyShuffleEnvironmentBuilder().build();
}

Example 15 with TestingHighAvailabilityServices

use of org.apache.flink.runtime.highavailability.TestingHighAvailabilityServices in project flink by apache.

the class TaskExecutorITCase method testSlotAllocation.

@Test
public void testSlotAllocation() throws Exception {
    TestingFatalErrorHandler testingFatalErrorHandler = new TestingFatalErrorHandler();
    TestingHighAvailabilityServices testingHAServices = new TestingHighAvailabilityServices();
    final Configuration configuration = new Configuration();
    final ScheduledExecutorService scheduledExecutorService = new ScheduledThreadPoolExecutor(1);
    final ResourceID taskManagerResourceId = new ResourceID("foobar");
    final UUID rmLeaderId = UUID.randomUUID();
    final TestingLeaderElectionService rmLeaderElectionService = new TestingLeaderElectionService();
    final TestingLeaderRetrievalService rmLeaderRetrievalService = new TestingLeaderRetrievalService();
    final String rmAddress = "rm";
    final String jmAddress = "jm";
    final UUID jmLeaderId = UUID.randomUUID();
    final JobID jobId = new JobID();
    final ResourceProfile resourceProfile = new ResourceProfile(1.0, 1);
    testingHAServices.setResourceManagerLeaderElectionService(rmLeaderElectionService);
    testingHAServices.setResourceManagerLeaderRetriever(rmLeaderRetrievalService);
    testingHAServices.setJobMasterLeaderRetriever(jobId, new TestingLeaderRetrievalService(jmAddress, jmLeaderId));
    TestingSerialRpcService rpcService = new TestingSerialRpcService();
    ResourceManagerConfiguration resourceManagerConfiguration = new ResourceManagerConfiguration(Time.milliseconds(500L), Time.milliseconds(500L), Time.minutes(5L));
    SlotManagerFactory slotManagerFactory = new DefaultSlotManager.Factory();
    JobLeaderIdService jobLeaderIdService = new JobLeaderIdService(testingHAServices, rpcService.getScheduledExecutor(), resourceManagerConfiguration.getJobTimeout());
    MetricRegistry metricRegistry = mock(MetricRegistry.class);
    HeartbeatServices heartbeatServices = mock(HeartbeatServices.class, RETURNS_MOCKS);
    final TaskManagerConfiguration taskManagerConfiguration = TaskManagerConfiguration.fromConfiguration(configuration);
    final TaskManagerLocation taskManagerLocation = new TaskManagerLocation(taskManagerResourceId, InetAddress.getLocalHost(), 1234);
    final MemoryManager memoryManager = mock(MemoryManager.class);
    final IOManager ioManager = mock(IOManager.class);
    final NetworkEnvironment networkEnvironment = mock(NetworkEnvironment.class);
    final TaskManagerMetricGroup taskManagerMetricGroup = mock(TaskManagerMetricGroup.class);
    final BroadcastVariableManager broadcastVariableManager = mock(BroadcastVariableManager.class);
    final FileCache fileCache = mock(FileCache.class);
    final TaskSlotTable taskSlotTable = new TaskSlotTable(Arrays.asList(resourceProfile), new TimerService<AllocationID>(scheduledExecutorService, 100L));
    final JobManagerTable jobManagerTable = new JobManagerTable();
    final JobLeaderService jobLeaderService = new JobLeaderService(taskManagerLocation);
    ResourceManager<ResourceID> resourceManager = new StandaloneResourceManager(rpcService, resourceManagerConfiguration, testingHAServices, slotManagerFactory, metricRegistry, jobLeaderIdService, testingFatalErrorHandler);
    TaskExecutor taskExecutor = new TaskExecutor(taskManagerConfiguration, taskManagerLocation, rpcService, memoryManager, ioManager, networkEnvironment, testingHAServices, heartbeatServices, metricRegistry, taskManagerMetricGroup, broadcastVariableManager, fileCache, taskSlotTable, jobManagerTable, jobLeaderService, testingFatalErrorHandler);
    JobMasterGateway jmGateway = mock(JobMasterGateway.class);
    when(jmGateway.registerTaskManager(any(String.class), any(TaskManagerLocation.class), eq(jmLeaderId), any(Time.class))).thenReturn(FlinkCompletableFuture.<RegistrationResponse>completed(new JMTMRegistrationSuccess(taskManagerResourceId, 1234)));
    when(jmGateway.getHostname()).thenReturn(jmAddress);
    rpcService.registerGateway(rmAddress, resourceManager.getSelf());
    rpcService.registerGateway(jmAddress, jmGateway);
    final AllocationID allocationId = new AllocationID();
    final SlotRequest slotRequest = new SlotRequest(jobId, allocationId, resourceProfile);
    final SlotOffer slotOffer = new SlotOffer(allocationId, 0, resourceProfile);
    try {
        resourceManager.start();
        taskExecutor.start();
        // notify the RM that it is the leader
        rmLeaderElectionService.isLeader(rmLeaderId);
        // notify the TM about the new RM leader
        rmLeaderRetrievalService.notifyListener(rmAddress, rmLeaderId);
        Future<RegistrationResponse> registrationResponseFuture = resourceManager.registerJobManager(rmLeaderId, jmLeaderId, jmAddress, jobId);
        RegistrationResponse registrationResponse = registrationResponseFuture.get();
        assertTrue(registrationResponse instanceof JobMasterRegistrationSuccess);
        resourceManager.requestSlot(jmLeaderId, rmLeaderId, slotRequest);
        verify(jmGateway).offerSlots(eq(taskManagerResourceId), (Iterable<SlotOffer>) argThat(Matchers.contains(slotOffer)), eq(jmLeaderId), any(Time.class));
    } finally {
        if (testingFatalErrorHandler.hasExceptionOccurred()) {
            testingFatalErrorHandler.rethrowError();
        }
    }
}