Examples with ResourceID org.apache.flink.runtime.clusterframework.types.ResourceID used on opensource projects

Example 56 with ResourceID

use of org.apache.flink.runtime.clusterframework.types.ResourceID 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();
        }
    }
}

Example 57 with ResourceID

use of org.apache.flink.runtime.clusterframework.types.ResourceID in project flink by apache.

the class TaskExecutorTest method testHeartbeatTimeoutWithJobManager.

@Test
public void testHeartbeatTimeoutWithJobManager() throws Exception {
    final JobID jobId = new JobID();
    final Configuration configuration = new Configuration();
    final TaskManagerConfiguration tmConfig = TaskManagerConfiguration.fromConfiguration(configuration);
    final ResourceID tmResourceId = new ResourceID("tm");
    final TaskManagerLocation taskManagerLocation = new TaskManagerLocation(tmResourceId, InetAddress.getLoopbackAddress(), 1234);
    final TaskSlotTable taskSlotTable = new TaskSlotTable(Arrays.asList(mock(ResourceProfile.class)), mock(TimerService.class));
    final TestingSerialRpcService rpc = new TestingSerialRpcService();
    final JobLeaderService jobLeaderService = new JobLeaderService(taskManagerLocation);
    final TestingHighAvailabilityServices haServices = new TestingHighAvailabilityServices();
    final TestingLeaderRetrievalService rmLeaderRetrievalService = new TestingLeaderRetrievalService();
    final TestingLeaderRetrievalService jmLeaderRetrievalService = new TestingLeaderRetrievalService();
    haServices.setJobMasterLeaderRetriever(jobId, jmLeaderRetrievalService);
    haServices.setResourceManagerLeaderRetriever(rmLeaderRetrievalService);
    final TestingFatalErrorHandler testingFatalErrorHandler = new TestingFatalErrorHandler();
    final long heartbeatTimeout = 10L;
    HeartbeatServices heartbeatServices = mock(HeartbeatServices.class);
    when(heartbeatServices.createHeartbeatManager(eq(taskManagerLocation.getResourceID()), any(HeartbeatListener.class), any(ScheduledExecutor.class), any(Logger.class))).thenAnswer(new Answer<HeartbeatManagerImpl<Void, Void>>() {

        @Override
        public HeartbeatManagerImpl<Void, Void> answer(InvocationOnMock invocation) throws Throwable {
            return new HeartbeatManagerImpl<>(heartbeatTimeout, taskManagerLocation.getResourceID(), (HeartbeatListener<Void, Void>) invocation.getArguments()[1], (Executor) invocation.getArguments()[2], (ScheduledExecutor) invocation.getArguments()[2], (Logger) invocation.getArguments()[3]);
        }
    });
    final String jobMasterAddress = "jm";
    final UUID jmLeaderId = UUID.randomUUID();
    final ResourceID jmResourceId = new ResourceID(jobMasterAddress);
    final JobMasterGateway jobMasterGateway = mock(JobMasterGateway.class);
    final int blobPort = 42;
    when(jobMasterGateway.registerTaskManager(any(String.class), eq(taskManagerLocation), eq(jmLeaderId), any(Time.class))).thenReturn(FlinkCompletableFuture.<RegistrationResponse>completed(new JMTMRegistrationSuccess(jmResourceId, blobPort)));
    when(jobMasterGateway.getAddress()).thenReturn(jobMasterAddress);
    when(jobMasterGateway.getHostname()).thenReturn("localhost");
    try {
        final TaskExecutor taskManager = new TaskExecutor(tmConfig, taskManagerLocation, rpc, mock(MemoryManager.class), mock(IOManager.class), mock(NetworkEnvironment.class), haServices, heartbeatServices, mock(MetricRegistry.class), mock(TaskManagerMetricGroup.class), mock(BroadcastVariableManager.class), mock(FileCache.class), taskSlotTable, new JobManagerTable(), jobLeaderService, testingFatalErrorHandler);
        taskManager.start();
        rpc.registerGateway(jobMasterAddress, jobMasterGateway);
        // we have to add the job after the TaskExecutor, because otherwise the service has not
        // been properly started.
        jobLeaderService.addJob(jobId, jobMasterAddress);
        // now inform the task manager about the new job leader
        jmLeaderRetrievalService.notifyListener(jobMasterAddress, jmLeaderId);
        // register task manager success will trigger monitoring heartbeat target between tm and jm
        verify(jobMasterGateway).registerTaskManager(eq(taskManager.getAddress()), eq(taskManagerLocation), eq(jmLeaderId), any(Time.class));
        // the timeout should trigger disconnecting from the JobManager
        verify(jobMasterGateway, timeout(heartbeatTimeout * 5)).disconnectTaskManager(eq(taskManagerLocation.getResourceID()), any(TimeoutException.class));
        // check if a concurrent error occurred
        testingFatalErrorHandler.rethrowError();
    } finally {
        rpc.stopService();
    }
}

Example 58 with ResourceID

use of org.apache.flink.runtime.clusterframework.types.ResourceID in project flink by apache.

the class TaskExecutorTest method testRejectAllocationRequestsForOutOfSyncSlots.

/**
	 * Tests that all allocation requests for slots are ignored if the slot has been reported as
	 * free by the TaskExecutor but this report hasn't been confirmed by the ResourceManager.
	 *
	 * This is essential for the correctness of the state of the ResourceManager.
	 */
@Ignore
@Test
public void testRejectAllocationRequestsForOutOfSyncSlots() throws Exception {
    final ResourceID resourceID = ResourceID.generate();
    final String address1 = "/resource/manager/address/one";
    final UUID leaderId = UUID.randomUUID();
    final JobID jobId = new JobID();
    final String jobManagerAddress = "foobar";
    final TestingSerialRpcService rpc = new TestingSerialRpcService();
    try {
        // register the mock resource manager gateways
        ResourceManagerGateway rmGateway1 = mock(ResourceManagerGateway.class);
        rpc.registerGateway(address1, rmGateway1);
        TestingLeaderRetrievalService testLeaderService = new TestingLeaderRetrievalService();
        TestingHighAvailabilityServices haServices = new TestingHighAvailabilityServices();
        haServices.setResourceManagerLeaderRetriever(testLeaderService);
        TaskManagerConfiguration taskManagerServicesConfiguration = mock(TaskManagerConfiguration.class);
        when(taskManagerServicesConfiguration.getNumberSlots()).thenReturn(1);
        TaskManagerLocation taskManagerLocation = mock(TaskManagerLocation.class);
        when(taskManagerLocation.getResourceID()).thenReturn(resourceID);
        final TestingFatalErrorHandler testingFatalErrorHandler = new TestingFatalErrorHandler();
        TaskExecutor taskManager = new TaskExecutor(taskManagerServicesConfiguration, taskManagerLocation, rpc, mock(MemoryManager.class), mock(IOManager.class), mock(NetworkEnvironment.class), haServices, mock(HeartbeatServices.class, RETURNS_MOCKS), mock(MetricRegistry.class), mock(TaskManagerMetricGroup.class), mock(BroadcastVariableManager.class), mock(FileCache.class), mock(TaskSlotTable.class), mock(JobManagerTable.class), mock(JobLeaderService.class), testingFatalErrorHandler);
        taskManager.start();
        String taskManagerAddress = taskManager.getAddress();
        // no connection initially, since there is no leader
        assertNull(taskManager.getResourceManagerConnection());
        // define a leader and see that a registration happens
        testLeaderService.notifyListener(address1, leaderId);
        verify(rmGateway1).registerTaskExecutor(eq(leaderId), eq(taskManagerAddress), eq(resourceID), any(SlotReport.class), any(Time.class));
        assertNotNull(taskManager.getResourceManagerConnection());
        // test that allocating a slot works
        final SlotID slotID = new SlotID(resourceID, 0);
        TMSlotRequestReply tmSlotRequestReply = taskManager.requestSlot(slotID, jobId, new AllocationID(), jobManagerAddress, leaderId);
        assertTrue(tmSlotRequestReply instanceof TMSlotRequestRegistered);
        // TODO: Figure out the concrete allocation behaviour between RM and TM. Maybe we don't need the SlotID...
        // test that we can't allocate slots which are blacklisted due to pending confirmation of the RM
        final SlotID unconfirmedFreeSlotID = new SlotID(resourceID, 1);
        TMSlotRequestReply tmSlotRequestReply2 = taskManager.requestSlot(unconfirmedFreeSlotID, jobId, new AllocationID(), jobManagerAddress, leaderId);
        assertTrue(tmSlotRequestReply2 instanceof TMSlotRequestRejected);
        // re-register
        verify(rmGateway1).registerTaskExecutor(eq(leaderId), eq(taskManagerAddress), eq(resourceID), any(SlotReport.class), any(Time.class));
        testLeaderService.notifyListener(address1, leaderId);
        // now we should be successful because the slots status has been synced
        // test that we can't allocate slots which are blacklisted due to pending confirmation of the RM
        TMSlotRequestReply tmSlotRequestReply3 = taskManager.requestSlot(unconfirmedFreeSlotID, jobId, new AllocationID(), jobManagerAddress, leaderId);
        assertTrue(tmSlotRequestReply3 instanceof TMSlotRequestRegistered);
        // check if a concurrent error occurred
        testingFatalErrorHandler.rethrowError();
    } finally {
        rpc.stopService();
    }
}

Example 59 with ResourceID

use of org.apache.flink.runtime.clusterframework.types.ResourceID in project flink by apache.

the class TaskExecutorTest method testImmediatelyRegistersIfLeaderIsKnown.

@Test
public void testImmediatelyRegistersIfLeaderIsKnown() throws Exception {
    final ResourceID resourceID = ResourceID.generate();
    final String resourceManagerAddress = "/resource/manager/address/one";
    final TestingSerialRpcService rpc = new TestingSerialRpcService();
    try {
        final FatalErrorHandler errorHandler = mock(FatalErrorHandler.class);
        // register a mock resource manager gateway
        ResourceManagerGateway rmGateway = mock(ResourceManagerGateway.class);
        when(rmGateway.registerTaskExecutor(any(UUID.class), anyString(), any(ResourceID.class), any(SlotReport.class), any(Time.class))).thenReturn(FlinkCompletableFuture.<RegistrationResponse>completed(new RegistrationResponse.Success()));
        TaskManagerConfiguration taskManagerServicesConfiguration = mock(TaskManagerConfiguration.class);
        when(taskManagerServicesConfiguration.getNumberSlots()).thenReturn(1);
        rpc.registerGateway(resourceManagerAddress, rmGateway);
        TaskManagerLocation taskManagerLocation = mock(TaskManagerLocation.class);
        when(taskManagerLocation.getResourceID()).thenReturn(resourceID);
        NonHaServices haServices = new NonHaServices(resourceManagerAddress);
        final TaskSlotTable taskSlotTable = mock(TaskSlotTable.class);
        final SlotReport slotReport = new SlotReport();
        when(taskSlotTable.createSlotReport(any(ResourceID.class))).thenReturn(slotReport);
        final TestingFatalErrorHandler testingFatalErrorHandler = new TestingFatalErrorHandler();
        TaskExecutor taskManager = new TaskExecutor(taskManagerServicesConfiguration, taskManagerLocation, rpc, mock(MemoryManager.class), mock(IOManager.class), mock(NetworkEnvironment.class), haServices, mock(HeartbeatServices.class, RETURNS_MOCKS), mock(MetricRegistry.class), mock(TaskManagerMetricGroup.class), mock(BroadcastVariableManager.class), mock(FileCache.class), taskSlotTable, mock(JobManagerTable.class), mock(JobLeaderService.class), testingFatalErrorHandler);
        taskManager.start();
        String taskManagerAddress = taskManager.getAddress();
        verify(rmGateway).registerTaskExecutor(any(UUID.class), eq(taskManagerAddress), eq(resourceID), eq(slotReport), any(Time.class));
        // check if a concurrent error occurred
        testingFatalErrorHandler.rethrowError();
    } finally {
        rpc.stopService();
    }
}

Example 60 with ResourceID

use of org.apache.flink.runtime.clusterframework.types.ResourceID in project flink by apache.

the class TaskExecutorTest method testSlotAcceptance.

/**
	 * Tests that accepted slots go into state assigned and the others are returned to the resource
	 * manager.
	 */
@Test
public void testSlotAcceptance() throws Exception {
    final JobID jobId = new JobID();
    final TestingSerialRpcService rpc = new TestingSerialRpcService();
    final Configuration configuration = new Configuration();
    final TaskManagerConfiguration taskManagerConfiguration = TaskManagerConfiguration.fromConfiguration(configuration);
    final ResourceID resourceId = new ResourceID("foobar");
    final TaskManagerLocation taskManagerLocation = new TaskManagerLocation(resourceId, InetAddress.getLoopbackAddress(), 1234);
    final TestingHighAvailabilityServices haServices = new TestingHighAvailabilityServices();
    final TimerService<AllocationID> timerService = mock(TimerService.class);
    final TaskSlotTable taskSlotTable = new TaskSlotTable(Arrays.asList(mock(ResourceProfile.class), mock(ResourceProfile.class)), timerService);
    final JobManagerTable jobManagerTable = new JobManagerTable();
    final JobLeaderService jobLeaderService = new JobLeaderService(taskManagerLocation);
    final TestingFatalErrorHandler testingFatalErrorHandler = new TestingFatalErrorHandler();
    final String resourceManagerAddress = "rm";
    final UUID resourceManagerLeaderId = UUID.randomUUID();
    final String jobManagerAddress = "jm";
    final UUID jobManagerLeaderId = UUID.randomUUID();
    final LeaderRetrievalService resourceManagerLeaderRetrievalService = new TestingLeaderRetrievalService(resourceManagerAddress, resourceManagerLeaderId);
    final LeaderRetrievalService jobManagerLeaderRetrievalService = new TestingLeaderRetrievalService(jobManagerAddress, jobManagerLeaderId);
    haServices.setResourceManagerLeaderRetriever(resourceManagerLeaderRetrievalService);
    haServices.setJobMasterLeaderRetriever(jobId, jobManagerLeaderRetrievalService);
    final ResourceManagerGateway resourceManagerGateway = mock(ResourceManagerGateway.class);
    final InstanceID registrationId = new InstanceID();
    when(resourceManagerGateway.registerTaskExecutor(eq(resourceManagerLeaderId), any(String.class), eq(resourceId), any(SlotReport.class), any(Time.class))).thenReturn(FlinkCompletableFuture.<RegistrationResponse>completed(new TaskExecutorRegistrationSuccess(registrationId, 1000L)));
    final ResourceID jmResourceId = new ResourceID(jobManagerAddress);
    final int blobPort = 42;
    final AllocationID allocationId1 = new AllocationID();
    final AllocationID allocationId2 = new AllocationID();
    final SlotOffer offer1 = new SlotOffer(allocationId1, 0, ResourceProfile.UNKNOWN);
    final JobMasterGateway jobMasterGateway = mock(JobMasterGateway.class);
    when(jobMasterGateway.registerTaskManager(any(String.class), eq(taskManagerLocation), eq(jobManagerLeaderId), any(Time.class))).thenReturn(FlinkCompletableFuture.<RegistrationResponse>completed(new JMTMRegistrationSuccess(jmResourceId, blobPort)));
    when(jobMasterGateway.getHostname()).thenReturn(jobManagerAddress);
    when(jobMasterGateway.offerSlots(any(ResourceID.class), any(Iterable.class), eq(jobManagerLeaderId), any(Time.class))).thenReturn(FlinkCompletableFuture.completed((Iterable<SlotOffer>) Collections.singleton(offer1)));
    rpc.registerGateway(resourceManagerAddress, resourceManagerGateway);
    rpc.registerGateway(jobManagerAddress, jobMasterGateway);
    try {
        TaskExecutor taskManager = new TaskExecutor(taskManagerConfiguration, taskManagerLocation, rpc, mock(MemoryManager.class), mock(IOManager.class), mock(NetworkEnvironment.class), haServices, mock(HeartbeatServices.class, RETURNS_MOCKS), mock(MetricRegistry.class), mock(TaskManagerMetricGroup.class), mock(BroadcastVariableManager.class), mock(FileCache.class), taskSlotTable, jobManagerTable, jobLeaderService, testingFatalErrorHandler);
        taskManager.start();
        taskSlotTable.allocateSlot(0, jobId, allocationId1, Time.milliseconds(10000L));
        taskSlotTable.allocateSlot(1, jobId, allocationId2, Time.milliseconds(10000L));
        // we have to add the job after the TaskExecutor, because otherwise the service has not
        // been properly started.
        jobLeaderService.addJob(jobId, jobManagerAddress);
        verify(resourceManagerGateway).notifySlotAvailable(eq(resourceManagerLeaderId), eq(registrationId), eq(new SlotID(resourceId, 1)));
        assertTrue(taskSlotTable.existsActiveSlot(jobId, allocationId1));
        assertFalse(taskSlotTable.existsActiveSlot(jobId, allocationId2));
        assertTrue(taskSlotTable.isSlotFree(1));
        // check if a concurrent error occurred
        testingFatalErrorHandler.rethrowError();
    } finally {
        rpc.stopService();
    }
}