use of org.apache.flink.runtime.leaderelection.TestingLeaderElectionService in project flink by apache.
the class ResourceManagerTaskExecutorTest method setup.
@Before
public void setup() throws Exception {
rpcService = new TestingSerialRpcService();
taskExecutorResourceID = mockTaskExecutor(taskExecutorAddress);
TestingLeaderElectionService rmLeaderElectionService = new TestingLeaderElectionService();
testingFatalErrorHandler = new TestingFatalErrorHandler();
resourceManager = createAndStartResourceManager(rmLeaderElectionService, testingFatalErrorHandler);
leaderSessionId = grantLeadership(rmLeaderElectionService);
}
use of org.apache.flink.runtime.leaderelection.TestingLeaderElectionService 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();
}
}
}
use of org.apache.flink.runtime.leaderelection.TestingLeaderElectionService in project flink by apache.
the class JobManagerHARecoveryTest method testFailingJobRecovery.
/**
* Tests that a failing job recovery won't cause other job recoveries to fail.
*/
@Test
public void testFailingJobRecovery() throws Exception {
final FiniteDuration timeout = new FiniteDuration(10, TimeUnit.SECONDS);
final FiniteDuration jobRecoveryTimeout = new FiniteDuration(0, TimeUnit.SECONDS);
Deadline deadline = new FiniteDuration(1, TimeUnit.MINUTES).fromNow();
final Configuration flinkConfiguration = new Configuration();
UUID leaderSessionID = UUID.randomUUID();
ActorRef jobManager = null;
JobID jobId1 = new JobID();
JobID jobId2 = new JobID();
// set HA mode to zookeeper so that we try to recover jobs
flinkConfiguration.setString(HighAvailabilityOptions.HA_MODE, "zookeeper");
try {
final SubmittedJobGraphStore submittedJobGraphStore = mock(SubmittedJobGraphStore.class);
SubmittedJobGraph submittedJobGraph = mock(SubmittedJobGraph.class);
when(submittedJobGraph.getJobId()).thenReturn(jobId2);
when(submittedJobGraphStore.getJobIds()).thenReturn(Arrays.asList(jobId1, jobId2));
// fail the first job recovery
when(submittedJobGraphStore.recoverJobGraph(eq(jobId1))).thenThrow(new Exception("Test exception"));
// succeed the second job recovery
when(submittedJobGraphStore.recoverJobGraph(eq(jobId2))).thenReturn(submittedJobGraph);
final TestingLeaderElectionService myLeaderElectionService = new TestingLeaderElectionService();
final Collection<JobID> recoveredJobs = new ArrayList<>(2);
Props jobManagerProps = Props.create(TestingFailingHAJobManager.class, flinkConfiguration, TestingUtils.defaultExecutor(), TestingUtils.defaultExecutor(), mock(InstanceManager.class), mock(Scheduler.class), new BlobLibraryCacheManager(mock(BlobService.class), 1 << 20), ActorRef.noSender(), new FixedDelayRestartStrategy.FixedDelayRestartStrategyFactory(Int.MaxValue(), 100), timeout, myLeaderElectionService, submittedJobGraphStore, mock(CheckpointRecoveryFactory.class), jobRecoveryTimeout, Option.<MetricRegistry>apply(null), recoveredJobs).withDispatcher(CallingThreadDispatcher.Id());
jobManager = system.actorOf(jobManagerProps);
Future<Object> started = Patterns.ask(jobManager, new Identify(42), deadline.timeLeft().toMillis());
Await.ready(started, deadline.timeLeft());
// make the job manager the leader --> this triggers the recovery of all jobs
myLeaderElectionService.isLeader(leaderSessionID);
// check that we have successfully recovered the second job
assertThat(recoveredJobs, containsInAnyOrder(jobId2));
} finally {
TestingUtils.stopActor(jobManager);
}
}
Aggregations