Search in sources :

Example 66 with ApplicationAttemptId

use of org.apache.hadoop.yarn.api.records.ApplicationAttemptId in project hadoop by apache.

the class TestClientRMService method testGetApplicationAttempts.

@Test
public void testGetApplicationAttempts() throws YarnException, IOException {
    ClientRMService rmService = createRMService();
    RecordFactory recordFactory = RecordFactoryProvider.getRecordFactory(null);
    GetApplicationAttemptsRequest request = recordFactory.newRecordInstance(GetApplicationAttemptsRequest.class);
    ApplicationAttemptId attemptId = ApplicationAttemptId.newInstance(ApplicationId.newInstance(123456, 1), 1);
    request.setApplicationId(ApplicationId.newInstance(123456, 1));
    try {
        GetApplicationAttemptsResponse response = rmService.getApplicationAttempts(request);
        Assert.assertEquals(1, response.getApplicationAttemptList().size());
        Assert.assertEquals(attemptId, response.getApplicationAttemptList().get(0).getApplicationAttemptId());
    } catch (ApplicationNotFoundException ex) {
        Assert.fail(ex.getMessage());
    }
}
Also used : RecordFactory(org.apache.hadoop.yarn.factories.RecordFactory) ApplicationNotFoundException(org.apache.hadoop.yarn.exceptions.ApplicationNotFoundException) GetApplicationAttemptsRequest(org.apache.hadoop.yarn.api.protocolrecords.GetApplicationAttemptsRequest) ApplicationAttemptId(org.apache.hadoop.yarn.api.records.ApplicationAttemptId) GetApplicationAttemptsResponse(org.apache.hadoop.yarn.api.protocolrecords.GetApplicationAttemptsResponse) Test(org.junit.Test)

Example 67 with ApplicationAttemptId

use of org.apache.hadoop.yarn.api.records.ApplicationAttemptId in project hadoop by apache.

the class TestNodeBlacklistingOnAMFailures method makeAMContainerExit.

private void makeAMContainerExit(MockRM rm, ContainerId amContainer, MockNM node, int exitStatus) throws Exception, InterruptedException {
    ContainerStatus containerStatus = BuilderUtils.newContainerStatus(amContainer, ContainerState.COMPLETE, "", exitStatus, Resources.createResource(200));
    node.containerStatus(containerStatus);
    ApplicationAttemptId amAttemptID = amContainer.getApplicationAttemptId();
    rm.waitForState(amAttemptID, RMAppAttemptState.FAILED);
    rm.waitForState(amAttemptID.getApplicationId(), RMAppState.ACCEPTED);
}
Also used : ContainerStatus(org.apache.hadoop.yarn.api.records.ContainerStatus) ApplicationAttemptId(org.apache.hadoop.yarn.api.records.ApplicationAttemptId)

Example 68 with ApplicationAttemptId

use of org.apache.hadoop.yarn.api.records.ApplicationAttemptId in project hadoop by apache.

the class TestOpportunisticContainerAllocatorAMService method testContainerPromoteAndDemoteBeforeContainerStart.

@Test(timeout = 600000)
public void testContainerPromoteAndDemoteBeforeContainerStart() throws Exception {
    HashMap<NodeId, MockNM> nodes = new HashMap<>();
    MockNM nm1 = new MockNM("h1:1234", 4096, rm.getResourceTrackerService());
    nodes.put(nm1.getNodeId(), nm1);
    MockNM nm2 = new MockNM("h1:4321", 4096, rm.getResourceTrackerService());
    nodes.put(nm2.getNodeId(), nm2);
    MockNM nm3 = new MockNM("h2:1234", 4096, rm.getResourceTrackerService());
    nodes.put(nm3.getNodeId(), nm3);
    MockNM nm4 = new MockNM("h2:4321", 4096, rm.getResourceTrackerService());
    nodes.put(nm4.getNodeId(), nm4);
    nm1.registerNode();
    nm2.registerNode();
    nm3.registerNode();
    nm4.registerNode();
    OpportunisticContainerAllocatorAMService amservice = (OpportunisticContainerAllocatorAMService) rm.getApplicationMasterService();
    RMApp app1 = rm.submitApp(1 * GB, "app", "user", null, "default");
    ApplicationAttemptId attemptId = app1.getCurrentAppAttempt().getAppAttemptId();
    MockAM am1 = MockRM.launchAndRegisterAM(app1, rm, nm2);
    ResourceScheduler scheduler = rm.getResourceScheduler();
    RMNode rmNode1 = rm.getRMContext().getRMNodes().get(nm1.getNodeId());
    RMNode rmNode2 = rm.getRMContext().getRMNodes().get(nm2.getNodeId());
    RMNode rmNode3 = rm.getRMContext().getRMNodes().get(nm3.getNodeId());
    RMNode rmNode4 = rm.getRMContext().getRMNodes().get(nm4.getNodeId());
    nm1.nodeHeartbeat(true);
    nm2.nodeHeartbeat(true);
    nm3.nodeHeartbeat(true);
    nm4.nodeHeartbeat(true);
    ((RMNodeImpl) rmNode1).setOpportunisticContainersStatus(getOppurtunisticStatus(-1, 100));
    ((RMNodeImpl) rmNode2).setOpportunisticContainersStatus(getOppurtunisticStatus(-1, 100));
    ((RMNodeImpl) rmNode3).setOpportunisticContainersStatus(getOppurtunisticStatus(-1, 100));
    ((RMNodeImpl) rmNode4).setOpportunisticContainersStatus(getOppurtunisticStatus(-1, 100));
    OpportunisticContainerContext ctxt = ((CapacityScheduler) scheduler).getApplicationAttempt(attemptId).getOpportunisticContainerContext();
    // Send add and update node events to AM Service.
    amservice.handle(new NodeAddedSchedulerEvent(rmNode1));
    amservice.handle(new NodeAddedSchedulerEvent(rmNode2));
    amservice.handle(new NodeAddedSchedulerEvent(rmNode3));
    amservice.handle(new NodeAddedSchedulerEvent(rmNode4));
    amservice.handle(new NodeUpdateSchedulerEvent(rmNode1));
    amservice.handle(new NodeUpdateSchedulerEvent(rmNode2));
    amservice.handle(new NodeUpdateSchedulerEvent(rmNode3));
    amservice.handle(new NodeUpdateSchedulerEvent(rmNode4));
    // All nodes 1 - 4 will be applicable for scheduling.
    nm1.nodeHeartbeat(true);
    nm2.nodeHeartbeat(true);
    nm3.nodeHeartbeat(true);
    nm4.nodeHeartbeat(true);
    Thread.sleep(1000);
    QueueMetrics metrics = ((CapacityScheduler) scheduler).getRootQueue().getMetrics();
    // Verify Metrics
    verifyMetrics(metrics, 15360, 15, 1024, 1, 1);
    AllocateResponse allocateResponse = am1.allocate(Arrays.asList(ResourceRequest.newInstance(Priority.newInstance(1), "*", Resources.createResource(1 * GB), 2, true, null, ExecutionTypeRequest.newInstance(ExecutionType.OPPORTUNISTIC, true))), null);
    List<Container> allocatedContainers = allocateResponse.getAllocatedContainers();
    Assert.assertEquals(2, allocatedContainers.size());
    Container container = allocatedContainers.get(0);
    MockNM allocNode = nodes.get(container.getNodeId());
    MockNM sameHostDiffNode = null;
    for (NodeId n : nodes.keySet()) {
        if (n.getHost().equals(allocNode.getNodeId().getHost()) && n.getPort() != allocNode.getNodeId().getPort()) {
            sameHostDiffNode = nodes.get(n);
        }
    }
    // Verify Metrics After OPP allocation (Nothing should change)
    verifyMetrics(metrics, 15360, 15, 1024, 1, 1);
    am1.sendContainerUpdateRequest(Arrays.asList(UpdateContainerRequest.newInstance(0, container.getId(), ContainerUpdateType.PROMOTE_EXECUTION_TYPE, null, ExecutionType.GUARANTEED)));
    // Node on same host should not result in allocation
    sameHostDiffNode.nodeHeartbeat(true);
    Thread.sleep(200);
    allocateResponse = am1.allocate(new ArrayList<>(), new ArrayList<>());
    Assert.assertEquals(0, allocateResponse.getUpdatedContainers().size());
    // Verify Metrics After OPP allocation (Nothing should change again)
    verifyMetrics(metrics, 15360, 15, 1024, 1, 1);
    // Send Promotion req again... this should result in update error
    allocateResponse = am1.sendContainerUpdateRequest(Arrays.asList(UpdateContainerRequest.newInstance(0, container.getId(), ContainerUpdateType.PROMOTE_EXECUTION_TYPE, null, ExecutionType.GUARANTEED)));
    Assert.assertEquals(0, allocateResponse.getUpdatedContainers().size());
    Assert.assertEquals(1, allocateResponse.getUpdateErrors().size());
    Assert.assertEquals("UPDATE_OUTSTANDING_ERROR", allocateResponse.getUpdateErrors().get(0).getReason());
    Assert.assertEquals(container.getId(), allocateResponse.getUpdateErrors().get(0).getUpdateContainerRequest().getContainerId());
    // Send Promotion req again with incorrect version...
    // this should also result in update error
    allocateResponse = am1.sendContainerUpdateRequest(Arrays.asList(UpdateContainerRequest.newInstance(1, container.getId(), ContainerUpdateType.PROMOTE_EXECUTION_TYPE, null, ExecutionType.GUARANTEED)));
    Assert.assertEquals(0, allocateResponse.getUpdatedContainers().size());
    Assert.assertEquals(1, allocateResponse.getUpdateErrors().size());
    Assert.assertEquals("INCORRECT_CONTAINER_VERSION_ERROR", allocateResponse.getUpdateErrors().get(0).getReason());
    Assert.assertEquals(0, allocateResponse.getUpdateErrors().get(0).getCurrentContainerVersion());
    Assert.assertEquals(container.getId(), allocateResponse.getUpdateErrors().get(0).getUpdateContainerRequest().getContainerId());
    // Ensure after correct node heartbeats, we should get the allocation
    allocNode.nodeHeartbeat(true);
    Thread.sleep(200);
    allocateResponse = am1.allocate(new ArrayList<>(), new ArrayList<>());
    Assert.assertEquals(1, allocateResponse.getUpdatedContainers().size());
    Container uc = allocateResponse.getUpdatedContainers().get(0).getContainer();
    Assert.assertEquals(ExecutionType.GUARANTEED, uc.getExecutionType());
    Assert.assertEquals(uc.getId(), container.getId());
    Assert.assertEquals(uc.getVersion(), container.getVersion() + 1);
    // Verify Metrics After OPP allocation :
    // Allocated cores+mem should have increased, available should decrease
    verifyMetrics(metrics, 14336, 14, 2048, 2, 2);
    nm1.nodeHeartbeat(true);
    nm2.nodeHeartbeat(true);
    nm3.nodeHeartbeat(true);
    nm4.nodeHeartbeat(true);
    Thread.sleep(200);
    // Verify that the container is still in ACQUIRED state wrt the RM.
    RMContainer rmContainer = ((CapacityScheduler) scheduler).getApplicationAttempt(uc.getId().getApplicationAttemptId()).getRMContainer(uc.getId());
    Assert.assertEquals(RMContainerState.ACQUIRED, rmContainer.getState());
    // Now demote the container back..
    allocateResponse = am1.sendContainerUpdateRequest(Arrays.asList(UpdateContainerRequest.newInstance(uc.getVersion(), uc.getId(), ContainerUpdateType.DEMOTE_EXECUTION_TYPE, null, ExecutionType.OPPORTUNISTIC)));
    // This should happen in the same heartbeat..
    Assert.assertEquals(1, allocateResponse.getUpdatedContainers().size());
    uc = allocateResponse.getUpdatedContainers().get(0).getContainer();
    Assert.assertEquals(ExecutionType.OPPORTUNISTIC, uc.getExecutionType());
    Assert.assertEquals(uc.getId(), container.getId());
    Assert.assertEquals(uc.getVersion(), container.getVersion() + 2);
    // Verify Metrics After OPP allocation :
    // Everything should have reverted to what it was
    verifyMetrics(metrics, 15360, 15, 1024, 1, 1);
}
Also used : RMApp(org.apache.hadoop.yarn.server.resourcemanager.rmapp.RMApp) NodeUpdateSchedulerEvent(org.apache.hadoop.yarn.server.resourcemanager.scheduler.event.NodeUpdateSchedulerEvent) NodeAddedSchedulerEvent(org.apache.hadoop.yarn.server.resourcemanager.scheduler.event.NodeAddedSchedulerEvent) HashMap(java.util.HashMap) ArrayList(java.util.ArrayList) ApplicationAttemptId(org.apache.hadoop.yarn.api.records.ApplicationAttemptId) RMContainer(org.apache.hadoop.yarn.server.resourcemanager.rmcontainer.RMContainer) DistributedSchedulingAllocateResponse(org.apache.hadoop.yarn.server.api.protocolrecords.DistributedSchedulingAllocateResponse) AllocateResponse(org.apache.hadoop.yarn.api.protocolrecords.AllocateResponse) QueueMetrics(org.apache.hadoop.yarn.server.resourcemanager.scheduler.QueueMetrics) RMNode(org.apache.hadoop.yarn.server.resourcemanager.rmnode.RMNode) RMContainer(org.apache.hadoop.yarn.server.resourcemanager.rmcontainer.RMContainer) Container(org.apache.hadoop.yarn.api.records.Container) NodeId(org.apache.hadoop.yarn.api.records.NodeId) ResourceScheduler(org.apache.hadoop.yarn.server.resourcemanager.scheduler.ResourceScheduler) OpportunisticContainerContext(org.apache.hadoop.yarn.server.scheduler.OpportunisticContainerContext) RMNodeImpl(org.apache.hadoop.yarn.server.resourcemanager.rmnode.RMNodeImpl) Test(org.junit.Test)

Example 69 with ApplicationAttemptId

use of org.apache.hadoop.yarn.api.records.ApplicationAttemptId in project hadoop by apache.

the class TestClientRMService method testGetContainerReport.

@Test
public void testGetContainerReport() throws YarnException, IOException {
    ClientRMService rmService = createRMService();
    RecordFactory recordFactory = RecordFactoryProvider.getRecordFactory(null);
    GetContainerReportRequest request = recordFactory.newRecordInstance(GetContainerReportRequest.class);
    ApplicationAttemptId attemptId = ApplicationAttemptId.newInstance(ApplicationId.newInstance(123456, 1), 1);
    ContainerId containerId = ContainerId.newContainerId(attemptId, 1);
    request.setContainerId(containerId);
    try {
        GetContainerReportResponse response = rmService.getContainerReport(request);
        Assert.assertEquals(containerId, response.getContainerReport().getContainerId());
    } catch (ApplicationNotFoundException ex) {
        Assert.fail(ex.getMessage());
    }
}
Also used : RecordFactory(org.apache.hadoop.yarn.factories.RecordFactory) ContainerId(org.apache.hadoop.yarn.api.records.ContainerId) ApplicationNotFoundException(org.apache.hadoop.yarn.exceptions.ApplicationNotFoundException) GetContainerReportResponse(org.apache.hadoop.yarn.api.protocolrecords.GetContainerReportResponse) ApplicationAttemptId(org.apache.hadoop.yarn.api.records.ApplicationAttemptId) GetContainerReportRequest(org.apache.hadoop.yarn.api.protocolrecords.GetContainerReportRequest) Test(org.junit.Test)

Example 70 with ApplicationAttemptId

use of org.apache.hadoop.yarn.api.records.ApplicationAttemptId in project hadoop by apache.

the class TestClientRMService method testGetContainers.

@Test
public void testGetContainers() throws YarnException, IOException {
    ClientRMService rmService = createRMService();
    RecordFactory recordFactory = RecordFactoryProvider.getRecordFactory(null);
    GetContainersRequest request = recordFactory.newRecordInstance(GetContainersRequest.class);
    ApplicationAttemptId attemptId = ApplicationAttemptId.newInstance(ApplicationId.newInstance(123456, 1), 1);
    ContainerId containerId = ContainerId.newContainerId(attemptId, 1);
    request.setApplicationAttemptId(attemptId);
    try {
        GetContainersResponse response = rmService.getContainers(request);
        Assert.assertEquals(containerId, response.getContainerList().get(0).getContainerId());
    } catch (ApplicationNotFoundException ex) {
        Assert.fail(ex.getMessage());
    }
}
Also used : RecordFactory(org.apache.hadoop.yarn.factories.RecordFactory) ContainerId(org.apache.hadoop.yarn.api.records.ContainerId) ApplicationNotFoundException(org.apache.hadoop.yarn.exceptions.ApplicationNotFoundException) GetContainersResponse(org.apache.hadoop.yarn.api.protocolrecords.GetContainersResponse) ApplicationAttemptId(org.apache.hadoop.yarn.api.records.ApplicationAttemptId) GetContainersRequest(org.apache.hadoop.yarn.api.protocolrecords.GetContainersRequest) Test(org.junit.Test)

Aggregations

ApplicationAttemptId (org.apache.hadoop.yarn.api.records.ApplicationAttemptId)514 Test (org.junit.Test)362 ApplicationId (org.apache.hadoop.yarn.api.records.ApplicationId)222 ContainerId (org.apache.hadoop.yarn.api.records.ContainerId)170 YarnConfiguration (org.apache.hadoop.yarn.conf.YarnConfiguration)109 RMApp (org.apache.hadoop.yarn.server.resourcemanager.rmapp.RMApp)104 Configuration (org.apache.hadoop.conf.Configuration)87 Resource (org.apache.hadoop.yarn.api.records.Resource)82 ArrayList (java.util.ArrayList)75 NodeId (org.apache.hadoop.yarn.api.records.NodeId)74 NodeAddedSchedulerEvent (org.apache.hadoop.yarn.server.resourcemanager.scheduler.event.NodeAddedSchedulerEvent)65 RMNode (org.apache.hadoop.yarn.server.resourcemanager.rmnode.RMNode)63 NodeUpdateSchedulerEvent (org.apache.hadoop.yarn.server.resourcemanager.scheduler.event.NodeUpdateSchedulerEvent)60 Path (org.apache.hadoop.fs.Path)55 JobId (org.apache.hadoop.mapreduce.v2.api.records.JobId)53 Priority (org.apache.hadoop.yarn.api.records.Priority)52 RMContainer (org.apache.hadoop.yarn.server.resourcemanager.rmcontainer.RMContainer)51 Container (org.apache.hadoop.yarn.api.records.Container)50 FiCaSchedulerApp (org.apache.hadoop.yarn.server.resourcemanager.scheduler.common.fica.FiCaSchedulerApp)49 HashMap (java.util.HashMap)42