Search in sources :

Example 96 with NodeAddedSchedulerEvent

use of org.apache.hadoop.yarn.server.resourcemanager.scheduler.event.NodeAddedSchedulerEvent in project hadoop by apache.

the class TestOpportunisticContainerAllocatorAMService method testContainerPromoteAfterContainerComplete.

@Test(timeout = 600000)
public void testContainerPromoteAfterContainerComplete() 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("h2:1234", 4096, rm.getResourceTrackerService());
    nodes.put(nm2.getNodeId(), nm2);
    nm1.registerNode();
    nm2.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());
    nm1.nodeHeartbeat(true);
    nm2.nodeHeartbeat(true);
    ((RMNodeImpl) rmNode1).setOpportunisticContainersStatus(getOppurtunisticStatus(-1, 100));
    ((RMNodeImpl) rmNode2).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 NodeUpdateSchedulerEvent(rmNode1));
    amservice.handle(new NodeUpdateSchedulerEvent(rmNode2));
    // All nodes 1 to 2 will be applicable for scheduling.
    nm1.nodeHeartbeat(true);
    nm2.nodeHeartbeat(true);
    Thread.sleep(1000);
    QueueMetrics metrics = ((CapacityScheduler) scheduler).getRootQueue().getMetrics();
    // Verify Metrics
    verifyMetrics(metrics, 7168, 7, 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());
    // Start Container in NM
    allocNode.nodeHeartbeat(Arrays.asList(ContainerStatus.newInstance(container.getId(), ExecutionType.OPPORTUNISTIC, ContainerState.RUNNING, "", 0)), true);
    Thread.sleep(200);
    // Verify that container is actually running wrt the RM..
    RMContainer rmContainer = ((CapacityScheduler) scheduler).getApplicationAttempt(container.getId().getApplicationAttemptId()).getRMContainer(container.getId());
    Assert.assertEquals(RMContainerState.RUNNING, rmContainer.getState());
    // Container Completed in the NM
    allocNode.nodeHeartbeat(Arrays.asList(ContainerStatus.newInstance(container.getId(), ExecutionType.OPPORTUNISTIC, ContainerState.COMPLETE, "", 0)), true);
    Thread.sleep(200);
    // Verify that container has been removed..
    rmContainer = ((CapacityScheduler) scheduler).getApplicationAttempt(container.getId().getApplicationAttemptId()).getRMContainer(container.getId());
    Assert.assertNull(rmContainer);
    // Verify Metrics After OPP allocation (Nothing should change)
    verifyMetrics(metrics, 7168, 7, 1024, 1, 1);
    // Send Promotion req... this should result in update error
    // Since the container doesn't exist anymore..
    allocateResponse = am1.sendContainerUpdateRequest(Arrays.asList(UpdateContainerRequest.newInstance(0, container.getId(), ContainerUpdateType.PROMOTE_EXECUTION_TYPE, null, ExecutionType.GUARANTEED)));
    Assert.assertEquals(1, allocateResponse.getCompletedContainersStatuses().size());
    Assert.assertEquals(container.getId(), allocateResponse.getCompletedContainersStatuses().get(0).getContainerId());
    Assert.assertEquals(0, allocateResponse.getUpdatedContainers().size());
    Assert.assertEquals(1, allocateResponse.getUpdateErrors().size());
    Assert.assertEquals("INVALID_CONTAINER_ID", allocateResponse.getUpdateErrors().get(0).getReason());
    Assert.assertEquals(container.getId(), allocateResponse.getUpdateErrors().get(0).getUpdateContainerRequest().getContainerId());
    // Verify Metrics After OPP allocation (Nothing should change again)
    verifyMetrics(metrics, 7168, 7, 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) 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) CapacityScheduler(org.apache.hadoop.yarn.server.resourcemanager.scheduler.capacity.CapacityScheduler) Test(org.junit.Test)

Example 97 with NodeAddedSchedulerEvent

use of org.apache.hadoop.yarn.server.resourcemanager.scheduler.event.NodeAddedSchedulerEvent in project hadoop by apache.

the class OpportunisticContainerAllocatorAMService method handle.

@Override
public void handle(SchedulerEvent event) {
    switch(event.getType()) {
        case NODE_ADDED:
            if (!(event instanceof NodeAddedSchedulerEvent)) {
                throw new RuntimeException("Unexpected event type: " + event);
            }
            NodeAddedSchedulerEvent nodeAddedEvent = (NodeAddedSchedulerEvent) event;
            nodeMonitor.addNode(nodeAddedEvent.getContainerReports(), nodeAddedEvent.getAddedRMNode());
            break;
        case NODE_REMOVED:
            if (!(event instanceof NodeRemovedSchedulerEvent)) {
                throw new RuntimeException("Unexpected event type: " + event);
            }
            NodeRemovedSchedulerEvent nodeRemovedEvent = (NodeRemovedSchedulerEvent) event;
            nodeMonitor.removeNode(nodeRemovedEvent.getRemovedRMNode());
            break;
        case NODE_UPDATE:
            if (!(event instanceof NodeUpdateSchedulerEvent)) {
                throw new RuntimeException("Unexpected event type: " + event);
            }
            NodeUpdateSchedulerEvent nodeUpdatedEvent = (NodeUpdateSchedulerEvent) event;
            nodeMonitor.updateNode(nodeUpdatedEvent.getRMNode());
            break;
        case NODE_RESOURCE_UPDATE:
            if (!(event instanceof NodeResourceUpdateSchedulerEvent)) {
                throw new RuntimeException("Unexpected event type: " + event);
            }
            NodeResourceUpdateSchedulerEvent nodeResourceUpdatedEvent = (NodeResourceUpdateSchedulerEvent) event;
            nodeMonitor.updateNodeResource(nodeResourceUpdatedEvent.getRMNode(), nodeResourceUpdatedEvent.getResourceOption());
            break;
        // <-- IGNORED EVENTS : START -->
        case APP_ADDED:
            break;
        case APP_REMOVED:
            break;
        case APP_ATTEMPT_ADDED:
            break;
        case APP_ATTEMPT_REMOVED:
            break;
        case CONTAINER_EXPIRED:
            break;
        case NODE_LABELS_UPDATE:
            break;
        // <-- IGNORED EVENTS : END -->
        default:
            LOG.error("Unknown event arrived at" + "OpportunisticContainerAllocatorAMService: " + event.toString());
    }
}
Also used : NodeUpdateSchedulerEvent(org.apache.hadoop.yarn.server.resourcemanager.scheduler.event.NodeUpdateSchedulerEvent) NodeAddedSchedulerEvent(org.apache.hadoop.yarn.server.resourcemanager.scheduler.event.NodeAddedSchedulerEvent) NodeRemovedSchedulerEvent(org.apache.hadoop.yarn.server.resourcemanager.scheduler.event.NodeRemovedSchedulerEvent) NodeResourceUpdateSchedulerEvent(org.apache.hadoop.yarn.server.resourcemanager.scheduler.event.NodeResourceUpdateSchedulerEvent)

Aggregations

NodeAddedSchedulerEvent (org.apache.hadoop.yarn.server.resourcemanager.scheduler.event.NodeAddedSchedulerEvent)97 RMNode (org.apache.hadoop.yarn.server.resourcemanager.rmnode.RMNode)90 Test (org.junit.Test)83 ApplicationAttemptId (org.apache.hadoop.yarn.api.records.ApplicationAttemptId)62 NodeUpdateSchedulerEvent (org.apache.hadoop.yarn.server.resourcemanager.scheduler.event.NodeUpdateSchedulerEvent)61 FileWriter (java.io.FileWriter)24 PrintWriter (java.io.PrintWriter)24 NodeRemovedSchedulerEvent (org.apache.hadoop.yarn.server.resourcemanager.scheduler.event.NodeRemovedSchedulerEvent)21 ResourceRequest (org.apache.hadoop.yarn.api.records.ResourceRequest)19 MockRM (org.apache.hadoop.yarn.server.resourcemanager.MockRM)18 ContainerId (org.apache.hadoop.yarn.api.records.ContainerId)17 AppAttemptRemovedSchedulerEvent (org.apache.hadoop.yarn.server.resourcemanager.scheduler.event.AppAttemptRemovedSchedulerEvent)15 YarnConfiguration (org.apache.hadoop.yarn.conf.YarnConfiguration)14 ArrayList (java.util.ArrayList)13 RMContainer (org.apache.hadoop.yarn.server.resourcemanager.rmcontainer.RMContainer)13 Resource (org.apache.hadoop.yarn.api.records.Resource)12 AppAddedSchedulerEvent (org.apache.hadoop.yarn.server.resourcemanager.scheduler.event.AppAddedSchedulerEvent)11 AppAttemptAddedSchedulerEvent (org.apache.hadoop.yarn.server.resourcemanager.scheduler.event.AppAttemptAddedSchedulerEvent)11 ApplicationId (org.apache.hadoop.yarn.api.records.ApplicationId)10 Configuration (org.apache.hadoop.conf.Configuration)9