Examples with NodeAddedSchedulerEvent org.apache.hadoop.yarn.server.resourcemanager.scheduler.event.NodeAddedSchedulerEvent used on opensource projects

Example 21 with NodeAddedSchedulerEvent

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

the class TestFairScheduler method testReservationMetrics.

@Test
public void testReservationMetrics() throws IOException {
    scheduler.init(conf);
    scheduler.start();
    scheduler.reinitialize(conf, resourceManager.getRMContext());
    QueueMetrics metrics = scheduler.getRootQueueMetrics();
    RMNode node1 = MockNodes.newNodeInfo(1, Resources.createResource(4096, 4), 1, "127.0.0.1");
    NodeAddedSchedulerEvent nodeEvent = new NodeAddedSchedulerEvent(node1);
    scheduler.handle(nodeEvent);
    ApplicationAttemptId appAttemptId = createAppAttemptId(1, 1);
    createApplicationWithAMResource(appAttemptId, "default", "user1", null);
    NodeUpdateSchedulerEvent updateEvent = new NodeUpdateSchedulerEvent(node1);
    scheduler.update();
    scheduler.handle(updateEvent);
    createSchedulingRequestExistingApplication(1024, 1, 1, appAttemptId);
    scheduler.update();
    scheduler.handle(updateEvent);
    // no reservation yet
    assertEquals(0, metrics.getReservedContainers());
    assertEquals(0, metrics.getReservedMB());
    assertEquals(0, metrics.getReservedVirtualCores());
    // create reservation of {4096, 4}
    createSchedulingRequestExistingApplication(4096, 4, 1, appAttemptId);
    scheduler.update();
    scheduler.handle(updateEvent);
    // reservation created
    assertEquals(1, metrics.getReservedContainers());
    assertEquals(4096, metrics.getReservedMB());
    assertEquals(4, metrics.getReservedVirtualCores());
    // remove AppAttempt
    AppAttemptRemovedSchedulerEvent attRemoveEvent = new AppAttemptRemovedSchedulerEvent(appAttemptId, RMAppAttemptState.KILLED, false);
    scheduler.handle(attRemoveEvent);
    // The reservation metrics should be subtracted
    assertEquals(0, metrics.getReservedContainers());
    assertEquals(0, metrics.getReservedMB());
    assertEquals(0, metrics.getReservedVirtualCores());
}

Example 22 with NodeAddedSchedulerEvent

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

the class TestFairScheduler method testStrictLocality.

@Test
public void testStrictLocality() throws IOException {
    scheduler.init(conf);
    scheduler.start();
    scheduler.reinitialize(conf, resourceManager.getRMContext());
    RMNode node1 = MockNodes.newNodeInfo(1, Resources.createResource(1024), 1, "127.0.0.1");
    NodeAddedSchedulerEvent nodeEvent1 = new NodeAddedSchedulerEvent(node1);
    scheduler.handle(nodeEvent1);
    RMNode node2 = MockNodes.newNodeInfo(1, Resources.createResource(1024), 2, "127.0.0.2");
    NodeAddedSchedulerEvent nodeEvent2 = new NodeAddedSchedulerEvent(node2);
    scheduler.handle(nodeEvent2);
    ApplicationAttemptId attId1 = createSchedulingRequest(1024, "queue1", "user1", 0);
    ResourceRequest nodeRequest = createResourceRequest(1024, node1.getHostName(), 1, 1, true);
    ResourceRequest rackRequest = createResourceRequest(1024, node1.getRackName(), 1, 1, false);
    ResourceRequest anyRequest = createResourceRequest(1024, ResourceRequest.ANY, 1, 1, false);
    createSchedulingRequestExistingApplication(nodeRequest, attId1);
    createSchedulingRequestExistingApplication(rackRequest, attId1);
    createSchedulingRequestExistingApplication(anyRequest, attId1);
    scheduler.update();
    NodeUpdateSchedulerEvent node1UpdateEvent = new NodeUpdateSchedulerEvent(node1);
    NodeUpdateSchedulerEvent node2UpdateEvent = new NodeUpdateSchedulerEvent(node2);
    // no matter how many heartbeats, node2 should never get a container
    FSAppAttempt app = scheduler.getSchedulerApp(attId1);
    for (int i = 0; i < 10; i++) {
        scheduler.handle(node2UpdateEvent);
        assertEquals(0, app.getLiveContainers().size());
        assertEquals(0, app.getReservedContainers().size());
    }
    // then node1 should get the container
    scheduler.handle(node1UpdateEvent);
    assertEquals(1, app.getLiveContainers().size());
}

Example 23 with NodeAddedSchedulerEvent

use of org.apache.hadoop.yarn.server.resourcemanager.scheduler.event.NodeAddedSchedulerEvent 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);
}

Example 24 with NodeAddedSchedulerEvent

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

the class TestFifoScheduler method testBlackListNodes.

@Test(timeout = 50000)
public void testBlackListNodes() throws Exception {
    Configuration conf = new Configuration();
    conf.setClass(YarnConfiguration.RM_SCHEDULER, FifoScheduler.class, ResourceScheduler.class);
    MockRM rm = new MockRM(conf);
    rm.start();
    FifoScheduler fs = (FifoScheduler) rm.getResourceScheduler();
    int rack_num_0 = 0;
    int rack_num_1 = 1;
    // Add 4 nodes in 2 racks
    // host_0_0 in rack0
    String host_0_0 = "127.0.0.1";
    RMNode n1 = MockNodes.newNodeInfo(rack_num_0, MockNodes.newResource(4 * GB), 1, host_0_0);
    fs.handle(new NodeAddedSchedulerEvent(n1));
    // host_0_1 in rack0
    String host_0_1 = "127.0.0.2";
    RMNode n2 = MockNodes.newNodeInfo(rack_num_0, MockNodes.newResource(4 * GB), 1, host_0_1);
    fs.handle(new NodeAddedSchedulerEvent(n2));
    // host_1_0 in rack1
    String host_1_0 = "127.0.0.3";
    RMNode n3 = MockNodes.newNodeInfo(rack_num_1, MockNodes.newResource(4 * GB), 1, host_1_0);
    fs.handle(new NodeAddedSchedulerEvent(n3));
    // host_1_1 in rack1
    String host_1_1 = "127.0.0.4";
    RMNode n4 = MockNodes.newNodeInfo(rack_num_1, MockNodes.newResource(4 * GB), 1, host_1_1);
    fs.handle(new NodeAddedSchedulerEvent(n4));
    // Add one application
    ApplicationId appId1 = BuilderUtils.newApplicationId(100, 1);
    ApplicationAttemptId appAttemptId1 = BuilderUtils.newApplicationAttemptId(appId1, 1);
    createMockRMApp(appAttemptId1, rm.getRMContext());
    SchedulerEvent appEvent = new AppAddedSchedulerEvent(appId1, "queue", "user");
    fs.handle(appEvent);
    SchedulerEvent attemptEvent = new AppAttemptAddedSchedulerEvent(appAttemptId1, false);
    fs.handle(attemptEvent);
    List<ContainerId> emptyId = new ArrayList<ContainerId>();
    List<ResourceRequest> emptyAsk = new ArrayList<ResourceRequest>();
    // Allow rack-locality for rack_1, but blacklist host_1_0
    // Set up resource requests
    // Ask for a 1 GB container for app 1
    List<ResourceRequest> ask1 = new ArrayList<ResourceRequest>();
    ask1.add(BuilderUtils.newResourceRequest(BuilderUtils.newPriority(0), "rack1", BuilderUtils.newResource(GB, 1), 1, RMNodeLabelsManager.NO_LABEL));
    ask1.add(BuilderUtils.newResourceRequest(BuilderUtils.newPriority(0), ResourceRequest.ANY, BuilderUtils.newResource(GB, 1), 1, RMNodeLabelsManager.NO_LABEL));
    fs.allocate(appAttemptId1, ask1, emptyId, Collections.singletonList(host_1_0), null, NULL_UPDATE_REQUESTS);
    // Trigger container assignment
    fs.handle(new NodeUpdateSchedulerEvent(n3));
    // Get the allocation for the application and verify no allocation on
    // blacklist node
    Allocation allocation1 = fs.allocate(appAttemptId1, emptyAsk, emptyId, null, null, NULL_UPDATE_REQUESTS);
    Assert.assertEquals("allocation1", 0, allocation1.getContainers().size());
    // verify host_1_1 can get allocated as not in blacklist
    fs.handle(new NodeUpdateSchedulerEvent(n4));
    Allocation allocation2 = fs.allocate(appAttemptId1, emptyAsk, emptyId, null, null, NULL_UPDATE_REQUESTS);
    Assert.assertEquals("allocation2", 1, allocation2.getContainers().size());
    List<Container> containerList = allocation2.getContainers();
    for (Container container : containerList) {
        Assert.assertEquals("Container is allocated on n4", container.getNodeId(), n4.getNodeID());
    }
    // Ask for a 1 GB container again for app 1
    List<ResourceRequest> ask2 = new ArrayList<ResourceRequest>();
    // this time, rack0 is also in blacklist, so only host_1_1 is available to
    // be assigned
    ask2.add(BuilderUtils.newResourceRequest(BuilderUtils.newPriority(0), ResourceRequest.ANY, BuilderUtils.newResource(GB, 1), 1));
    fs.allocate(appAttemptId1, ask2, emptyId, Collections.singletonList("rack0"), null, NULL_UPDATE_REQUESTS);
    // verify n1 is not qualified to be allocated
    fs.handle(new NodeUpdateSchedulerEvent(n1));
    Allocation allocation3 = fs.allocate(appAttemptId1, emptyAsk, emptyId, null, null, NULL_UPDATE_REQUESTS);
    Assert.assertEquals("allocation3", 0, allocation3.getContainers().size());
    // verify n2 is not qualified to be allocated
    fs.handle(new NodeUpdateSchedulerEvent(n2));
    Allocation allocation4 = fs.allocate(appAttemptId1, emptyAsk, emptyId, null, null, NULL_UPDATE_REQUESTS);
    Assert.assertEquals("allocation4", 0, allocation4.getContainers().size());
    // verify n3 is not qualified to be allocated
    fs.handle(new NodeUpdateSchedulerEvent(n3));
    Allocation allocation5 = fs.allocate(appAttemptId1, emptyAsk, emptyId, null, null, NULL_UPDATE_REQUESTS);
    Assert.assertEquals("allocation5", 0, allocation5.getContainers().size());
    fs.handle(new NodeUpdateSchedulerEvent(n4));
    Allocation allocation6 = fs.allocate(appAttemptId1, emptyAsk, emptyId, null, null, NULL_UPDATE_REQUESTS);
    Assert.assertEquals("allocation6", 1, allocation6.getContainers().size());
    containerList = allocation6.getContainers();
    for (Container container : containerList) {
        Assert.assertEquals("Container is allocated on n4", container.getNodeId(), n4.getNodeID());
    }
    rm.stop();
}

Example 25 with NodeAddedSchedulerEvent

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

the class TestFifoScheduler method testNodeLocalAssignment.

@Test(timeout = 2000)
public void testNodeLocalAssignment() throws Exception {
    AsyncDispatcher dispatcher = new InlineDispatcher();
    Configuration conf = new Configuration();
    RMContainerTokenSecretManager containerTokenSecretManager = new RMContainerTokenSecretManager(conf);
    containerTokenSecretManager.rollMasterKey();
    NMTokenSecretManagerInRM nmTokenSecretManager = new NMTokenSecretManagerInRM(conf);
    nmTokenSecretManager.rollMasterKey();
    RMApplicationHistoryWriter writer = mock(RMApplicationHistoryWriter.class);
    FifoScheduler scheduler = new FifoScheduler();
    RMContext rmContext = new RMContextImpl(dispatcher, null, null, null, null, null, containerTokenSecretManager, nmTokenSecretManager, null, scheduler);
    rmContext.setSystemMetricsPublisher(mock(SystemMetricsPublisher.class));
    rmContext.setRMApplicationHistoryWriter(mock(RMApplicationHistoryWriter.class));
    ((RMContextImpl) rmContext).setYarnConfiguration(new YarnConfiguration());
    scheduler.setRMContext(rmContext);
    scheduler.init(conf);
    scheduler.start();
    scheduler.reinitialize(new Configuration(), rmContext);
    RMNode node0 = MockNodes.newNodeInfo(1, Resources.createResource(1024 * 64), 1, "127.0.0.1");
    NodeAddedSchedulerEvent nodeEvent1 = new NodeAddedSchedulerEvent(node0);
    scheduler.handle(nodeEvent1);
    int _appId = 1;
    int _appAttemptId = 1;
    ApplicationAttemptId appAttemptId = createAppAttemptId(_appId, _appAttemptId);
    createMockRMApp(appAttemptId, rmContext);
    AppAddedSchedulerEvent appEvent = new AppAddedSchedulerEvent(appAttemptId.getApplicationId(), "queue1", "user1");
    scheduler.handle(appEvent);
    AppAttemptAddedSchedulerEvent attemptEvent = new AppAttemptAddedSchedulerEvent(appAttemptId, false);
    scheduler.handle(attemptEvent);
    int memory = 64;
    int nConts = 3;
    int priority = 20;
    List<ResourceRequest> ask = new ArrayList<ResourceRequest>();
    ResourceRequest nodeLocal = createResourceRequest(memory, node0.getHostName(), priority, nConts);
    ResourceRequest rackLocal = createResourceRequest(memory, node0.getRackName(), priority, nConts);
    ResourceRequest any = createResourceRequest(memory, ResourceRequest.ANY, priority, nConts);
    ask.add(nodeLocal);
    ask.add(rackLocal);
    ask.add(any);
    scheduler.allocate(appAttemptId, ask, new ArrayList<ContainerId>(), null, null, NULL_UPDATE_REQUESTS);
    NodeUpdateSchedulerEvent node0Update = new NodeUpdateSchedulerEvent(node0);
    // Before the node update event, there are 3 local requests outstanding
    Assert.assertEquals(3, nodeLocal.getNumContainers());
    scheduler.handle(node0Update);
    // After the node update event, check that there are no more local requests
    // outstanding
    Assert.assertEquals(0, nodeLocal.getNumContainers());
    //Also check that the containers were scheduled
    SchedulerAppReport info = scheduler.getSchedulerAppInfo(appAttemptId);
    Assert.assertEquals(3, info.getLiveContainers().size());
    scheduler.stop();
}