Examples with ConnectorAwareSplitSource io.trino.split.ConnectorAwareSplitSource used on opensource projects

Example 1 with ConnectorAwareSplitSource

use of io.trino.split.ConnectorAwareSplitSource in project trino by trinodb.

the class TestSourcePartitionedScheduler method testNewTaskScheduledWhenChildStageBufferIsUnderutilized.

@Test
public void testNewTaskScheduledWhenChildStageBufferIsUnderutilized() {
    NodeTaskMap nodeTaskMap = new NodeTaskMap(finalizerService);
    // use private node manager so we can add a node later
    InMemoryNodeManager nodeManager = new InMemoryNodeManager();
    nodeManager.addNode(CONNECTOR_ID, new InternalNode("other1", URI.create("http://127.0.0.1:11"), NodeVersion.UNKNOWN, false), new InternalNode("other2", URI.create("http://127.0.0.1:12"), NodeVersion.UNKNOWN, false), new InternalNode("other3", URI.create("http://127.0.0.1:13"), NodeVersion.UNKNOWN, false));
    NodeScheduler nodeScheduler = new NodeScheduler(new UniformNodeSelectorFactory(nodeManager, new NodeSchedulerConfig().setIncludeCoordinator(false), nodeTaskMap, new Duration(0, SECONDS)));
    PlanFragment plan = createFragment();
    StageExecution stage = createStageExecution(plan, nodeTaskMap);
    // setting under utilized child output buffer
    StageScheduler scheduler = newSourcePartitionedSchedulerAsStageScheduler(stage, TABLE_SCAN_NODE_ID, new ConnectorAwareSplitSource(CONNECTOR_ID, createFixedSplitSource(500, TestingSplit::createRemoteSplit)), new DynamicSplitPlacementPolicy(nodeScheduler.createNodeSelector(session, Optional.of(CONNECTOR_ID)), stage::getAllTasks), 500, new DynamicFilterService(metadata, functionManager, typeOperators, new DynamicFilterConfig()), new TableExecuteContextManager(), () -> false);
    // the queues of 3 running nodes should be full
    ScheduleResult scheduleResult = scheduler.schedule();
    assertEquals(scheduleResult.getBlockedReason().get(), SPLIT_QUEUES_FULL);
    assertEquals(scheduleResult.getNewTasks().size(), 3);
    assertEquals(scheduleResult.getSplitsScheduled(), 300);
    for (RemoteTask remoteTask : scheduleResult.getNewTasks()) {
        PartitionedSplitsInfo splitsInfo = remoteTask.getPartitionedSplitsInfo();
        assertEquals(splitsInfo.getCount(), 100);
    }
    // new node added - the pending splits should go to it since the child tasks are not blocked
    nodeManager.addNode(CONNECTOR_ID, new InternalNode("other4", URI.create("http://127.0.0.4:14"), NodeVersion.UNKNOWN, false));
    scheduleResult = scheduler.schedule();
    // split queue is full but still the source task creation isn't blocked
    assertEquals(scheduleResult.getBlockedReason().get(), SPLIT_QUEUES_FULL);
    assertEquals(scheduleResult.getNewTasks().size(), 1);
    assertEquals(scheduleResult.getSplitsScheduled(), 100);
}

Example 2 with ConnectorAwareSplitSource

use of io.trino.split.ConnectorAwareSplitSource in project trino by trinodb.

the class TestSourcePartitionedScheduler method testNoNewTaskScheduledWhenChildStageBufferIsOverutilized.

@Test
public void testNoNewTaskScheduledWhenChildStageBufferIsOverutilized() {
    NodeTaskMap nodeTaskMap = new NodeTaskMap(finalizerService);
    // use private node manager so we can add a node later
    InMemoryNodeManager nodeManager = new InMemoryNodeManager();
    nodeManager.addNode(CONNECTOR_ID, new InternalNode("other1", URI.create("http://127.0.0.1:11"), NodeVersion.UNKNOWN, false), new InternalNode("other2", URI.create("http://127.0.0.1:12"), NodeVersion.UNKNOWN, false), new InternalNode("other3", URI.create("http://127.0.0.1:13"), NodeVersion.UNKNOWN, false));
    NodeScheduler nodeScheduler = new NodeScheduler(new UniformNodeSelectorFactory(nodeManager, new NodeSchedulerConfig().setIncludeCoordinator(false), nodeTaskMap, new Duration(0, SECONDS)));
    PlanFragment plan = createFragment();
    StageExecution stage = createStageExecution(plan, nodeTaskMap);
    // setting over utilized child output buffer
    StageScheduler scheduler = newSourcePartitionedSchedulerAsStageScheduler(stage, TABLE_SCAN_NODE_ID, new ConnectorAwareSplitSource(CONNECTOR_ID, createFixedSplitSource(400, TestingSplit::createRemoteSplit)), new DynamicSplitPlacementPolicy(nodeScheduler.createNodeSelector(session, Optional.of(CONNECTOR_ID)), stage::getAllTasks), 400, new DynamicFilterService(metadata, functionManager, typeOperators, new DynamicFilterConfig()), new TableExecuteContextManager(), () -> true);
    // the queues of 3 running nodes should be full
    ScheduleResult scheduleResult = scheduler.schedule();
    assertEquals(scheduleResult.getBlockedReason().get(), SPLIT_QUEUES_FULL);
    assertEquals(scheduleResult.getNewTasks().size(), 3);
    assertEquals(scheduleResult.getSplitsScheduled(), 300);
    for (RemoteTask remoteTask : scheduleResult.getNewTasks()) {
        PartitionedSplitsInfo splitsInfo = remoteTask.getPartitionedSplitsInfo();
        assertEquals(splitsInfo.getCount(), 100);
    }
    // new node added but 1 child's output buffer is overutilized - so lockdown the tasks
    nodeManager.addNode(CONNECTOR_ID, new InternalNode("other4", URI.create("http://127.0.0.4:14"), NodeVersion.UNKNOWN, false));
    scheduleResult = scheduler.schedule();
    assertEquals(scheduleResult.getBlockedReason().get(), SPLIT_QUEUES_FULL);
    assertEquals(scheduleResult.getNewTasks().size(), 0);
    assertEquals(scheduleResult.getSplitsScheduled(), 0);
}

Example 3 with ConnectorAwareSplitSource

use of io.trino.split.ConnectorAwareSplitSource in project trino by trinodb.

the class TestSourcePartitionedScheduler method getSourcePartitionedScheduler.

private StageScheduler getSourcePartitionedScheduler(ConnectorSplitSource splitSource, StageExecution stage, InternalNodeManager nodeManager, NodeTaskMap nodeTaskMap, int splitBatchSize, SplitsBalancingPolicy splitsBalancingPolicy) {
    NodeSchedulerConfig nodeSchedulerConfig = new NodeSchedulerConfig().setIncludeCoordinator(false).setMaxSplitsPerNode(20).setMaxPendingSplitsPerTask(0).setSplitsBalancingPolicy(splitsBalancingPolicy);
    NodeScheduler nodeScheduler = new NodeScheduler(new UniformNodeSelectorFactory(nodeManager, nodeSchedulerConfig, nodeTaskMap, new Duration(0, SECONDS)));
    SplitPlacementPolicy placementPolicy = new DynamicSplitPlacementPolicy(nodeScheduler.createNodeSelector(session, Optional.of(CONNECTOR_ID)), stage::getAllTasks);
    return newSourcePartitionedSchedulerAsStageScheduler(stage, TABLE_SCAN_NODE_ID, new ConnectorAwareSplitSource(CONNECTOR_ID, splitSource), placementPolicy, splitBatchSize, new DynamicFilterService(metadata, functionManager, typeOperators, new DynamicFilterConfig()), new TableExecuteContextManager(), () -> false);
}

Example 4 with ConnectorAwareSplitSource

use of io.trino.split.ConnectorAwareSplitSource in project trino by trinodb.

the class TestSourcePartitionedScheduler method testDynamicFiltersUnblockedOnBlockedBuildSource.

@Test
public void testDynamicFiltersUnblockedOnBlockedBuildSource() {
    PlanFragment plan = createFragment();
    NodeTaskMap nodeTaskMap = new NodeTaskMap(finalizerService);
    StageExecution stage = createStageExecution(plan, nodeTaskMap);
    NodeScheduler nodeScheduler = new NodeScheduler(new UniformNodeSelectorFactory(nodeManager, new NodeSchedulerConfig().setIncludeCoordinator(false), nodeTaskMap));
    DynamicFilterService dynamicFilterService = new DynamicFilterService(metadata, functionManager, typeOperators, new DynamicFilterConfig());
    dynamicFilterService.registerQuery(QUERY_ID, TEST_SESSION, ImmutableSet.of(DYNAMIC_FILTER_ID), ImmutableSet.of(DYNAMIC_FILTER_ID), ImmutableSet.of(DYNAMIC_FILTER_ID));
    StageScheduler scheduler = newSourcePartitionedSchedulerAsStageScheduler(stage, TABLE_SCAN_NODE_ID, new ConnectorAwareSplitSource(CONNECTOR_ID, createBlockedSplitSource()), new DynamicSplitPlacementPolicy(nodeScheduler.createNodeSelector(session, Optional.of(CONNECTOR_ID)), stage::getAllTasks), 2, dynamicFilterService, new TableExecuteContextManager(), () -> true);
    SymbolAllocator symbolAllocator = new SymbolAllocator();
    Symbol symbol = symbolAllocator.newSymbol("DF_SYMBOL1", BIGINT);
    DynamicFilter dynamicFilter = dynamicFilterService.createDynamicFilter(QUERY_ID, ImmutableList.of(new DynamicFilters.Descriptor(DYNAMIC_FILTER_ID, symbol.toSymbolReference())), ImmutableMap.of(symbol, new TestingColumnHandle("probeColumnA")), symbolAllocator.getTypes());
    // make sure dynamic filtering collecting task was created immediately
    assertEquals(stage.getState(), PLANNED);
    scheduler.start();
    assertEquals(stage.getAllTasks().size(), 1);
    assertEquals(stage.getState(), SCHEDULING);
    // make sure dynamic filter is initially blocked
    assertFalse(dynamicFilter.isBlocked().isDone());
    // make sure dynamic filter is unblocked due to build side source tasks being blocked
    ScheduleResult scheduleResult = scheduler.schedule();
    assertTrue(dynamicFilter.isBlocked().isDone());
    // no new probe splits should be scheduled
    assertEquals(scheduleResult.getSplitsScheduled(), 0);
}