Examples with DualInputPlanNode org.apache.flink.optimizer.plan.DualInputPlanNode used on opensource projects

Example 16 with DualInputPlanNode

use of org.apache.flink.optimizer.plan.DualInputPlanNode in project flink by apache.

the class CoGroupCustomPartitioningTest method testIncompatibleHashAndCustomPartitioning.

@Test
public void testIncompatibleHashAndCustomPartitioning() {
    try {
        ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();
        DataSet<Tuple3<Long, Long, Long>> input = env.fromElements(new Tuple3<Long, Long, Long>(0L, 0L, 0L));
        DataSet<Tuple3<Long, Long, Long>> partitioned = input.partitionCustom(new Partitioner<Long>() {

            @Override
            public int partition(Long key, int numPartitions) {
                return 0;
            }
        }, 0).map(new IdentityMapper<Tuple3<Long, Long, Long>>()).withForwardedFields("0", "1", "2");
        DataSet<Tuple3<Long, Long, Long>> grouped = partitioned.distinct(0, 1).groupBy(1).sortGroup(0, Order.ASCENDING).reduceGroup(new IdentityGroupReducerCombinable<Tuple3<Long, Long, Long>>()).withForwardedFields("0", "1");
        grouped.coGroup(partitioned).where(0).equalTo(0).with(new DummyCoGroupFunction<Tuple3<Long, Long, Long>, Tuple3<Long, Long, Long>>()).output(new DiscardingOutputFormat<Tuple2<Tuple3<Long, Long, Long>, Tuple3<Long, Long, Long>>>());
        Plan p = env.createProgramPlan();
        OptimizedPlan op = compileNoStats(p);
        SinkPlanNode sink = op.getDataSinks().iterator().next();
        DualInputPlanNode coGroup = (DualInputPlanNode) sink.getInput().getSource();
        assertEquals(ShipStrategyType.PARTITION_HASH, coGroup.getInput1().getShipStrategy());
        assertTrue(coGroup.getInput2().getShipStrategy() == ShipStrategyType.PARTITION_HASH || coGroup.getInput2().getShipStrategy() == ShipStrategyType.FORWARD);
    } catch (Exception e) {
        e.printStackTrace();
        fail(e.getMessage());
    }
}

Example 17 with DualInputPlanNode

use of org.apache.flink.optimizer.plan.DualInputPlanNode in project flink by apache.

the class CoGroupCustomPartitioningTest method testCoGroupWithTuples.

@Test
public void testCoGroupWithTuples() {
    try {
        final Partitioner<Long> partitioner = new TestPartitionerLong();
        ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();
        DataSet<Tuple2<Long, Long>> input1 = env.fromElements(new Tuple2<Long, Long>(0L, 0L));
        DataSet<Tuple3<Long, Long, Long>> input2 = env.fromElements(new Tuple3<Long, Long, Long>(0L, 0L, 0L));
        input1.coGroup(input2).where(1).equalTo(0).withPartitioner(partitioner).with(new DummyCoGroupFunction<Tuple2<Long, Long>, Tuple3<Long, Long, Long>>()).output(new DiscardingOutputFormat<Tuple2<Tuple2<Long, Long>, Tuple3<Long, Long, Long>>>());
        Plan p = env.createProgramPlan();
        OptimizedPlan op = compileNoStats(p);
        SinkPlanNode sink = op.getDataSinks().iterator().next();
        DualInputPlanNode join = (DualInputPlanNode) sink.getInput().getSource();
        assertEquals(ShipStrategyType.PARTITION_CUSTOM, join.getInput1().getShipStrategy());
        assertEquals(ShipStrategyType.PARTITION_CUSTOM, join.getInput2().getShipStrategy());
        assertEquals(partitioner, join.getInput1().getPartitioner());
        assertEquals(partitioner, join.getInput2().getPartitioner());
    } catch (Exception e) {
        e.printStackTrace();
        fail(e.getMessage());
    }
}

Example 18 with DualInputPlanNode

use of org.apache.flink.optimizer.plan.DualInputPlanNode in project flink by apache.

the class CustomPartitioningGlobalOptimizationTest method testJoinReduceCombination.

@Test
public void testJoinReduceCombination() {
    try {
        final Partitioner<Long> partitioner = new TestPartitionerLong();
        ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();
        DataSet<Tuple2<Long, Long>> input1 = env.fromElements(new Tuple2<Long, Long>(0L, 0L));
        DataSet<Tuple3<Long, Long, Long>> input2 = env.fromElements(new Tuple3<Long, Long, Long>(0L, 0L, 0L));
        DataSet<Tuple3<Long, Long, Long>> joined = input1.join(input2).where(1).equalTo(0).projectFirst(0, 1).<Tuple3<Long, Long, Long>>projectSecond(2).withPartitioner(partitioner);
        joined.groupBy(1).withPartitioner(partitioner).reduceGroup(new IdentityGroupReducerCombinable<Tuple3<Long, Long, Long>>()).output(new DiscardingOutputFormat<Tuple3<Long, Long, Long>>());
        Plan p = env.createProgramPlan();
        OptimizedPlan op = compileNoStats(p);
        SinkPlanNode sink = op.getDataSinks().iterator().next();
        SingleInputPlanNode reducer = (SingleInputPlanNode) sink.getInput().getSource();
        assertTrue("Reduce is not chained, property reuse does not happen", reducer.getInput().getSource() instanceof DualInputPlanNode);
        DualInputPlanNode join = (DualInputPlanNode) reducer.getInput().getSource();
        assertEquals(ShipStrategyType.PARTITION_CUSTOM, join.getInput1().getShipStrategy());
        assertEquals(ShipStrategyType.PARTITION_CUSTOM, join.getInput2().getShipStrategy());
        assertEquals(partitioner, join.getInput1().getPartitioner());
        assertEquals(partitioner, join.getInput2().getPartitioner());
        assertEquals(ShipStrategyType.FORWARD, reducer.getInput().getShipStrategy());
    } catch (Exception e) {
        e.printStackTrace();
        fail(e.getMessage());
    }
}

Example 19 with DualInputPlanNode

use of org.apache.flink.optimizer.plan.DualInputPlanNode in project flink by apache.

the class PartitioningReusageTest method reuseBothPartitioningJoin5.

@Test
public void reuseBothPartitioningJoin5() {
    ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();
    DataSet<Tuple3<Integer, Integer, Integer>> set1 = env.readCsvFile(IN_FILE).types(Integer.class, Integer.class, Integer.class);
    DataSet<Tuple3<Integer, Integer, Integer>> set2 = env.readCsvFile(IN_FILE).types(Integer.class, Integer.class, Integer.class);
    DataSet<Tuple3<Integer, Integer, Integer>> joined = set1.partitionByHash(2).map(new MockMapper()).withForwardedFields("2").join(set2.partitionByHash(1).map(new MockMapper()).withForwardedFields("1"), JoinOperatorBase.JoinHint.REPARTITION_HASH_FIRST).where(0, 2).equalTo(2, 1).with(new MockJoin());
    joined.output(new DiscardingOutputFormat<Tuple3<Integer, Integer, Integer>>());
    Plan plan = env.createProgramPlan();
    OptimizedPlan oPlan = compileWithStats(plan);
    SinkPlanNode sink = oPlan.getDataSinks().iterator().next();
    DualInputPlanNode join = (DualInputPlanNode) sink.getInput().getSource();
    checkValidJoinInputProperties(join);
}

Example 20 with DualInputPlanNode

use of org.apache.flink.optimizer.plan.DualInputPlanNode in project flink by apache.

the class PartitioningReusageTest method reuseSinglePartitioningCoGroup5.

@Test
public void reuseSinglePartitioningCoGroup5() {
    ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();
    DataSet<Tuple3<Integer, Integer, Integer>> set1 = env.readCsvFile(IN_FILE).types(Integer.class, Integer.class, Integer.class);
    DataSet<Tuple3<Integer, Integer, Integer>> set2 = env.readCsvFile(IN_FILE).types(Integer.class, Integer.class, Integer.class);
    DataSet<Tuple3<Integer, Integer, Integer>> coGrouped = set1.coGroup(set2.partitionByHash(2).map(new MockMapper()).withForwardedFields("2")).where(0, 1).equalTo(2, 1).with(new MockCoGroup());
    coGrouped.output(new DiscardingOutputFormat<Tuple3<Integer, Integer, Integer>>());
    Plan plan = env.createProgramPlan();
    OptimizedPlan oPlan = compileWithStats(plan);
    SinkPlanNode sink = oPlan.getDataSinks().iterator().next();
    DualInputPlanNode coGroup = (DualInputPlanNode) sink.getInput().getSource();
    checkValidCoGroupInputProperties(coGroup);
}