org.apache.flink.streaming.runtime.partitioner.ForwardPartitioner Java Examples

The following examples show how to use org.apache.flink.streaming.runtime.partitioner.ForwardPartitioner. You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may check out the related API usage on the sidebar.
Example #1
Source File: StreamGraphHasherV2.java    From Flink-CEPplus with Apache License 2.0 6 votes vote down vote up
private boolean isChainable(StreamEdge edge, boolean isChainingEnabled, StreamGraph streamGraph) {
	StreamNode upStreamVertex = streamGraph.getSourceVertex(edge);
	StreamNode downStreamVertex = streamGraph.getTargetVertex(edge);

	StreamOperator<?> headOperator = upStreamVertex.getOperator();
	StreamOperator<?> outOperator = downStreamVertex.getOperator();

	return downStreamVertex.getInEdges().size() == 1
			&& outOperator != null
			&& headOperator != null
			&& upStreamVertex.isSameSlotSharingGroup(downStreamVertex)
			&& outOperator.getChainingStrategy() == ChainingStrategy.ALWAYS
			&& (headOperator.getChainingStrategy() == ChainingStrategy.HEAD ||
			headOperator.getChainingStrategy() == ChainingStrategy.ALWAYS)
			&& (edge.getPartitioner() instanceof ForwardPartitioner)
			&& upStreamVertex.getParallelism() == downStreamVertex.getParallelism()
			&& isChainingEnabled;
}
 
Example #2
Source File: StreamingJobGraphGenerator.java    From Flink-CEPplus with Apache License 2.0 6 votes vote down vote up
public static boolean isChainable(StreamEdge edge, StreamGraph streamGraph) {
	StreamNode upStreamVertex = streamGraph.getSourceVertex(edge);
	StreamNode downStreamVertex = streamGraph.getTargetVertex(edge);

	StreamOperator<?> headOperator = upStreamVertex.getOperator();
	StreamOperator<?> outOperator = downStreamVertex.getOperator();

	return downStreamVertex.getInEdges().size() == 1
			&& outOperator != null
			&& headOperator != null
			&& upStreamVertex.isSameSlotSharingGroup(downStreamVertex)
			&& outOperator.getChainingStrategy() == ChainingStrategy.ALWAYS
			&& (headOperator.getChainingStrategy() == ChainingStrategy.HEAD ||
				headOperator.getChainingStrategy() == ChainingStrategy.ALWAYS)
			&& (edge.getPartitioner() instanceof ForwardPartitioner)
			&& upStreamVertex.getParallelism() == downStreamVertex.getParallelism()
			&& streamGraph.isChainingEnabled();
}
 
Example #3
Source File: DataStreamUtils.java    From flink with Apache License 2.0 6 votes vote down vote up
/**
 * Reinterprets the given {@link DataStream} as a {@link KeyedStream}, which extracts keys with the given
 * {@link KeySelector}.
 *
 * <p>IMPORTANT: For every partition of the base stream, the keys of events in the base stream must be
 * partitioned exactly in the same way as if it was created through a {@link DataStream#keyBy(KeySelector)}.
 *
 * @param stream      The data stream to reinterpret. For every partition, this stream must be partitioned exactly
 *                    in the same way as if it was created through a {@link DataStream#keyBy(KeySelector)}.
 * @param keySelector Function that defines how keys are extracted from the data stream.
 * @param typeInfo    Explicit type information about the key type.
 * @param <T>         Type of events in the data stream.
 * @param <K>         Type of the extracted keys.
 * @return The reinterpretation of the {@link DataStream} as a {@link KeyedStream}.
 */
public static <T, K> KeyedStream<T, K> reinterpretAsKeyedStream(
	DataStream<T> stream,
	KeySelector<T, K> keySelector,
	TypeInformation<K> typeInfo) {

	PartitionTransformation<T> partitionTransformation = new PartitionTransformation<>(
		stream.getTransformation(),
		new ForwardPartitioner<>());

	return new KeyedStream<>(
		stream,
		partitionTransformation,
		keySelector,
		typeInfo);
}
 
Example #4
Source File: StreamingJobGraphGeneratorWithGlobalDataExchangeModeTest.java    From flink with Apache License 2.0 6 votes vote down vote up
/**
 * Topology: source(parallelism=1) --(forward)--> map1(parallelism=1)
 *           --(rescale)--> map2(parallelism=2) --(rebalance)--> sink(parallelism=2).
 */
private static StreamGraph createStreamGraph() {
	final StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();

	final DataStream<Integer> source = env.fromElements(1, 2, 3).setParallelism(1);

	final DataStream<Integer> forward = new DataStream<>(env, new PartitionTransformation<>(
		source.getTransformation(), new ForwardPartitioner<>(), ShuffleMode.UNDEFINED));
	final DataStream<Integer> map1 = forward.map(i -> i).startNewChain().setParallelism(1);

	final DataStream<Integer> rescale = new DataStream<>(env, new PartitionTransformation<>(
		map1.getTransformation(), new RescalePartitioner<>(), ShuffleMode.UNDEFINED));
	final DataStream<Integer> map2 = rescale.map(i -> i).setParallelism(2);

	map2.rebalance().print().setParallelism(2);

	return env.getStreamGraph();
}
 
Example #5
Source File: StreamGraphHasherV2.java    From flink with Apache License 2.0 6 votes vote down vote up
private boolean isChainable(StreamEdge edge, boolean isChainingEnabled, StreamGraph streamGraph) {
	StreamNode upStreamVertex = streamGraph.getSourceVertex(edge);
	StreamNode downStreamVertex = streamGraph.getTargetVertex(edge);

	StreamOperatorFactory<?> headOperator = upStreamVertex.getOperatorFactory();
	StreamOperatorFactory<?> outOperator = downStreamVertex.getOperatorFactory();

	return downStreamVertex.getInEdges().size() == 1
			&& outOperator != null
			&& headOperator != null
			&& upStreamVertex.isSameSlotSharingGroup(downStreamVertex)
			&& outOperator.getChainingStrategy() == ChainingStrategy.ALWAYS
			&& (headOperator.getChainingStrategy() == ChainingStrategy.HEAD ||
			headOperator.getChainingStrategy() == ChainingStrategy.ALWAYS)
			&& (edge.getPartitioner() instanceof ForwardPartitioner)
			&& upStreamVertex.getParallelism() == downStreamVertex.getParallelism()
			&& isChainingEnabled;
}
 
Example #6
Source File: StreamingJobGraphGeneratorWithGlobalDataExchangeModeTest.java    From flink with Apache License 2.0 6 votes vote down vote up
@Test
public void testGlobalDataExchangeModeDoesNotOverrideSpecifiedShuffleMode() {
	final StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
	final DataStream<Integer> source = env.fromElements(1, 2, 3).setParallelism(1);
	final DataStream<Integer> forward = new DataStream<>(env, new PartitionTransformation<>(
		source.getTransformation(), new ForwardPartitioner<>(), ShuffleMode.PIPELINED));
	forward.map(i -> i).startNewChain().setParallelism(1);
	final StreamGraph streamGraph = env.getStreamGraph();
	streamGraph.setGlobalDataExchangeMode(GlobalDataExchangeMode.ALL_EDGES_BLOCKING);

	final JobGraph jobGraph = StreamingJobGraphGenerator.createJobGraph(streamGraph);

	final List<JobVertex> verticesSorted = jobGraph.getVerticesSortedTopologicallyFromSources();
	final JobVertex sourceVertex = verticesSorted.get(0);

	assertEquals(ResultPartitionType.PIPELINED_BOUNDED, sourceVertex.getProducedDataSets().get(0).getResultType());
}
 
Example #7
Source File: StreamingJobGraphGenerator.java    From flink with Apache License 2.0 6 votes vote down vote up
public static boolean isChainable(StreamEdge edge, StreamGraph streamGraph) {
	StreamNode upStreamVertex = streamGraph.getSourceVertex(edge);
	StreamNode downStreamVertex = streamGraph.getTargetVertex(edge);

	StreamOperatorFactory<?> headOperator = upStreamVertex.getOperatorFactory();
	StreamOperatorFactory<?> outOperator = downStreamVertex.getOperatorFactory();

	return downStreamVertex.getInEdges().size() == 1
			&& outOperator != null
			&& headOperator != null
			&& upStreamVertex.isSameSlotSharingGroup(downStreamVertex)
			&& outOperator.getChainingStrategy() == ChainingStrategy.ALWAYS
			&& (headOperator.getChainingStrategy() == ChainingStrategy.HEAD ||
				headOperator.getChainingStrategy() == ChainingStrategy.ALWAYS)
			&& (edge.getPartitioner() instanceof ForwardPartitioner)
			&& edge.getShuffleMode() != ShuffleMode.BATCH
			&& upStreamVertex.getParallelism() == downStreamVertex.getParallelism()
			&& streamGraph.isChainingEnabled();
}
 
Example #8
Source File: StreamingJobGraphGenerator.java    From flink with Apache License 2.0 6 votes vote down vote up
private ResultPartitionType determineResultPartitionType(StreamPartitioner<?> partitioner) {
	switch (streamGraph.getGlobalDataExchangeMode()) {
		case ALL_EDGES_BLOCKING:
			return ResultPartitionType.BLOCKING;
		case FORWARD_EDGES_PIPELINED:
			if (partitioner instanceof ForwardPartitioner) {
				return ResultPartitionType.PIPELINED_BOUNDED;
			} else {
				return ResultPartitionType.BLOCKING;
			}
		case POINTWISE_EDGES_PIPELINED:
			if (isPointwisePartitioner(partitioner)) {
				return ResultPartitionType.PIPELINED_BOUNDED;
			} else {
				return ResultPartitionType.BLOCKING;
			}
		case ALL_EDGES_PIPELINED:
			return ResultPartitionType.PIPELINED_BOUNDED;
		default:
			throw new RuntimeException("Unrecognized global data exchange mode " + streamGraph.getGlobalDataExchangeMode());
	}
}
 
Example #9
Source File: DataStreamUtils.java    From flink with Apache License 2.0 6 votes vote down vote up
/**
 * Reinterprets the given {@link DataStream} as a {@link KeyedStream}, which extracts keys with the given
 * {@link KeySelector}.
 *
 * <p>IMPORTANT: For every partition of the base stream, the keys of events in the base stream must be
 * partitioned exactly in the same way as if it was created through a {@link DataStream#keyBy(KeySelector)}.
 *
 * @param stream      The data stream to reinterpret. For every partition, this stream must be partitioned exactly
 *                    in the same way as if it was created through a {@link DataStream#keyBy(KeySelector)}.
 * @param keySelector Function that defines how keys are extracted from the data stream.
 * @param typeInfo    Explicit type information about the key type.
 * @param <T>         Type of events in the data stream.
 * @param <K>         Type of the extracted keys.
 * @return The reinterpretation of the {@link DataStream} as a {@link KeyedStream}.
 */
public static <T, K> KeyedStream<T, K> reinterpretAsKeyedStream(
	DataStream<T> stream,
	KeySelector<T, K> keySelector,
	TypeInformation<K> typeInfo) {

	PartitionTransformation<T> partitionTransformation = new PartitionTransformation<>(
		stream.getTransformation(),
		new ForwardPartitioner<>());

	return new KeyedStream<>(
		stream,
		partitionTransformation,
		keySelector,
		typeInfo);
}
 
Example #10
Source File: DataStreamUtils.java    From Flink-CEPplus with Apache License 2.0 6 votes vote down vote up
/**
 * Reinterprets the given {@link DataStream} as a {@link KeyedStream}, which extracts keys with the given
 * {@link KeySelector}.
 *
 * <p>IMPORTANT: For every partition of the base stream, the keys of events in the base stream must be
 * partitioned exactly in the same way as if it was created through a {@link DataStream#keyBy(KeySelector)}.
 *
 * @param stream      The data stream to reinterpret. For every partition, this stream must be partitioned exactly
 *                    in the same way as if it was created through a {@link DataStream#keyBy(KeySelector)}.
 * @param keySelector Function that defines how keys are extracted from the data stream.
 * @param typeInfo    Explicit type information about the key type.
 * @param <T>         Type of events in the data stream.
 * @param <K>         Type of the extracted keys.
 * @return The reinterpretation of the {@link DataStream} as a {@link KeyedStream}.
 */
public static <T, K> KeyedStream<T, K> reinterpretAsKeyedStream(
	DataStream<T> stream,
	KeySelector<T, K> keySelector,
	TypeInformation<K> typeInfo) {

	PartitionTransformation<T> partitionTransformation = new PartitionTransformation<>(
		stream.getTransformation(),
		new ForwardPartitioner<>());

	return new KeyedStream<>(
		stream,
		partitionTransformation,
		keySelector,
		typeInfo);
}
 
Example #11
Source File: StreamingJobGraphGeneratorTest.java    From flink with Apache License 2.0 5 votes vote down vote up
/**
 * Test setting shuffle mode to {@link ShuffleMode#UNDEFINED}.
 */
@Test
public void testShuffleModeUndefined() {
	StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
	// fromElements -> Map -> Print
	DataStream<Integer> sourceDataStream = env.fromElements(1, 2, 3);

	DataStream<Integer> partitionAfterSourceDataStream = new DataStream<>(env, new PartitionTransformation<>(
			sourceDataStream.getTransformation(), new ForwardPartitioner<>(), ShuffleMode.UNDEFINED));
	DataStream<Integer> mapDataStream = partitionAfterSourceDataStream.map(value -> value).setParallelism(1);

	DataStream<Integer> partitionAfterMapDataStream = new DataStream<>(env, new PartitionTransformation<>(
			mapDataStream.getTransformation(), new RescalePartitioner<>(), ShuffleMode.UNDEFINED));
	partitionAfterMapDataStream.print().setParallelism(2);

	JobGraph jobGraph = StreamingJobGraphGenerator.createJobGraph(env.getStreamGraph());

	List<JobVertex> verticesSorted = jobGraph.getVerticesSortedTopologicallyFromSources();
	assertEquals(2, verticesSorted.size());

	// it can be chained with UNDEFINED shuffle mode
	JobVertex sourceAndMapVertex = verticesSorted.get(0);

	// UNDEFINED shuffle mode is translated into PIPELINED_BOUNDED result partition by default
	assertEquals(ResultPartitionType.PIPELINED_BOUNDED,
		sourceAndMapVertex.getProducedDataSets().get(0).getResultType());
}
 
Example #12
Source File: StreamingJobGraphGeneratorTest.java    From flink with Apache License 2.0 5 votes vote down vote up
/**
 * Test setting shuffle mode to {@link ShuffleMode#UNDEFINED}.
 */
@Test
public void testShuffleModeUndefined() {
	StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
	// fromElements -> Map -> Print
	DataStream<Integer> sourceDataStream = env.fromElements(1, 2, 3);

	DataStream<Integer> partitionAfterSourceDataStream = new DataStream<>(env, new PartitionTransformation<>(
			sourceDataStream.getTransformation(), new ForwardPartitioner<>(), ShuffleMode.UNDEFINED));
	DataStream<Integer> mapDataStream = partitionAfterSourceDataStream.map(value -> value).setParallelism(1);

	DataStream<Integer> partitionAfterMapDataStream = new DataStream<>(env, new PartitionTransformation<>(
			mapDataStream.getTransformation(), new RescalePartitioner<>(), ShuffleMode.UNDEFINED));
	partitionAfterMapDataStream.print().setParallelism(2);

	JobGraph jobGraph = StreamingJobGraphGenerator.createJobGraph(env.getStreamGraph());

	List<JobVertex> verticesSorted = jobGraph.getVerticesSortedTopologicallyFromSources();
	assertEquals(2, verticesSorted.size());

	// it can be chained with UNDEFINED shuffle mode
	JobVertex sourceAndMapVertex = verticesSorted.get(0);

	// UNDEFINED shuffle mode is translated into PIPELINED_BOUNDED result partition by default
	assertEquals(ResultPartitionType.PIPELINED_BOUNDED,
		sourceAndMapVertex.getProducedDataSets().get(0).getResultType());
}
 
Example #13
Source File: StreamingJobGraphGeneratorTest.java    From flink with Apache License 2.0 5 votes vote down vote up
/**
 * Test setting shuffle mode to {@link ShuffleMode#BATCH}.
 */
@Test
public void testShuffleModeBatch() {
	StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
	// fromElements -> Map -> Print
	DataStream<Integer> sourceDataStream = env.fromElements(1, 2, 3);

	DataStream<Integer> partitionAfterSourceDataStream = new DataStream<>(env, new PartitionTransformation<>(
			sourceDataStream.getTransformation(), new ForwardPartitioner<>(), ShuffleMode.BATCH));
	DataStream<Integer> mapDataStream = partitionAfterSourceDataStream.map(value -> value).setParallelism(1);

	DataStream<Integer> partitionAfterMapDataStream = new DataStream<>(env, new PartitionTransformation<>(
			mapDataStream.getTransformation(), new RescalePartitioner<>(), ShuffleMode.BATCH));
	partitionAfterMapDataStream.print().setParallelism(2);

	JobGraph jobGraph = StreamingJobGraphGenerator.createJobGraph(env.getStreamGraph());

	List<JobVertex> verticesSorted = jobGraph.getVerticesSortedTopologicallyFromSources();
	assertEquals(3, verticesSorted.size());

	// it can not be chained with BATCH shuffle mode
	JobVertex sourceVertex = verticesSorted.get(0);
	JobVertex mapVertex = verticesSorted.get(1);

	// BATCH shuffle mode is translated into BLOCKING result partition
	assertEquals(ResultPartitionType.BLOCKING,
		sourceVertex.getProducedDataSets().get(0).getResultType());
	assertEquals(ResultPartitionType.BLOCKING,
		mapVertex.getProducedDataSets().get(0).getResultType());
}
 
Example #14
Source File: StreamingJobGraphGeneratorTest.java    From flink with Apache License 2.0 5 votes vote down vote up
/**
 * Test setting shuffle mode to {@link ShuffleMode#PIPELINED}.
 */
@Test
public void testShuffleModePipelined() {
	StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
	// fromElements -> Map -> Print
	DataStream<Integer> sourceDataStream = env.fromElements(1, 2, 3);

	DataStream<Integer> partitionAfterSourceDataStream = new DataStream<>(env, new PartitionTransformation<>(
			sourceDataStream.getTransformation(), new ForwardPartitioner<>(), ShuffleMode.PIPELINED));
	DataStream<Integer> mapDataStream = partitionAfterSourceDataStream.map(value -> value).setParallelism(1);

	DataStream<Integer> partitionAfterMapDataStream = new DataStream<>(env, new PartitionTransformation<>(
			mapDataStream.getTransformation(), new RescalePartitioner<>(), ShuffleMode.PIPELINED));
	partitionAfterMapDataStream.print().setParallelism(2);

	JobGraph jobGraph = StreamingJobGraphGenerator.createJobGraph(env.getStreamGraph());

	List<JobVertex> verticesSorted = jobGraph.getVerticesSortedTopologicallyFromSources();
	assertEquals(2, verticesSorted.size());

	// it can be chained with PIPELINED shuffle mode
	JobVertex sourceAndMapVertex = verticesSorted.get(0);

	// PIPELINED shuffle mode is translated into PIPELINED_BOUNDED result partition
	assertEquals(ResultPartitionType.PIPELINED_BOUNDED,
			sourceAndMapVertex.getProducedDataSets().get(0).getResultType());
}
 
Example #15
Source File: StreamingJobGraphGenerator.java    From flink with Apache License 2.0 5 votes vote down vote up
public static boolean isChainable(StreamEdge edge, StreamGraph streamGraph) {
	StreamNode upStreamVertex = streamGraph.getSourceVertex(edge);
	StreamNode downStreamVertex = streamGraph.getTargetVertex(edge);

	return downStreamVertex.getInEdges().size() == 1
			&& upStreamVertex.isSameSlotSharingGroup(downStreamVertex)
			&& areOperatorsChainable(upStreamVertex, downStreamVertex, streamGraph)
			&& (edge.getPartitioner() instanceof ForwardPartitioner)
			&& edge.getShuffleMode() != ShuffleMode.BATCH
			&& upStreamVertex.getParallelism() == downStreamVertex.getParallelism()
			&& streamGraph.isChainingEnabled();
}
 
Example #16
Source File: StreamingJobGraphGeneratorTest.java    From flink with Apache License 2.0 5 votes vote down vote up
/**
 * Test enabling the property "blockingConnectionsBetweenChains".
 */
@Test
public void testBlockingConnectionsBetweenChainsEnabled() {
	StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
	// fromElements -> Filter -> Map -> Print
	DataStream<Integer> sourceDataStream = env.fromElements(1, 2, 3);

	// partition transformation with an undefined shuffle mode between source and filter
	DataStream<Integer> partitionAfterSourceDataStream = new DataStream<>(env, new PartitionTransformation<>(
		sourceDataStream.getTransformation(), new RescalePartitioner<>(), ShuffleMode.UNDEFINED));
	DataStream<Integer> filterDataStream = partitionAfterSourceDataStream.filter(value -> true).setParallelism(2);

	DataStream<Integer> partitionAfterFilterDataStream = new DataStream<>(env, new PartitionTransformation<>(
		filterDataStream.getTransformation(), new ForwardPartitioner<>(), ShuffleMode.UNDEFINED));
	partitionAfterFilterDataStream.map(value -> value).setParallelism(2);

	DataStream<Integer> partitionAfterMapDataStream = new DataStream<>(env, new PartitionTransformation<>(
		filterDataStream.getTransformation(), new RescalePartitioner<>(), ShuffleMode.PIPELINED));
	partitionAfterMapDataStream.print().setParallelism(1);

	StreamGraph streamGraph = env.getStreamGraph();
	streamGraph.setBlockingConnectionsBetweenChains(true);
	JobGraph jobGraph = StreamingJobGraphGenerator.createJobGraph(streamGraph);

	List<JobVertex> verticesSorted = jobGraph.getVerticesSortedTopologicallyFromSources();
	assertEquals(3, verticesSorted.size());

	JobVertex sourceVertex = verticesSorted.get(0);
	// still can be chained
	JobVertex filterAndMapVertex = verticesSorted.get(1);
	JobVertex printVertex = verticesSorted.get(2);

	// the edge with undefined shuffle mode is translated into BLOCKING
	assertEquals(ResultPartitionType.BLOCKING, sourceVertex.getProducedDataSets().get(0).getResultType());
	// the edge with PIPELINED shuffle mode is translated into PIPELINED_BOUNDED
	assertEquals(ResultPartitionType.PIPELINED_BOUNDED, filterAndMapVertex.getProducedDataSets().get(0).getResultType());
	assertEquals(ResultPartitionType.PIPELINED_BOUNDED, printVertex.getInputs().get(0).getSource().getResultType());
}
 
Example #17
Source File: StreamingJobGraphGeneratorTest.java    From flink with Apache License 2.0 5 votes vote down vote up
/**
 * Verify that "blockingConnectionsBetweenChains" is off by default.
 */
@Test
public void testBlockingAfterChainingOffDisabled() {
	StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
	// fromElements -> Filter -> Print
	DataStream<Integer> sourceDataStream = env.fromElements(1, 2, 3);

	// partition transformation with an undefined shuffle mode between source and filter
	DataStream<Integer> partitionAfterSourceDataStream = new DataStream<>(env, new PartitionTransformation<>(
		sourceDataStream.getTransformation(), new RescalePartitioner<>(), ShuffleMode.UNDEFINED));
	DataStream<Integer> filterDataStream = partitionAfterSourceDataStream.filter(value -> true).setParallelism(2);

	DataStream<Integer> partitionAfterFilterDataStream = new DataStream<>(env, new PartitionTransformation<>(
		filterDataStream.getTransformation(), new ForwardPartitioner<>(), ShuffleMode.UNDEFINED));

	partitionAfterFilterDataStream.print().setParallelism(2);

	JobGraph jobGraph = StreamingJobGraphGenerator.createJobGraph(env.getStreamGraph());

	List<JobVertex> verticesSorted = jobGraph.getVerticesSortedTopologicallyFromSources();
	assertEquals(2, verticesSorted.size());

	JobVertex sourceVertex = verticesSorted.get(0);
	JobVertex filterAndPrintVertex = verticesSorted.get(1);

	assertEquals(ResultPartitionType.PIPELINED_BOUNDED, sourceVertex.getProducedDataSets().get(0).getResultType());
	assertEquals(ResultPartitionType.PIPELINED_BOUNDED,
			filterAndPrintVertex.getInputs().get(0).getSource().getResultType());
}
 
Example #18
Source File: StreamingJobGraphGeneratorTest.java    From flink with Apache License 2.0 5 votes vote down vote up
/**
 * Test setting shuffle mode to {@link ShuffleMode#BATCH}.
 */
@Test
public void testShuffleModeBatch() {
	StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
	// fromElements -> Map -> Print
	DataStream<Integer> sourceDataStream = env.fromElements(1, 2, 3);

	DataStream<Integer> partitionAfterSourceDataStream = new DataStream<>(env, new PartitionTransformation<>(
			sourceDataStream.getTransformation(), new ForwardPartitioner<>(), ShuffleMode.BATCH));
	DataStream<Integer> mapDataStream = partitionAfterSourceDataStream.map(value -> value).setParallelism(1);

	DataStream<Integer> partitionAfterMapDataStream = new DataStream<>(env, new PartitionTransformation<>(
			mapDataStream.getTransformation(), new RescalePartitioner<>(), ShuffleMode.BATCH));
	partitionAfterMapDataStream.print().setParallelism(2);

	JobGraph jobGraph = StreamingJobGraphGenerator.createJobGraph(env.getStreamGraph());

	List<JobVertex> verticesSorted = jobGraph.getVerticesSortedTopologicallyFromSources();
	assertEquals(3, verticesSorted.size());

	// it can not be chained with BATCH shuffle mode
	JobVertex sourceVertex = verticesSorted.get(0);
	JobVertex mapVertex = verticesSorted.get(1);

	// BATCH shuffle mode is translated into BLOCKING result partition
	assertEquals(ResultPartitionType.BLOCKING,
		sourceVertex.getProducedDataSets().get(0).getResultType());
	assertEquals(ResultPartitionType.BLOCKING,
		mapVertex.getProducedDataSets().get(0).getResultType());
}
 
Example #19
Source File: StreamingJobGraphGeneratorTest.java    From flink with Apache License 2.0 5 votes vote down vote up
/**
 * Test setting shuffle mode to {@link ShuffleMode#PIPELINED}.
 */
@Test
public void testShuffleModePipelined() {
	StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
	// fromElements -> Map -> Print
	DataStream<Integer> sourceDataStream = env.fromElements(1, 2, 3);

	DataStream<Integer> partitionAfterSourceDataStream = new DataStream<>(env, new PartitionTransformation<>(
			sourceDataStream.getTransformation(), new ForwardPartitioner<>(), ShuffleMode.PIPELINED));
	DataStream<Integer> mapDataStream = partitionAfterSourceDataStream.map(value -> value).setParallelism(1);

	DataStream<Integer> partitionAfterMapDataStream = new DataStream<>(env, new PartitionTransformation<>(
			mapDataStream.getTransformation(), new RescalePartitioner<>(), ShuffleMode.PIPELINED));
	partitionAfterMapDataStream.print().setParallelism(2);

	JobGraph jobGraph = StreamingJobGraphGenerator.createJobGraph(env.getStreamGraph());

	List<JobVertex> verticesSorted = jobGraph.getVerticesSortedTopologicallyFromSources();
	assertEquals(2, verticesSorted.size());

	// it can be chained with PIPELINED shuffle mode
	JobVertex sourceAndMapVertex = verticesSorted.get(0);

	// PIPELINED shuffle mode is translated into PIPELINED_BOUNDED result partition
	assertEquals(ResultPartitionType.PIPELINED_BOUNDED,
			sourceAndMapVertex.getProducedDataSets().get(0).getResultType());
}
 
Example #20
Source File: StreamingJobGraphGenerator.java    From Flink-CEPplus with Apache License 2.0 5 votes vote down vote up
private void connect(Integer headOfChain, StreamEdge edge) {

		physicalEdgesInOrder.add(edge);

		Integer downStreamvertexID = edge.getTargetId();

		JobVertex headVertex = jobVertices.get(headOfChain);
		JobVertex downStreamVertex = jobVertices.get(downStreamvertexID);

		StreamConfig downStreamConfig = new StreamConfig(downStreamVertex.getConfiguration());

		downStreamConfig.setNumberOfInputs(downStreamConfig.getNumberOfInputs() + 1);

		StreamPartitioner<?> partitioner = edge.getPartitioner();
		JobEdge jobEdge;
		if (partitioner instanceof ForwardPartitioner || partitioner instanceof RescalePartitioner) {
			jobEdge = downStreamVertex.connectNewDataSetAsInput(
				headVertex,
				DistributionPattern.POINTWISE,
				ResultPartitionType.PIPELINED_BOUNDED);
		} else {
			jobEdge = downStreamVertex.connectNewDataSetAsInput(
					headVertex,
					DistributionPattern.ALL_TO_ALL,
					ResultPartitionType.PIPELINED_BOUNDED);
		}
		// set strategy name so that web interface can show it.
		jobEdge.setShipStrategyName(partitioner.toString());

		if (LOG.isDebugEnabled()) {
			LOG.debug("CONNECTED: {} - {} -> {}", partitioner.getClass().getSimpleName(),
					headOfChain, downStreamvertexID);
		}
	}
 
Example #21
Source File: StreamingJobGraphGenerator.java    From flink with Apache License 2.0 4 votes vote down vote up
private static boolean isPointwisePartitioner(StreamPartitioner<?> partitioner) {
	return partitioner instanceof ForwardPartitioner || partitioner instanceof RescalePartitioner;
}
 
Example #22
Source File: DataStreamTest.java    From flink with Apache License 2.0 4 votes vote down vote up
@Test
public void testChannelSelectors() {
	StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();

	DataStreamSource<Long> src = env.generateSequence(0, 0);

	DataStream<Long> broadcast = src.broadcast();
	DataStreamSink<Long> broadcastSink = broadcast.print();
	StreamPartitioner<?> broadcastPartitioner =
			env.getStreamGraph().getStreamEdges(src.getId(),
					broadcastSink.getTransformation().getId()).get(0).getPartitioner();
	assertTrue(broadcastPartitioner instanceof BroadcastPartitioner);

	DataStream<Long> shuffle = src.shuffle();
	DataStreamSink<Long> shuffleSink = shuffle.print();
	StreamPartitioner<?> shufflePartitioner =
			env.getStreamGraph().getStreamEdges(src.getId(),
					shuffleSink.getTransformation().getId()).get(0).getPartitioner();
	assertTrue(shufflePartitioner instanceof ShufflePartitioner);

	DataStream<Long> forward = src.forward();
	DataStreamSink<Long> forwardSink = forward.print();
	StreamPartitioner<?> forwardPartitioner =
			env.getStreamGraph().getStreamEdges(src.getId(),
					forwardSink.getTransformation().getId()).get(0).getPartitioner();
	assertTrue(forwardPartitioner instanceof ForwardPartitioner);

	DataStream<Long> rebalance = src.rebalance();
	DataStreamSink<Long> rebalanceSink = rebalance.print();
	StreamPartitioner<?> rebalancePartitioner =
			env.getStreamGraph().getStreamEdges(src.getId(),
					rebalanceSink.getTransformation().getId()).get(0).getPartitioner();
	assertTrue(rebalancePartitioner instanceof RebalancePartitioner);

	DataStream<Long> global = src.global();
	DataStreamSink<Long> globalSink = global.print();
	StreamPartitioner<?> globalPartitioner =
			env.getStreamGraph().getStreamEdges(src.getId(),
					globalSink.getTransformation().getId()).get(0).getPartitioner();
	assertTrue(globalPartitioner instanceof GlobalPartitioner);
}
 
Example #23
Source File: DataStreamTest.java    From flink with Apache License 2.0 4 votes vote down vote up
@Test
public void testChannelSelectors() {
	StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();

	DataStreamSource<Long> src = env.generateSequence(0, 0);

	DataStream<Long> broadcast = src.broadcast();
	DataStreamSink<Long> broadcastSink = broadcast.print();
	StreamPartitioner<?> broadcastPartitioner =
			getStreamGraph(env).getStreamEdges(src.getId(),
					broadcastSink.getTransformation().getId()).get(0).getPartitioner();
	assertTrue(broadcastPartitioner instanceof BroadcastPartitioner);

	DataStream<Long> shuffle = src.shuffle();
	DataStreamSink<Long> shuffleSink = shuffle.print();
	StreamPartitioner<?> shufflePartitioner =
			getStreamGraph(env).getStreamEdges(src.getId(),
					shuffleSink.getTransformation().getId()).get(0).getPartitioner();
	assertTrue(shufflePartitioner instanceof ShufflePartitioner);

	DataStream<Long> forward = src.forward();
	DataStreamSink<Long> forwardSink = forward.print();
	StreamPartitioner<?> forwardPartitioner =
			getStreamGraph(env).getStreamEdges(src.getId(),
					forwardSink.getTransformation().getId()).get(0).getPartitioner();
	assertTrue(forwardPartitioner instanceof ForwardPartitioner);

	DataStream<Long> rebalance = src.rebalance();
	DataStreamSink<Long> rebalanceSink = rebalance.print();
	StreamPartitioner<?> rebalancePartitioner =
			getStreamGraph(env).getStreamEdges(src.getId(),
					rebalanceSink.getTransformation().getId()).get(0).getPartitioner();
	assertTrue(rebalancePartitioner instanceof RebalancePartitioner);

	DataStream<Long> global = src.global();
	DataStreamSink<Long> globalSink = global.print();
	StreamPartitioner<?> globalPartitioner =
			getStreamGraph(env).getStreamEdges(src.getId(),
					globalSink.getTransformation().getId()).get(0).getPartitioner();
	assertTrue(globalPartitioner instanceof GlobalPartitioner);
}
 
Example #24
Source File: StreamingJobGraphGenerator.java    From flink with Apache License 2.0 4 votes vote down vote up
private void connect(Integer headOfChain, StreamEdge edge) {

		physicalEdgesInOrder.add(edge);

		Integer downStreamvertexID = edge.getTargetId();

		JobVertex headVertex = jobVertices.get(headOfChain);
		JobVertex downStreamVertex = jobVertices.get(downStreamvertexID);

		StreamConfig downStreamConfig = new StreamConfig(downStreamVertex.getConfiguration());

		downStreamConfig.setNumberOfInputs(downStreamConfig.getNumberOfInputs() + 1);

		StreamPartitioner<?> partitioner = edge.getPartitioner();

		ResultPartitionType resultPartitionType;
		switch (edge.getShuffleMode()) {
			case PIPELINED:
				resultPartitionType = ResultPartitionType.PIPELINED_BOUNDED;
				break;
			case BATCH:
				resultPartitionType = ResultPartitionType.BLOCKING;
				break;
			case UNDEFINED:
				resultPartitionType = streamGraph.isBlockingConnectionsBetweenChains() ?
						ResultPartitionType.BLOCKING : ResultPartitionType.PIPELINED_BOUNDED;
				break;
			default:
				throw new UnsupportedOperationException("Data exchange mode " +
					edge.getShuffleMode() + " is not supported yet.");
		}

		JobEdge jobEdge;
		if (partitioner instanceof ForwardPartitioner || partitioner instanceof RescalePartitioner) {
			jobEdge = downStreamVertex.connectNewDataSetAsInput(
				headVertex,
				DistributionPattern.POINTWISE,
				resultPartitionType);
		} else {
			jobEdge = downStreamVertex.connectNewDataSetAsInput(
					headVertex,
					DistributionPattern.ALL_TO_ALL,
					resultPartitionType);
		}
		// set strategy name so that web interface can show it.
		jobEdge.setShipStrategyName(partitioner.toString());

		if (LOG.isDebugEnabled()) {
			LOG.debug("CONNECTED: {} - {} -> {}", partitioner.getClass().getSimpleName(),
					headOfChain, downStreamvertexID);
		}
	}
 
Example #25
Source File: DataStreamTest.java    From Flink-CEPplus with Apache License 2.0 4 votes vote down vote up
@Test
public void testChannelSelectors() {
	StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();

	DataStreamSource<Long> src = env.generateSequence(0, 0);

	DataStream<Long> broadcast = src.broadcast();
	DataStreamSink<Long> broadcastSink = broadcast.print();
	StreamPartitioner<?> broadcastPartitioner =
			env.getStreamGraph().getStreamEdges(src.getId(),
					broadcastSink.getTransformation().getId()).get(0).getPartitioner();
	assertTrue(broadcastPartitioner instanceof BroadcastPartitioner);

	DataStream<Long> shuffle = src.shuffle();
	DataStreamSink<Long> shuffleSink = shuffle.print();
	StreamPartitioner<?> shufflePartitioner =
			env.getStreamGraph().getStreamEdges(src.getId(),
					shuffleSink.getTransformation().getId()).get(0).getPartitioner();
	assertTrue(shufflePartitioner instanceof ShufflePartitioner);

	DataStream<Long> forward = src.forward();
	DataStreamSink<Long> forwardSink = forward.print();
	StreamPartitioner<?> forwardPartitioner =
			env.getStreamGraph().getStreamEdges(src.getId(),
					forwardSink.getTransformation().getId()).get(0).getPartitioner();
	assertTrue(forwardPartitioner instanceof ForwardPartitioner);

	DataStream<Long> rebalance = src.rebalance();
	DataStreamSink<Long> rebalanceSink = rebalance.print();
	StreamPartitioner<?> rebalancePartitioner =
			env.getStreamGraph().getStreamEdges(src.getId(),
					rebalanceSink.getTransformation().getId()).get(0).getPartitioner();
	assertTrue(rebalancePartitioner instanceof RebalancePartitioner);

	DataStream<Long> global = src.global();
	DataStreamSink<Long> globalSink = global.print();
	StreamPartitioner<?> globalPartitioner =
			env.getStreamGraph().getStreamEdges(src.getId(),
					globalSink.getTransformation().getId()).get(0).getPartitioner();
	assertTrue(globalPartitioner instanceof GlobalPartitioner);
}
 
Example #26
Source File: DataStream.java    From flink with Apache License 2.0 2 votes vote down vote up
/**
 * Sets the partitioning of the {@link DataStream} so that the output elements
 * are forwarded to the local subtask of the next operation.
 *
 * @return The DataStream with forward partitioning set.
 */
public DataStream<T> forward() {
	return setConnectionType(new ForwardPartitioner<T>());
}
 
Example #27
Source File: DataStream.java    From flink with Apache License 2.0 2 votes vote down vote up
/**
 * Sets the partitioning of the {@link DataStream} so that the output elements
 * are forwarded to the local subtask of the next operation.
 *
 * @return The DataStream with forward partitioning set.
 */
public DataStream<T> forward() {
	return setConnectionType(new ForwardPartitioner<T>());
}
 
Example #28
Source File: DataStream.java    From Flink-CEPplus with Apache License 2.0 2 votes vote down vote up
/**
 * Sets the partitioning of the {@link DataStream} so that the output elements
 * are forwarded to the local subtask of the next operation.
 *
 * @return The DataStream with forward partitioning set.
 */
public DataStream<T> forward() {
	return setConnectionType(new ForwardPartitioner<T>());
}