Examples with DiscardingOutputFormat org.apache.flink.api.java.io.DiscardingOutputFormat used on opensource projects

Example 6 with DiscardingOutputFormat

use of org.apache.flink.api.java.io.DiscardingOutputFormat in project flink by apache.

the class GroupReduceCompilationTest method testGroupedReduceWithFieldPositionKeyCombinable.

@Test
public void testGroupedReduceWithFieldPositionKeyCombinable() {
    try {
        ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();
        env.setParallelism(8);
        DataSet<Tuple2<String, Double>> data = env.readCsvFile("file:///will/never/be/read").types(String.class, Double.class).name("source").setParallelism(6);
        GroupReduceOperator<Tuple2<String, Double>, Tuple2<String, Double>> reduced = data.groupBy(1).reduceGroup(new CombineReducer()).name("reducer");
        reduced.setCombinable(true);
        reduced.output(new DiscardingOutputFormat<Tuple2<String, Double>>()).name("sink");
        Plan p = env.createProgramPlan();
        OptimizedPlan op = compileNoStats(p);
        OptimizerPlanNodeResolver resolver = getOptimizerPlanNodeResolver(op);
        // get the original nodes
        SourcePlanNode sourceNode = resolver.getNode("source");
        SingleInputPlanNode reduceNode = resolver.getNode("reducer");
        SinkPlanNode sinkNode = resolver.getNode("sink");
        // get the combiner
        SingleInputPlanNode combineNode = (SingleInputPlanNode) reduceNode.getInput().getSource();
        // check wiring
        assertEquals(sourceNode, combineNode.getInput().getSource());
        assertEquals(reduceNode, sinkNode.getInput().getSource());
        // check that both reduce and combiner have the same strategy
        assertEquals(DriverStrategy.SORTED_GROUP_REDUCE, reduceNode.getDriverStrategy());
        assertEquals(DriverStrategy.SORTED_GROUP_COMBINE, combineNode.getDriverStrategy());
        // check the keys
        assertEquals(new FieldList(1), reduceNode.getKeys(0));
        assertEquals(new FieldList(1), combineNode.getKeys(0));
        assertEquals(new FieldList(1), combineNode.getKeys(1));
        assertEquals(new FieldList(1), reduceNode.getInput().getLocalStrategyKeys());
        // check parallelism
        assertEquals(6, sourceNode.getParallelism());
        assertEquals(6, combineNode.getParallelism());
        assertEquals(8, reduceNode.getParallelism());
        assertEquals(8, sinkNode.getParallelism());
    } catch (Exception e) {
        System.err.println(e.getMessage());
        e.printStackTrace();
        fail(e.getClass().getSimpleName() + " in test: " + e.getMessage());
    }
}

Example 7 with DiscardingOutputFormat

use of org.apache.flink.api.java.io.DiscardingOutputFormat in project flink by apache.

the class GroupReduceCompilationTest method testGroupedReduceWithSelectorFunctionKeyCombinable.

@Test
public void testGroupedReduceWithSelectorFunctionKeyCombinable() {
    try {
        ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();
        env.setParallelism(8);
        DataSet<Tuple2<String, Double>> data = env.readCsvFile("file:///will/never/be/read").types(String.class, Double.class).name("source").setParallelism(6);
        GroupReduceOperator<Tuple2<String, Double>, Tuple2<String, Double>> reduced = data.groupBy(new KeySelector<Tuple2<String, Double>, String>() {

            public String getKey(Tuple2<String, Double> value) {
                return value.f0;
            }
        }).reduceGroup(new CombineReducer()).name("reducer");
        reduced.setCombinable(true);
        reduced.output(new DiscardingOutputFormat<Tuple2<String, Double>>()).name("sink");
        Plan p = env.createProgramPlan();
        OptimizedPlan op = compileNoStats(p);
        OptimizerPlanNodeResolver resolver = getOptimizerPlanNodeResolver(op);
        // get the original nodes
        SourcePlanNode sourceNode = resolver.getNode("source");
        SingleInputPlanNode reduceNode = resolver.getNode("reducer");
        SinkPlanNode sinkNode = resolver.getNode("sink");
        // get the combiner
        SingleInputPlanNode combineNode = (SingleInputPlanNode) reduceNode.getInput().getSource();
        // get the key extractors and projectors
        SingleInputPlanNode keyExtractor = (SingleInputPlanNode) combineNode.getInput().getSource();
        SingleInputPlanNode keyProjector = (SingleInputPlanNode) sinkNode.getInput().getSource();
        // check wiring
        assertEquals(sourceNode, keyExtractor.getInput().getSource());
        assertEquals(keyProjector, sinkNode.getInput().getSource());
        // check that both reduce and combiner have the same strategy
        assertEquals(DriverStrategy.SORTED_GROUP_REDUCE, reduceNode.getDriverStrategy());
        assertEquals(DriverStrategy.SORTED_GROUP_COMBINE, combineNode.getDriverStrategy());
        // check the keys
        assertEquals(new FieldList(0), reduceNode.getKeys(0));
        assertEquals(new FieldList(0), combineNode.getKeys(0));
        assertEquals(new FieldList(0), combineNode.getKeys(1));
        assertEquals(new FieldList(0), reduceNode.getInput().getLocalStrategyKeys());
        // check parallelism
        assertEquals(6, sourceNode.getParallelism());
        assertEquals(6, keyExtractor.getParallelism());
        assertEquals(6, combineNode.getParallelism());
        assertEquals(8, reduceNode.getParallelism());
        assertEquals(8, keyProjector.getParallelism());
        assertEquals(8, sinkNode.getParallelism());
    } catch (Exception e) {
        System.err.println(e.getMessage());
        e.printStackTrace();
        fail(e.getClass().getSimpleName() + " in test: " + e.getMessage());
    }
}

Example 8 with DiscardingOutputFormat

use of org.apache.flink.api.java.io.DiscardingOutputFormat in project flink by apache.

the class GroupReduceCompilationTest method testGroupedReduceWithSelectorFunctionKeyNoncombinable.

@Test
public void testGroupedReduceWithSelectorFunctionKeyNoncombinable() {
    try {
        ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();
        env.setParallelism(8);
        DataSet<Tuple2<String, Double>> data = env.readCsvFile("file:///will/never/be/read").types(String.class, Double.class).name("source").setParallelism(6);
        data.groupBy(new KeySelector<Tuple2<String, Double>, String>() {

            public String getKey(Tuple2<String, Double> value) {
                return value.f0;
            }
        }).reduceGroup(new RichGroupReduceFunction<Tuple2<String, Double>, Tuple2<String, Double>>() {

            public void reduce(Iterable<Tuple2<String, Double>> values, Collector<Tuple2<String, Double>> out) {
            }
        }).name("reducer").output(new DiscardingOutputFormat<Tuple2<String, Double>>()).name("sink");
        Plan p = env.createProgramPlan();
        OptimizedPlan op = compileNoStats(p);
        OptimizerPlanNodeResolver resolver = getOptimizerPlanNodeResolver(op);
        // get the original nodes
        SourcePlanNode sourceNode = resolver.getNode("source");
        SingleInputPlanNode reduceNode = resolver.getNode("reducer");
        SinkPlanNode sinkNode = resolver.getNode("sink");
        // get the key extractors and projectors
        SingleInputPlanNode keyExtractor = (SingleInputPlanNode) reduceNode.getInput().getSource();
        SingleInputPlanNode keyProjector = (SingleInputPlanNode) sinkNode.getInput().getSource();
        // check wiring
        assertEquals(sourceNode, keyExtractor.getInput().getSource());
        assertEquals(keyProjector, sinkNode.getInput().getSource());
        // check that both reduce and combiner have the same strategy
        assertEquals(DriverStrategy.SORTED_GROUP_REDUCE, reduceNode.getDriverStrategy());
        // check the keys
        assertEquals(new FieldList(0), reduceNode.getKeys(0));
        assertEquals(new FieldList(0), reduceNode.getInput().getLocalStrategyKeys());
        // check parallelism
        assertEquals(6, sourceNode.getParallelism());
        assertEquals(6, keyExtractor.getParallelism());
        assertEquals(8, reduceNode.getParallelism());
        assertEquals(8, keyProjector.getParallelism());
        assertEquals(8, sinkNode.getParallelism());
    } catch (Exception e) {
        System.err.println(e.getMessage());
        e.printStackTrace();
        fail(e.getClass().getSimpleName() + " in test: " + e.getMessage());
    }
}

Example 9 with DiscardingOutputFormat

use of org.apache.flink.api.java.io.DiscardingOutputFormat in project flink by apache.

the class PregelCompilerTest method testPregelCompilerWithBroadcastVariable.

@SuppressWarnings("serial")
@Test
public void testPregelCompilerWithBroadcastVariable() {
    try {
        final String BC_VAR_NAME = "borat variable";
        ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();
        env.setParallelism(DEFAULT_PARALLELISM);
        // compose test program
        {
            DataSet<Long> bcVar = env.fromElements(1L);
            DataSet<Vertex<Long, Long>> initialVertices = env.fromElements(new Tuple2<>(1L, 1L), new Tuple2<>(2L, 2L)).map(new Tuple2ToVertexMap<Long, Long>());
            DataSet<Edge<Long, NullValue>> edges = env.fromElements(new Tuple2<>(1L, 2L)).map(new MapFunction<Tuple2<Long, Long>, Edge<Long, NullValue>>() {

                public Edge<Long, NullValue> map(Tuple2<Long, Long> edge) {
                    return new Edge<>(edge.f0, edge.f1, NullValue.getInstance());
                }
            });
            Graph<Long, Long, NullValue> graph = Graph.fromDataSet(initialVertices, edges, env);
            VertexCentricConfiguration parameters = new VertexCentricConfiguration();
            parameters.addBroadcastSet(BC_VAR_NAME, bcVar);
            DataSet<Vertex<Long, Long>> result = graph.runVertexCentricIteration(new CCCompute(), null, 100, parameters).getVertices();
            result.output(new DiscardingOutputFormat<Vertex<Long, Long>>());
        }
        Plan p = env.createProgramPlan("Pregel Connected Components");
        OptimizedPlan op = compileNoStats(p);
        // check the sink
        SinkPlanNode sink = op.getDataSinks().iterator().next();
        assertEquals(ShipStrategyType.FORWARD, sink.getInput().getShipStrategy());
        assertEquals(DEFAULT_PARALLELISM, sink.getParallelism());
        // check the iteration
        WorksetIterationPlanNode iteration = (WorksetIterationPlanNode) sink.getInput().getSource();
        assertEquals(DEFAULT_PARALLELISM, iteration.getParallelism());
        // check the solution set delta
        PlanNode ssDelta = iteration.getSolutionSetDeltaPlanNode();
        assertTrue(ssDelta instanceof SingleInputPlanNode);
        SingleInputPlanNode ssFlatMap = (SingleInputPlanNode) ((SingleInputPlanNode) (ssDelta)).getInput().getSource();
        assertEquals(DEFAULT_PARALLELISM, ssFlatMap.getParallelism());
        assertEquals(ShipStrategyType.FORWARD, ssFlatMap.getInput().getShipStrategy());
        // check the computation coGroup
        DualInputPlanNode computationCoGroup = (DualInputPlanNode) (ssFlatMap.getInput().getSource());
        assertEquals(DEFAULT_PARALLELISM, computationCoGroup.getParallelism());
        assertEquals(ShipStrategyType.FORWARD, computationCoGroup.getInput1().getShipStrategy());
        assertEquals(ShipStrategyType.PARTITION_HASH, computationCoGroup.getInput2().getShipStrategy());
        assertTrue(computationCoGroup.getInput2().getTempMode().isCached());
        assertEquals(new FieldList(0), computationCoGroup.getInput2().getShipStrategyKeys());
        // check that the initial partitioning is pushed out of the loop
        assertEquals(ShipStrategyType.PARTITION_HASH, iteration.getInput1().getShipStrategy());
        assertEquals(new FieldList(0), iteration.getInput1().getShipStrategyKeys());
    } catch (Exception e) {
        System.err.println(e.getMessage());
        e.printStackTrace();
        fail(e.getMessage());
    }
}

Example 10 with DiscardingOutputFormat

use of org.apache.flink.api.java.io.DiscardingOutputFormat in project flink by apache.

the class PregelTranslationTest method testTranslationPlainEdges.

@Test
public void testTranslationPlainEdges() {
    try {
        final String ITERATION_NAME = "Test Name";
        final String AGGREGATOR_NAME = "AggregatorName";
        final String BC_SET_NAME = "borat messages";
        final int NUM_ITERATIONS = 13;
        final int ITERATION_parallelism = 77;
        ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();
        DataSet<Long> bcVar = env.fromElements(1L);
        DataSet<Vertex<String, Double>> result;
        // ------------ construct the test program ------------------
        {
            DataSet<Tuple2<String, Double>> initialVertices = env.fromElements(new Tuple2<>("abc", 3.44));
            DataSet<Tuple2<String, String>> edges = env.fromElements(new Tuple2<>("a", "c"));
            Graph<String, Double, NullValue> graph = Graph.fromTupleDataSet(initialVertices, edges.map(new MapFunction<Tuple2<String, String>, Tuple3<String, String, NullValue>>() {

                public Tuple3<String, String, NullValue> map(Tuple2<String, String> edge) {
                    return new Tuple3<>(edge.f0, edge.f1, NullValue.getInstance());
                }
            }), env);
            VertexCentricConfiguration parameters = new VertexCentricConfiguration();
            parameters.addBroadcastSet(BC_SET_NAME, bcVar);
            parameters.setName(ITERATION_NAME);
            parameters.setParallelism(ITERATION_parallelism);
            parameters.registerAggregator(AGGREGATOR_NAME, new LongSumAggregator());
            result = graph.runVertexCentricIteration(new MyCompute(), null, NUM_ITERATIONS, parameters).getVertices();
            result.output(new DiscardingOutputFormat<Vertex<String, Double>>());
        }
        // ------------- validate the java program ----------------
        assertTrue(result instanceof DeltaIterationResultSet);
        DeltaIterationResultSet<?, ?> resultSet = (DeltaIterationResultSet<?, ?>) result;
        DeltaIteration<?, ?> iteration = resultSet.getIterationHead();
        // check the basic iteration properties
        assertEquals(NUM_ITERATIONS, resultSet.getMaxIterations());
        assertArrayEquals(new int[] { 0 }, resultSet.getKeyPositions());
        assertEquals(ITERATION_parallelism, iteration.getParallelism());
        assertEquals(ITERATION_NAME, iteration.getName());
        assertEquals(AGGREGATOR_NAME, iteration.getAggregators().getAllRegisteredAggregators().iterator().next().getName());
        TwoInputUdfOperator<?, ?, ?, ?> computationCoGroup = (TwoInputUdfOperator<?, ?, ?, ?>) ((SingleInputUdfOperator<?, ?, ?>) resultSet.getNextWorkset()).getInput();
        // validate that the broadcast sets are forwarded
        assertEquals(bcVar, computationCoGroup.getBroadcastSets().get(BC_SET_NAME));
    } catch (Exception e) {
        System.err.println(e.getMessage());
        e.printStackTrace();
        fail(e.getMessage());
    }
}