Examples with ShipStrategyType org.apache.flink.runtime.operators.shipping.ShipStrategyType used on opensource projects

Example 11 with ShipStrategyType

use of org.apache.flink.runtime.operators.shipping.ShipStrategyType in project flink by apache.

the class ReplicatingDataSourceTest method checkJoinWithReplicatedSourceInputBehindMapPartition.

/**
 * Tests join program with replicated data source behind map partition.
 */
@Test
public void checkJoinWithReplicatedSourceInputBehindMapPartition() {
    ExecutionEnvironment env = ExecutionEnvironment.createLocalEnvironment();
    env.setParallelism(DEFAULT_PARALLELISM);
    TupleTypeInfo<Tuple1<String>> typeInfo = TupleTypeInfo.getBasicTupleTypeInfo(String.class);
    ReplicatingInputFormat<Tuple1<String>, FileInputSplit> rif = new ReplicatingInputFormat<Tuple1<String>, FileInputSplit>(new TupleCsvInputFormat<Tuple1<String>>(new Path("/some/path"), typeInfo));
    DataSet<Tuple1<String>> source1 = env.createInput(rif, new TupleTypeInfo<Tuple1<String>>(BasicTypeInfo.STRING_TYPE_INFO));
    DataSet<Tuple1<String>> source2 = env.readCsvFile("/some/otherpath").types(String.class);
    DataSink<Tuple2<Tuple1<String>, Tuple1<String>>> out = source1.mapPartition(new IdPMap()).join(source2).where("*").equalTo("*").writeAsText("/some/newpath");
    Plan plan = env.createProgramPlan();
    // submit the plan to the compiler
    OptimizedPlan oPlan = compileNoStats(plan);
    // check the optimized Plan
    // when join should have forward strategy on both sides
    SinkPlanNode sinkNode = oPlan.getDataSinks().iterator().next();
    DualInputPlanNode joinNode = (DualInputPlanNode) sinkNode.getPredecessor();
    ShipStrategyType joinIn1 = joinNode.getInput1().getShipStrategy();
    ShipStrategyType joinIn2 = joinNode.getInput2().getShipStrategy();
    Assert.assertEquals("Invalid ship strategy for an operator.", ShipStrategyType.FORWARD, joinIn1);
    Assert.assertEquals("Invalid ship strategy for an operator.", ShipStrategyType.FORWARD, joinIn2);
}

Example 12 with ShipStrategyType

use of org.apache.flink.runtime.operators.shipping.ShipStrategyType in project flink by apache.

the class ReplicatingDataSourceTest method checkJoinWithReplicatedSourceInput.

/**
 * Tests join program with replicated data source.
 */
@Test
public void checkJoinWithReplicatedSourceInput() {
    ExecutionEnvironment env = ExecutionEnvironment.createLocalEnvironment();
    env.setParallelism(DEFAULT_PARALLELISM);
    TupleTypeInfo<Tuple1<String>> typeInfo = TupleTypeInfo.getBasicTupleTypeInfo(String.class);
    ReplicatingInputFormat<Tuple1<String>, FileInputSplit> rif = new ReplicatingInputFormat<Tuple1<String>, FileInputSplit>(new TupleCsvInputFormat<Tuple1<String>>(new Path("/some/path"), typeInfo));
    DataSet<Tuple1<String>> source1 = env.createInput(rif, new TupleTypeInfo<Tuple1<String>>(BasicTypeInfo.STRING_TYPE_INFO));
    DataSet<Tuple1<String>> source2 = env.readCsvFile("/some/otherpath").types(String.class);
    DataSink<Tuple2<Tuple1<String>, Tuple1<String>>> out = source1.join(source2).where("*").equalTo("*").writeAsText("/some/newpath");
    Plan plan = env.createProgramPlan();
    // submit the plan to the compiler
    OptimizedPlan oPlan = compileNoStats(plan);
    // check the optimized Plan
    // when join should have forward strategy on both sides
    SinkPlanNode sinkNode = oPlan.getDataSinks().iterator().next();
    DualInputPlanNode joinNode = (DualInputPlanNode) sinkNode.getPredecessor();
    ShipStrategyType joinIn1 = joinNode.getInput1().getShipStrategy();
    ShipStrategyType joinIn2 = joinNode.getInput2().getShipStrategy();
    Assert.assertEquals("Invalid ship strategy for an operator.", ShipStrategyType.FORWARD, joinIn1);
    Assert.assertEquals("Invalid ship strategy for an operator.", ShipStrategyType.FORWARD, joinIn2);
}

Example 13 with ShipStrategyType

use of org.apache.flink.runtime.operators.shipping.ShipStrategyType in project flink by apache.

the class TwoInputNode method getAlternativePlans.

@Override
public List<PlanNode> getAlternativePlans(CostEstimator estimator) {
    // check if we have a cached version
    if (this.cachedPlans != null) {
        return this.cachedPlans;
    }
    boolean childrenSkippedDueToReplicatedInput = false;
    // step down to all producer nodes and calculate alternative plans
    final List<? extends PlanNode> subPlans1 = getFirstPredecessorNode().getAlternativePlans(estimator);
    final List<? extends PlanNode> subPlans2 = getSecondPredecessorNode().getAlternativePlans(estimator);
    // calculate alternative sub-plans for predecessor
    final Set<RequestedGlobalProperties> intGlobal1 = this.input1.getInterestingProperties().getGlobalProperties();
    final Set<RequestedGlobalProperties> intGlobal2 = this.input2.getInterestingProperties().getGlobalProperties();
    // calculate alternative sub-plans for broadcast inputs
    final List<Set<? extends NamedChannel>> broadcastPlanChannels = new ArrayList<Set<? extends NamedChannel>>();
    List<DagConnection> broadcastConnections = getBroadcastConnections();
    List<String> broadcastConnectionNames = getBroadcastConnectionNames();
    for (int i = 0; i < broadcastConnections.size(); i++) {
        DagConnection broadcastConnection = broadcastConnections.get(i);
        String broadcastConnectionName = broadcastConnectionNames.get(i);
        List<PlanNode> broadcastPlanCandidates = broadcastConnection.getSource().getAlternativePlans(estimator);
        // wrap the plan candidates in named channels
        HashSet<NamedChannel> broadcastChannels = new HashSet<NamedChannel>(broadcastPlanCandidates.size());
        for (PlanNode plan : broadcastPlanCandidates) {
            final NamedChannel c = new NamedChannel(broadcastConnectionName, plan);
            DataExchangeMode exMode = DataExchangeMode.select(broadcastConnection.getDataExchangeMode(), ShipStrategyType.BROADCAST, broadcastConnection.isBreakingPipeline());
            c.setShipStrategy(ShipStrategyType.BROADCAST, exMode);
            broadcastChannels.add(c);
        }
        broadcastPlanChannels.add(broadcastChannels);
    }
    final GlobalPropertiesPair[] allGlobalPairs;
    final LocalPropertiesPair[] allLocalPairs;
    {
        Set<GlobalPropertiesPair> pairsGlob = new HashSet<GlobalPropertiesPair>();
        Set<LocalPropertiesPair> pairsLoc = new HashSet<LocalPropertiesPair>();
        for (OperatorDescriptorDual ods : getProperties()) {
            pairsGlob.addAll(ods.getPossibleGlobalProperties());
            pairsLoc.addAll(ods.getPossibleLocalProperties());
        }
        allGlobalPairs = pairsGlob.toArray(new GlobalPropertiesPair[pairsGlob.size()]);
        allLocalPairs = pairsLoc.toArray(new LocalPropertiesPair[pairsLoc.size()]);
    }
    final ArrayList<PlanNode> outputPlans = new ArrayList<PlanNode>();
    final ExecutionMode input1Mode = this.input1.getDataExchangeMode();
    final ExecutionMode input2Mode = this.input2.getDataExchangeMode();
    final int parallelism = getParallelism();
    final int inParallelism1 = getFirstPredecessorNode().getParallelism();
    final int inParallelism2 = getSecondPredecessorNode().getParallelism();
    final boolean dopChange1 = parallelism != inParallelism1;
    final boolean dopChange2 = parallelism != inParallelism2;
    final boolean input1breaksPipeline = this.input1.isBreakingPipeline();
    final boolean input2breaksPipeline = this.input2.isBreakingPipeline();
    // create all candidates
    for (PlanNode child1 : subPlans1) {
        if (child1.getGlobalProperties().isFullyReplicated()) {
            // fully replicated input is always locally forwarded if parallelism is not changed
            if (dopChange1) {
                // can not continue with this child
                childrenSkippedDueToReplicatedInput = true;
                continue;
            } else {
                this.input1.setShipStrategy(ShipStrategyType.FORWARD);
            }
        }
        for (PlanNode child2 : subPlans2) {
            if (child2.getGlobalProperties().isFullyReplicated()) {
                // changed
                if (dopChange2) {
                    // can not continue with this child
                    childrenSkippedDueToReplicatedInput = true;
                    continue;
                } else {
                    this.input2.setShipStrategy(ShipStrategyType.FORWARD);
                }
            }
            // candidate at the joined branch plan.
            if (!areBranchCompatible(child1, child2)) {
                continue;
            }
            for (RequestedGlobalProperties igps1 : intGlobal1) {
                // create a candidate channel for the first input. mark it cached, if the
                // connection says so
                final Channel c1 = new Channel(child1, this.input1.getMaterializationMode());
                if (this.input1.getShipStrategy() == null) {
                    // free to choose the ship strategy
                    igps1.parameterizeChannel(c1, dopChange1, input1Mode, input1breaksPipeline);
                    // ship strategy preserves/establishes them even under changing parallelisms
                    if (dopChange1 && !c1.getShipStrategy().isNetworkStrategy()) {
                        c1.getGlobalProperties().reset();
                    }
                } else {
                    // ship strategy fixed by compiler hint
                    ShipStrategyType shipType = this.input1.getShipStrategy();
                    DataExchangeMode exMode = DataExchangeMode.select(input1Mode, shipType, input1breaksPipeline);
                    if (this.keys1 != null) {
                        c1.setShipStrategy(shipType, this.keys1.toFieldList(), exMode);
                    } else {
                        c1.setShipStrategy(shipType, exMode);
                    }
                    if (dopChange1) {
                        c1.adjustGlobalPropertiesForFullParallelismChange();
                    }
                }
                for (RequestedGlobalProperties igps2 : intGlobal2) {
                    // create a candidate channel for the second input. mark it cached, if the
                    // connection says so
                    final Channel c2 = new Channel(child2, this.input2.getMaterializationMode());
                    if (this.input2.getShipStrategy() == null) {
                        // free to choose the ship strategy
                        igps2.parameterizeChannel(c2, dopChange2, input2Mode, input2breaksPipeline);
                        // parallelisms
                        if (dopChange2 && !c2.getShipStrategy().isNetworkStrategy()) {
                            c2.getGlobalProperties().reset();
                        }
                    } else {
                        // ship strategy fixed by compiler hint
                        ShipStrategyType shipType = this.input2.getShipStrategy();
                        DataExchangeMode exMode = DataExchangeMode.select(input2Mode, shipType, input2breaksPipeline);
                        if (this.keys2 != null) {
                            c2.setShipStrategy(shipType, this.keys2.toFieldList(), exMode);
                        } else {
                            c2.setShipStrategy(shipType, exMode);
                        }
                        if (dopChange2) {
                            c2.adjustGlobalPropertiesForFullParallelismChange();
                        }
                    }
                    outer: for (GlobalPropertiesPair gpp : allGlobalPairs) {
                        if (gpp.getProperties1().isMetBy(c1.getGlobalProperties()) && gpp.getProperties2().isMetBy(c2.getGlobalProperties())) {
                            for (OperatorDescriptorDual desc : getProperties()) {
                                if (desc.areCompatible(gpp.getProperties1(), gpp.getProperties2(), c1.getGlobalProperties(), c2.getGlobalProperties())) {
                                    Channel c1Clone = c1.clone();
                                    c1Clone.setRequiredGlobalProps(gpp.getProperties1());
                                    c2.setRequiredGlobalProps(gpp.getProperties2());
                                    // we form a valid combination, so create the local
                                    // candidates
                                    // for this
                                    addLocalCandidates(c1Clone, c2, broadcastPlanChannels, igps1, igps2, outputPlans, allLocalPairs, estimator);
                                    break outer;
                                }
                            }
                        }
                    }
                    // so we can stop after the first
                    if (this.input2.getShipStrategy() != null) {
                        break;
                    }
                }
                // so we can stop after the first
                if (this.input1.getShipStrategy() != null) {
                    break;
                }
            }
        }
    }
    if (outputPlans.isEmpty()) {
        if (childrenSkippedDueToReplicatedInput) {
            throw new CompilerException("No plan meeting the requirements could be created @ " + this + ". Most likely reason: Invalid use of replicated input.");
        } else {
            throw new CompilerException("No plan meeting the requirements could be created @ " + this + ". Most likely reason: Too restrictive plan hints.");
        }
    }
    // cost and prune the plans
    for (PlanNode node : outputPlans) {
        estimator.costOperator(node);
    }
    prunePlanAlternatives(outputPlans);
    outputPlans.trimToSize();
    this.cachedPlans = outputPlans;
    return outputPlans;
}

Example 14 with ShipStrategyType

use of org.apache.flink.runtime.operators.shipping.ShipStrategyType in project flink by apache.

the class SingleInputNode method setInput.

@Override
public void setInput(Map<Operator<?>, OptimizerNode> contractToNode, ExecutionMode defaultExchangeMode) throws CompilerException {
    // see if an internal hint dictates the strategy to use
    final Configuration conf = getOperator().getParameters();
    final String shipStrategy = conf.getString(Optimizer.HINT_SHIP_STRATEGY, null);
    final ShipStrategyType preSet;
    if (shipStrategy != null) {
        if (shipStrategy.equalsIgnoreCase(Optimizer.HINT_SHIP_STRATEGY_REPARTITION_HASH)) {
            preSet = ShipStrategyType.PARTITION_HASH;
        } else if (shipStrategy.equalsIgnoreCase(Optimizer.HINT_SHIP_STRATEGY_REPARTITION_RANGE)) {
            preSet = ShipStrategyType.PARTITION_RANGE;
        } else if (shipStrategy.equalsIgnoreCase(Optimizer.HINT_SHIP_STRATEGY_FORWARD)) {
            preSet = ShipStrategyType.FORWARD;
        } else if (shipStrategy.equalsIgnoreCase(Optimizer.HINT_SHIP_STRATEGY_REPARTITION)) {
            preSet = ShipStrategyType.PARTITION_RANDOM;
        } else {
            throw new CompilerException("Unrecognized ship strategy hint: " + shipStrategy);
        }
    } else {
        preSet = null;
    }
    // get the predecessor node
    Operator<?> children = ((SingleInputOperator<?, ?, ?>) getOperator()).getInput();
    OptimizerNode pred;
    DagConnection conn;
    if (children == null) {
        throw new CompilerException("Error: Node for '" + getOperator().getName() + "' has no input.");
    } else {
        pred = contractToNode.get(children);
        conn = new DagConnection(pred, this, defaultExchangeMode);
        if (preSet != null) {
            conn.setShipStrategy(preSet);
        }
    }
    // create the connection and add it
    setIncomingConnection(conn);
    pred.addOutgoingConnection(conn);
}

Example 15 with ShipStrategyType

use of org.apache.flink.runtime.operators.shipping.ShipStrategyType in project flink by apache.

the class WorksetIterationsJavaApiCompilerTest method testJavaApiWithDeferredSoltionSetUpdateWithMapper.

@Test
public void testJavaApiWithDeferredSoltionSetUpdateWithMapper() {
    try {
        Plan plan = getJavaTestPlan(false, true);
        OptimizedPlan oPlan = compileNoStats(plan);
        OptimizerPlanNodeResolver resolver = getOptimizerPlanNodeResolver(oPlan);
        DualInputPlanNode joinWithInvariantNode = resolver.getNode(JOIN_WITH_INVARIANT_NAME);
        DualInputPlanNode joinWithSolutionSetNode = resolver.getNode(JOIN_WITH_SOLUTION_SET);
        SingleInputPlanNode worksetReducer = resolver.getNode(NEXT_WORKSET_REDUCER_NAME);
        SingleInputPlanNode deltaMapper = resolver.getNode(SOLUTION_DELTA_MAPPER_NAME);
        // iteration preserves partitioning in reducer, so the first partitioning is out of the
        // loop,
        // the in-loop partitioning is before the final reducer
        // verify joinWithInvariant
        assertEquals(ShipStrategyType.FORWARD, joinWithInvariantNode.getInput1().getShipStrategy());
        assertEquals(ShipStrategyType.PARTITION_HASH, joinWithInvariantNode.getInput2().getShipStrategy());
        assertEquals(new FieldList(1, 2), joinWithInvariantNode.getKeysForInput1());
        assertEquals(new FieldList(1, 2), joinWithInvariantNode.getKeysForInput2());
        // verify joinWithSolutionSet
        assertEquals(ShipStrategyType.PARTITION_HASH, joinWithSolutionSetNode.getInput1().getShipStrategy());
        assertEquals(ShipStrategyType.FORWARD, joinWithSolutionSetNode.getInput2().getShipStrategy());
        assertEquals(new FieldList(1, 0), joinWithSolutionSetNode.getKeysForInput1());
        // verify reducer
        assertEquals(ShipStrategyType.PARTITION_HASH, worksetReducer.getInput().getShipStrategy());
        assertEquals(new FieldList(1, 2), worksetReducer.getKeys(0));
        // currently, the system may partition before or after the mapper
        ShipStrategyType ss1 = deltaMapper.getInput().getShipStrategy();
        ShipStrategyType ss2 = deltaMapper.getOutgoingChannels().get(0).getShipStrategy();
        assertTrue((ss1 == ShipStrategyType.FORWARD && ss2 == ShipStrategyType.PARTITION_HASH) || (ss2 == ShipStrategyType.FORWARD && ss1 == ShipStrategyType.PARTITION_HASH));
        new JobGraphGenerator().compileJobGraph(oPlan);
    } catch (Exception e) {
        System.err.println(e.getMessage());
        e.printStackTrace();
        fail("Test errored: " + e.getMessage());
    }
}