use of org.apache.flink.optimizer.dag.ReduceNode in project flink by apache.
the class AllReduceProperties method instantiate.
@Override
public SingleInputPlanNode instantiate(Channel in, SingleInputNode node) {
if (in.getShipStrategy() == ShipStrategyType.FORWARD) {
// locally connected, directly instantiate
return new SingleInputPlanNode(node, "Reduce (" + node.getOperator().getName() + ")", in, DriverStrategy.ALL_REDUCE);
} else {
// non forward case.plug in a combiner
Channel toCombiner = new Channel(in.getSource());
toCombiner.setShipStrategy(ShipStrategyType.FORWARD, DataExchangeMode.PIPELINED);
// create an input node for combine with same parallelism as input node
ReduceNode combinerNode = ((ReduceNode) node).getCombinerUtilityNode();
combinerNode.setParallelism(in.getSource().getParallelism());
SingleInputPlanNode combiner = new SingleInputPlanNode(combinerNode, "Combine (" + node.getOperator().getName() + ")", toCombiner, DriverStrategy.ALL_REDUCE);
combiner.setCosts(new Costs(0, 0));
combiner.initProperties(toCombiner.getGlobalProperties(), toCombiner.getLocalProperties());
Channel toReducer = new Channel(combiner);
toReducer.setShipStrategy(in.getShipStrategy(), in.getShipStrategyKeys(), in.getShipStrategySortOrder(), in.getDataExchangeMode());
toReducer.setLocalStrategy(in.getLocalStrategy(), in.getLocalStrategyKeys(), in.getLocalStrategySortOrder());
return new SingleInputPlanNode(node, "Reduce (" + node.getOperator().getName() + ")", toReducer, DriverStrategy.ALL_REDUCE);
}
}
use of org.apache.flink.optimizer.dag.ReduceNode in project flink by apache.
the class ReduceProperties method instantiate.
@Override
public SingleInputPlanNode instantiate(Channel in, SingleInputNode node) {
if (in.getShipStrategy() == ShipStrategyType.FORWARD || (node.getBroadcastConnections() != null && !node.getBroadcastConnections().isEmpty())) {
if (in.getSource().getOptimizerNode() instanceof PartitionNode) {
LOG.warn("Cannot automatically inject combiner for ReduceFunction. Please add an explicit combiner with combineGroup() in front of the partition operator.");
}
return new SingleInputPlanNode(node, "Reduce (" + node.getOperator().getName() + ")", in, DriverStrategy.SORTED_REDUCE, this.keyList);
} else {
// non forward case. all local properties are killed anyways, so we can safely plug in a combiner
Channel toCombiner = new Channel(in.getSource());
toCombiner.setShipStrategy(ShipStrategyType.FORWARD, DataExchangeMode.PIPELINED);
// create an input node for combine with same parallelism as input node
ReduceNode combinerNode = ((ReduceNode) node).getCombinerUtilityNode();
combinerNode.setParallelism(in.getSource().getParallelism());
SingleInputPlanNode combiner = new SingleInputPlanNode(combinerNode, "Combine (" + node.getOperator().getName() + ")", toCombiner, this.combinerStrategy, this.keyList);
combiner.setCosts(new Costs(0, 0));
combiner.initProperties(toCombiner.getGlobalProperties(), toCombiner.getLocalProperties());
Channel toReducer = new Channel(combiner);
toReducer.setShipStrategy(in.getShipStrategy(), in.getShipStrategyKeys(), in.getShipStrategySortOrder(), in.getDataExchangeMode());
toReducer.setLocalStrategy(LocalStrategy.SORT, in.getLocalStrategyKeys(), in.getLocalStrategySortOrder());
return new SingleInputPlanNode(node, "Reduce(" + node.getOperator().getName() + ")", toReducer, DriverStrategy.SORTED_REDUCE, this.keyList);
}
}
use of org.apache.flink.optimizer.dag.ReduceNode in project flink by apache.
the class GraphCreatingVisitor method preVisit.
@SuppressWarnings("deprecation")
@Override
public boolean preVisit(Operator<?> c) {
// check if we have been here before
if (this.con2node.containsKey(c)) {
return false;
}
final OptimizerNode n;
// create a node for the operator (or sink or source) if we have not been here before
if (c instanceof GenericDataSinkBase) {
DataSinkNode dsn = new DataSinkNode((GenericDataSinkBase<?>) c);
this.sinks.add(dsn);
n = dsn;
} else if (c instanceof GenericDataSourceBase) {
n = new DataSourceNode((GenericDataSourceBase<?, ?>) c);
} else if (c instanceof MapOperatorBase) {
n = new MapNode((MapOperatorBase<?, ?, ?>) c);
} else if (c instanceof MapPartitionOperatorBase) {
n = new MapPartitionNode((MapPartitionOperatorBase<?, ?, ?>) c);
} else if (c instanceof FlatMapOperatorBase) {
n = new FlatMapNode((FlatMapOperatorBase<?, ?, ?>) c);
} else if (c instanceof FilterOperatorBase) {
n = new FilterNode((FilterOperatorBase<?, ?>) c);
} else if (c instanceof ReduceOperatorBase) {
n = new ReduceNode((ReduceOperatorBase<?, ?>) c);
} else if (c instanceof GroupCombineOperatorBase) {
n = new GroupCombineNode((GroupCombineOperatorBase<?, ?, ?>) c);
} else if (c instanceof GroupReduceOperatorBase) {
n = new GroupReduceNode((GroupReduceOperatorBase<?, ?, ?>) c);
} else if (c instanceof InnerJoinOperatorBase) {
n = new JoinNode((InnerJoinOperatorBase<?, ?, ?, ?>) c);
} else if (c instanceof OuterJoinOperatorBase) {
n = new OuterJoinNode((OuterJoinOperatorBase<?, ?, ?, ?>) c);
} else if (c instanceof CoGroupOperatorBase) {
n = new CoGroupNode((CoGroupOperatorBase<?, ?, ?, ?>) c);
} else if (c instanceof CoGroupRawOperatorBase) {
n = new CoGroupRawNode((CoGroupRawOperatorBase<?, ?, ?, ?>) c);
} else if (c instanceof CrossOperatorBase) {
n = new CrossNode((CrossOperatorBase<?, ?, ?, ?>) c);
} else if (c instanceof BulkIterationBase) {
n = new BulkIterationNode((BulkIterationBase<?>) c);
} else if (c instanceof DeltaIterationBase) {
n = new WorksetIterationNode((DeltaIterationBase<?, ?>) c);
} else if (c instanceof Union) {
n = new BinaryUnionNode((Union<?>) c);
} else if (c instanceof PartitionOperatorBase) {
n = new PartitionNode((PartitionOperatorBase<?>) c);
} else if (c instanceof SortPartitionOperatorBase) {
n = new SortPartitionNode((SortPartitionOperatorBase<?>) c);
} else if (c instanceof BulkIterationBase.PartialSolutionPlaceHolder) {
if (this.parent == null) {
throw new InvalidProgramException("It is currently not supported to create data sinks inside iterations.");
}
final BulkIterationBase.PartialSolutionPlaceHolder<?> holder = (BulkIterationBase.PartialSolutionPlaceHolder<?>) c;
final BulkIterationBase<?> enclosingIteration = holder.getContainingBulkIteration();
final BulkIterationNode containingIterationNode = (BulkIterationNode) this.parent.con2node.get(enclosingIteration);
// catch this for the recursive translation of step functions
BulkPartialSolutionNode p = new BulkPartialSolutionNode(holder, containingIterationNode);
p.setParallelism(containingIterationNode.getParallelism());
n = p;
} else if (c instanceof DeltaIterationBase.WorksetPlaceHolder) {
if (this.parent == null) {
throw new InvalidProgramException("It is currently not supported to create data sinks inside iterations.");
}
final DeltaIterationBase.WorksetPlaceHolder<?> holder = (DeltaIterationBase.WorksetPlaceHolder<?>) c;
final DeltaIterationBase<?, ?> enclosingIteration = holder.getContainingWorksetIteration();
final WorksetIterationNode containingIterationNode = (WorksetIterationNode) this.parent.con2node.get(enclosingIteration);
// catch this for the recursive translation of step functions
WorksetNode p = new WorksetNode(holder, containingIterationNode);
p.setParallelism(containingIterationNode.getParallelism());
n = p;
} else if (c instanceof DeltaIterationBase.SolutionSetPlaceHolder) {
if (this.parent == null) {
throw new InvalidProgramException("It is currently not supported to create data sinks inside iterations.");
}
final DeltaIterationBase.SolutionSetPlaceHolder<?> holder = (DeltaIterationBase.SolutionSetPlaceHolder<?>) c;
final DeltaIterationBase<?, ?> enclosingIteration = holder.getContainingWorksetIteration();
final WorksetIterationNode containingIterationNode = (WorksetIterationNode) this.parent.con2node.get(enclosingIteration);
// catch this for the recursive translation of step functions
SolutionSetNode p = new SolutionSetNode(holder, containingIterationNode);
p.setParallelism(containingIterationNode.getParallelism());
n = p;
} else {
throw new IllegalArgumentException("Unknown operator type: " + c);
}
this.con2node.put(c, n);
// key-less reducer (all-reduce)
if (n.getParallelism() < 1) {
// set the parallelism
int par = c.getParallelism();
if (n instanceof BinaryUnionNode) {
// Keep parallelism of union undefined for now.
// It will be determined based on the parallelism of its successor.
par = -1;
} else if (par > 0) {
if (this.forceParallelism && par != this.defaultParallelism) {
par = this.defaultParallelism;
Optimizer.LOG.warn("The parallelism of nested dataflows (such as step functions in iterations) is " + "currently fixed to the parallelism of the surrounding operator (the iteration).");
}
} else {
par = this.defaultParallelism;
}
n.setParallelism(par);
}
return true;
}
Aggregations