peter-toth commented on code in PR #54330: URL: https://github.com/apache/spark/pull/54330#discussion_r2883976854
########## sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/GroupPartitionsExec.scala: ########## @@ -0,0 +1,219 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + + +package org.apache.spark.sql.execution.datasources.v2 + +import scala.collection.mutable.ArrayBuffer + +import org.apache.spark.{Partition, SparkException} +import org.apache.spark.rdd.{CoalescedRDD, PartitionCoalescer, PartitionGroup, RDD} +import org.apache.spark.sql.catalyst.InternalRow +import org.apache.spark.sql.catalyst.expressions._ +import org.apache.spark.sql.catalyst.plans.physical.{KeyedPartitioning, Partitioning} +import org.apache.spark.sql.catalyst.util.InternalRowComparableWrapper +import org.apache.spark.sql.connector.catalog.functions.Reducer +import org.apache.spark.sql.execution.{SparkPlan, UnaryExecNode} +import org.apache.spark.sql.types.DataType +import org.apache.spark.sql.vectorized.ColumnarBatch + +/** + * Physical operator that groups input partitions by their partition keys. + * + * This operator is used to coalesce partitions from bucketed/partitioned data sources + * where multiple input partitions share the same partition key. It's commonly used in + * storage-partitioned joins to align partitions from different sides of the join. + * + * @param child The child plan providing bucketed/partitioned input + * @param joinKeyPositions Optional projection to select a subset of the partitioning key + * for join compatibility (e.g., when join keys are a subset of + * partition keys) + * @param expectedPartitionKeys Optional sequence of expected partition key values and their + * split counts + * @param reducers Optional reducers to apply to partition keys for grouping compatibility + * @param applyPartialClustering Whether to apply partial clustering for skewed data + * @param replicatePartitions Whether to replicate partitions across multiple keys + */ +case class GroupPartitionsExec( + child: SparkPlan, + @transient joinKeyPositions: Option[Seq[Int]] = None, + @transient expectedPartitionKeys: Option[Seq[(InternalRowComparableWrapper, Int)]] = None, + @transient reducers: Option[Seq[Option[Reducer[_, _]]]] = None, + @transient applyPartialClustering: Boolean = false, + @transient replicatePartitions: Boolean = false + ) extends UnaryExecNode { + + override def outputPartitioning: Partitioning = { + child.outputPartitioning match { + case p: Partitioning with Expression => + // There can be multiple `KeyedPartitioning` in an output partitioning of a join, but they + // can only differ in `expressions`. `partitionKeys` must match so we can calculate it only + // once via `groupedPartitions`. + + val keyedPartitionings = p.collect { case k: KeyedPartitioning => k } + if (keyedPartitionings.size > 1) { + val first = keyedPartitionings.head + keyedPartitionings.tail.foreach { k => + assert(k.partitionKeys == first.partitionKeys, + "All KeyedPartitioning nodes must have identical partition keys") + } + } + + p.transform { + case k: KeyedPartitioning => + val projectedExpressions = joinKeyPositions.fold(k.expressions)(_.map(k.expressions)) + KeyedPartitioning(projectedExpressions, groupedPartitions.map(_._1), isGrouped = true) + }.asInstanceOf[Partitioning] + case o => o + } + } + + /** + * Aligns partitions based on `expectedPartitionKeys` and clustering mode. + */ + private def alignToExpectedKeys(keyMap: Map[InternalRowComparableWrapper, Seq[Int]]) = { + expectedPartitionKeys.get.flatMap { case (key, numSplits) => + val splits = keyMap.getOrElse(key, Seq.empty) + if (applyPartialClustering && !replicatePartitions) { + // Distribute splits across expected partitions, padding with empty sequences + val paddedSplits = splits.map(Seq(_)).padTo(numSplits, Seq.empty) + paddedSplits.map((key, _)) + } else { + // Replicate all splits to each expected partition + Seq.fill(numSplits)((key, splits)) + } + } + } + + /** + * Groups and sorts partitions by their keys in ascending order. + */ + private def groupAndSortByKeys( + keyMap: Map[InternalRowComparableWrapper, Seq[Int]], + dataTypes: Seq[DataType]) = { + val keyOrdering = RowOrdering.createNaturalAscendingOrdering(dataTypes) + keyMap.toSeq.sorted(keyOrdering.on((t: (InternalRowComparableWrapper, _)) => t._1.row)) + } + + /** + * Computes the grouped partitions by: + * 1. Projecting partition keys if joinKeyPositions is specified + * 2. Reducing keys if reducers are specified + * 3. Grouping input partition indices by their (possibly projected/reduced) keys + * 4. Sorting or distributing based on whether partial clustering is enabled + * + * Returns a sequence of (partitionKey, inputPartitionIndices) pairs representing + * how input partitions should be grouped together. + */ + @transient lazy val groupedPartitions = { + // There must be a `KeyedPartitioning` in child's output partitioning as a + // `GroupPartitionsExec` node is added to a plan only in that case. + val keyedPartitioning = child.outputPartitioning + .asInstanceOf[Partitioning with Expression] + .collectFirst { case k: KeyedPartitioning => k } Review Comment: We use the first one only for extracting the keys, the keys must be the same in others as well. The only reason why there can be multiple in a collection is that the expressions might be different due to projections. -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
