cloud-fan commented on code in PR #38799: URL: https://github.com/apache/spark/pull/38799#discussion_r1036836089
########## sql/core/src/main/scala/org/apache/spark/sql/execution/window/WindowGroupLimitExec.scala: ########## @@ -0,0 +1,236 @@ +/* + * 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.window + +import org.apache.spark.rdd.RDD +import org.apache.spark.sql.catalyst.InternalRow +import org.apache.spark.sql.catalyst.expressions.{Ascending, Attribute, DenseRank, Expression, Rank, RowNumber, SortOrder, UnsafeProjection, UnsafeRow} +import org.apache.spark.sql.catalyst.expressions.codegen.GenerateOrdering +import org.apache.spark.sql.catalyst.plans.physical.{AllTuples, ClusteredDistribution, Distribution, Partitioning} +import org.apache.spark.sql.execution.{ExternalAppendOnlyUnsafeRowArray, SparkPlan, UnaryExecNode} + +sealed trait WindowGroupLimitMode + +case object Partial extends WindowGroupLimitMode + +case object Final extends WindowGroupLimitMode + +/** + * This operator is designed to filter out unnecessary rows before WindowExec + * for top-k computation. + * @param partitionSpec Should be the same as [[WindowExec#partitionSpec]] + * @param orderSpec Should be the same as [[WindowExec#orderSpec]] + * @param rankLikeFunction The function to compute row rank, should be RowNumber/Rank/DenseRank. + */ +case class WindowGroupLimitExec( + partitionSpec: Seq[Expression], + orderSpec: Seq[SortOrder], + rankLikeFunction: Expression, + limit: Int, + mode: WindowGroupLimitMode, + child: SparkPlan) extends UnaryExecNode { + + override def output: Seq[Attribute] = child.output + + override def requiredChildDistribution: Seq[Distribution] = mode match { + case Partial => super.requiredChildDistribution + case Final => + if (partitionSpec.isEmpty) { + // Only show warning when the number of bytes is larger than 100 MiB? + logWarning("No Partition Defined for Window operation! Moving all data to a single " + + "partition, this can cause serious performance degradation.") + AllTuples :: Nil + } else { + ClusteredDistribution(partitionSpec) :: Nil + } + } + + override def requiredChildOrdering: Seq[Seq[SortOrder]] = Review Comment: shall we make it part of this PR? This is different from https://github.com/apache/spark/pull/38799/files#diff-21f071d73070b8257ad76e6e16ec5ed38a13d1278fe94bd42546c258a69f4410R688 and we are likely to change many code in this file to add it. -- 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]
