beliefer commented on code in PR #35789: URL: https://github.com/apache/spark/pull/35789#discussion_r979150037
########## sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/InjectRuntimeFilter.scala: ########## @@ -0,0 +1,303 @@ +/* + * 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.catalyst.optimizer + +import org.apache.spark.sql.catalyst.expressions._ +import org.apache.spark.sql.catalyst.expressions.aggregate.{AggregateExpression, BloomFilterAggregate, Complete} +import org.apache.spark.sql.catalyst.planning.{ExtractEquiJoinKeys, PhysicalOperation} +import org.apache.spark.sql.catalyst.plans._ +import org.apache.spark.sql.catalyst.plans.logical._ +import org.apache.spark.sql.catalyst.rules.Rule +import org.apache.spark.sql.catalyst.trees.TreePattern.{INVOKE, JSON_TO_STRUCT, LIKE_FAMLIY, PYTHON_UDF, REGEXP_EXTRACT_FAMILY, REGEXP_REPLACE, SCALA_UDF} +import org.apache.spark.sql.internal.SQLConf +import org.apache.spark.sql.types._ + +/** + * Insert a filter on one side of the join if the other side has a selective predicate. + * The filter could be an IN subquery (converted to a semi join), a bloom filter, or something + * else in the future. + */ +object InjectRuntimeFilter extends Rule[LogicalPlan] with PredicateHelper with JoinSelectionHelper { + + // Wraps `expr` with a hash function if its byte size is larger than an integer. + private def mayWrapWithHash(expr: Expression): Expression = { + if (expr.dataType.defaultSize > IntegerType.defaultSize) { + new Murmur3Hash(Seq(expr)) + } else { + expr + } + } + + private def injectFilter( + filterApplicationSideExp: Expression, + filterApplicationSidePlan: LogicalPlan, + filterCreationSideExp: Expression, + filterCreationSidePlan: LogicalPlan): LogicalPlan = { + require(conf.runtimeFilterBloomFilterEnabled || conf.runtimeFilterSemiJoinReductionEnabled) + if (conf.runtimeFilterBloomFilterEnabled) { + injectBloomFilter( + filterApplicationSideExp, + filterApplicationSidePlan, + filterCreationSideExp, + filterCreationSidePlan + ) + } else { + injectInSubqueryFilter( + filterApplicationSideExp, + filterApplicationSidePlan, + filterCreationSideExp, + filterCreationSidePlan + ) + } + } + + private def injectBloomFilter( + filterApplicationSideExp: Expression, + filterApplicationSidePlan: LogicalPlan, + filterCreationSideExp: Expression, + filterCreationSidePlan: LogicalPlan): LogicalPlan = { + // Skip if the filter creation side is too big + if (filterCreationSidePlan.stats.sizeInBytes > conf.runtimeFilterCreationSideThreshold) { + return filterApplicationSidePlan + } + val rowCount = filterCreationSidePlan.stats.rowCount + val bloomFilterAgg = + if (rowCount.isDefined && rowCount.get.longValue > 0L) { + new BloomFilterAggregate(new XxHash64(Seq(filterCreationSideExp)), + Literal(rowCount.get.longValue)) + } else { + new BloomFilterAggregate(new XxHash64(Seq(filterCreationSideExp))) + } + val aggExp = AggregateExpression(bloomFilterAgg, Complete, isDistinct = false, None) + val alias = Alias(aggExp, "bloomFilter")() + val aggregate = ConstantFolding(Aggregate(Nil, Seq(alias), filterCreationSidePlan)) + val bloomFilterSubquery = ScalarSubquery(aggregate, Nil) + val filter = BloomFilterMightContain(bloomFilterSubquery, + new XxHash64(Seq(filterApplicationSideExp))) + Filter(filter, filterApplicationSidePlan) + } + + private def injectInSubqueryFilter( + filterApplicationSideExp: Expression, + filterApplicationSidePlan: LogicalPlan, + filterCreationSideExp: Expression, + filterCreationSidePlan: LogicalPlan): LogicalPlan = { + require(filterApplicationSideExp.dataType == filterCreationSideExp.dataType) + val actualFilterKeyExpr = mayWrapWithHash(filterCreationSideExp) + val alias = Alias(actualFilterKeyExpr, actualFilterKeyExpr.toString)() + val aggregate = Aggregate(Seq(alias), Seq(alias), filterCreationSidePlan) + if (!canBroadcastBySize(aggregate, conf)) { + // Skip the InSubquery filter if the size of `aggregate` is beyond broadcast join threshold, + // i.e., the semi-join will be a shuffled join, which is not worthwhile. + return filterApplicationSidePlan + } + val filter = InSubquery(Seq(mayWrapWithHash(filterApplicationSideExp)), + ListQuery(aggregate, childOutputs = aggregate.output)) + Filter(filter, filterApplicationSidePlan) Review Comment: Since we are going to use semi-join, can you tell me the performance problems in detail? -- 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: reviews-unsubscr...@spark.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
