Github user rdblue commented on a diff in the pull request: https://github.com/apache/spark/pull/19424#discussion_r143597547 --- Diff: sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/PushDownOperatorsToDataSource.scala --- @@ -0,0 +1,104 @@ +/* + * 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 org.apache.spark.sql.catalyst.expressions.{And, Attribute, AttributeMap, Expression, PredicateHelper} +import org.apache.spark.sql.catalyst.optimizer.{PushDownPredicate, RemoveRedundantProject} +import org.apache.spark.sql.catalyst.plans.logical.{Filter, LogicalPlan, Project} +import org.apache.spark.sql.catalyst.rules.Rule +import org.apache.spark.sql.execution.datasources.DataSourceStrategy +import org.apache.spark.sql.sources +import org.apache.spark.sql.sources.v2.reader._ + +/** + * Pushes down various operators to the underlying data source for better performance. Operators are + * being pushed down with a specific order. As an example, given a LIMIT has a FILTER child, you + * can't push down LIMIT if FILTER is not completely pushed down. When both are pushed down, the + * data source should execute FILTER before LIMIT. And required columns are calculated at the end, + * because when more operators are pushed down, we may need less columns at Spark side. + */ +object PushDownOperatorsToDataSource extends Rule[LogicalPlan] with PredicateHelper { + override def apply(plan: LogicalPlan): LogicalPlan = { + // make sure filters are at very bottom. + val prepared = PushDownPredicate(plan) + val afterPushDown = prepared transformUp { + case Filter(condition, r @ DataSourceV2Relation(_, reader)) => + val (candidates, containingNonDeterministic) = + splitConjunctivePredicates(condition).span(_.deterministic) + + val stayUpFilters: Seq[Expression] = reader match { + case r: SupportsPushDownCatalystFilters => + r.pushCatalystFilters(candidates.toArray) + + case r: SupportsPushDownFilters => + // A map from original Catalyst expressions to corresponding translated data source + // filters. If a predicate is not in this map, it means it cannot be pushed down. + val translatedMap: Map[Expression, sources.Filter] = candidates.flatMap { p => + DataSourceStrategy.translateFilter(p).map(f => p -> f) + }.toMap + + // Catalyst predicate expressions that cannot be converted to data source filters. + val nonConvertiblePredicates = candidates.filterNot(translatedMap.contains) + + // Data source filters that cannot be pushed down. An unhandled filter means + // the data source cannot guarantee the rows returned can pass the filter. + // As a result we must return it so Spark can plan an extra filter operator. + val unhandledFilters = r.pushFilters(translatedMap.values.toArray).toSet + val unhandledPredicates = translatedMap.filter { case (_, f) => + unhandledFilters.contains(f) + }.keys + + nonConvertiblePredicates ++ unhandledPredicates + + case _ => candidates + } + + val filterCondition = (stayUpFilters ++ containingNonDeterministic).reduceLeftOption(And) + filterCondition.map(Filter(_, r)).getOrElse(r) + + // TODO: add more push down rules. + } + + // TODO: nested fields pruning + def pushDownRequiredColumns(plan: LogicalPlan, requiredByParent: Seq[Attribute]): Unit = { + plan match { + case Project(projectList, child) => + val required = projectList.filter(requiredByParent.contains).flatMap(_.references) + pushDownRequiredColumns(child, required) + + case Filter(condition, child) => + val required = requiredByParent ++ condition.references + pushDownRequiredColumns(child, required) + + case DataSourceV2Relation(fullOutput, reader) => reader match { + case r: SupportsPushDownRequiredColumns => + val attrMap = AttributeMap(fullOutput.zip(fullOutput)) + val requiredColumns = requiredByParent.map(attrMap) + // Match original case of attributes. --- End diff -- Shouldn't this comment be on line 90? That's the purpose of looking up the required attributes in the set of attrs that was produced from the data source's schema right? That lookup happens by exprId, which was generated by the `DataSourceV2Relation` so we know we have a copy of the original attribute and case.
--- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org