Github user wzhfy commented on a diff in the pull request: https://github.com/apache/spark/pull/17138#discussion_r106781914 --- Diff: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/CostBasedJoinReorder.scala --- @@ -0,0 +1,297 @@ +/* + * 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 scala.collection.mutable + +import org.apache.spark.sql.catalyst.CatalystConf +import org.apache.spark.sql.catalyst.expressions.{And, Attribute, AttributeSet, Expression, PredicateHelper} +import org.apache.spark.sql.catalyst.plans.{Inner, InnerLike} +import org.apache.spark.sql.catalyst.plans.logical.{BinaryNode, Join, LogicalPlan, Project} +import org.apache.spark.sql.catalyst.rules.Rule + + +/** + * Cost-based join reorder. + * We may have several join reorder algorithms in the future. This class is the entry of these + * algorithms, and chooses which one to use. + */ +case class CostBasedJoinReorder(conf: CatalystConf) extends Rule[LogicalPlan] with PredicateHelper { + def apply(plan: LogicalPlan): LogicalPlan = { + if (!conf.cboEnabled || !conf.joinReorderEnabled) { + plan + } else { + val result = plan transform { + case p @ Project(projectList, j @ Join(_, _, _: InnerLike, _)) => + reorder(p, p.outputSet) + case j @ Join(_, _, _: InnerLike, _) => + reorder(j, j.outputSet) + } + // After reordering is finished, convert OrderedJoin back to Join + result transform { + case oj: OrderedJoin => oj.join + } + } + } + + def reorder(plan: LogicalPlan, output: AttributeSet): LogicalPlan = { + val (items, conditions) = extractInnerJoins(plan) --- End diff -- Sorry my words are not accurate. By `leaf plan` I mean basic reorder unit, it can be any node. I want to use `item` to mean it's a basic unit, while `subplan` can be any level reordered results.
--- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature enabled and wishes so, or if the feature is enabled but not working, please contact infrastructure at infrastruct...@apache.org or file a JIRA ticket with INFRA. --- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org