Github user cloud-fan commented on a diff in the pull request: https://github.com/apache/spark/pull/7417#discussion_r41081828 --- Diff: sql/core/src/main/scala/org/apache/spark/sql/execution/SparkStrategies.scala --- @@ -274,12 +275,30 @@ private[sql] abstract class SparkStrategies extends QueryPlanner[SparkPlan] { } object CartesianProduct extends Strategy { + def getSmallSide(left: LogicalPlan, right: LogicalPlan): BuildSide = { + if (right.statistics.sizeInBytes < left.statistics.sizeInBytes) { + joins.BuildRight + } else { + joins.BuildLeft + } + } + def apply(plan: LogicalPlan): Seq[SparkPlan] = plan match { + // If plan can broadcast we use BroadcastNestedLoopJoin, as we know for inner join with true + // condition is same as Cartesian. + case logical.Join(CanBroadcast(left), right, joinType, condition) => + execution.joins.BroadcastNestedLoopJoin( + planLater(left), planLater(right), joins.BuildLeft, joinType, condition) :: Nil + case logical.Join(left, CanBroadcast(right), joinType, condition) => + execution.joins.BroadcastNestedLoopJoin( + planLater(left), planLater(right), joins.BuildRight, joinType, condition) :: Nil case logical.Join(left, right, _, None) => - execution.joins.CartesianProduct(planLater(left), planLater(right)) :: Nil + execution.joins.CartesianProduct(planLater(left), planLater(right), + getSmallSide(left, right)) :: Nil case logical.Join(left, right, Inner, Some(condition)) => execution.Filter(condition, - execution.joins.CartesianProduct(planLater(left), planLater(right))) :: Nil + execution.joins.CartesianProduct(planLater(left), planLater(right), + getSmallSide(left, right))) :: Nil --- End diff -- instead of passing a `BuildSide` to `CartesianProduct`, why not just change the parameters order according to the data size? like ``` if (left < right) { CartesianProduct(left, right) } else { CartesianProduct(right, left) } ```
--- 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