cloud-fan commented on a change in pull request #28676:
URL: https://github.com/apache/spark/pull/28676#discussion_r455710758
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/joins/HashJoin.scala
##########
@@ -62,21 +62,30 @@ trait HashJoin extends BaseJoinExec {
protected lazy val (buildKeys, streamedKeys) = {
require(leftKeys.map(_.dataType) == rightKeys.map(_.dataType),
"Join keys from two sides should have same types")
- val lkeys = bindReferences(HashJoin.rewriteKeyExpr(leftKeys), left.output)
- val rkeys = bindReferences(HashJoin.rewriteKeyExpr(rightKeys),
right.output)
buildSide match {
- case BuildLeft => (lkeys, rkeys)
- case BuildRight => (rkeys, lkeys)
+ case BuildLeft => (leftKeys, rightKeys)
+ case BuildRight => (rightKeys, leftKeys)
}
}
+ private lazy val (buildOutput, streamedOutput) = {
+ buildSide match {
+ case BuildLeft => (left.output, right.output)
+ case BuildRight => (right.output, left.output)
+ }
+ }
+
+ protected lazy val buildBoundKeys =
+ bindReferences(HashJoin.rewriteKeyExpr(buildKeys), buildOutput)
+ protected lazy val streamedBoundKeys =
Review comment:
we add many class variables in this PR. Let's add `@transient` if they
don't need to serialized and sent to executors.
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/joins/HashJoin.scala
##########
@@ -62,21 +62,30 @@ trait HashJoin extends BaseJoinExec {
protected lazy val (buildKeys, streamedKeys) = {
require(leftKeys.map(_.dataType) == rightKeys.map(_.dataType),
"Join keys from two sides should have same types")
- val lkeys = bindReferences(HashJoin.rewriteKeyExpr(leftKeys), left.output)
- val rkeys = bindReferences(HashJoin.rewriteKeyExpr(rightKeys),
right.output)
buildSide match {
- case BuildLeft => (lkeys, rkeys)
- case BuildRight => (rkeys, lkeys)
+ case BuildLeft => (leftKeys, rightKeys)
+ case BuildRight => (rightKeys, leftKeys)
}
}
+ private lazy val (buildOutput, streamedOutput) = {
+ buildSide match {
+ case BuildLeft => (left.output, right.output)
+ case BuildRight => (right.output, left.output)
+ }
+ }
+
+ protected lazy val buildBoundKeys =
+ bindReferences(HashJoin.rewriteKeyExpr(buildKeys), buildOutput)
+ protected lazy val streamedBoundKeys =
Review comment:
we add many class variables in this PR. Let's add `@transient` if they
don't need to be serialized and sent to executors.
----------------------------------------------------------------
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.
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
