leanken commented on a change in pull request #29104:
URL: https://github.com/apache/spark/pull/29104#discussion_r459820829
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/joins/BroadcastHashJoinExec.scala
##########
@@ -454,6 +491,48 @@ case class BroadcastHashJoinExec(
val (matched, checkCondition, _) = getJoinCondition(ctx, input)
val numOutput = metricTerm(ctx, "numOutputRows")
+ // fast stop if isOriginalInputEmpty = true, should accept all rows in
streamedSide
+ if (broadcastRelation.value.isOriginalInputEmpty) {
+ return s"""
+ |// Anti Join isOriginalInputEmpty(true) accept all
+ |$numOutput.add(1);
+ |${consume(ctx, input)}
+ """.stripMargin
+ }
+
+ if (isNullAwareAntiJoin) {
+ if (broadcastRelation.value.allNullColumnKeyExistsInOriginalInput) {
+ return s"""
+ |// NAAJ
Review comment:
```
see break keyword in basicPhysicalOperators.scala.
it might be ok for NAAJ to use break too. let me do the update and test.
while ($loopCondition) {
if ($nextIndex == $batchEnd) {
long $nextBatchTodo;
if ($numElementsTodo > ${batchSize}L) {
$nextBatchTodo = ${batchSize}L;
$numElementsTodo -= ${batchSize}L;
} else {
$nextBatchTodo = $numElementsTodo;
$numElementsTodo = 0;
if ($nextBatchTodo == 0) break;
}
$batchEnd += $nextBatchTodo * ${step}L;
}
```
----------------------------------------------------------------
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]
