anishshri-db commented on code in PR #52642:
URL: https://github.com/apache/spark/pull/52642#discussion_r2450421664
##########
sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/runtime/MicroBatchExecution.scala:
##########
@@ -344,9 +344,40 @@ class MicroBatchExecution(
setLatestExecutionContext(execCtx)
populateStartOffsets(execCtx, sparkSessionForStream)
+
+ // SPARK-53941: This code path is executed for the first batch, regardless
of whether it's a
+ // fresh new run or restart.
+ disableAQESupportInStatelessIfUnappropriated(sparkSessionForStream)
+
logInfo(log"Stream started from ${MDC(LogKeys.STREAMING_OFFSETS_START,
execCtx.startOffsets)}")
execCtx
}
+
+ private def disableAQESupportInStatelessIfUnappropriated(
+ sparkSessionToRunBatches: SparkSession): Unit = {
+ def containsStatefulOperator(p: LogicalPlan): Boolean = {
+ p.exists {
+ case node: Aggregate if node.isStreaming => true
+ case node: Deduplicate if node.isStreaming => true
+ case node: DeduplicateWithinWatermark if node.isStreaming => true
+ case node: Distinct if node.isStreaming => true
+ case node: Join if node.left.isStreaming && node.right.isStreaming =>
true
+ case node: FlatMapGroupsWithState if node.isStreaming => true
Review Comment:
What about AIPWS and TWSInPandas ?
--
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.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
