ericm-db commented on code in PR #47490:
URL: https://github.com/apache/spark/pull/47490#discussion_r1698875796
##########
sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/IncrementalExecution.scala:
##########
@@ -79,6 +79,38 @@ class IncrementalExecution(
StreamingTransformWithStateStrategy :: Nil
}
+ // Methods to enable the use of AsyncLogPurge
+ protected val minLogEntriesToMaintain: Int =
+ sparkSession.sessionState.conf.minBatchesToRetain
+
+ val errorNotifier: ErrorNotifier = new ErrorNotifier()
+
+ override protected def purge(threshold: Long): Unit = {}
+
+ override protected def purgeOldest(planWithStateOpId: SparkPlan): Unit = {
+ planWithStateOpId.collect {
+ case ssw: StateStoreWriter =>
+ ssw.operatorStateMetadataVersion match {
+ case 2 =>
+ val fileManager = new OperatorStateMetadataV2FileManager(
+ new Path(checkpointLocation,
ssw.getStateInfo.operatorId.toString),
+ ssw.stateSchemaFilePath(Some(StateStoreId.DEFAULT_STORE_NAME)),
+ hadoopConf)
+ fileManager.keepNEntries(minLogEntriesToMaintain)
Review Comment:
Sorry, what does this mean?
If we want to keep the metadata for the latest N runs, we can just sort the
files by batchId, right?
--
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]
