anishshri-db commented on code in PR #46233: URL: https://github.com/apache/spark/pull/46233#discussion_r1580520020
########## sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/HDFSBackedStateStoreProvider.scala: ########## @@ -437,6 +437,23 @@ private[sql] class HDFSBackedStateStoreProvider extends StateStoreProvider with private def putStateIntoStateCacheMap( newVersion: Long, map: HDFSBackedStateStoreMap): Unit = synchronized { + val loadedEntries = loadedMaps.size() + val earliestLoadedVersion: Option[Long] = if (loadedEntries > 0) { + Some(loadedMaps.lastKey()) + } else { + None + } + + if (earliestLoadedVersion.isDefined) { + logInfo(s"Trying to add version=$newVersion to state cache map with " + + s"current_size=$loadedEntries and earliest_loaded_version=${earliestLoadedVersion.get} " + Review Comment: I think its ok to just know earliest ? we know current size anyway and versions are supposed to sequential here since we call this function on each commit ? -- 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: reviews-unsubscr...@spark.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org