HeartSaVioR commented on a change in pull request #31495: URL: https://github.com/apache/spark/pull/31495#discussion_r571798020
########## File path: sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/HDFSMetadataLog.scala ########## @@ -239,18 +239,35 @@ class HDFSMetadataLog[T <: AnyRef : ClassTag](sparkSession: SparkSession, path: .reverse } + private var lastPurgedBatchId: Long = -1L + /** * Removes all the log entry earlier than thresholdBatchId (exclusive). */ override def purge(thresholdBatchId: Long): Unit = { - val batchIds = fileManager.list(metadataPath, batchFilesFilter) - .map(f => pathToBatchId(f.getPath)) - - for (batchId <- batchIds if batchId < thresholdBatchId) { - val path = batchIdToPath(batchId) - fileManager.delete(path) - logTrace(s"Removed metadata log file: $path") + val possibleTargetBatchIds = (lastPurgedBatchId + 1 until thresholdBatchId) + if (possibleTargetBatchIds.length <= 3) { + // avoid using list if we only need to purge at most 3 elements + possibleTargetBatchIds.foreach { batchId => + val path = batchIdToPath(batchId) + if (fileManager.exists(path)) { Review comment: Yeah that also makes sense. I'm not sure about how much the cost would be saved though. Let me play with this a bit. ---------------------------------------------------------------- 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: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org