akashrn5 commented on a change in pull request #3854: URL: https://github.com/apache/carbondata/pull/3854#discussion_r459607797
########## File path: integration/spark/src/main/scala/org/apache/spark/sql/secondaryindex/events/CleanFilesPostEventListener.scala ########## @@ -54,7 +60,70 @@ class CleanFilesPostEventListener extends OperationEventListener with Logging { SegmentStatusManager.deleteLoadsAndUpdateMetadata( indexTable, true, partitions.map(_.asJava).orNull) CarbonUpdateUtil.cleanUpDeltaFiles(indexTable, true) + cleanUpUnwantedSegmentsOfSIAndUpdateMetadata(indexTable, carbonTable) } } } + + /** + * This method added to clean the segments which are success in SI and may be compacted or marked + * for delete in main table, which can happen in case of concurrent scenarios. + */ + def cleanUpUnwantedSegmentsOfSIAndUpdateMetadata(indexTable: CarbonTable, + mainTable: CarbonTable): Unit = { + val mainTableStatusLock: ICarbonLock = CarbonLockFactory + .getCarbonLockObj(mainTable.getAbsoluteTableIdentifier, LockUsage.TABLE_STATUS_LOCK) + val indexTableStatusLock: ICarbonLock = CarbonLockFactory + .getCarbonLockObj(indexTable.getAbsoluteTableIdentifier, LockUsage.TABLE_STATUS_LOCK) + var mainTableLocked = false + var indexTableLocked = false + try { + mainTableLocked = mainTableStatusLock.lockWithRetries() Review comment: done ########## File path: integration/spark/src/main/scala/org/apache/spark/sql/secondaryindex/events/CleanFilesPostEventListener.scala ########## @@ -54,7 +60,68 @@ class CleanFilesPostEventListener extends OperationEventListener with Logging { SegmentStatusManager.deleteLoadsAndUpdateMetadata( indexTable, true, partitions.map(_.asJava).orNull) CarbonUpdateUtil.cleanUpDeltaFiles(indexTable, true) + cleanUpUnwantedSegmentsOfSIAndUpdateMetadata(indexTable, carbonTable) } } } + + /** + * This method added to clean the segments which are success in SI and may be compacted or marked + * for delete in main table, which can happen in case of concurrent scenarios. + */ + def cleanUpUnwantedSegmentsOfSIAndUpdateMetadata(indexTable: CarbonTable, + mainTable: CarbonTable): Unit = { + val mainTableStatusLock: ICarbonLock = CarbonLockFactory + .getCarbonLockObj(mainTable.getAbsoluteTableIdentifier, LockUsage.TABLE_STATUS_LOCK) + val indexTableStatusLock: ICarbonLock = CarbonLockFactory + .getCarbonLockObj(indexTable.getAbsoluteTableIdentifier, LockUsage.TABLE_STATUS_LOCK) + var mainTableLocked = false + var indexTableLocked = false + try { + mainTableLocked = mainTableStatusLock.lockWithRetries() + indexTableLocked = indexTableStatusLock.lockWithRetries() + if (mainTableLocked && indexTableLocked) { + val mainTableMetadataDetails = + SegmentStatusManager.readLoadMetadata(mainTable.getMetadataPath).toSet ++ + SegmentStatusManager.readLoadHistoryMetadata(mainTable.getMetadataPath).toSet + val indexTableMetadataDetails = + SegmentStatusManager.readLoadMetadata(indexTable.getMetadataPath).toSet + val segToStatusMap = mainTableMetadataDetails + .map(detail => detail.getLoadName -> detail.getSegmentStatus).toMap + + val unnecessarySegmentsOfSI = indexTableMetadataDetails.filter { indexDetail => + indexDetail.getSegmentStatus.equals(SegmentStatus.SUCCESS) && + segToStatusMap.contains(indexDetail.getLoadName) && + (segToStatusMap(indexDetail.getLoadName).equals(SegmentStatus.COMPACTED) || + segToStatusMap(indexDetail.getLoadName).equals(SegmentStatus.MARKED_FOR_DELETE)) + } + LOGGER.info(s"Unwanted SI segments are: $unnecessarySegmentsOfSI") + unnecessarySegmentsOfSI.foreach { detail => + val carbonFile = FileFactory + .getCarbonFile(CarbonTablePath + .getSegmentPath(indexTable.getTablePath, detail.getLoadName)) + CarbonUtil.deleteFoldersAndFiles(carbonFile) + } + unnecessarySegmentsOfSI.foreach { detail => + detail.setSegmentStatus(segToStatusMap(detail.getLoadName)) + detail.setVisibility("false") + } + CarbonInternalLoaderUtil.recordLoadMetadata( Review comment: done ---------------------------------------------------------------- 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