gaoyajun02 commented on PR #46934: URL: https://github.com/apache/spark/pull/46934#issuecomment-2176127394
Additionally, I have also encountered scenarios of data duplication: updateChunkInfo is also called after the block merge is completed. In this case (see code: [link](https://github.com/apache/spark/blob/80bba4463eba29a56cdd90642f0681c3710ce87c/common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/RemoteBlockPushResolver.java#L1571)), if updating the metaFile fails due to IOException: No space left on device, the mapTracker will not record the mapId, but the chunkTracker is not reset. When finalizePartition is executed later and disk space is restored, the metaFile update succeeds, but the mapTracker does not lack this mapId. -- 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]
