jianzhenwu commented on issue #5736: URL: https://github.com/apache/incubator-gluten/issues/5736#issuecomment-3713524505
hi @marin-ma We meet this issue again. I printed out the buffers for the shuffle writer and reader. The data written by RssPartitionWriter is ``` E20260106 12:07:02.147404 3830552 RssPartitionWriter.cc:110] [ShuffleWriteDump] partition=0, size=144 E20260106 12:07:02.147465 3830552 RssPartitionWriter.cc:112] [ShuffleWriteDump] HEX: 28 b5 2f fd 00 48 3d 04 00 e4 06 60 00 00 00 04 00 90 a4 eb c9 70 03 ``` The data read in by ShuffleReader is ``` E20260106 12:11:19.396942 3970403 Utils.h:426] input_len=6865, compressed_size=6865, compressed_pos=0 E20260106 12:11:19.397058 3970403 Utils.h:429] output_len=1048576 E20260106 12:11:19.397078 3970403 Utils.h:438] input[0..63]: 5a 53 54 44 42 6c 6f 63 6b 10 90 00 00 00 90 00 00 00 62 47 d1 7d 28 b5 2f fd 00 48 3d 04 00 e4 06 60 00 00 00 04 00 90 a4 eb c9 70 03 ``` I noticed that it added `5a 53 54 44 42 6c 6f 63 6b` (which means ZSTDBlock) to the beginning of the data. -- 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]
