mbutrovich commented on issue #3882: URL: https://github.com/apache/datafusion-comet/issues/3882#issuecomment-4181293267
I mentioned this to @andygrove the other day, but applying compression (lz4, snappy, etc.) at the batch granularity is likely too small to get all their benefits. I’d be curious to know if Spark compresses shuffle at the file granularity or something more fine-grained. We could consider writing larger batches for shuffle, then use CometScan to hand out slices at `batch_size` number of rows. -- 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]
