pvary commented on PR #18393: URL: https://github.com/apache/iceberg/pull/18393#issuecomment-6011039014
Thanks @anuragmantri for the PR. I have one serious concern: Each file starts its batches fresh at its own row-group boundaries. Once any file's row-group size isn't a multiple of the batch size, almost every output batch is split which kills performance. A smaller perf concern is that we read and decode every row even when we skip them (I think this is an issue too with the PR this one is based on) -- 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]
