gabotechs commented on issue #26130: URL: https://github.com/apache/datafusion/issues/26130#issuecomment-6058616400
Just a small correction on: > https://github.com/datafusion-contrib/datafusion-distributed/issues/759 is another scan skew report from an engine that runs with work stealing off. `datafusion-distributed` does run with work stealing on. Work stealing is local to each physical worker, so this is not that big a problem there. Even if intra-worker work stealing masks this, there's no inter-worker work stealing mechanism, so there's still benefit from pruning files at planning time based on statistics so that the planned `DataSource`'s partitions are as balanced as possible. I'd probably not be able to work on this myself, but happy to help with reviews as well 👍 -- 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]
