jiangjiangtian commented on issue #10892: URL: https://github.com/apache/incubator-gluten/issues/10892#issuecomment-3410044343
> Thank you [@jiangjiangtian](https://github.com/jiangjiangtian) . > > ``` > child 17 estimated byte size 1171856976 > encoding: LAZY, isLazy: 1, type: ARRAY<VARCHAR> > isLoaded: 1, ARRAY > child 18 estimated byte size 61148981 > encoding: LAZY, isLazy: 1, type: ARRAY<VARCHAR> > isLoaded: 1, ARRAY > child 19 estimated byte size 195852983 > encoding: LAZY, isLazy: 1, type: ARRAY<VARCHAR> > isLoaded: 1, ARRAY > child 20 estimated byte size 537728511 > encoding: LAZY, isLazy: 1, type: ARRAY<VARCHAR> > isLoaded: 1, ARRAY > ``` > > This part is huge. I think we do need to cap output by a target byte size in `VeloxBatchResizer` to avoid OOMs. Yeah, I think it is a good idea. We can add a config to control it. If you think it is a workable solution, I can work on it. Thanks! @zhztheplayer -- 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]
