andygrove commented on pull request #33140: URL: https://github.com/apache/spark/pull/33140#issuecomment-872683064
> why does the final plan matter? are you going to change `df.collect` to leverage columnar execution as well? We have no plans currently to change `df.collect`. The main issue is that `AdaptiveSparkPlanExec` isn't always the final plan. It can be contained inside other plans. One example is when writing the results of an adaptive plan to Parquet and we want to avoid unnecessary columnar-to-row followed by row-to-columnar when doing the columnar write. -- 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: reviews-unsubscr...@spark.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
