ulysses-you commented on pull request #31653: URL: https://github.com/apache/spark/pull/31653#issuecomment-823707302
We found the same issue about failed to optimize skewed join due to the extra shuffle. Before submit a ticket, I just found this PR and [#30829](https://github.com/apache/spark/pull/30829). Can we add the config to allow extra shuffle directly ? I think it's fine in first step although the new added shuffle can not be optimized by AQE framwork. And then we can make an another ticket to discuss how to make AQE optimize the shuffle which added during optimize query stages. What do you think about @ekoifman @cloud-fan -- 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. 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