Github user liyinan926 commented on the issue: https://github.com/apache/spark/pull/20460 Agreed. It seems much more complicated than expected, considering the interaction between `spark.executor.cores` and `spark.task.cpus` and the implication for each scheduler backend. Will do a more thorough investigation.
--- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org