Github user squito commented on the issue: https://github.com/apache/spark/pull/21456 From my understanding, that option is only available with G1GC, which is not really a good fit for spark (forget the exact details but something about humongous allocations which are common with all the large byte buffers typical for spark).
--- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org