Github user ankuriitg commented on the issue: https://github.com/apache/spark/pull/23058 The change looks good to me. I understand that this change uses memory efficiently but I am wondering whether it causes any performance degradation compared to memory mapping. If yes, can we measure the performance impact and document it with this change.
--- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org