Github user cloud-fan commented on the issue: https://github.com/apache/spark/pull/18747 LGTM except 2 minor comments. Can you benchmark some complex queries instead of full scan? I was expecting to see larger speed up via the columnar reader.
--- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org