Github user dongjoon-hyun commented on a diff in the pull request: https://github.com/apache/spark/pull/20395#discussion_r163965864 --- Diff: sql/core/src/test/scala/org/apache/spark/sql/execution/vectorized/ColumnarBatchBenchmark.scala --- @@ -479,10 +475,10 @@ object ColumnarBatchBenchmark { Array Vector Read: Best/Avg Time(ms) Rate(M/s) Per Row(ns) Relative ------------------------------------------------------------------------------------------------ - On Heap Read Size Only 416 / 423 393.5 2.5 1.0X - Off Heap Read Size Only 396 / 404 413.6 2.4 1.1X - On Heap Read Elements 2569 / 2590 63.8 15.7 0.2X - Off Heap Read Elements 3302 / 3333 49.6 20.2 0.1X + On Heap Read Size Only 426 / 437 384.9 2.6 1.0X + Off Heap Read Size Only 406 / 421 404.0 2.5 1.0X + On Heap Read Elements 2636 / 2642 62.2 16.1 0.2X + Off Heap Read Elements 3770 / 3774 43.5 23.0 0.1X --- End diff -- Thank you for updating this in the PR. It seems to cause a little performance degradation. Could you update `OrcReadBenchmark` and `FilterPushdownBenchmark`, too?
--- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org