Github user bersprockets commented on the issue: https://github.com/apache/spark/pull/22188 OK, I reran the tests for the lower column count cases, and the runs with the patch consistently show a tiny (1-3%) improvement compared to the master branch. So even the lower column count cases benefit a little.
--- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org