[VL] Slow scan with Spark runtime filter when split-preloading is turned on

In some cases when runtime filter is added, `spark.gluten.sql.columnar.backend.velox.IOThreads=0` (which turns Velox's preload / prefetch off) could gain better performance than the default settings (`spark.gluten.sql.columnar.backend.velox.IOThreads=`).

Caused by https://github.com/facebookincubator/velox/issues/10173

To temporarily bypass the issue if found, just set `spark.gluten.sql.columnar.backend.velox.IOThreads=0`.

Start by reproducing the slow scan with a Spark runtime filter while split-preloading is enabled, comparing the default IOThreads setting with IOThreads=0. Read the linked Velox issue 10173 for the reported cause; done means the performance problem is addressed or its affected conditions are clearly established.

Written by the indexing model from the issue text.