RFR (XXS): 8202829: Implement CollectedHeap::get_safepoint_workers() for G1
thomas.schatzl at oracle.com
Mon May 14 09:21:18 UTC 2018
On Wed, 2018-05-09 at 20:03 +0200, Roman Kennke wrote:
> In Shenandoah GC we use a separate thread pool for this. I am trying
> to remember why :-) It might have been because Shenandoah workers are
> not suspending at safepoints. It might also have been because it is
> not benefitial to throw that many workers on the safepoint cleanup.
> It might be worth to evaluate the usefulness on large box / many
> threads setups, and probably limit the number of workers to give to
> safepoint cleanup.
We are aware of issues with thread startup on large boxes with many
threads, and we are working on it.
In this case, ideally, all this work would be done concurrently
> Other than that: go!
Thanks for your review,
More information about the hotspot-gc-dev