On Mon, 15 Jul 2024 12:34:37 GMT, Jorn Vernee <jver...@openjdk.org> wrote:
> This is the baseline if I change `closing` to use a confined arena: > > ``` > Benchmark Mode Cnt Score Error > Units > ConcurrentClose.sharedClose avgt 10 8.089 ± 0.006 > us/op > ConcurrentClose.sharedClose:closing avgt 10 0.001 ± 0.001 > us/op > ConcurrentClose.sharedClose:memorySegmentAccess avgt 10 20.046 ± 0.019 > us/op > ConcurrentClose.sharedClose:otherAccess avgt 10 4.220 ± 0.002 > us/op > ``` This is promising. Effectively, once all the issues surrounding reachability fences will be addressed, we should be able to achieve numbers similar to above even in the case of shared close. The only thing being slower in that case would be the closing thread itself. ------------- PR Comment: https://git.openjdk.org/jdk/pull/20158#issuecomment-2228448722