RFR: 8322732: ForkJoinPool may underutilize cores in async mode [v17]

[Alan Bateman]

On Fri, 31 May 2024 13:18:33 GMT, Doug Lea <dl at openjdk.org> wrote:

>> This set of changes address causes of poor utilization with small numbers of cores due to overly aggressive contention avoidance. A number of further adjustments were needed to still avoid most contention effects in deployments with large numbers of cores
>
> Doug Lea has updated the pull request incrementally with one additional commit since the last revision:
> 
>   Reconcile changes

Viktor (mostly) and I have been testing and reviewing these changes at each iteration. I think we are happy with where things are at, significantly very positive in some of the streams/gatherer tests. The Starvation test is the canary to catch a scenario that has been observed along the way, but not with the current version. So I think this is good to integrate.

-------------

Marked as reviewed by alanb (Reviewer).

PR Review: https://git.openjdk.org/jdk/pull/19131#pullrequestreview-2098894992