On Tue, 15 Sep 2026 17:46:08 GMT, Alan Bateman <[email protected]> wrote:
>> @AlanBateman I've put together a JMH bench for the exchange-method (which is >> the bench that generated the numbers in the PR description), I could clean >> that bench up a bit and attach it to this PR so that there's something to >> guide any tuning of the SPINS-constant in the future. > >> I could clean that bench up a bit and attach it to this PR so that there's >> something to guide any tuning of the SPINS-constant in the future. > > If you have the cycles to do this then I think it would be useful to have > something in test/micro/org/openjdk/bench/java/util/concurrent as the spin > count may be something that needs to be tuned/tweaked periodically. @AlanBateman @DougLea Added the benchmark to this PR now ------------- PR Comment: https://git.openjdk.org/jdk/pull/32886#issuecomment-5688165821
