RFR: 8292591: Experimentally add back barrier-less Java thread transitions [v5]

Patricio Chilano Mateo pchilanomate at openjdk.org
Fri Sep 9 16:35:44 UTC 2022


On Fri, 9 Sep 2022 10:05:11 GMT, Robbin Ehn <rehn at openjdk.org> wrote:

>> Please consider, only implemented on x64/aarch64 linux/windows. (@TheRealMDoerr have now contributed PPC64)
>> 
>> On my box calling clock_gettime via JNI goes from 35ns to 28ns when enabled.
>> 
>> Passes t1-7 with option forced on, also passes t1-4 as is in this PR.
>
> Robbin Ehn has updated the pull request incrementally with one additional commit since the last revision:
> 
>   Fixed ws

Looks good to me! I think we can avoid always emitting the memory barrier for the JFR sampler if we move it inside the thread_state_in_native() case and then re-read the state after the barrier.

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

Marked as reviewed by pchilanomate (Reviewer).

PR: https://git.openjdk.org/jdk/pull/10123


More information about the hotspot-dev mailing list