RFR: 8358621: Reduce busy waiting in worse case at the synchronization point returning from native in CPU Time Profiler

[Johannes Bechberger]

On Tue, 15 Jul 2025 11:36:51 GMT, Johannes Bechberger <jbechberger at openjdk.org> wrote:

> Simple optimization to reduce busy waiting in safepoint handlers.

Thanks. As a background: This lock should almost never be locked (confirmed with renaissance benchmark), when the safepoint handler comes in. So it is more a defence against a rare outlier.

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

PR Comment: https://git.openjdk.org/jdk/pull/26314#issuecomment-3073349264