LIU Hao wrote: > In '[PATCH 09/24] winpthreads: mutex.c: simplify `pthread_mutex_*lock` > functions' and '[PATCH 11/24] > winpthreads: mutex.c: refactor implementation', I see that for normal mutexes > there's no longer a fast > path and now `_pthread_wait_for_single_object()` is always called which leads > to a syscall. That is a > severe performance regression and is unacceptable; see attached figure.
Should we add similar fast paths for spinlocks? After spinlock changes in May, they always call `WaitForSingleObject` which means they suffer from the same syscall overhead. I mentioned in the past that some source files (barrier.c, rwlock.c) use file-global spinlock when accessing _any_ object, so having fast paths could give noticeable performance improvement in some cases. - Kirill Makurin _______________________________________________ Mingw-w64-public mailing list [email protected] https://lists.sourceforge.net/lists/listinfo/mingw-w64-public
