![]() | ||||||||||
Messages in this thread |
* Linus Torvalds <torvalds@linux-foundation.org> wrote: > I think turning the BKL into a semaphore was fine per se, but that was > when semaphores were fast. hm, do we know it for a fact that the 40% AIM regression is due to the fastpath overhead of the BKL? It would be extraordinary if so. I think it is far more likely that it's due to the different scheduling and wakeup behavior of the new kernel/semaphore.c code. So the fix would be to restore the old scheduling behavior - that's what Yanmin's manual revert did and that's what got him back the previous AIM7 performance. Ingo | |||||||||
| Last update: 2008-05-07 16:23 [W:0.503 / U:0.040 seconds] ©2003-2008 Jasper Spaans | ||||||||||