Messages in this thread | | | From | "Manfred" <> | Subject | Re: spin_unlock optimization(i386) | Date | Sun, 21 Nov 1999 13:54:07 +0100 |
| |
> In my opinion, relying on apparent ordering instead of enforcing it may > lead to subtil race conditions. We may, for example, be victimized by some > hardware erratum due to brain-deaded hardware optimizations, if we try to > be clever when we should avoid to do so. > I agree, but - Ingo molnar noticed a 4 % speed-up with lmbench - IMHO this means that we should try hard to use the optimization. - it's a CPU semaphore, ie a bad PCI card cannot cause any problems. - both CPU's are very similar [Intel says that both should have the same stepping, and the list of supported combinations with different steppings is short]
-- Manfred
- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.rutgers.edu Please read the FAQ at http://www.tux.org/lkml/
| |