![]() | |||||||||||||
Messages in this thread |
Jesse Barnes wrote: > On Wednesday, September 8, 2004 9:31 pm, George Anzinger wrote: > >>a.) resolution. If you don't put a limit on this you will invite timer >>storms. Currently, by useing 1/HZ resolution, all timer "line up" on ticks >>and reduce the interrupt overhead that would occure if we actually tried to >>give "exactly" what was asked for. This is a matter of math and can be >>handled (assuming we resist the urge to go shopping :))> > > This can be bad though if lots of CPUs hit it at the same time or nearly so if > they're all trying to write the same cacheline or two. I think that most of the SMP issues your talking about have gone away with 2.6 where we have seperate timer lists for each cpu. -- George Anzinger george@mvista.com High-res-timers: http://sourceforge.net/projects/high-res-timers/ Preemption patch: http://www.kernel.org/pub/linux/kernel/people/rml - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/ | ||||||||||||
| Last update: 2005-03-22 14:06 [from the cache] ©2003-2008 | |||||||||||||