Messages in this thread | | | Date | Tue, 6 Jan 2009 21:16:34 -0600 | From | Jack Steiner <> | Subject | Re: [PATCH] configure HAVE_UNSTABLE_SCHED_CLOCK for SGI_SN systems |
| |
On Wed, Jan 07, 2009 at 04:00:30AM +0100, Nick Piggin wrote: > On Wed, Jan 07, 2009 at 12:16:03AM +0100, Peter Zijlstra wrote: > > > > > > But doesn't scheduler tick advance the rq->clock? Why do the others > > > need to fiddle with a remote runqueue's clock? When that cpu starts > > > taking ticks again, it will update it's rq->clock field and start the > > > processes. I guess I am a lot underinformed about the new scheduler > > > design. > > > > We try to do better than tick based time accounting these days. > > But if you contain the drift to within one tick, it shouldn't be much > problem to just truncate negative deltas I would have thought? The > time between events on different CPUs is pretty fuzzy at the ns level > anyway, I think ;)
Unfortunately, not possible on SGI IA64 systems. The cpus on different nodes (blades) are not required to be the same steppings or core frequencies. Core frequencies within the SSI can differ by hundreds of MHz (~25%).
(I don't recall if we support systems with mixed madison & montecito processors. If so, IIRC, the itc frequencies of these differ by 4X for the same core frequency).
--- jack
| |