Messages in this thread | | | Date | Mon, 29 Oct 2007 15:45:10 -0700 | From | Jeremy Fitzhardinge <> | Subject | Re: [PATCH] raise tsc clocksource rating |
| |
Zachary Amsden wrote: > On Mon, 2007-10-29 at 20:10 -0300, Glauber de Oliveira Costa wrote: > >> From: Glauber de Oliveira Costa <glauber@t60.localdomain> >> >> tsc is very good time source (when it does not have drifts, does not >> change it's frequency, i.e. when it works), so it should have its rating >> raised to a value greater than, or equal 400. >> >> Since it's being a tendency among paravirt clocksources to use values >> around 400, we should declare tsc as even better: So we use 500. >> > > Why is the TSC better than a paravirt clocksource? In our case this is > definitely inaccurate. Paravirt clocksources should be preferred to > TSC, and both must be made available in hardware for platforms which do > not support paravirt. > > Also, please cc all the paravirt developers on things related to > paravirt, especially things with such broad effect. I think 400 is a > good value for a perfect native clocksource. >400 should be reserved > for super-real (i.e. paravirt) sources that should always be chosen over > a hardware realistic implementation in a virtual environment. >
Yes, agreed. The tsc is never the right thing to use if there's a paravirt clocksource available.
What's wrong with rating it 300? What inferior clocksource does it lose out to? Shouldn't that clocksource be lowered? (Why don't we just use 1 to 10?)
J - 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/
| |