From: Ian P. <Ian...@cl...> - 2007-10-30 00:58:36
|
> > Sigh, I don't really want to have this fight again. >=20 > i dont remember us having discussed this before, ever. If there's any > "fight" about monotonicity and SMP then it would be a pretty onesided > affair, with you being beaten up seriously ;-) Actually, it is possible, even for NUMA systems with CPUs running off completely different oscillators, and in the presence of CPU frequency changes, power management, and even in the presence of thermal throttling (though the latter introduces temporary inaccuracies it doesn't affect monotonicity or rate). Take a look at the Xen code to see how each physical CPU is independently calibrated on an ongoing basis, how movement of VCPUs between physical CPUs is tracked, and how shared variables are used to ensure montonicity if a guest requires it.=20 The fixed-rate TSCs on newer CPUs make some of this stuff easier, but you still need to cope with different source oscillators and some power management states. =20 Ian > > I don't really see what point there is in raising the tsc's rating > > (why is 300 insufficient again?), but regardless of the value, the Xen > > clocksource rating needs to be higher. >=20 > anyway, i agree that this patch cannot go in in its current form. >=20 > Ingo > - > To unsubscribe from this list: send the line "unsubscribe linux-kernel" > in > the body of a message to maj...@vg... > More majordomo info at http://vger.kernel.org/majordomo-info.html > Please read the FAQ at http://www.tux.org/lkml/ |