On Tue, 14 Nov 2017, Linus Torvalds wrote:
> On Tue, Nov 14, 2017 at 3:53 PM, Thomas Gleixner <[email protected]> wrote:
> > Current head + Raphaels patch:
> >
> > real 0m0.029s
> > user 0m0.000s
> > sys 0m0.010s
> >
> > So that patch is actually slower.
>
> Oh it definitely is expected to be slower, because it does the IPI to
> all the cores and actually gets their frequency right.
>
> It was the old one that we had to revert (because it did so
> sequentially) that was really bad, and took something like 2+ seconds
> on Ingo's 160-core thing, iirc.
>
Tired brain did not connect it to the revert.
On that machine with ea0ee3398877: Revert "x86: CPU: Fix up "cpu MHz" in
/proc/cpuinfo" reverted it takes:
real 0m4.497s
user 0m0.012s
sys 0m0.000s
> It sounds like the current patch is slower, but likely acceptable
> considering that you get the right results now ..
Correct and the factor 10, i.e. 30ms vs. 3ms is not horrible, while the 4.5
seconds are.
Thanks,
tglx
