| From: |
| Linus Torvalds <torvalds-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b-AT-public.gmane.org> |
| To: |
| Mathieu Desnoyers <mathieu.desnoyers-vg+e7yoeK/dWk0Htik3J/w-AT-public.gmane.org> |
| Subject: |
| Re: [RFC PATCH v8 1/9] Restartable sequences system call |
| Date: |
| Fri, 19 Aug 2016 13:23:57 -0700 |
| Message-ID: |
| <CA+55aFz+Q33m1+ju3ANaznBwYCcWo9D9WDr2=p0YLEF4gJF12g@mail.gmail.com> |
| Cc: |
| Peter Zijlstra <peterz-wEGCiKHe2LqWVfeAwA7xHQ-AT-public.gmane.org>, "Paul E. McKenney" <paulmck-23VcF4HTsmIX0ybBhKVfKdBPR1lH4CV8-AT-public.gmane.org>, Boqun Feng <boqun.feng-Re5JQEeQqe8AvxtiuMwx3w-AT-public.gmane.org>, Andy Lutomirski <luto-kltTT9wpgjJwATOyAt5JVQ-AT-public.gmane.org>, Dave Watson <davejwatson-b10kYP2dOMg-AT-public.gmane.org>, Linux Kernel Mailing List <linux-kernel-u79uwXL29TY76Z2rM5mHXA-AT-public.gmane.org>, Linux API <linux-api-u79uwXL29TY76Z2rM5mHXA-AT-public.gmane.org>, Paul Turner <pjt-hpIqsD4AKlfQT0dZR+AlfA-AT-public.gmane.org>, Andrew Morton <akpm-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b-AT-public.gmane.org>, Russell King <linux-lFZ/pmaqli7XmaaqVzeoHQ-AT-public.gmane.org>, Thomas Gleixner <tglx-hfZtesqFncYOwBW4kG4KsQ-AT-public.gmane.org>, Ingo Molnar <mingo-H+wXaHxf7aLQT0dZR+AlfA-AT-public.gmane.org>, "H. Peter Anvin" <hpa-YMNOUZJC4hwAvxtiuMwx3w-AT-public.gmane.org>, Andrew Hunter <ahh-hpIqsD4AKlfQT0dZR+AlfA-AT-public.gmane.org>, Andi Kleen <andi-Vw/NltI1exuRpAAqCnN02g-AT-public.gmane.org>, Chris Lameter <cl-vYTEC60ixJUAvxtiuMwx3w-AT-public.gmane.org>, Ben Maurer <bmaurer-b10kYP2dOMg-AT-public.gmane.org>, Steven Rostedt <rostedt-nx8X9YLhiw1AfugRpC6u6w-AT-public.gmane.org>, Josh Triplett <josh-iaAMLnmF4UmaiuxdJuQwMA-AT-public.gmane.org>, Catalin Marinas <catalin.marinas-5wv7dgnIgG8-AT-public.gmane.org>, |
On Fri, Aug 19, 2016 at 1:07 PM, Mathieu Desnoyers
<mathieu.desnoyers-vg+e7yoeK/dWk0Htik3J/w@public.gmane.org> wrote:
>
> Benchmarking various approaches for reading the current CPU number:
So I'd like to see the benchmarks of something that actually *does* something.
IOW, what's the bigger-picture "this is what it actually is useful
for, and how it speeds things up".
Nobody gets a cpu number just to get a cpu number - it's not a useful
thing to benchmark. What does getcpu() so much that we care?
We've had tons of clever features that nobody actually uses, because
they aren't really portable enough. I'd like to be convinced that this
is actually going to be used by real applications.
Linus
