Messages in this thread | | | Subject | Re: [RFC][PATCH 0/5] Signal scalability series | From | Matt Fleming <> | Date | Mon, 03 Oct 2011 16:43:33 +0100 |
| |
On Mon, 2011-10-03 at 08:28 -0700, Linus Torvalds wrote: > On Sat, Oct 1, 2011 at 2:35 AM, Matt Fleming <matt@console-pimps.org> wrote: > > > > You and me both. Unfortunately, the ia64 guys had a different opinion, > > http://www.spinics.net/lists/linux-ia64/msg08363.html > > Well, considering that it apparently slows down the single-threaded > case by 50% on an architecture that actually *matters*, I think the > whole discussion is somewhat academic, don't you? > > "Scalability" is pretty much never a valid excuse for "slows down the > common case".
Where did you get the 50% slow down figure from?
Oh, are you referring to Oleg's email about the slow down under kvm? Yeah, admittedly that's a pretty clear indicator that something is wrong with the approach in this patch series.
I thought I'd replied to that email but I guess not.
-- Matt Fleming, Intel Open Source Technology Center
| |