[Devel] Re: [RFC] [PATCH 0/3] Add group fairness to CFS

[William Lee Irwin III]

* William Lee Irwin III <wli at holomorphy.com> wrote:
>> [...] sched_yield() semantics are yet another twist.

On Wed, May 23, 2007 at 08:40:35PM +0200, Ingo Molnar wrote:
> that's nonsense, sched_yield() semantics are totally uninteresting. It 
> is a fundamentally broken interface.

They're not totally uninteresting. People will complain when apps
break or perform poorly due to changes in its semantics. As an
interface it may be poor and worse yet poorly specified, but it has
non-negligible effects on performance issues that can't be ignored
and that will remain the case for the foreseeable future.

The content of my comment was that the patch does something to
sched_yield() semantics, so it raises the question of what will happen
in benchmarks and other performance affairs that are sensitive to
sched_yield() semantics changes.


-- wli
_______________________________________________
Containers mailing list
Containers at lists.linux-foundation.org
https://lists.linux-foundation.org/mailman/listinfo/containers