Re: [RFC -v2 PATCH 2/3] sched: add yield_to function

[Mike Galbraith]

On Mon, 2010-12-20 at 12:49 +0200, Avi Kivity wrote:
> On 12/20/2010 12:46 PM, Mike Galbraith wrote:
> > >
> > >  However, if I'm all alone on my cpu, and the other task is runnable but
> > >  not running, behind some unrelated task, then I do need that task to be
> > >  preempted (or to move tasks around).
> >
> > So in that case, a pull may be advantageous.
> 
> Yes.
> 
> > >  >  Would a kick/hint option be useful?
> > >
> > >  Depends on what it does...
> >
> > Let you decide whether you only want to drop a hint and leave it at
> > that, or also attempt a preemption.
> 
> Who is "you" in this?  the scheduler?

The caller.

> I'm fine with hints so long as they are usually acted upon (if it isn't, 
> I'll go back to the guest, spin a bit more, and retry).



--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/