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

[Mike Galbraith]

On Mon, 2010-12-20 at 12:39 +0200, Avi Kivity wrote:
> On 12/20/2010 12:33 PM, Mike Galbraith wrote:
> > >
> > >  Correct.  I don't want the other task to run before me, I just don't
> > >  want to run before it.
> >
> > OK, so what I gather is that if you can preempt another of your own
> > threads to get the target to cpu, that would be a good thing whether
> > he's on the same cpu as yield_to() caller or not.  If the target is
> > sharing a cpu with you, that's even better.  Correct?
> 
> Correct.  I'm not interested in scheduling wrt other tasks, just my tasks.
> 
> 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.

> > 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.

	-Mike


--
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/