Re: [RFC PATCH 1/2] sched: Clean up SD_BALANCE_WAKE flags in sched domain build-up

From: Yuyang Du
Date: Wed Jun 01 2016 - 23:32:43 EST


On Wed, Jun 01, 2016 at 11:24:45AM +0200, Vincent Guittot wrote:
> >
> > So with the patch, we will have a little bit semantic change, SD_BALANCE_WAKE
> > implies SD_WAKE_AFFINE if allowed, and will favor "fast path" if possible. I don't
> > think we should do anything otherwise.
>
> Why should we not do anything else ?
>
> The current default configuration is to only use the wake_affine path.
> With your changes, the default configuration will try to use wake
> affine and will fall back to long load balance sequence if wake affine
> doesn't find a sched_domain
>
> That's a major changes in the behavior

Well, I won't argue that this hasn't changed, but I'd argue that this change
isn't a bad change: (a) it restores the flags to their meanings and makes them
more "elegant", (b) we definitely need further work to improve
select_task_rq_fair(), there has already been a comment marked XXX, right? :)