[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20160601193524.GZ18670@intel.com>
Date: Thu, 2 Jun 2016 03:35:24 +0800
From: Yuyang Du <yuyang.du@...el.com>
To: Vincent Guittot <vincent.guittot@...aro.org>
Cc: Mike Galbraith <umgwanakikbuti@...il.com>,
Peter Zijlstra <peterz@...radead.org>,
Ingo Molnar <mingo@...nel.org>,
linux-kernel <linux-kernel@...r.kernel.org>,
Benjamin Segall <bsegall@...gle.com>,
Paul Turner <pjt@...gle.com>,
Morten Rasmussen <morten.rasmussen@....com>,
Dietmar Eggemann <dietmar.eggemann@....com>
Subject: Re: [RFC PATCH 1/2] sched: Clean up SD_BALANCE_WAKE flags in sched
domain build-up
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? :)
Powered by blists - more mailing lists