lkml.org 
[lkml]   [2015]   [Sep]   [8]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
From
SubjectRE: [PATCH] sched: fix lose fair sleeper bonus in switch_to_fair()
Date


> -----Original Message-----
> From: Wanpeng Li [mailto:wanpeng.li@hotmail.com]
> Sent: Tuesday, September 08, 2015 5:46 PM
> To: Byungchul Park
> Cc: Peter Zijlstra; Ingo Molnar; linux-kernel@vger.kernel.org;
> yuyang.du@intel.com
> Subject: Re: [PATCH] sched: fix lose fair sleeper bonus in
switch_to_fair()
>
> On 9/8/15 4:38 PM, Wanpeng Li wrote:
> > On 9/8/15 4:22 PM, Byungchul Park wrote:
> >> On Tue, Sep 08, 2015 at 04:04:49PM +0800, Wanpeng Li wrote:
> >>>>> However, if se->vruntime -= cfs_rq->min_vruntime is positive, the
> >>>>> behavior is different after your patch. e.g. se->vruntime(the
> >>>>> relative vruntime in switched_to_fair()) < min_vruntime -
> >>>>> sysctl_sched_latency/2
> >>>>>
> >>>>> before your patch:
> >>>>>
> >>>>> se->vruntime = min_vruntime - sysctl_sched_latency/2
(place_entity())
> >>>> my patch is based on ff277d4 commit at tip/sched/core.
> >>>>
> >>>> there's no change between before and after.
> >>>>
> >>>> check it please.
> >>>>
> >>>> and this logic seems to be no problem to me. :(
> >>> Your logic will lose fair sleeper bonus in the scenario which I
> >>> pointed out.
> >> i mean in ff277d4 commit:
> >
> > Please include the commit subject when you point out a commit, do you
> > mean this one?
> >
> > commit ff277d4250fe715b6666219b1a3423b863418794
> > Author: Andrea Parri <parri.andrea@gmail.com>
> > Date: Wed Aug 5 15:56:19 2015 +0200
> >
> > sched/deadline: Fix comment in enqueue_task_dl()
> >
> > The "dl_boosted" flag is set by comparing *absolute* deadlines
> > (c.f., rt_mutex_setprio()).
> >
> >
> > What's the relationship w/ this patch?
>
> I think you mean your commit:
>
> commit 7855a35ac07a350e2cd26f09568a6d8e372be358
> Author: Byungchul Park <byungchul.park@lge.com>
> Date: Mon Aug 10 18:02:55 2015 +0900
>
> sched: Ensure a task has a non-normalized vruntime when returning
> back to CFS
>
>
> However, that is wrong in the scenario which I mentioned.

Ah.. Ok. What you are pointing out against, is this commit.
I will focus on verifying if this commit is wrong or not from now.
Let me think about this commit more.

Thanks,
byungchul

>
> Regards,
> Wanpeng Li



\
 
 \ /
  Last update: 2015-09-08 11:21    [W:0.054 / U:0.424 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site