Re: [PATCH] process cputimer is moving faster than its corresponding clock

[Olivier Langlois <olivier@trillion01.com>]

On Fri, 2013-04-19 at 11:08 -0700, KOSAKI Motohiro wrote:
> On Fri, Apr 19, 2013 at 10:38 AM, KOSAKI Motohiro
> <kosaki.motohiro@gmail.com> wrote:
> >> I feel we are hitting the same issue than this patch:
> >> https://lkml.org/lkml/2013/4/5/116
> >>
> >> I'm adding Kosaki in Cc, who proposed roughly the same fix.
> >
> > Thanks to CCing. I'm now sitting LSF and I can't read whole tons emails.
> > However the fix is definitely same and I definitely agree this approach.
> >
> > thank you.
> 
> And if I understand correctly, update_gt_cputime() is no longer
> necessary after this patch because time never makes backward.
> 
> What do you think?

Kosaki, I would tend to say that what you propose is exact. After having
added the task deltas I was puzzled to see the cputimer still moving
faster than the process clock. I was seeing it with the the help of
printk statement inside update_gt_cputime().

After nailing down the last remaining cause of that inside sched/core.c,
I have never seen after the cputimer being in advance.