lkml.org 
[lkml]   [2014]   [Aug]   [24]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
SubjectRe: [GIT PULL] nohz: Fix double clock write on idle ticks

* Frederic Weisbecker <fweisbec@gmail.com> wrote:

> Le dimanche 24 août 2014, Ingo Molnar <mingo@kernel.org> a écrit :
>
> > * Frederic Weisbecker <fweisbec@gmail.com <javascript:;>> wrote:
> >
> > > From: Frederic Weisbecker <fweisbec@gmail.com <javascript:;>>
> > >
> > > Ingo,
> > >
> > > Please pull the nohz/drop-double-write-v3 branch that can be found at:
> > >
> > > git://
> > git.kernel.org/pub/scm/linux/kernel/git/frederic/linux-dynticks.git
> > > nohz/drop-double-write-v3
> > >
> > > Although the 1st patch fixes a bug, it was a longstanding issue so
> > > that branch doesn't need to be applied in 3.17. The next merge window
> > > looks better.
> > >
> > > --
> > > The tick reschedules itself unconditionally. It's relevant in periodic
> > > mode but not in dynticks mode where it results in spurious double clock
> > > writes and even spurious periodic behaviour for low-res case.
> > >
> > > This set fixes that:
> > >
> > > * 1st patch removes low-res periodic tick rescheduling in nohz mode.
> > > This fixes spurious periodic behaviour.
> > >
> > > * 2nd patch does the same for high-res mode. Here there is no such
> > > spurious periodic behaviour but it still spares a double clock write
> > > in some cases.
> > > ---
> > >
> > >
> > > Thanks,
> > > Frederic
> > > ---
> > >
> > > Viresh Kumar (2):
> > > nohz: Fix spurious periodic tick behaviour in low-res dynticks mode
> > > nohz: Avoid tick's double reprogramming in highres mode
> > >
> > >
> > > kernel/time/tick-sched.c | 8 ++++++++
> > > 1 file changed, 8 insertions(+)
> >
> > > These fixes are pretty small - any objections
>
> > against putting it into
> > > timers/urgent and including it in v3.17?
>
>
> OK sounds good to me. They are easily reverted if any problem arises.

On a second thought, 'spurious periodic behavior' is really just
sub-optimal full-nohz behavior - it's not an outright
user-noticeable bug, correct?

Thanks,

Ingo
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/

\
 
 \ /
  Last update: 2014-08-24 17:01    [W:0.044 / U:0.372 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site