Messages in this thread | | | Date | Sat, 15 Nov 2008 10:04:04 -0800 | From | Arjan van de Ven <> | Subject | Re: Bootup time regression from 2.6.27 to 2.6.28-rc3+ |
| |
On Sat, 15 Nov 2008 18:16:31 +0100 Frans Pop <elendil@planet.nl> wrote:
> On Friday 14 November 2008, Frans Pop wrote: > > > Find below the lineup of the timers-fixes-for-linus branch of the > > > tip tree (the same as Arjan posted minus the irq fixes) > > > > Could either of you maybe give a status update on this patch set and > > the remaining issues with it that were reported (especially the > > high C0 reported by powertop)? > > I guess part of the answer is: > commit ae99286b4f1be7788f2d6947c66a91dbd6351eec > Author: Thomas Gleixner <tglx@linutronix.de> > Date: Mon Nov 10 13:20:23 2008 +0100 > nohz: disable tick_nohz_kick_tick() for now > > I've just done some testing using v2.6.28-rc4-322-g58e20d8 which > includes this patch. > > CPU usage reported by powertop is now normal again (close to 100% in > lowest C state), but I'm still getting high counts for: > - <kernel IPI> : Rescheduling interrupts > Typically 3-5 on .26/.27; 15-17 on .28.
these are caused by the scheduler, not by the timer code. (And sometimes they're caused by the scheduler on behalf of something else even)
> - <interrupt> : extra timer interrupt > Consistently more prominent for .28 (though not with high values)
if it's less than 5 total, don't worry about it, some of that can well be rounding/measurement effects (powertop has to make a few approximations around the edges of the measurement interval because things don't always line up perfectly)
> than for .27, but way better than for .26. > > > powertop questions > ------------------ > - What's with this change from "polling" to "C0" for the 2nd C state?
that sounds like an interesting bug...
> After boot I always (both when booted on mains and on battery) get > "polling", but after inserting or removing mains it will continue to > show "C0" independent of any further power state changes. > - After switching to battery the first time I get something like: > C1 0.0ms (614891469122. > This is reproducible. I guess a rounding error due to the change in > the number of C states. Later updates clear this.
yeah it's annoying but it is only for one display period
> - Looks like someone could not make up his mind between comma and > slash here: "(long term: 26.2W,/1.6h)"
that sounds easy to fix ;-)
Thanks for the bugreports; either me or Auke will take a look at these shortly.
-- Arjan van de Ven Intel Open Source Technology Centre For development, discussion and tips for power savings, visit http://www.lesswatts.org
| |