Re: [RFC GIT PULL] nohz: Basic cputime accounting for adaptivetickless

[Ingo Molnar]

* Frederic Weisbecker <fweisbec@xxxxxxxxx> wrote:

> On Thu, Jun 14, 2012 at 11:07:09AM +0200, Peter Zijlstra wrote:
> > On Wed, 2012-06-13 at 18:19 +0200, Frederic Weisbecker wrote:
> > > Ingo, Thomas,
> > > 
> > > This starts the basic code that allow accounting of cputime spent tickless
> > > outside idle, which is a first step to prepare for the adaptive nohz
> > > infrastructure.
> > > 
> > > I hope we can set a tree in -tip for that. If you're fine with it
> > > this is pullable from:
> > 
> > There's a number of architecture that already does fine grained
> > user/kernel time accounting on syscall boundaries etc.. s390, powerpc
> > and ia64.
> > 
> > You're now adding a 3rd way of accounting user/kernel time.. I'm not
> > much looking fwd to that..
> 
> You're right, I should have looked into CONFIG_VIRT_CPU_ACCOUNTING sooner
> and see if I can reuse it.
> 
> I'll try something with that.

Maybe sanitize all the variants under a single set of 
wrappers/callbacks?

Thanks,

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