Re: [resend] Timer broadcast question

From: Thomas Gleixner <tglx@linutronix.de>
To: Andy Lutomirski <luto@amacapital.net>
Cc: Daniel Lezcano <daniel.lezcano@linaro.org>,
	John Stultz <john.stultz@linaro.org>,
	Frederic Weisbecker <fweisbec@gmail.com>,
	Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
	"linaro-dev >> Lists Linaro-dev" <linaro-dev@lists.linaro.org>
Subject: Re: [resend] Timer broadcast question
Date: Wed, 20 Feb 2013 11:09:03 +0100 (CET)	[thread overview]
Message-ID: <alpine.LFD.2.02.1302201106590.22263@ionos> (raw)
In-Reply-To: <512400B2.9010801@mit.edu>

On Tue, 19 Feb 2013, Andy Lutomirski wrote:
> On 02/19/2013 10:21 AM, Daniel Lezcano wrote:
> > On 02/19/2013 07:10 PM, Thomas Gleixner wrote:
> >> On Tue, 19 Feb 2013, Daniel Lezcano wrote:
> >>> I am working on identifying the different wakeup sources from the
> >>> interrupts and I have a question regarding the timer broadcast.
> >>>
> >>> The broadcast timer is setup to the next event and that will wake up any
> >>> idle cpu belonging to the "broadcast cpumask", right ?
> >>>
> >>> The cpu which has been woken up will look for each cpu the next-event
> >>> and send an IPI to wake it up.
> >>>  
> >>> Although, it is possible the sender of this IPI may not be concerned by
> >>> the timer expiration and has been woken up just for sending the IPI, right ?
> >>
> >> Correct.
> >>  
> >>> If this is correct, is it possible to setup the timer irq affinity to a
> >>> cpu which will be concerned by the timer expiration ? so we prevent an
> >>> unnecessary wake up for a cpu.
> >>
> >> It is possible, but we never implemented it.
> >>
> >> If we go there, we want to make that conditional on a property flag,
> >> because some interrupt controllers especially on x86 only allow to
> >> move the affinity from interrupt context, which is pointless.
> > 
> > Thanks Thomas for your quick answer. I will write a RFC patchset.
> 
> I'm curious what the use case is.  I played with this code awhile ago,
> and AFAICT it's not used on sensible (i.e. modern) systems.  Is there
> anything other than old x86 machines that needs it?

If the local apic timer is not affected by C-States, it's irrelevant,
but there are enough machines out there which do not have that. The
point is that we want a flag on the broadcast device which tells us
whether we should use dynamic affinity settings or not. On x86 we
would not set that flag ever.

Thanks,

	tglx