Subject: Re: [RFC PATCH] x86:Use cpu_khz for loops_per_jiffy calculation
From: Alok Kataria <akataria@vmware.com>
Reply-To: akataria@vmware.com
To: Pavel Machek <pavel@ucw.cz>
Cc: kernel list <linux-kernel@vger.kernel.org>
In-Reply-To: <20080626173536.GA16783@elf.ucw.cz>
References: <1212540069.19290.57.camel@promb-2n-dhcp368.eng.vmware.com>
	 <20080603182014.79a38d03@infradead.org>
	 <35f686220806032101h103152dat841818982aaa5052@mail.gmail.com>
	 <20080604061637.6bab3f67@infradead.org>
	 <1213924953.27983.52.camel@promb-2n-dhcp368.eng.vmware.com>
	 <20080620113922.GG7439@elte.hu>
	 <1213999593.31598.52.camel@promb-2n-dhcp368.eng.vmware.com>
	 <20080624175753.GG5642@ucw.cz>
	 <1214500831.3351.10.camel@promb-2n-dhcp368.eng.vmware.com>
	 <20080626173536.GA16783@elf.ucw.cz>
Content-Type: text/plain
Organization: VMware INC.
Date: Thu, 26 Jun 2008 11:10:49 -0700
Message-Id: <1214503849.3351.35.camel@promb-2n-dhcp368.eng.vmware.com>
Mime-Version: 1.0
Content-Transfer-Encoding: 7bit
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 2295
Lines: 63

On Thu, 2008-06-26 at 10:35 -0700, Pavel Machek wrote:
> On Thu 2008-06-26 10:20:31, Alok Kataria wrote:
> > On Tue, 2008-06-24 at 10:57 -0700, Pavel Machek wrote:
> > > Hi!
> > >
> > > > On X86 platform we can use the value of tsc_khz computed during tsc calibration
> > > > to calculate the loops_per_jiffy value. Its very important to keep the error in
> > > > lpj values to minimum as any error in that may result in kernel panic in
> > > > check_timer.
> > > > In virtualization environment, On a highly overloaded host the guest delay
> > > > calibration may sometimes result in errors beyond the ~50% that timer_irq_works
> > > > can handle, resulting in the guest panicking.
> > >
> > > How did you adress 'khz has nothing to do with loops per jiffie'
> > > comment?
> > >
> > > Some cpus can do loop in cycle , some need two cycles, some need half.
> >
> > Hi Pavel,
> >
> > When you say loops per jiffies has nothing to do with khz, by khz you
> > mean the cpu frequency, right ?
> 
> Yes.
> 
> > AFAIU in calibrate_delay_direct too we measure the amount by which timer
> > has ticked until DELAY_CALIBRATION_TICKS amount of jiffies has passed.
> > So IMO the code there too assumes that there is one loop per timer
> > cycle ?
> 
> On my machine, it reports:
> 
> delay using timer specific routine.. 3661.98 BogoMIPS (lpj=7323971)
> ...
> Detected 1828.828 MHz processor.
> 
> (/proc/cpuinfo)
> model name      : Genuine Intel(R) CPU           T2400  @ 1.83GHz
> ...
> cpu MHz         : 1000.000
How is it 1000 here ? shouldn't this be 1830.xx
> ...
> bogomips        : 3657.54
> 
> So you'd break it by setting lpj (aka bogomips) to cpu_khz, right?

We are not setting it to cpu_khz but to tsc_khz, i am assuming that in
this case tsc_khz will be different than cpu_khz. Can you please mail me
the full dmesg log.

Thanks,
Alok
> 
>                                                         Pavel
> --
> (english) http://www.livejournal.com/~pavelmachek
> (cesky, pictures) http://atrey.karlin.mff.cuni.cz/~pavel/picture/horses/blog.html

--
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/