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@suse.cz>
Cc: kernel list <linux-kernel@vger.kernel.org>, Dan Hecht <dhecht@vmware.com>
In-Reply-To: <20080626221634.GE18719@elf.ucw.cz>
References: <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>
	 <1214503849.3351.35.camel@promb-2n-dhcp368.eng.vmware.com>
	 <20080626221634.GE18719@elf.ucw.cz>
Content-Type: text/plain
Organization: VMware INC.
Date: Thu, 26 Jun 2008 16:10:34 -0700
Message-Id: <1214521834.3351.54.camel@promb-2n-dhcp368.eng.vmware.com>
Mime-Version: 1.0
Content-Transfer-Encoding: 7bit
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 2185
Lines: 73

On Thu, 2008-06-26 at 15:16 -0700, Pavel Machek wrote:
> Hi!
> 
> > > > > 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
> 
> cpufreq effect, I believe.
> 
> > > 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.
> 
> Yes, but neither cpu_khz nor tsc_khz will be 3657 bogoMips, right?

Hi Pavel,

Thanks for the dmesg. The HZ value that you are using on this system is
250, right ?

If you note the calculations
> +     lpj = ((u64)tsc_khz * 1000);
> +     do_div(lpj, HZ);

We are dividing by HZ over here. So you are right in saying that tsc_khz
wont be equal to bogoMips but lpj_fine will surely be computed correct
since we do consider the HZ value.

Please let me know if you still have any doubts.
Or can i safely assume that you will ACK the patch ;-)

Thanks,
Alok


> 
> Anyway, here are my boot messages.
>                                                                 Pavel
> 


--
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/