Re: DIfferent BogoMIPS value after bbaa06702719 ("clocksource/drivers/arm_global_timer: Register delay timer")

[RafaÅ MiÅecki]

On 03/02/2017 03:13 PM, Russell King - ARM Linux wrote:
> On Thu, Mar 02, 2017 at 02:36:23PM +0100, RafaÅ MiÅecki wrote:
> > Hi,
> >
> > I just updated kernel on my SmartRG SR400ac (bcm4708-smartrg-sr400ac.dts) from
> > 4.4 to 4.9 and noticed that this part of the log:
> > [    0.020820] Calibrating delay loop... 1594.16 BogoMIPS (lpj=7970816)
> > (...)
> > [    0.190806] Brought up 2 CPUs
> > [    0.200022] SMP: Total of 2 processors activated (3188.32 BogoMIPS).
> >
> > became:
> > [    0.027082] Calibrating delay loop (skipped), value calculated using timer frequency.. 800.00 BogoMIPS (lpj=4000000)
> > (...)
> > [    0.078858] Brought up 2 CPUs
> > [    0.088254] SMP: Total of 2 processors activated (1600.00 BogoMIPS).
> >
> > This is caused by commit bbaa06702719 ("clocksource/drivers/arm_global_timer:
> > Register delay timer").
> >
> > Is this something expected?
>
> Yes.
>
> > Or should I be worried about this? I'm aware it's just BogoMIPS, but I
> > still prefer to ask :)
>
> It's *bogus*.  Bogomips is the calibration value that the kernel uses
> to achieve delays.  It has nothing to do with the speed of the CPU on
> modern systems that use a timer instead.  (In that case, it's a
> calibration value for the timer, rather than a calibration value for
> the number of software loops required to achieve a delay.)

Now I can sleep calm ;) thanks!