Riccardo Vestrini | 22 Jul 11:28 2004
Picon

is it really better speedstep-ich vs. p4-clockmod cpufreq driver?

it seems that speedstep-ich and acpi cpufreq driver have only two usable 
clock frequencies, while p4-clockmod has eight
my cpu is: Intel Mobile Intel(R) Pentium(R) 4   CPU 3.06GHz stepping 09

last 2.6 kernel I tried (2.6.7) has introduced a warning while loading 
p4-clockmod module:

p4-clockmod: P4/Xeon(TM) CPU On-Demand Clock Modulation available
p4-clockmod: Warning: Pentium 4-M detected. The speedstep-ich or acpi 
cpufreq modules offer voltage scaling in addition of frequency scaling. 
You should use either one instead of p4-clockmod, if possible.

so I immediatly switched to speedstep-ich discovering that:
$ cat /sys/devices/system/cpu/cpu0/cpufreq/scaling_available_frequencies
3066590 1599960

while with p4-clockmod I have:
$ cat /sys/devices/system/cpu/cpu0/cpufreq/scaling_available_frequencies
383323 766647 1149971 1533295 1916618 2299942 2683266 3066590

using acpi driver gives a message:
cpufreq: CPU0 - ACPI performance management activated.
cpufreq:  P0: 3059 MHz, 24000 mW, 100 uS
cpufreq: *P1: 1596 MHz, 12000 mW, 100 uS
but:
$ cat /sys/devices/system/cpu/cpu0/cpufreq/scaling_available_frequencies
3059000 1596000

so, what driver is supposed to be better? and why speedstep-ich driver 
has only two frequencies?
(Continue reading)

Jim Carter | 22 Jul 18:20 2004

Re: is it really better speedstep-ich vs. p4-clockmod cpufreq driver?

On Thu, 22 Jul 2004, Riccardo Vestrini wrote:

> it seems that speedstep-ich and acpi cpufreq driver have only two usable clock
> frequencies, while p4-clockmod has eight
> my cpu is: Intel Mobile Intel(R) Pentium(R) 4   CPU 3.06GHz stepping 09

> p4-clockmod: P4/Xeon(TM) CPU On-Demand Clock Modulation available
> p4-clockmod: Warning: Pentium 4-M detected. The speedstep-ich or acpi cpufreq
> modules offer voltage scaling in addition of frequency scaling. You should use
> either one instead of p4-clockmod, if possible.
> 
> so, what driver is supposed to be better? and why speedstep-ich driver has
> only two frequencies?

The CPU on my laptop is a Pentium III-M (Coppermine) and so only 
speedstep-ich is useful for me.  However, I can shed some light on this 
issue.  My CPU frequencies are 733 MHz and 1000 MHz, but at the lower speed 
the CPU also runs at 3.3 volts, vs. 5 volts at high speed.  This means that 
the power consumption is about half at low speed (it's approximately speed 
times voltage), which is important for me when operating in the field on 
battery power.  Also, when running high speed I need to put a pillow on my 
lap and the machine on the pillow, because the bottom gets so hot.  (Yes, I 
make very sure that the pillow doesn't block the air ducts, and the fan 
does a good job of keeping the insides cool.  The CPU and graphics chip 
have a big heat-pipe running into the air duct.)

Definitely the voltage modulation is important to have.

Also as for strategies, if you have dynamic speed modulation, generally if
the CPU is busy less than 73% of the time, then my machine should be run at
(Continue reading)

Riccardo Vestrini | 23 Jul 01:10 2004
Picon

Re: is it really better speedstep-ich vs. p4-clockmod cpufreq driver?

Jim Carter wrote:
> On Thu, 22 Jul 2004, Riccardo Vestrini wrote:
  >>it seems that speedstep-ich and acpi cpufreq driver have only two 
usable clock
>>frequencies, while p4-clockmod has eight
>>my cpu is: Intel Mobile Intel(R) Pentium(R) 4   CPU 3.06GHz stepping 09
> 
> 
> Definitely the voltage modulation is important to have.
you right, but I do not know if it is better to have a 0.3 GHz clock 
most of the time, or a 1.5 GHz with half voltage
> 
> Also as for strategies, if you have dynamic speed modulation, generally if
> the CPU is busy less than 73% of the time, then my machine should be run at
> the lowest speed, whereas if tasks are waiting to run then it should be put
> in the highest speed.  In a typical workload it's very rare for the needed
> throughput to be steadily between 73% and 100% so the intermediate speeds
> could be useful; this is true even if the available speed range is greater.  
> Actually, hardly anyone uses the full capacity of their CPU, and I don't
> even bother to run the dynamic modulation daemon, just leaving it at low
> speed all the time.  I switch manually if I have a big simulation to do.
> 
it is the same for me, cpu is almost always set to the lowest frequency, 
  but I often compile programs, so I need the full power

  I consider strange the fact that a more specific driver 
(speedstep-ich) is not able to put my laptop to half voltage + mininum 
clock (which is 0.3 GHz) while p4-clockmod is only able to adjust clock 
and not voltage;
probably these capabilities can be merged some way ...
(Continue reading)

Max T. Woodbury | 23 Jul 16:56 2004
Picon
Picon

Thinkpad 760ED configuration problems

I have a Thinkpad 760 ED. (Model 9546-U3A, BIOS HZET72WW 08/07/99)

There is fairly strong evidence that the BIOS on this machine is not
setting up the PCI configuration registers to the standard Linux 
expects.  For example, a temporary patch suggested by Bartlomiej 
Zolnierkiewicz on the linux-ide list ended up crashing the 2.6.7 
kernel during init and there are messages about unassigned IRQs and
DMA addresses in the log.

I suspect that the correct way to fix this problem is to have a
routine redo the PCI configuration fairly early in the kernel setup 
sequence, but I'm not sure exactly where/when to put it.  It should be 
done after the CPU and memory are setup, but before PCI setup ends.  
I suspect that it should be done at the beginning of the PCI setup 
process.  There is a whole bunch of stuff in 'quirks' that seems to be
similar but I've only skimmed that code so far.  Does this belong there?
If so, which list has people who fiddle with PCI on it?

I'm also not sure how to detect when this correction is needed. I
suspect that the revision number of some BIOS component would be
key to determining if this should be done, but I have no idea
how to get that information.  It is probably covered by some
standard specification, but I've been looking for a couple weeks
and I don't think I've found the correct specification yet. (I
did find a new load of specifications yesterday and haven't finished
reading them, thus the 'think'.)  Suggestions on where this might
be documented would be appreciated.

Finally, the actual configuration information is stored someplace.
I suspect that it is in the cmos memory.  The kernel-module-thinkpad
(Continue reading)


Gmane