Intel Pentium Dual Core E5200 and Enhanced Speedstep
glavoie at gmail.com
Tue Dec 9 06:52:30 PST 2008
2008/12/9 Ian Smith <smithi at nimnet.asn.au>
> [ skipping lots until you've seen how powerd goes on it .. and please
> drop gmail's HTML attachments on messages to the FreeBSD lists]
I found the option to disable HTML in the reply. Is it better now?
I enabled powerd and it seems to work for now.
> Ok. If updated est code isn't in 7.0p6 you maybe could apply a patch if
> you won't be upgrading to 7.1, assuming I'm right about recent new code.
I do plan to upgrade to 7.1 when it's out as it will probably include
the driver for my onboard network adapter.
> There may be some BIOS stuff about SpeedStep options too. Basically you
> should expect FreeBSD to ignore BIOS settings, except how they influence
> the ACPI implementation, but some BIOSes can contain surprises.
Yes, there are options about SpeedStep.
> I suspect 3-4W, even per core, would be at a much lower freq than 1GHz,
> probably nearer the minimum of ~125MHz.
The < 5W consumption isn't even at the lowest speed. The 45nm CPUs are
supposed to have an excellent power efficiency. Under Windows/Linux,
Enhanced Intel SpeedStep Technology (EIST) doesn't step down the
frequency at the lowest value possible. On my C2D (65nm), like I said,
it drops to 2 GHz from 2.66. It seems the idle power consumption of
those C2D is around 15W. With EIST on the 45nm Intel CPUs, the idle
power usage has been tested to be under 4W with a quad-core unit, and
this is not at the lowest possible frequency. The 1.25 GHz frequency I
see in the BIOS is probably related to the frequency step down EIST
automatically does as with my C2D, the BIOS always shows 2 GHz but
under Windows/Linux, when the CPU is working, the frequency comes back
to 2.66 GHz. I guess that the FreeBSD est driver needs to work with my
processor to enable this behaviour.
> No, if it were based on load while looking at the BIOS it'd show you the
> lowest speed for sure. This sounds like a selection more than a report?
No, it's a report.
> 2GHz is hardly idling .. maybe there's a BIOS option affecting that too,
> but it should only affect the starting freq, which powerd should ignore.
The 2 GHz is the stop down EIST does when the CPU is idling. I was
surprised to see this when I got my C2D last January. I was wondering
why the CPU was at 2 GHz when it was supposed to be running at 2.66
> Under powerd it should drop right back at idle. In fact there've been
> problems with some machines dropping back to 125, 100, even 75MHz under
> no or very light load, such that interactive responsiveness is shot and
> some processes needing fast interrupt response (bursts of wifi traffic,
> for one) have had issues, prompting some recent new work on algorithms
> for powerd on SMP systems.
I noticed that after I enabled powerd. At 313 MHz with my system the
responsiveness took a hit. I enabled powerd with those parameters and
it seems to step up the frequency quickly enough. Responsiveness
doesn't seems to be a problem with a polling time of 100ms.
powerd_flags="-i 90 -r 90 -p 100"
> See cpufreq(4) about all this, and especially you might want to set
> debug.cpufreq.lowest to some sensible minimum freq, say 3-500MHz?
> The acpi@ list is really a better place for this; not too many of the
> heavy hitters there seem to have much spare time to read questions@ and
> where I'm mostly just an interested bystander, trying to learn :)
I'll ask there if there are still problems after I check my BIOS
> cheers, Ian
glavoie at gmail.com
More information about the freebsd-questions