Re: cpufreq & enhanced speedstep

Am Dienstag, 15. Mai 2007 schrieb Rui Paulo:
At Tue, 15 May 2007 12:47:18 +0200,

Harald Schmalzbauer wrote:
Am Dienstag, 15. Mai 2007 schrieb Rui Paulo:
At Mon, 14 May 2007 23:48:07 +0200,

Harald Schmalzbauer wrote:

[...]

I have a E6600 core2 and tried to reduce power dissipation by
enabling some speedstep technology.
acpi_perf seems to work since dev.cpu.freq shows 800 (possible
2400/1600/800) and goes up while compiling, but I frequently get the
following errors:

kernel: acpi_perf0: Px transition to 1600 failed
kernel: acpi_perf0: set freq failed, err 6

I don't really know why it fails..

With acpi_throttle and p4tcc disabled, like you advised, this
message doesn't occur any more.
But I only have two possible speed steps, 2400 and 1600. But it's
switching smoothly between them, atm. I don't have a power meter handy,
so I can't see if it really works (and saves power).

I have a driver to gather the temperature reading of the CPU.
If the temperature drops when you've enabled powerd, then it's most
likely working.
(Check my message "MacBook patches" if you wanna try it out)

I did (I had to copy src/backlight and src/msrtemp to src/sys/dev/ and
src/sys/modules/).
Here is what I get when I load the module:
msrtemp0: <CPU On-Die Thermal Sensors> on cpu0
est1: <Enhanced SpeedStep Frequency Control> on cpu1
est: CPU supports Enhanced Speedstep, but is not recognized.
est: cpu_vendor GenuineIntel, msr 928092806000928
device_attach: est1 attach returned 6
msrtemp1: <CPU On-Die Thermal Sensors> on cpu1

But these values are too high, my BIOS tells me ~50°C:
dev.cpu.0.temperature: 68
dev.cpu.1.temperature: 69

Also my bios shows temperatures for ather chips, namely ich, gmch, and system.
I haven't tried mbmon or consolehm or healthd but I guess they won't give any
results via smbus with that new monitoring devices.

Is there anything I can do to correct the ACPI table for the right power
values of my CPU?

Thanks a lot,

-Harry


But in any case, the Watt values (dev.cpu.0.freq_levels: 2400/88000
1600/56000) are wrong for my core2 CPU.
Where does acpi_perf get them from? Ok, form est (since without
cpufreq loaded
the values are /-1) but are they readable from any registers or are
they hard
coded according to the CPU type or are they in any table in the (acpi)
BIOS?

It gets the values from ACPI methods.

--
Rui Paulo



--
OmniSEC - UNIX und Windows Netzwerke - Sicher
Harald Schmalzbauer
Flintsbacher Str. 3
80686 München
+49 (0) 89 18947781
+49 (0) 160 93860101
USt-IdNr.: DE253184753
_______________________________________________
freebsd-current@xxxxxxxxxxx mailing list
http://lists.freebsd.org/mailman/listinfo/freebsd-current
To unsubscribe, send any mail to "freebsd-current-unsubscribe@xxxxxxxxxxx"

Relevant Pages

  • Re: cpufreq & enhanced speedstep
    ... Harald Schmalzbauer wrote: ... Mai 2007 schrieb Rui Paulo: ... I have a driver to gather the temperature reading of the CPU. ... It gets the values from ACPI methods. ...
    (freebsd-current)
  • Re: cpufreq broken on core2duo
    ... and Intel Enhanced SpeedStep in bios on a 3.00GHZ p4 CPU I see: ... cpu0: <ACPI CPU> on acpi0 ... have to enable SpeedStep in your BIOS to achieve throttling CPU clock ...
    (freebsd-stable)
  • Re: HP PAVILION 5000
    ... laptops as Linux uses the CPU's HLT instructions to pause the CPU ... All SpeedStep does is work around the problem of an OS that uses an idle ... Windows, but I can squeeze about 2:35 out of it on Linux. ...
    (microsoft.public.windowsxp.general)
  • Re: cpufreq broken on core2duo
    ... and Intel Enhanced SpeedStep in bios on a 3.00GHZ p4 CPU I see: ... cpu0: <ACPI CPU> on acpi0 ... have to enable SpeedStep in your BIOS to achieve throttling CPU clock ...
    (freebsd-stable)
  • Re: HP PAVILION 5000
    ... laptops as Linux uses the CPU's HLT instructions to pause the CPU ... All SpeedStep does is work around the problem of an OS that uses an idle ...
    (microsoft.public.windowsxp.general)