1 |
On Wed, Dec 29, 2010 at 11:13 AM, Bill Longman <bill.longman@×××××.com> wrote: |
2 |
> A strangeness I have noted is that /proc/cpuinfo has this for its power |
3 |
> capabilities: |
4 |
> power management: |
5 |
> Nothing. |
6 |
|
7 |
FWIW I have Core i7 920, and it also has nothing in the power |
8 |
management in cpuinfo, but CPU frequency scaling does work and speeds |
9 |
change (using ondemand governor, in a desktop machine). |
10 |
|
11 |
$ cat /sys/devices/system/cpu/cpu0/cpufreq/scaling_* |
12 |
2661000 2660000 2527000 2394000 2261000 2128000 1995000 1862000 1729000 1596000 |
13 |
conservative userspace powersave ondemand performance |
14 |
1596000 |
15 |
acpi-cpufreq |
16 |
ondemand |
17 |
2661000 |
18 |
1596000 |
19 |
<unsupported> |
20 |
|
21 |
So it seems similar to yours except that your max_freq and min_freq |
22 |
are the same! Which matches what you say about it never going faster |
23 |
than the minimum speed. |
24 |
|
25 |
In kernel docs Documentation/cpu-freq/cpu-drivers.txt there is some |
26 |
information about how the min and max speed are set by the policy that |
27 |
is in use (by whatever driver is controlling the scaling). So I don't |
28 |
know if there is a userspace program (like KDE laptop stuff) that |
29 |
might be overriding with its own faulty settings? |
30 |
|
31 |
Seems like your kernel settings are probably okay since you can see |
32 |
all of that so far. If you run powertop can it see all of the C-states |
33 |
and P-states without any problems? |