Detlef.Drewanz wrote:

> Rafael,
> can you help me getting this test version.
> @Aubrey: I though powertop is just a "monitoring" tool. So you mean
> that with this new version we might better see the different speed
> changes ? 

PowerTOP in 111b has a bug so that the frequency residency report is not
accurate, the new version can fix this bug and give us the right report.

Thanks,
-Aubrey

> 
> Thanks
> -Detlef
> 
> Li, Aubrey schrieb, On 22.05.09 02:45:
>> Hi Detlef,
>> 
>> Detlef Drewanz wrote:
>> 
>>> Eric,
>>> thanks for this workaround. Yes this works and it works also after
>>> suspend/resume. So I see now in powertop the frequency changing
>>> between 800 and 2001 Mhz in event mode.
>>> 
>>> Thanks.
>>> ... and if 111b will be the final build for osol2009.06 this
>>> workaround could be part of the release notes ...
>> 
>> We have a new version of powertop to fix frequency residency bug.
>> Rafael can help you to get a copy. I just want to see the percent of
>> each frequency residency and make sure the highest frequency
>> residency is not too high with the change when idle.
>> 
>> Thanks,
>> -Aubrey
>> 
>>> Detlef
>>> 
>>> Eric Saxe schrieb, On 21.05.09 20:17:
>>>> Hi Detlef, Mark,
>>>> 
>>>> Mark Haywood wrote:
>>>>> Detlef Drewanz wrote:
>>>>> Why? Given what I have seen I don't believe that this worked
>>>>> correctly in 2008.11 either. 
>>>>> 
>>>>>> Maybe there is some quick workaround to set with mdb some
>>> value ... ?
>>>> Try adding this to /etc/system:
>>>> set cpupm_ti_gov_multiple=100
>>>> 
>>>> ..and then run in event mode. This will make the system more
>>>> aggressive about power managing the CPUs despite ambient background
>>>> activity. I have a fix going back shortly (today?) to address
>>>> this. Does this help? 
>>>> 
>>>> Thanks,
>>>> -Eric


Reply via email to