Re: My latest powernow-k8.c

Re: My latest powernow-k8.c

[Pavel Machek]

Hi!

> Attached are my latest .c and .h ... I am sending the whole files rather than patches, as a check that I did not miss a patch that you wanted. Mail here has been a little less reliable that one might wish for.
> 
> I added back in the cpu number in the dprintks to aid MP debugging. I fixed a PSB problem where the battery limits were getting lost. And, I tweaked the smp processor init stuff as discussed in emails.
> 
> I am still thinking about the FIXME where Dominik asked for more validity checking. So, that is still FIXME.

Huh, now this is strange:

root@amd:~# echo "0%88%88%powersave" > /proc/cpufreq
root@amd:~# cat /proc/cpufreq
          minimum CPU frequency  -  maximum CPU frequency  -  policy
CPU  0      1584000 kHz ( 88 %)  -    1600000 kHz ( 88 %)  - powersave
root@amd:~#

								Pavel
-- 
When do you have a heart between your knees?
[Johanka's followup: and *two* hearts?]

Re: My latest powernow-k8.c

[Bruno Ducrot]

On Fri, Mar 19, 2004 at 12:24:29PM +0100, Pavel Machek wrote:
> Hi!
> 
> > Attached are my latest .c and .h ... I am sending the whole files rather than patches, as a check that I did not miss a patch that you wanted. Mail here has been a little less reliable that one might wish for.
> > 
> > I added back in the cpu number in the dprintks to aid MP debugging. I fixed a PSB problem where the battery limits were getting lost. And, I tweaked the smp processor init stuff as discussed in emails.
> > 
> > I am still thinking about the FIXME where Dominik asked for more validity checking. So, that is still FIXME.
> 
> Huh, now this is strange:
> 
> root@amd:~# echo "0%88%88%powersave" > /proc/cpufreq
> root@amd:~# cat /proc/cpufreq
>           minimum CPU frequency  -  maximum CPU frequency  -  policy
> CPU  0      1584000 kHz ( 88 %)  -    1600000 kHz ( 88 %)  - powersave
> root@amd:~#
> 

2.4 or 2.6 ?

-- 
Bruno Ducrot

--  Which is worse:  ignorance or apathy?
--  Don't know.  Don't care.

Re: My latest powernow-k8.c

[Dominik Brodowski]

[-- Attachment #1.1: Type: text/plain, Size: 1067 bytes --]

On Fri, Mar 19, 2004 at 01:41:22PM +0100, Bruno Ducrot wrote:
> On Fri, Mar 19, 2004 at 12:24:29PM +0100, Pavel Machek wrote:
> > Hi!
> > 
> > > Attached are my latest .c and .h ... I am sending the whole files rather than patches, as a check that I did not miss a patch that you wanted. Mail here has been a little less reliable that one might wish for.
> > > 
> > > I added back in the cpu number in the dprintks to aid MP debugging. I fixed a PSB problem where the battery limits were getting lost. And, I tweaked the smp processor init stuff as discussed in emails.
> > > 
> > > I am still thinking about the FIXME where Dominik asked for more validity checking. So, that is still FIXME.
> > 
> > Huh, now this is strange:
> > 
> > root@amd:~# echo "0%88%88%powersave" > /proc/cpufreq
> > root@amd:~# cat /proc/cpufreq
> >           minimum CPU frequency  -  maximum CPU frequency  -  policy
> > CPU  0      1584000 kHz ( 88 %)  -    1600000 kHz ( 88 %)  - powersave
> > root@amd:~#

Why is this strange? Can you elaborate, please?

	Dominik

[-- Attachment #1.2: Type: application/pgp-signature, Size: 189 bytes --]

[-- Attachment #2: Type: text/plain, Size: 143 bytes --]

_______________________________________________
Cpufreq mailing list
Cpufreq@www.linux.org.uk
http://www.linux.org.uk/mailman/listinfo/cpufreq

Re: My latest powernow-k8.c

[Pavel Machek]

Hi!
> > > > Attached are my latest .c and .h ... I am sending the whole files rather than patches, as a check that I did not miss a patch that you wanted. Mail here has been a little less reliable that one might wish for.
> > > > 
> > > > I added back in the cpu number in the dprintks to aid MP debugging. I fixed a PSB problem where the battery limits were getting lost. And, I tweaked the smp processor init stuff as discussed in emails.
> > > > 
> > > > I am still thinking about the FIXME where Dominik asked for more validity checking. So, that is still FIXME.
> > > 
> > > Huh, now this is strange:
> > > 
> > > root@amd:~# echo "0%88%88%powersave" > /proc/cpufreq
> > > root@amd:~# cat /proc/cpufreq
> > >           minimum CPU frequency  -  maximum CPU frequency  -  policy
> > > CPU  0      1584000 kHz ( 88 %)  -    1600000 kHz ( 88 %)  - powersave
> > > root@amd:~#
> 
> Why is this strange? Can you elaborate, please?

CPU can not do 1.584MHz. Why did it round 88% down to 1.584GHz but
maximum frequency  1.6GHz? Kernel 2.6.
							Pavel

-- 
When do you have a heart between your knees?
[Johanka's followup: and *two* hearts?]

Re: My latest powernow-k8.c

[Dominik Brodowski]

[-- Attachment #1.1: Type: text/plain, Size: 1449 bytes --]

On Fri, Mar 19, 2004 at 02:56:05PM +0100, Pavel Machek wrote:
> Hi!
> > > > > Attached are my latest .c and .h ... I am sending the whole files rather than patches, as a check that I did not miss a patch that you wanted. Mail here has been a little less reliable that one might wish for.
> > > > > 
> > > > > I added back in the cpu number in the dprintks to aid MP debugging. I fixed a PSB problem where the battery limits were getting lost. And, I tweaked the smp processor init stuff as discussed in emails.
> > > > > 
> > > > > I am still thinking about the FIXME where Dominik asked for more validity checking. So, that is still FIXME.
> > > > 
> > > > Huh, now this is strange:
> > > > 
> > > > root@amd:~# echo "0%88%88%powersave" > /proc/cpufreq
> > > > root@amd:~# cat /proc/cpufreq
> > > >           minimum CPU frequency  -  maximum CPU frequency  -  policy
> > > > CPU  0      1584000 kHz ( 88 %)  -    1600000 kHz ( 88 %)  - powersave
> > > > root@amd:~#
> > 
> > Why is this strange? Can you elaborate, please?
> 
> CPU can not do 1.584MHz. Why did it round 88% down to 1.584GHz but
> maximum frequency  1.6GHz? Kernel 2.6.

1.8 GHz * 0.88 = 1584000 kHz -- min and max are set to this value at first.
As there is no state the CPU can be set to in between min and max, the max
value is increased to the next higher state [see
cpufreq_frequency_table_verify()] So there's nothing strange here, IMHO.

	Dominik

[-- Attachment #1.2: Type: application/pgp-signature, Size: 189 bytes --]

[-- Attachment #2: Type: text/plain, Size: 143 bytes --]

_______________________________________________
Cpufreq mailing list
Cpufreq@www.linux.org.uk
http://www.linux.org.uk/mailman/listinfo/cpufreq

Re: My latest powernow-k8.c

[Bruno Ducrot]

On Fri, Mar 19, 2004 at 03:33:06PM +0100, Dominik Brodowski wrote:
> 
> 1.8 GHz * 0.88 = 1584000 kHz -- min and max are set to this value at first.
> As there is no state the CPU can be set to in between min and max, the max
> value is increased to the next higher state [see
> cpufreq_frequency_table_verify()] So there's nothing strange here, IMHO.

Agreed, but I expected that the % will change in fact.

-- 
Bruno Ducrot

--  Which is worse:  ignorance or apathy?
--  Don't know.  Don't care.

Re: My latest powernow-k8.c

[Dominik Brodowski]

[-- Attachment #1.1: Type: text/plain, Size: 611 bytes --]

On Fri, Mar 19, 2004 at 04:52:20PM +0100, Bruno Ducrot wrote:
> On Fri, Mar 19, 2004 at 03:33:06PM +0100, Dominik Brodowski wrote:
> > 
> > 1.8 GHz * 0.88 = 1584000 kHz -- min and max are set to this value at first.
> > As there is no state the CPU can be set to in between min and max, the max
> > value is increased to the next higher state [see
> > cpufreq_frequency_table_verify()] So there's nothing strange here, IMHO.
> 
> Agreed, but I expected that the % will change in fact.

1800000 kHz * 0.88 = 1584000 kHz
1600000 kHz / 1800000 kHz = 0.8888888... which is truncated to 0.88

	Dominik

[-- Attachment #1.2: Type: application/pgp-signature, Size: 189 bytes --]

[-- Attachment #2: Type: text/plain, Size: 143 bytes --]

_______________________________________________
Cpufreq mailing list
Cpufreq@www.linux.org.uk
http://www.linux.org.uk/mailman/listinfo/cpufreq