|
From: Sven A. <an...@an...> - 2007-04-06 23:21:59
Attachments:
signature.asc
anders.vcf
|
Hello!
I spend my day analysing why the Linux could not use the C4 state(s).
Here my results...
For a start we take a look at the current available c-states:
#> cat /proc/acpi/processor/CPU?/power
active state: C3
max_cstate: C8
bus master activity: 00000000
maximum allowed latency: 8000 usec
states:
C1: type[C1] promotion[C2] demotion[--] latency[001]
usage[00002590] duration[00000000000000000000]
C2: type[C2] promotion[C3] demotion[C1] latency[001]
usage[00002086] duration[00000000000006795863]
*C3: type[C3] promotion[--] demotion[C2] latency[055]
usage[00003633] duration[00000000000009200376]
(The "max_cstate" value here is the number of the maximum used states,
if they are supported. It's not the number of states available!)
Because Linux uses ACPI to control the processors power state, I
diassembled the ACPI code (DSDT, SSDT and FACP) and found out the
following:
In the PNOT method (Processor notify), we see:
Notify (\_PR.CPU0, 0x80)
If (And (PDC0, 0x10))
{
Sleep (0x64)
Notify (\_PR.CPU0, 0x81)
}
This is (I think) the cause of the ACPI event (if you unplug the AC).
Here the output from the "acpid":
[Fri Apr 6 23:54:47 2007] received event "ac_adapter ADP1 00000080 00000000"
[Fri Apr 6 23:54:47 2007] completed event "ac_adapter ADP1 00000080 00000000"
[Fri Apr 6 23:54:47 2007] received event "processor CPU0 00000080 00000000"
[Fri Apr 6 23:54:47 2007] completed event "processor CPU0 00000080 00000000"
[Fri Apr 6 23:54:47 2007] received event "processor CPU0 00000081 00000000"
[Fri Apr 6 23:54:47 2007] completed event "processor CPU0 00000081 00000000"
[Fri Apr 6 23:54:47 2007] received event "processor CPU1 00000080 00000000"
[Fri Apr 6 23:54:47 2007] completed event "processor CPU1 00000080 00000000"
[Fri Apr 6 23:54:47 2007] received event "processor CPU1 00000081 00000000"
[Fri Apr 6 23:54:47 2007] completed event "processor CPU1 00000081 00000000"
[Fri Apr 6 23:54:47 2007] received event "battery BAT0 00000080 00000001"
[Fri Apr 6 23:54:47 2007] completed event "battery BAT0 00000080 00000001"
The PNOT method is called from some special methods in the SMB0 device
section (SmartBattery or SystemManagmentBus device).
So Linux (or MacOS X) will be notified about the change. Under Linux, this
will cause a call of "acpi_processor_cst_has_changed(pr);" [in
acpi_processor_notify()] which will get the (new) c-states.
On other laptops this will show a new state C4.
The problem under Linux (and Windows) on Apple laptops is, that the ACPI did
not provide any information about the advanced power-states. These states are
specifed via the _CST control method, but this is (according to the FACP)
not supported. Here the relevant part:
[05Fh 095 1] _CST Support : 00
[060h 096 2] C2 Latency : 0065
[062h 098 2] C3 Latency : 03E9
MacOS X must use ACPI only to some extend and will do it's own thing, when
it comes to using all c-states.
I think three possible solutions exist:
1) Patch "acpi_processor_cst_has_changed()" function, to return
the C4 state(s) on Apple laptops.
(This quick hack should be easy.)
2) Fix the ACPI table by adding the _CST method and load it via the
the initrd (Patch from "http://gaugusch.at/kernel.shtml" needed).
The biggest problem here will be, that we must change the FACP
table to enable the _CST support. But this is the "Fixed ACPI
Description Table" - so I think we cannot change it easily...
3) Beg Apple to fix the ACPI table.
(Does anybody have another laptop, where we can get the relevant _CST part
from?)
Regards
Sven
--
Sven Anders <an...@an...> () Ascii Ribbon Campaign
/\ Support plain text e-mail
ANDURAS service solutions AG
Innstraße 71 - 94036 Passau - Germany
Web: www.anduras.de - Tel: +49 (0)851-4 90 50-0 - Fax: +49 (0)851-4 90 50-55
Rechtsform: Aktiengesellschaft - Sitz: Passau - Amtsgericht Passau HRB 6032
Mitglieder des Vorstands: Sven Anders, Marcus Junker
Vorsitzender des Aufsichtsrats: Dipl. Kfm. Thomas Träger
|
|
From: Ludovic R. <lud...@gm...> - 2007-04-07 12:41:51
|
On 07/04/07, Sven Anders <an...@an...> wrote:
> For a start we take a look at the current available c-states:
>
> #> cat /proc/acpi/processor/CPU?/power
>
> active state: C3
> max_cstate: C8
> bus master activity: 00000000
> maximum allowed latency: 8000 usec
> states:
> C1: type[C1] promotion[C2] demotion[--] latency[001]
> usage[00002590] duration[00000000000000000000]
> C2: type[C2] promotion[C3] demotion[C1] latency[001]
> usage[00002086] duration[00000000000006795863]
> *C3: type[C3] promotion[--] demotion[C2] latency[055]
> usage[00003633] duration[00000000000009200376]
I don't know if it is of any interest but I have a different result:
$ cat /proc/acpi/processor/CPU0/power
active state: C2
max_cstate: C8
bus master activity: 00000000
states:
C1: type[C1] promotion[C2] demotion[--]
latency[000] usage[00000010] duration[00000000000000000000]
*C2: type[C2] promotion[--] demotion[C1]
latency[001] usage[01409563] duration[00000000005313483434]
I have a MacBook Pro with Core1Duo and using the Debian Etch
2.6.18-4-686 kernel (no additional patch)
Bye
--
Dr. Ludovic Rousseau
|
|
From: Nicolas B. <ni...@bo...> - 2007-04-07 12:52:49
|
-----BEGIN PGP SIGNED MESSAGE-----
Hash: SHA1
Ludovic Rousseau wrote:
> On 07/04/07, Sven Anders <an...@an...> wrote:
>> For a start we take a look at the current available c-states:
>>
>> #> cat /proc/acpi/processor/CPU?/power
>>
>> active state: C3
>> max_cstate: C8
>> bus master activity: 00000000
>> maximum allowed latency: 8000 usec
>> states:
>> C1: type[C1] promotion[C2] demotion[--] latency[001]
>> usage[00002590] duration[00000000000000000000]
>> C2: type[C2] promotion[C3] demotion[C1] latency[001]
>> usage[00002086] duration[00000000000006795863]
>> *C3: type[C3] promotion[--] demotion[C2] latency[055]
>> usage[00003633] duration[00000000000009200376]
>
> I don't know if it is of any interest but I have a different result:
>
> $ cat /proc/acpi/processor/CPU0/power
> active state: C2
> max_cstate: C8
> bus master activity: 00000000
> states:
> C1: type[C1] promotion[C2] demotion[--]
> latency[000] usage[00000010] duration[00000000000000000000]
> *C2: type[C2] promotion[--] demotion[C1]
> latency[001] usage[01409563] duration[00000000005313483434]
>
> I have a MacBook Pro with Core1Duo and using the Debian Etch
> 2.6.18-4-686 kernel (no additional patch)
Macbook Pro Core1Duo, 2.6.21-rc5:
active state: C3
max_cstate: C8
bus master activity: 00000000
maximum allowed latency: 2000 usec
states:
C1: type[C1] promotion[C2] demotion[--]
latency[001] usage[00001320] duration[00000000000000000000]
C2: type[C2] promotion[C3] demotion[C1]
latency[001] usage[00001738] duration[00000000000004385854]
*C3: type[C3] promotion[--] demotion[C2]
latency[001] usage[00297883] duration[00000000001201193554]
Best regards,
Nicolas
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v2.0.3 (GNU/Linux)
Comment: Using GnuPG with Mozilla - http://enigmail.mozdev.org
iD8DBQFGF5QC01ajQnpJXgERAv+1AJ90z/3Gr9dtpfBAGNJ5TBQSMnwdwQCfeq8U
d1pHO9rESh8nNyBh0oHwrI4=
=2AhY
-----END PGP SIGNATURE-----
|
|
From: Sven A. <an...@an...> - 2007-04-07 14:07:17
Attachments:
signature.asc
anders.vcf
|
Ludovic Rousseau schrieb:
>> active state: C3
>> max_cstate: C8
>> bus master activity: 00000000
>> maximum allowed latency: 8000 usec
>> states:
>> C1: type[C1] promotion[C2] demotion[--] latency[001]
>> usage[00002590] duration[00000000000000000000]
>> C2: type[C2] promotion[C3] demotion[C1] latency[001]
>> usage[00002086] duration[00000000000006795863]
>> *C3: type[C3] promotion[--] demotion[C2] latency[055]
>> usage[00003633] duration[00000000000009200376]
>
> I don't know if it is of any interest but I have a different result:
>
> $ cat /proc/acpi/processor/CPU0/power
> active state: C2
> max_cstate: C8
> bus master activity: 00000000
> states:
> C1: type[C1] promotion[C2] demotion[--]
> latency[000] usage[00000010] duration[00000000000000000000]
> *C2: type[C2] promotion[--] demotion[C1]
> latency[001] usage[01409563] duration[00000000005313483434]
>
> I have a MacBook Pro with Core1Duo and using the Debian Etch
> 2.6.18-4-686 kernel (no additional patch)
Do you experiencing short battery-time and loud fans?
What does your dmesg output show?
Mine is as follows:
[ 1.673189] ACPI (exconfig-0455): Dynamic SSDT Load - OemId [APPLE ] OemTable
Id [ Cpu0Ist] [20060707]
[ 1.673606] ACPI (exconfig-0455): Dynamic SSDT Load - OemId [APPLE ] OemTable
Id [ Cpu0Cst] [20060707]
[ 1.674063] Monitor-Mwait will be used to enter C-1 state
[ 1.674065] Monitor-Mwait will be used to enter C-2 state
[ 1.674066] Monitor-Mwait will be used to enter C-3 state
[ 1.674071] ACPI: CPU0 (power states: C1[C1] C2[C2] C3[C3])
[ 1.674512] ACPI: Processor [CPU0] (supports 8 throttling states)
[ 1.675097] ACPI (exconfig-0455): Dynamic SSDT Load - OemId [APPLE ] OemTable
Id [ Cpu1Ist] [20060707]
[ 1.675496] ACPI (exconfig-0455): Dynamic SSDT Load - OemId [APPLE ] OemTable
Id [ Cpu1Cst] [20060707]
[ 1.675985] ACPI: CPU1 (power states: C1[C1] C2[C2] C3[C3])
[ 1.676434] ACPI: Processor [CPU1] (supports 8 throttling states)
Regards
Sven
--
Sven Anders <an...@an...> () Ascii Ribbon Campaign
/\ Support plain text e-mail
ANDURAS service solutions AG
Innstraße 71 - 94036 Passau - Germany
Web: www.anduras.de - Tel: +49 (0)851-4 90 50-0 - Fax: +49 (0)851-4 90 50-55
Rechtsform: Aktiengesellschaft - Sitz: Passau - Amtsgericht Passau HRB 6032
Mitglieder des Vorstands: Sven Anders, Marcus Junker
Vorsitzender des Aufsichtsrats: Dipl. Kfm. Thomas Träger
|
|
From: Ludovic R. <lud...@gm...> - 2007-04-07 14:19:41
|
On 07/04/07, Sven Anders <an...@an...> wrote: > Do you experiencing short battery-time and loud fans? short battery-time; yes, a bit. With a full charged battery the estimated remaining time is 2h13m. I have not tried/measured the effective time. loud fans: no (unless I recompile a kernel :-) The fan speed is ~1000 $ cd /sys/devices/platform/applesmc $ for i in fan*; do echo -n "$i: " ; cat $i; done fan0_actual_speed: 1031 fan0_manual: 0 fan0_maximum_speed: 5500 fan0_minimum_speed: 1000 fan0_safe_speed: 1200 fan0_target_speed: 1032 fan1_actual_speed: 1032 fan1_manual: 0 fan1_maximum_speed: 5500 fan1_minimum_speed: 1000 fan1_safe_speed: 1200 fan1_target_speed: 1032 > What does your dmesg output show? ACPI (exconfig-0455): Dynamic SSDT Load - OemId [APPLE ] OemTableId [ Cpu0Ist] [20060707] ACPI (exconfig-0455): Dynamic SSDT Load - OemId [APPLE ] OemTableId [ Cpu0Cst] [20060707] ACPI: CPU0 (power states: C1[C1] C2[C2]) ACPI: Processor [CPU0] (supports 8 throttling states) ACPI (exconfig-0455): Dynamic SSDT Load - OemId [APPLE ] OemTableId [ Cpu1Ist] [20060707] ACPI (exconfig-0455): Dynamic SSDT Load - OemId [APPLE ] OemTableId [ Cpu1Cst] [20060707] ACPI: CPU1 (power states: C1[C1] C2[C2]) ACPI: Processor [CPU1] (supports 8 throttling states) I can send the complete dmesg if needed. I use the Debian Etch kernel but I installed the modules appleir, applesmc and appletouch as external modules (compiled outside of the kernel). bye -- Dr. Ludovic Rousseau |
|
From: Sven A. <an...@an...> - 2007-04-07 14:53:20
Attachments:
signature.asc
anders.vcf
|
Ludovic Rousseau schrieb:
> On 07/04/07, Sven Anders <an...@an...> wrote:
>> Do you experiencing short battery-time and loud fans?
>
> short battery-time; yes, a bit.
> With a full charged battery the estimated remaining time is 2h13m.
> I have not tried/measured the effective time.
>
> loud fans: no (unless I recompile a kernel :-)
> The fan speed is ~1000
>
>> What does your dmesg output show?
>
> ACPI: CPU0 (power states: C1[C1] C2[C2])
This is VERY strange, because you are getting over 2h runtime even without
using the C3 state! And (moreover) your fans are running lower than anybody
elses fans...
I'm owning a MBP with a Core 2 Duo and (as far as I'm following the mails) my
2 hours runtime WITH using the C3 states (and running fans at ~2000) are very
good.
Are you using the ATI driver?
Can you send me the output of /proc/acpi/dsdt and /proc/acpi/fadt in
a separate mail?
Regards
Sven
--
Sven Anders <an...@an...> () Ascii Ribbon Campaign
/\ Support plain text e-mail
ANDURAS service solutions AG
Innstraße 71 - 94036 Passau - Germany
Web: www.anduras.de - Tel: +49 (0)851-4 90 50-0 - Fax: +49 (0)851-4 90 50-55
Rechtsform: Aktiengesellschaft - Sitz: Passau - Amtsgericht Passau HRB 6032
Mitglieder des Vorstands: Sven Anders, Marcus Junker
Vorsitzender des Aufsichtsrats: Dipl. Kfm. Thomas Träger
|
|
From: Miguel S. F. <mig...@gm...> - 2007-04-12 13:48:54
|
Hi all,
I too only have C1 and C2 states.
On 4/7/07, Ludovic Rousseau <lud...@gm...> wrote:
> On 07/04/07, Sven Anders <an...@an...> wrote:
> > For a start we take a look at the current available c-states:
> >
> > #> cat /proc/acpi/processor/CPU?/power
> >
> > active state: C3
> > max_cstate: C8
> > bus master activity: 00000000
> > maximum allowed latency: 8000 usec
> > states:
> > C1: type[C1] promotion[C2] demotion[--] latency[001]
> > usage[00002590] duration[00000000000000000000]
> > C2: type[C2] promotion[C3] demotion[C1] latency[001]
> > usage[00002086] duration[00000000000006795863]
> > *C3: type[C3] promotion[--] demotion[C2] latency[055]
> > usage[00003633] duration[00000000000009200376]
>
> I don't know if it is of any interest but I have a different result:
>
> $ cat /proc/acpi/processor/CPU0/power
> active state: C2
> max_cstate: C8
> bus master activity: 00000000
> states:
> C1: type[C1] promotion[C2] demotion[--]
> latency[000] usage[00000010] duration[00000000000000000000]
> *C2: type[C2] promotion[--] demotion[C1]
> latency[001] usage[01409563] duration[00000000005313483434]
>
> I have a MacBook Pro with Core1Duo and using the Debian Etch
> 2.6.18-4-686 kernel (no additional patch)
>
> Bye
This is a Macbook Pro 15.4", Dual Core T2500 cpu.
I get low battery uptime. (+/- 2h, not shure)
Kernel is 2.6.18.4-mactel
I'm using ATI drivers: fglrx 8.31.5
The distro is ubuntu 6.10
[CPU-POWERSTATES]
--(cray)-(pts2)-(14:30/12-Abr-07)--
--<~>-- cat /proc/acpi/processor/CPU?/power
active state: C2
max_cstate: C8
bus master activity: 00000000
states:
C1: type[C1] promotion[C2] demotion[--]
latency[000] usage[00000010] duration[00000000000000000000]
*C2: type[C2] promotion[--] demotion[C1]
latency[001] usage[43467481] duration[00000000203957347293]
active state: C2
max_cstate: C8
bus master activity: 00000000
states:
C1: type[C1] promotion[C2] demotion[--]
latency[000] usage[00000010] duration[00000000000000000000]
*C2: type[C2] promotion[--] demotion[C1]
latency[001] usage[43198784] duration[00000000208704738735]
Why doesn't the C3 state appear in here??
-- snippet of dmesg --
ACPI: (supports S0 S3 S4 S5)
...
ACPI (exconfig-0455): Dynamic SSDT Load - OemId [APPLE ] OemTableId [
Cpu0Ist] [20060707]
ACPI (exconfig-0455): Dynamic SSDT Load - OemId [APPLE ] OemTableId [
Cpu0Cst] [20060707]
ACPI: CPU0 (power states: C1[C1] C2[C2] C3[C3])
ACPI: Processor [CPU0] (supports 8 throttling states)
ACPI (exconfig-0455): Dynamic SSDT Load - OemId [APPLE ] OemTableId [
Cpu1Ist] [20060707]
ACPI (exconfig-0455): Dynamic SSDT Load - OemId [APPLE ] OemTableId [
Cpu1Cst] [20060707]
ACPI: CPU1 (power states: C1[C1] C2[C2] C3[C3])
ACPI: Processor [CPU1] (supports 8 throttling states)
[FANS]
--(cray)-(pts2)-(14:38/12-Abr-07)--
--</sys/devices/platform/applesmc>-- for i in fan*; do echo -n "$i: "
; cat $i; done
fan0_actual_speed: 998
fan0_manual: 0
fan0_maximum_speed: 6000
fan0_minimum_speed: 1000
fan0_safe_speed: 1200
fan0_target_speed: 1000
fan1_actual_speed: 996
fan1_manual: 0
fan1_maximum_speed: 6000
fan1_minimum_speed: 1000
fan1_safe_speed: 1200
fan1_target_speed: 1000
Any extra info about energy savings in linux ?
Best regards,
--
Miguel Sousa Filipe
|
|
From: Ludovic R. <lud...@gm...> - 2007-04-07 19:20:10
|
On 07/04/07, Thomas Meyer <th...@m3...> wrote: > I think you still have the boot rom version 1.0, like in this dmesg output: > http://www.mactel-linux.org/wiki/Dmesg What is important to check in this long list? > Please have a look here: > http://www.apple.com/support/downloads/macbookproefifirmwareupdate12.html My ROM version is MBP12.0061.B03 So I guess I already installed the "MacBook Pro EFI Firmware Update 1.2" My SMC version is: 1.5f10 My model: MacBookPro1,2 bye -- Dr. Ludovic Rousseau |
|
From: Sven A. <an...@an...> - 2007-04-07 19:58:36
Attachments:
signature.asc
anders.vcf
|
Sven Anders schrieb:
> Ludovic Rousseau schrieb:
>> On 07/04/07, Sven Anders <an...@an...> wrote:
>>> Do you experiencing short battery-time and loud fans?
>> short battery-time; yes, a bit.
>> With a full charged battery the estimated remaining time is 2h13m.
>> I have not tried/measured the effective time.
>>
>> loud fans: no (unless I recompile a kernel :-)
>> The fan speed is ~1000
>>
>>> What does your dmesg output show?
>> ACPI: CPU0 (power states: C1[C1] C2[C2])
>
> This is VERY strange, because you are getting over 2h runtime even without
> using the C3 state! And (moreover) your fans are running lower than anybody
> elses fans...
>
> I'm owning a MBP with a Core 2 Duo and (as far as I'm following the mails) my
> 2 hours runtime WITH using the C3 states (and running fans at ~2000) are very
> good.
Is it right, that you own an 17" MBP?
Is so, this will explain the fan speed and the 2h13m runtime in state C2.
And in this case, this is as bad as 2h on a 15" MBP...
Regards
Sven
--
Sven Anders <an...@an...> () Ascii Ribbon Campaign
/\ Support plain text e-mail
ANDURAS service solutions AG
Innstraße 71 - 94036 Passau - Germany
Web: www.anduras.de - Tel: +49 (0)851-4 90 50-0 - Fax: +49 (0)851-4 90 50-55
Rechtsform: Aktiengesellschaft - Sitz: Passau - Amtsgericht Passau HRB 6032
Mitglieder des Vorstands: Sven Anders, Marcus Junker
Vorsitzender des Aufsichtsrats: Dipl. Kfm. Thomas Träger
|
|
From: Ludovic R. <lud...@gm...> - 2007-04-07 20:12:42
|
On 07/04/07, Sven Anders <an...@an...> wrote: > Is it right, that you own an 17" MBP? yes > Is so, this will explain the fan speed and the 2h13m runtime in state C2. > And in this case, this is as bad as 2h on a 15" MBP... MacOS X gives me an estimate of 4h23m with full battery. So yes, autonomy under Linux is much worse than under MacOS X. But that does not explain why the fans are running faster under Linux than under MacOS X for some of you. For me, under Linux or MacOS X the speed is the same at around 1000 rpm. bye -- Dr. Ludovic Rousseau |
|
From: Sven A. <an...@an...> - 2007-04-12 18:48:46
Attachments:
signature.asc
anders.vcf
|
Miguel Sousa Filipe schrieb:
> Hi all,
>
> I too only have C1 and C2 states.
Does it change, if you remove the battery?
Which firmware revision do you use? Is it the latest?
Do you have an MacBook, Pro, 17"?
Regards
Sven
--
Sven Anders <an...@an...> () Ascii Ribbon Campaign
/\ Support plain text e-mail
ANDURAS service solutions AG
Innstraße 71 - 94036 Passau - Germany
Web: www.anduras.de - Tel: +49 (0)851-4 90 50-0 - Fax: +49 (0)851-4 90 50-55
Rechtsform: Aktiengesellschaft - Sitz: Passau - Amtsgericht Passau HRB 6032
Mitglieder des Vorstands: Sven Anders, Marcus Junker
Vorsitzender des Aufsichtsrats: Dipl. Kfm. Thomas Träger
|
|
From: Nick H. <li...@gm...> - 2007-04-13 00:39:25
|
On 13/04/07, Sven Anders <an...@an...> wrote:
>
> Miguel Sousa Filipe schrieb:
> > Hi all,
> >
> > I too only have C1 and C2 states.
>
> Does it change, if you remove the battery?
> Which firmware revision do you use? Is it the latest?
> Do you have an MacBook, Pro, 17"?
>
> Regards
> Sven
>
hi guys. just thought i'd throw some data in here too. i've got a 15" MBP
C2D, and with or without the battery, i only have states C1 and C2:
nick@wombat:~> cat /proc/acpi/processor/CPU?/power
active state: C2
max_cstate: C8
bus master activity: 00000000
states:
C1: type[C1] promotion[C2] demotion[--] latency[000]
usage[00000010] duration[00000000000000000000]
*C2: type[C2] promotion[--] demotion[C1] latency[001]
usage[00519404] duration[00000000002241198284]
active state: C2
max_cstate: C8
bus master activity: 00000000
states:
C1: type[C1] promotion[C2] demotion[--] latency[000]
usage[00000010] duration[00000000000000000000]
*C2: type[C2] promotion[--] demotion[C1] latency[001]
usage[00519437] duration[00000000002339078849]
nick@wombat:~>
how can i determine which firmware revision i'm using?
-Nick
|
|
From: Miguel S. F. <mig...@gm...> - 2007-04-14 12:12:44
|
Hi, On 4/12/07, Sven Anders <an...@an...> wrote: > Miguel Sousa Filipe schrieb: > > Hi all, > > > > I too only have C1 and C2 states. > > Does it change, if you remove the battery? I removed the power cord (on battery), and now the C3 state appears.! > Which firmware revision do you use? Is it the latest? how can I check that? > Do you have an MacBook, Pro, 17"? No, its a MacBook Pro 15.4", 1st generation (Core Duo @ 2.0ghz) Best regards, -- Miguel Sousa Filipe |
|
From: Sven A. <an...@an...> - 2007-04-28 20:33:37
Attachments:
signature.asc
anders.vcf
|
Len Brown schrieb:
>> #> cat /proc/acpi/processor/CPU?/power
>>
>> active state: C3
>> max_cstate: C8
>> bus master activity: 00000000
>> maximum allowed latency: 8000 usec
>> states:
>> C1: type[C1] promotion[C2] demotion[--] latency[001]
>> usage[00002590] duration[00000000000000000000]
>> C2: type[C2] promotion[C3] demotion[C1] latency[001]
>> usage[00002086] duration[00000000000006795863]
>> *C3: type[C3] promotion[--] demotion[C2] latency[055]
>> usage[00003633] duration[00000000000009200376]
>
> First note that there are "hardware C-states", and "ACPI C-states".
> The table above shows the ACPI C-states that the BIOS makes visible to the OS.
>
> The BIOS (via the FADT or _CST) can map any hardware C-state it wants
> to ACPI C3. It is likely that you are already getting hardware C4
> and simply skipping over hardware C3.
>
> If you provide the complete raw output from acpidump, then it should be
> possible to tell.
As stated some lines below that, I found out, that ACPI C3 should be hardware C4E.
Can you confirm that?
Regards
Sven
--
Sven Anders <an...@an...> () Ascii Ribbon Campaign
/\ Support plain text e-mail
ANDURAS service solutions AG
Innstraße 71 - 94036 Passau - Germany
Web: www.anduras.de - Tel: +49 (0)851-4 90 50-0 - Fax: +49 (0)851-4 90 50-55
Rechtsform: Aktiengesellschaft - Sitz: Passau - Amtsgericht Passau HRB 6032
Mitglieder des Vorstands: Sven Anders, Marcus Junker
Vorsitzender des Aufsichtsrats: Dipl. Kfm. Thomas Träger
|