FAQ Search Today's Posts Mark Forums Read
» Video Reviews

» Linux Archive

Linux-archive is a website aiming to archive linux email lists and to make them easily accessible for linux users/developers.


» Sponsor

» Partners

» Sponsor

Go Back   Linux Archive > Gentoo > Gentoo User

 
 
LinkBack Thread Tools
 
Old 05-10-2011, 03:24 PM
Volker Armin Hemmann
 
Default Check CPU for throttling

On Tuesday 10 May 2011 16:34:53 Helmut Jarausch wrote:
> On 05/10/2011 02:44:26 PM, Volker Armin Hemmann wrote:
> > On Tuesday 10 May 2011 08:27:42 Helmut Jarausch wrote:
> > > On 05/10/2011 02:36:33 AM, Volker Armin Hemmann wrote:
> > > > On Sunday 08 May 2011 12:59:57 Helmut Jarausch wrote:
> > > > > On 05/08/2011 11:21:06 AM, Florian Philipp wrote:
> > > > >
> > > > > sys-process/atop shows current CPU freqency
> > > > > I use it to check the effect of sys-power/powernowd
> > > >
> > > > why are you using powernowd?
> > >
> > > Why not? It's a daemon which reduces the CPU speed under certain
> > > circumstances.
> >
> > just like the kernel. Only the kernel does it better.
> >
> > > This not only saves power but it reduce the noise produced by the
> >
> > fan.
> >
> > fanspeed - if you have a pwm fan.
> >
> > Seriously, powernowd is so not needed. Just built a kernel with
> > ondemand cpu
> > governor. You are done.
>
> Hi,
> I've just tried that, but it doesn't work (at least, as the output of
> atop is concerned)
>
> dmesg shows
> cpuidle: using governor ladder
> cpuidle: using governor menu

that is a different can of worms
>
> Am I missing something?

yes:

*- 'ondemand' cpufreq policy governor
 
Old 05-10-2011, 03:36 PM
Alan McKinnon
 
Default Check CPU for throttling

Apparently, though unproven, at 17:14 on Tuesday 10 May 2011, Helmut Jarausch
did opine thusly:

> On 05/10/2011 04:57:05 PM, Sebastian Beίler wrote:
> > Am 10.05.2011 16:49, schrieb Helmut Jarausch:
> > > And that tells me that the CPU is running at full speed (3 GHz in
> >
> > my
> >
> > > case) although all CPUs are idle.
> >
> > What does
> > cat /sys/devices/system/cpu/cpu0/cpufreq/scaling_governor
> > and
> > cat /sys/devices/system/cpu/cpu0/cpufreq/
> > scaling_available_frequencies
> > and
> > cat /sys/devices/system/cpu/cpu0/cpufreq/scaling_available_governors
> > say?
>
> I have tried
> echo "ondemand" > /sys/devices/system/cpu/cpu0/cpufreq/
> scaling_governor
>
> and now I see an effect but not as good as powernowd
> e.g. I have stopped processed temporarily so that the CPU usage fell
> down to 1% (max). Still after waiting some minutes, only one core
> scaled down to 800 MHz and a a second one to 2.3 GHz.
>
> At least, powernowd it much more "agressive".
> If some cores are idle for a few seconds it scales these down stepwise
> to the lowest frequency.

The authors of powertop (employed by Intel) researched this topic extensively
and wrote up their findings on the project website and in the package docs.

In summary, it goes something like this:

Userspace cpu freq daemons are a waste of time, it takes excessive energy to
step wise change performance up and down. What you really want is for the cpu
to run full speed when it has something to do, get it done as quickly as
possible then rapidly fall back to the lowest idle speed once the job is
complete. That is how the ondemand governor is written.

I suppose this step-down-through-the-levels nonsense comes from flawed
comparisons with combustion engines and turbines - it makes sense to ramp
these up and down. It does not make sense to do this with a cpu as a cpu is a
completely different beast altogether. It is either doing something or
nothing; actually it never does nothing - it always does something even if
that is just the no-op instruction in a loop. And cpus do not "accelerate"
like engines and use almost no additional power to go from min to max speed.
So when something useful comes along to do, just switch over to max speed and
get the job done.

Really, this powernowd stuff looks neat on paper but the actual numbers say
otherwise. Just enable ondemand, disable everything else, and et the kernel
get on with doing what it does best:

the kernel should never try and be clever and second guess you, that way lies
madness. Similarly, you should never try and be clever and second guess the
kernel. That way also lies madness.


--
alan dot mckinnon at gmail dot com
 
Old 05-10-2011, 03:36 PM
Alan McKinnon
 
Default Check CPU for throttling

Apparently, though unproven, at 17:14 on Tuesday 10 May 2011, Helmut Jarausch
did opine thusly:

> On 05/10/2011 04:57:05 PM, Sebastian Beίler wrote:
> > Am 10.05.2011 16:49, schrieb Helmut Jarausch:
> > > And that tells me that the CPU is running at full speed (3 GHz in
> >
> > my
> >
> > > case) although all CPUs are idle.
> >
> > What does
> > cat /sys/devices/system/cpu/cpu0/cpufreq/scaling_governor
> > and
> > cat /sys/devices/system/cpu/cpu0/cpufreq/
> > scaling_available_frequencies
> > and
> > cat /sys/devices/system/cpu/cpu0/cpufreq/scaling_available_governors
> > say?
>
> I have tried
> echo "ondemand" > /sys/devices/system/cpu/cpu0/cpufreq/
> scaling_governor
>
> and now I see an effect but not as good as powernowd
> e.g. I have stopped processed temporarily so that the CPU usage fell
> down to 1% (max). Still after waiting some minutes, only one core
> scaled down to 800 MHz and a a second one to 2.3 GHz.
>
> At least, powernowd it much more "agressive".
> If some cores are idle for a few seconds it scales these down stepwise
> to the lowest frequency.

The authors of powertop (employed by Intel) researched this topic extensively
and wrote up their findings on the project website and in the package docs.

In summary, it goes something like this:

Userspace cpu freq daemons are a waste of time, it takes excessive energy to
step wise change performance up and down. What you really want is for the cpu
to run full speed when it has something to do, get it done as quickly as
possible then rapidly fall back to the lowest idle speed once the job is
complete. That is how the ondemand governor is written.

I suppose this step-down-through-the-levels nonsense comes from flawed
comparisons with combustion engines and turbines - it makes sense to ramp
these up and down. It does not make sense to do this with a cpu as a cpu is a
completely different beast altogether. It is either doing something or
nothing; actually it never does nothing - it always does something even if
that is just the no-op instruction in a loop. And cpus do not "accelerate"
like engines and use almost no additional power to go from min to max speed.
So when something useful comes along to do, just switch over to max speed and
get the job done.

Really, this powernowd stuff looks neat on paper but the actual numbers say
otherwise. Just enable ondemand, disable everything else, and et the kernel
get on with doing what it does best:

the kernel should never try and be clever and second guess you, that way lies
madness. Similarly, you should never try and be clever and second guess the
kernel. That way also lies madness.


--
alan dot mckinnon at gmail dot com
 
Old 05-10-2011, 03:54 PM
Bill Longman
 
Default Check CPU for throttling

On 05/10/2011 08:36 AM, Alan McKinnon wrote:
> I suppose this step-down-through-the-levels nonsense comes from flawed
> comparisons with combustion engines and turbines - it makes sense to ramp
> these up and down. It does not make sense to do this with a cpu as a cpu is a
> completely different beast altogether. It is either doing something or
> nothing; actually it never does nothing - it always does something even if
> that is just the no-op instruction in a loop. And cpus do not "accelerate"
> like engines and use almost no additional power to go from min to max speed.
> So when something useful comes along to do, just switch over to max speed and
> get the job done.

That's not exactly true. It does take time, aka latency, to move CPUs
out of sleep states. Sleep states are partially related to this because
once the load on a CPU goes to zero, the governor will, depending on
your configuration, put the CPU into a sleep state to conserve power.
Waking that sleeping CPU from its deepest sleep state takes an enormous
amount of time, in terms of CPU time, so it sometimes behooves the
scheduler to be a bit less dogmatic about putting CPUs to bed while
there's still work to do.
 
Old 05-10-2011, 04:34 PM
James
 
Default Check CPU for throttling

Alan McKinnon <alan.mckinnon <at> gmail.com> writes:


> otherwise. Just enable ondemand, disable everything else, and et the kernel
> get on with doing what it does best:

So this is what you are saying?

[*] CPU Frequency scaling β”‚ β”‚
β”‚ β”‚[*] Enable CPUfreq debugging β”‚ β”‚
β”‚ β”‚ <*> CPU frequency translation statistics β”‚ β”‚
β”‚ β”‚ [ ] CPU frequency translation statistics details β”‚ β”‚
β”‚ β”‚ Default CPUFreq governor (performance) ---> β”‚ β”‚
β”‚ β”‚ -*- 'performance' governor β”‚ β”‚
β”‚ β”‚ < > 'powersave' governor β”‚ β”‚
β”‚ β”‚ < > 'userspace' governor for userspace frequency scalingβ”‚ β”‚
β”‚ β”‚ <*> 'ondemand' cpufreq policy governor β”‚ β”‚
β”‚ β”‚ < > 'conservative' cpufreq governor β”‚ β”‚
β”‚ β”‚ *** CPUFreq processor drivers *** β”‚ β”‚
β”‚ β”‚ < > Processor Clocking Control interface driver β”‚ β”‚
β”‚ β”‚ <*> ACPI Processor P-States driver β”‚ β”‚
β”‚ β”‚ < > AMD Opteron/Athlon64 PowerNow! β”‚ β”‚
β”‚ β”‚ < > Intel Enhanced SpeedStep (deprecated) β”‚ β”‚
β”‚ β”‚ < > Intel Pentium 4 clock modulation
 
Old 05-10-2011, 04:38 PM
Bill Longman
 
Default Check CPU for throttling

On 05/10/2011 09:34 AM, James wrote:
> Alan McKinnon <alan.mckinnon <at> gmail.com> writes:
>
>
>> otherwise. Just enable ondemand, disable everything else, and et the kernel
>> get on with doing what it does best:
>
> So this is what you are saying?
>
>
>[*] CPU Frequency scaling β”‚ β”‚
> β”‚ β”‚[*] Enable CPUfreq debugging β”‚ β”‚
> β”‚ β”‚ <*> CPU frequency translation statistics β”‚ β”‚
> β”‚ β”‚ [ ] CPU frequency translation statistics details β”‚ β”‚
> β”‚ β”‚ Default CPUFreq governor (performance) ---> β”‚ β”‚
> β”‚ β”‚ -*- 'performance' governor β”‚ β”‚
> β”‚ β”‚ < > 'powersave' governor β”‚ β”‚
> β”‚ β”‚ < > 'userspace' governor for userspace frequency scalingβ”‚ β”‚
> β”‚ β”‚ <*> 'ondemand' cpufreq policy governor β”‚ β”‚
> β”‚ β”‚ < > 'conservative' cpufreq governor β”‚ β”‚
> β”‚ β”‚ *** CPUFreq processor drivers *** β”‚ β”‚
> β”‚ β”‚ < > Processor Clocking Control interface driver β”‚ β”‚
> β”‚ β”‚ <*> ACPI Processor P-States driver β”‚ β”‚
> β”‚ β”‚ < > AMD Opteron/Athlon64 PowerNow! β”‚ β”‚
> β”‚ β”‚ < > Intel Enhanced SpeedStep (deprecated) β”‚ β”‚
> β”‚ β”‚ < > Intel Pentium 4 clock modulation
>
>

Yes but no. Yes, those are the correct choices, but the default governor
should be ondemand.
 
Old 05-10-2011, 06:05 PM
Mark Knecht
 
Default Check CPU for throttling

On Tue, May 10, 2011 at 9:38 AM, Bill Longman <bill.longman@gmail.com> wrote:
> On 05/10/2011 09:34 AM, James wrote:
>> Alan McKinnon <alan.mckinnon <at> gmail.com> writes:
>>
>>
>>> otherwise. Just enable ondemand, disable everything else, and et the kernel
>>> get on with doing what it does best:
>>
>> So this is what you are saying?
>>
>>
>> Β*[*] CPU Frequency scaling Β* Β* Β* Β* Β* Β* Β* Β* Β* Β* Β* Β* Β* Β* Β* Β* Β* Β* Β* Β* β”‚ β”‚
>> Β* β”‚ β”‚ Β* Β*[*] Β* Enable CPUfreq debugging Β* Β* Β* Β* Β* Β* Β* Β* Β* Β* Β* Β* Β* Β*β”‚ β”‚
>> Β* β”‚ β”‚ Β* Β*<*> Β* CPU frequency translation statistics Β* Β* Β* Β* Β* Β* Β* Β*β”‚ β”‚
>> Β* β”‚ β”‚ Β* Β*[ ] Β* Β* CPU frequency translation statistics details Β* Β* Β*β”‚ β”‚
>> Β* β”‚ β”‚ Β* Β* Β* Β* Β*Default CPUFreq governor (performance) Β*---> Β* Β* Β* Β*β”‚ β”‚
>> Β* β”‚ β”‚ Β* Β*-*- Β* 'performance' governor Β* Β* Β* Β* Β* Β* Β* Β* Β* Β* Β* Β* Β* Β* Β*β”‚ β”‚
>> Β* β”‚ β”‚ Β* Β*< > Β* 'powersave' governor Β* Β* Β* Β* Β* Β* Β* Β* Β* Β* Β* Β* Β* Β* Β* Β*β”‚ β”‚
>> Β* β”‚ β”‚ Β* Β*< > Β* 'userspace' governor for userspace frequency scalingβ”‚ β”‚
>> Β* β”‚ β”‚ Β* Β*<*> Β* 'ondemand' cpufreq policy governor Β* Β* Β* Β* Β* Β* Β* Β* Β*β”‚ β”‚
>> Β* β”‚ β”‚ Β* Β*< > Β* 'conservative' cpufreq governor Β* Β* Β* Β* Β* Β* Β* Β* Β* Β* β”‚ β”‚
>> Β* β”‚ β”‚ Β* Β* Β* Β* Β**** CPUFreq processor drivers *** Β* Β* Β* Β* Β* Β* Β* Β* Β* β”‚ β”‚
>> Β* β”‚ β”‚ Β* Β*< > Β* Processor Clocking Control interface driver Β* Β* Β* Β* β”‚ β”‚
>> Β* β”‚ β”‚ Β* Β*<*> Β* ACPI Processor P-States driver Β* Β* Β* Β* Β* Β* Β* Β* Β* Β* Β*β”‚ β”‚
>> Β* β”‚ β”‚ Β* Β*< > Β* AMD Opteron/Athlon64 PowerNow! Β* Β* Β* Β* Β* Β* Β* Β* Β* Β* Β*β”‚ β”‚
>> Β* β”‚ β”‚ Β* Β*< > Β* Intel Enhanced SpeedStep (deprecated) Β* Β* Β* Β* Β* Β* Β* β”‚ β”‚
>> Β* β”‚ β”‚ Β* Β*< > Β* Intel Pentium 4 clock modulation
>>
>>
>
> Yes but no. Yes, those are the correct choices, but the default governor
> should be ondemand.

Or in the case of the OP who is brave enough (or silly enough?) to
risk the long term reliability of his CPU running it with no fan,
possibly choose powersave with a specific low clock rate as the
default and then switch to either ondemand or conservative manually
when he needs more performance. In a machine such as he's playing with
I wonder if he really wants ondemand (jumps to max and then slows down
over time) vs conservative which more slowly ramps up the clock rate
if the job at hand takes more time.

It's all a trade off of performance vs power & heat.

On my 12 thread server I've played with these two and frankly don't
see a lot of difference doing any large job. They are both a bot
slower than running performance, but I save a lot of power (and over
time money) using them so I'm happy.

- Mark
 
Old 05-10-2011, 08:18 PM
Alan McKinnon
 
Default Check CPU for throttling

Apparently, though unproven, at 18:34 on Tuesday 10 May 2011, James did opine
thusly:

> Alan McKinnon <alan.mckinnon <at> gmail.com> writes:
> > otherwise. Just enable ondemand, disable everything else, and et the
> > kernel
>
> > get on with doing what it does best:
> So this is what you are saying?
>
>
>[*] CPU Frequency scaling β”‚ β”‚
> β”‚ β”‚[*] Enable CPUfreq debugging β”‚ β”‚
> β”‚ β”‚ <*> CPU frequency translation statistics β”‚ β”‚
> β”‚ β”‚ [ ] CPU frequency translation statistics details β”‚ β”‚
> β”‚ β”‚ Default CPUFreq governor (performance) ---> β”‚ β”‚
> β”‚ β”‚ -*- 'performance' governor β”‚ β”‚
> β”‚ β”‚ < > 'powersave' governor β”‚ β”‚
> β”‚ β”‚ < > 'userspace' governor for userspace frequency scalingβ”‚ β”‚
> β”‚ β”‚ <*> 'ondemand' cpufreq policy governor β”‚ β”‚
> β”‚ β”‚ < > 'conservative' cpufreq governor β”‚ β”‚
> β”‚ β”‚ *** CPUFreq processor drivers *** β”‚ β”‚
> β”‚ β”‚ < > Processor Clocking Control interface driver β”‚ β”‚
> β”‚ β”‚ <*> ACPI Processor P-States driver β”‚ β”‚
> β”‚ β”‚ < > AMD Opteron/Athlon64 PowerNow! β”‚ β”‚
> β”‚ β”‚ < > Intel Enhanced SpeedStep (deprecated) β”‚ β”‚
> β”‚ β”‚ < > Intel Pentium 4 clock modulation

Mostly.

The performance governor cannot be disabled (-*-) so it is always selected,
and the default should be set to ondemand.

The above is for personal workstations, laptops etc. For servers requiring
decent throughput and where power and cooling is not an issue, one would use a
different approach of course.

--
alan dot mckinnon at gmail dot com
 
Old 05-10-2011, 08:30 PM
Mick
 
Default Check CPU for throttling

On Tuesday 10 May 2011 19:05:08 Mark Knecht wrote:
> On Tue, May 10, 2011 at 9:38 AM, Bill Longman <bill.longman@gmail.com>
wrote:
> > On 05/10/2011 09:34 AM, James wrote:
> >> Alan McKinnon <alan.mckinnon <at> gmail.com> writes:
> >>> otherwise. Just enable ondemand, disable everything else, and et the
> >>> kernel
> >>
> >>> get on with doing what it does best:
> >> So this is what you are saying?
> >>
> >>
> >>[*] CPU Frequency scaling β”‚ β”‚
> >> β”‚ β”‚[*] Enable CPUfreq debugging β”‚ β”‚
> >> β”‚ β”‚ <*> CPU frequency translation statistics β”‚ β”‚
> >> β”‚ β”‚ [ ] CPU frequency translation statistics details β”‚ β”‚
> >> β”‚ β”‚ Default CPUFreq governor (performance) ---> β”‚ β”‚
> >> β”‚ β”‚ -*- 'performance' governor β”‚ β”‚
> >> β”‚ β”‚ < > 'powersave' governor β”‚ β”‚
> >> β”‚ β”‚ < > 'userspace' governor for userspace frequency scalingβ”‚ β”‚
> >> β”‚ β”‚ <*> 'ondemand' cpufreq policy governor β”‚ β”‚
> >> β”‚ β”‚ < > 'conservative' cpufreq governor β”‚ β”‚
> >> β”‚ β”‚ *** CPUFreq processor drivers *** β”‚ β”‚
> >> β”‚ β”‚ < > Processor Clocking Control interface driver β”‚ β”‚
> >> β”‚ β”‚ <*> ACPI Processor P-States driver β”‚ β”‚
> >> β”‚ β”‚ < > AMD Opteron/Athlon64 PowerNow! β”‚ β”‚
> >> β”‚ β”‚ < > Intel Enhanced SpeedStep (deprecated) β”‚ β”‚
> >> β”‚ β”‚ < > Intel Pentium 4 clock modulation
> >
> > Yes but no. Yes, those are the correct choices, but the default governor
> > should be ondemand.
>
> Or in the case of the OP who is brave enough (or silly enough?) to
> risk the long term reliability of his CPU running it with no fan,
> possibly choose powersave with a specific low clock rate as the
> default and then switch to either ondemand or conservative manually
> when he needs more performance. In a machine such as he's playing with
> I wonder if he really wants ondemand (jumps to max and then slows down
> over time) vs conservative which more slowly ramps up the clock rate
> if the job at hand takes more time.
>
> It's all a trade off of performance vs power & heat.
>
> On my 12 thread server I've played with these two and frankly don't
> see a lot of difference doing any large job. They are both a bot
> slower than running performance, but I save a lot of power (and over
> time money) using them so I'm happy.

I just checked on a Pentium 4 32bit box and I couldn't find any declaration
about cpufreq under /sys/devices/system/cpu/cpu0/

I have enabled ondemand since I first built a kernel for that machine, but it
seems to have been pegged at 3.4GHz even when the plasma thingy shows minimum
CPU load.

grep MHz /proc/cpuinfo
cpu MHz : 3401.054
cpu MHz : 3401.054

ls -la /sys/devices/system/cpu/cpu0/
total 0
drwxr-xr-x 6 root root 0 May 10 18:51 .
drwxr-xr-x 6 root root 0 May 10 18:51 ..
drwxr-xr-x 4 root root 0 May 10 21:04 cache
drwxr-xr-x 2 root root 0 May 10 21:04 microcode
drwxr-xr-x 2 root root 0 May 10 21:04 thermal_throttle
drwxr-xr-x 2 root root 0 May 10 21:04 topology

cat /proc/cpuinfo
processor : 0
vendor_id : GenuineIntel
cpu family : 15
model : 3
model name : Intel(R) Pentium(R) 4 CPU 3.40GHz
stepping : 4
cpu MHz : 3401.054
cache size : 1024 KB
physical id : 0
siblings : 2
core id : 0
cpu cores : 1
apicid : 0
initial apicid : 0
fdiv_bug : no
hlt_bug : no
f00f_bug : no
coma_bug : no
fpu : yes
fpu_exception : yes
cpuid level : 5
wp : yes
flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov
pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe constant_tsc pebs
bts pni dtes64 monitor ds_cpl cid xtpr
bogomips : 6802.10
clflush size : 64
cache_alignment : 128
address sizes : 36 bits physical, 32 bits virtual
power management:

Same with the other virtual core, "power management" is blank.


Am I missing something in my kernel or is my MoBo/CPU feature poor?

cat .config | grep CPU_FREQ
CONFIG_CPU_FREQ=y
CONFIG_CPU_FREQ_TABLE=y
# CONFIG_CPU_FREQ_DEBUG is not set
CONFIG_CPU_FREQ_STAT=y
CONFIG_CPU_FREQ_STAT_DETAILS=y
# CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE is not set
# CONFIG_CPU_FREQ_DEFAULT_GOV_USERSPACE is not set
CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y
# CONFIG_CPU_FREQ_DEFAULT_GOV_CONSERVATIVE is not set
CONFIG_CPU_FREQ_GOV_PERFORMANCE=y
# CONFIG_CPU_FREQ_GOV_POWERSAVE is not set
CONFIG_CPU_FREQ_GOV_USERSPACE=y
CONFIG_CPU_FREQ_GOV_ONDEMAND=y
# CONFIG_CPU_FREQ_GOV_CONSERVATIVE is not set
--
Regards,
Mick
 
Old 05-10-2011, 08:36 PM
Bill Longman
 
Default Check CPU for throttling

On 05/10/2011 01:30 PM, Mick wrote:
> Same with the other virtual core, "power management" is blank.
>
>
> Am I missing something in my kernel or is my MoBo/CPU feature poor?
>
> cat .config | grep CPU_FREQ
> CONFIG_CPU_FREQ=y
> CONFIG_CPU_FREQ_TABLE=y
> # CONFIG_CPU_FREQ_DEBUG is not set
> CONFIG_CPU_FREQ_STAT=y
> CONFIG_CPU_FREQ_STAT_DETAILS=y
> # CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE is not set
> # CONFIG_CPU_FREQ_DEFAULT_GOV_USERSPACE is not set
> CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y
> # CONFIG_CPU_FREQ_DEFAULT_GOV_CONSERVATIVE is not set
> CONFIG_CPU_FREQ_GOV_PERFORMANCE=y
> # CONFIG_CPU_FREQ_GOV_POWERSAVE is not set
> CONFIG_CPU_FREQ_GOV_USERSPACE=y
> CONFIG_CPU_FREQ_GOV_ONDEMAND=y
> # CONFIG_CPU_FREQ_GOV_CONSERVATIVE is not set

It usually comes down to capabilities in your BIOS, Mick. My P4 won't do
it either, but that's on a Dell server from 2004. No BIOS support. And
the CPU can do HT but the BIOS is stupid, too. I still have only one
CPU/thread.
 

Thread Tools




All times are GMT. The time now is 02:32 PM.

VBulletin, Copyright ©2000 - 2014, Jelsoft Enterprises Ltd.
Content Relevant URLs by vBSEO ©2007, Crawlability, Inc.
Copyright ©2007 - 2008, www.linux-archive.org