Skip to contentSkip to conversation

starting governor ondemand failed

DISCUSSION Ivor Hewitt 2 participants 4 messages Apr 4, 2005

lore
Share & tools
lore
#0 lore raw

Hi,
I was trying to have a play with the ondemand governor but I just get the following logged when I try to switch to it:-

cpufreq-core: governor switch
cpufreq-core: __cpufreq_governor for CPU 0, event 2
userspace: managing cpu 0 stopped
cpufreq-core: __cpufreq_governor for CPU 0, event 1
cpufreq-core: starting governor ondemand failed
cpufreq-core: __cpufreq_governor for CPU 0, event 1

This is on a PIIIM using the speedstep-smi interface.
The cpu is only capable of switching between two frequencies, would this prevent ondemand starting up?

Regards,

Signature · 2 lines
Ivor
http://www.ivor.it
#1 lore raw
Quoted 11 lines · Ivor Hewitt

Hi,
I was trying to have a play with the ondemand governor but I just get the following logged when I try to switch to it:-

cpufreq-core: governor switch
cpufreq-core: __cpufreq_governor for CPU 0, event 2
userspace: managing cpu 0 stopped
cpufreq-core: __cpufreq_governor for CPU 0, event 1
cpufreq-core: starting governor ondemand failed
cpufreq-core: __cpufreq_governor for CPU 0, event 1

Quoted 3 lines

This is on a PIIIM using the speedstep-smi interface.
The cpu is only capable of switching between two frequencies, would this prevent ondemand starting up?

This isn't the problem, but the following: we do not know how long transitions using speedstep-smi take, therefore we still need to assume that it takes very long, thus making it unable to be used for ondemand frequency switching.

Dominik

#2 lore raw
Quoted 12 lines · Dominik Brodowski
Quoted 10 lines · Ivor Hewitt

Hi,
I was trying to have a play with the ondemand governor but I just get the following logged when I try to switch to it:-

cpufreq-core: governor switch
cpufreq-core: __cpufreq_governor for CPU 0, event 2
userspace: managing cpu 0 stopped
cpufreq-core: __cpufreq_governor for CPU 0, event 1
cpufreq-core: starting governor ondemand failed
cpufreq-core: __cpufreq_governor for CPU 0, event 1

Quoted 7 lines
Quoted 2 lines

This is on a PIIIM using the speedstep-smi interface.
The cpu is only capable of switching between two frequencies, would this prevent ondemand starting up?

This isn't the problem, but the following: we do not know how long transitions using speedstep-smi take, therefore we still need to assume that it takes very long, thus making it unable to be used for ondemand
frequency switching.

Hi,
I'll stick to to cpufreqd then. :-)

Ah I see "CPUFREQ_ETERNAL".

What should be an acceptable transition time? Is it possible for me to determine my speedstep-smi transition time and enable the switching? Or are you saying that there's no way of knowing how long the smi transition would take, therefore it has to be disabled?

Many thanks,

Signature · 2 lines
Ivor
http://www.ivor.it
#3 lore raw
Quoted 22 lines · Ivor Hewitt
Quoted 12 lines · Dominik Brodowski
Quoted 10 lines · Ivor Hewitt

Hi,
I was trying to have a play with the ondemand governor but I just get the following logged when I try to switch to it:-

cpufreq-core: governor switch
cpufreq-core: __cpufreq_governor for CPU 0, event 2
userspace: managing cpu 0 stopped
cpufreq-core: __cpufreq_governor for CPU 0, event 1
cpufreq-core: starting governor ondemand failed
cpufreq-core: __cpufreq_governor for CPU 0, event 1

Quoted 8 lines
Quoted 2 lines

This is on a PIIIM using the speedstep-smi interface.
The cpu is only capable of switching between two frequencies, would this prevent ondemand starting up?

This isn't the problem, but the following: we do not know how long transitions using speedstep-smi take, therefore we still need to assume that it takes very long, thus making it unable to be used for ondemand
frequency switching.

Quoted 8 lines

Hi,
I'll stick to to cpufreqd then. :-)

Ah I see "CPUFREQ_ETERNAL".

What should be an acceptable transition time? Is it possible for me to determine my speedstep-smi transition time and enable the switching? Or are you saying that there's no way of knowing how long the smi transition would take, therefore it has to be disabled?

Ok terrible form replying to myself! :-)

Using the magic transition value of 10000 seems to behave nicely; idling along nicely, kick off a compile and it turns the dial up to '11'.

Since I only have two frequency choices does the transition time matter that much?

Cheers,

Signature · 2 lines
Ivor
http://www.ivor.it