[RFD] Add debugfs for cpuidle ?

[RFD] Add debugfs for cpuidle ?

[Daniel Lezcano]

Hi all,

would it be interesting to add debugfs metrics for cpuidle in order to
read some statistics from there and investigate the behavior ?



-- 
 <http://www.linaro.org/> Linaro.org │ Open source software for ARM SoCs

Follow Linaro:  <http://www.facebook.com/pages/Linaro> Facebook |
<http://twitter.com/#!/linaroorg> Twitter |
<http://www.linaro.org/linaro-blog/> Blog

Re: [RFD] Add debugfs for cpuidle ?

[Rafael J. Wysocki]

On Thursday, May 24, 2018 10:14:31 AM CEST Daniel Lezcano wrote:
> 
> Hi all,

Hi,

> would it be interesting to add debugfs metrics for cpuidle in order to
> read some statistics from there and investigate the behavior ?

What exactly would you like to see in there?

Re: [RFD] Add debugfs for cpuidle ?

[Daniel Lezcano]

On 24/05/2018 10:28, Rafael J. Wysocki wrote:
> On Thursday, May 24, 2018 10:14:31 AM CEST Daniel Lezcano wrote:
>> 
>> Hi all,
> 
> Hi,
> 
>> would it be interesting to add debugfs metrics for cpuidle in order
>> to read some statistics from there and investigate the behavior ?
> 
> What exactly would you like to see in there?

It could be interesting to have statistics on a per cpu and global basis
for:

- prediction accuracy:

/sys/kernel/debug/cpuidle/prediction/[good|over|under]
/sys/kernel/debug/cpuidle/cpu*/state*/prediction/[good|over|under]

 - exit latency

In addition, it is often the case the idle states values are dropped
randomly, it is interesting to see the average exit latency for the
states. That could give also an indication the cluster idle state success.

/sys/kernel/debug/cpuidle/state*/latency/[min|max|avg|stddev]
/sys/kernel/debug/cpuidle/cpu*/state*/prediction/[min|max|avg|stddev]

And perhaps more information like the tick stopped stat ?



-- 
 <http://www.linaro.org/> Linaro.org │ Open source software for ARM SoCs

Follow Linaro:  <http://www.facebook.com/pages/Linaro> Facebook |
<http://twitter.com/#!/linaroorg> Twitter |
<http://www.linaro.org/linaro-blog/> Blog

Re: [RFD] Add debugfs for cpuidle ?

[Rafael J. Wysocki]

On Thursday, May 24, 2018 10:47:54 AM CEST Daniel Lezcano wrote:
> On 24/05/2018 10:28, Rafael J. Wysocki wrote:
> > On Thursday, May 24, 2018 10:14:31 AM CEST Daniel Lezcano wrote:
> >> 
> >> Hi all,
> > 
> > Hi,
> > 
> >> would it be interesting to add debugfs metrics for cpuidle in order
> >> to read some statistics from there and investigate the behavior ?
> > 
> > What exactly would you like to see in there?
> 
> It could be interesting to have statistics on a per cpu and global basis
> for:
> 
> - prediction accuracy:
> 
> /sys/kernel/debug/cpuidle/prediction/[good|over|under]
> /sys/kernel/debug/cpuidle/cpu*/state*/prediction/[good|over|under]
> 
>  - exit latency
> 
> In addition, it is often the case the idle states values are dropped
> randomly, it is interesting to see the average exit latency for the
> states. That could give also an indication the cluster idle state success.
> 
> /sys/kernel/debug/cpuidle/state*/latency/[min|max|avg|stddev]
> /sys/kernel/debug/cpuidle/cpu*/state*/prediction/[min|max|avg|stddev]
> 
> And perhaps more information like the tick stopped stat ?

Fair enough, but that must be minimum overhead.

Re: [RFD] Add debugfs for cpuidle ?

[Ulf Hansson]

On 24 May 2018 at 10:47, Daniel Lezcano <daniel.lezcano@linaro.org> wrote:
> On 24/05/2018 10:28, Rafael J. Wysocki wrote:
>> On Thursday, May 24, 2018 10:14:31 AM CEST Daniel Lezcano wrote:
>>>
>>> Hi all,
>>
>> Hi,
>>
>>> would it be interesting to add debugfs metrics for cpuidle in order
>>> to read some statistics from there and investigate the behavior ?
>>
>> What exactly would you like to see in there?
>
> It could be interesting to have statistics on a per cpu and global basis
> for:
>
> - prediction accuracy:
>
> /sys/kernel/debug/cpuidle/prediction/[good|over|under]
> /sys/kernel/debug/cpuidle/cpu*/state*/prediction/[good|over|under]
>
>  - exit latency
>
> In addition, it is often the case the idle states values are dropped
> randomly, it is interesting to see the average exit latency for the
> states. That could give also an indication the cluster idle state success.
>
> /sys/kernel/debug/cpuidle/state*/latency/[min|max|avg|stddev]
> /sys/kernel/debug/cpuidle/cpu*/state*/prediction/[min|max|avg|stddev]
>
> And perhaps more information like the tick stopped stat ?
>

Daniel,

Any chance that you have some draft version of actual code implementing this?

I would be very interested to try then - or help out to implement
this, in case you haven't started yet.

Kind regards
Uffe

Re: [RFD] Add debugfs for cpuidle ?

[Daniel Lezcano]

On 30/08/2018 10:22, Ulf Hansson wrote:
> On 24 May 2018 at 10:47, Daniel Lezcano <daniel.lezcano@linaro.org> wrote:
>> On 24/05/2018 10:28, Rafael J. Wysocki wrote:
>>> On Thursday, May 24, 2018 10:14:31 AM CEST Daniel Lezcano wrote:
>>>>
>>>> Hi all,
>>>
>>> Hi,
>>>
>>>> would it be interesting to add debugfs metrics for cpuidle in order
>>>> to read some statistics from there and investigate the behavior ?
>>>
>>> What exactly would you like to see in there?
>>
>> It could be interesting to have statistics on a per cpu and global basis
>> for:
>>
>> - prediction accuracy:
>>
>> /sys/kernel/debug/cpuidle/prediction/[good|over|under]
>> /sys/kernel/debug/cpuidle/cpu*/state*/prediction/[good|over|under]
>>
>>  - exit latency
>>
>> In addition, it is often the case the idle states values are dropped
>> randomly, it is interesting to see the average exit latency for the
>> states. That could give also an indication the cluster idle state success.
>>
>> /sys/kernel/debug/cpuidle/state*/latency/[min|max|avg|stddev]
>> /sys/kernel/debug/cpuidle/cpu*/state*/prediction/[min|max|avg|stddev]
>>
>> And perhaps more information like the tick stopped stat ?
>>
> 
> Daniel,
> 
> Any chance that you have some draft version of actual code implementing this?
> 
> I would be very interested to try then - or help out to implement
> this, in case you haven't started yet.

Yes, I have a draft version, a bit incomplete but easy to fill. I'm just
not fully convinced about the metrics we need yet.


-- 
 <http://www.linaro.org/> Linaro.org │ Open source software for ARM SoCs

Follow Linaro:  <http://www.facebook.com/pages/Linaro> Facebook |
<http://twitter.com/#!/linaroorg> Twitter |
<http://www.linaro.org/linaro-blog/> Blog