lkml.org 
[lkml]   [2019]   [Oct]   [31]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
SubjectRe: [Patch v4 0/6] Introduce Thermal Pressure
From
Date
On 10/31/2019 05:44 AM, Ionela Voinescu wrote:
> Hi Thara,
>
> On Tuesday 22 Oct 2019 at 16:34:19 (-0400), Thara Gopinath wrote:
>> Thermal governors can respond to an overheat event of a cpu by
>> capping the cpu's maximum possible frequency. This in turn
>> means that the maximum available compute capacity of the
>> cpu is restricted. But today in the kernel, task scheduler is
>> not notified of capping of maximum frequency of a cpu.
>> In other words, scheduler is unware of maximum capacity
>
> Nit: s/unware/unaware
>
>> restrictions placed on a cpu due to thermal activity.
>> This patch series attempts to address this issue.
>> The benefits identified are better task placement among available
>> cpus in event of overheating which in turn leads to better
>> performance numbers.
>>
>> The reduction in the maximum possible capacity of a cpu due to a
>> thermal event can be considered as thermal pressure. Instantaneous
>> thermal pressure is hard to record and can sometime be erroneous
>> as there can be mismatch between the actual capping of capacity
>> and scheduler recording it. Thus solution is to have a weighted
>> average per cpu value for thermal pressure over time.
>> The weight reflects the amount of time the cpu has spent at a
>> capped maximum frequency. Since thermal pressure is recorded as
>> an average, it must be decayed periodically. Exisiting algorithm
>> in the kernel scheduler pelt framework is re-used to calculate
>> the weighted average. This patch series also defines a sysctl
>> inerface to allow for a configurable decay period.
>>
>> Regarding testing, basic build, boot and sanity testing have been
>> performed on db845c platform with debian file system.
>> Further, dhrystone and hackbench tests have been
>> run with the thermal pressure algorithm. During testing, due to
>> constraints of step wise governor in dealing with big little systems,
>> trip point 0 temperature was made assymetric between cpus in little
>> cluster and big cluster; the idea being that
>> big core will heat up and cpu cooling device will throttle the
>> frequency of the big cores faster, there by limiting the maximum available
>> capacity and the scheduler will spread out tasks to little cores as well.
>>
>
> Can you please share the changes you've made to sdm845.dtsi and a kernel
> base on top of which to apply your patches? I would like to reproduce
> your results and run more tests and it would be good if our setups were
> as close as possible.
Hi Ionela
Thank you for the review.
So I tested this on 5.4-rc1 kernel. The dtsi changes is to reduce the
thermal trip points for the big CPUs to 60000 or 70000 from the default
90000. I did this for 2 reasons
1. I could never get the db845 to heat up sufficiently for my test cases
with the default trip.
2. I was using the default step-wise governor for thermal. I did not
want little and big to start throttling by the same % because then the
task placement ratio will remain the same between little and big cores.


>
>> Test Results
>>
>> Hackbench: 1 group , 30000 loops, 10 runs
>> Result SD
>> (Secs) (% of mean)
>> No Thermal Pressure 14.03 2.69%
>> Thermal Pressure PELT Algo. Decay : 32 ms 13.29 0.56%
>> Thermal Pressure PELT Algo. Decay : 64 ms 12.57 1.56%
>> Thermal Pressure PELT Algo. Decay : 128 ms 12.71 1.04%
>> Thermal Pressure PELT Algo. Decay : 256 ms 12.29 1.42%
>> Thermal Pressure PELT Algo. Decay : 512 ms 12.42 1.15%
>>
>> Dhrystone Run Time : 20 threads, 3000 MLOOPS
>> Result SD
>> (Secs) (% of mean)
>> No Thermal Pressure 9.452 4.49%
>> Thermal Pressure PELT Algo. Decay : 32 ms 8.793 5.30%
>> Thermal Pressure PELT Algo. Decay : 64 ms 8.981 5.29%
>> Thermal Pressure PELT Algo. Decay : 128 ms 8.647 6.62%
>> Thermal Pressure PELT Algo. Decay : 256 ms 8.774 6.45%
>> Thermal Pressure PELT Algo. Decay : 512 ms 8.603 5.41%
>>
>
> Do you happen to know by how much the CPUs were capped during these
> experiments?

I don't have any captured results here. I know that big cores were
capped and at times there was capacity inversion.

Also I will fix the nit comments above.

>
> Thanks,
> Ionela.
>



--
Warm Regards
Thara

\
 
 \ /
  Last update: 2019-10-31 17:41    [W:0.353 / U:1.332 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site