From: Daniel Lezcano <daniel.lezcano@linaro.org>
To: Ionela Voinescu <ionela.voinescu@arm.com>
Cc: Thara Gopinath <thara.gopinath@linaro.org>,
mingo@redhat.com, peterz@infradead.org,
vincent.guittot@linaro.org, rui.zhang@intel.com,
edubezval@gmail.com, qperret@google.com,
linux-kernel@vger.kernel.org, amit.kachhap@gmail.com,
javi.merino@kernel.org
Subject: Re: [Patch v4 0/6] Introduce Thermal Pressure
Date: Thu, 31 Oct 2019 12:54:03 +0100 [thread overview]
Message-ID: <2009bac3-405a-c60e-a1dd-191625ff3fc5@linaro.org> (raw)
In-Reply-To: <20191031100631.GC19197@e108754-lin>
Hi Ionela,
On 31/10/2019 11:07, Ionela Voinescu wrote:
> Hi Daniel,
>
> On Tuesday 29 Oct 2019 at 16:34:11 (+0100), Daniel Lezcano wrote:
>> Hi Thara,
>>
>> On 22/10/2019 22:34, 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
>>> 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.
>>>
>>> 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%
>>
>> I took the opportunity to try glmark2 on the db845c platform with the
>> default decay and got the following glmark2 scores:
>>
>> Without thermal pressure:
>>
>> # NumSamples = 9; Min = 790.00; Max = 805.00
>> # Mean = 794.888889; Variance = 19.209877; SD = 4.382907; Median 794.000000
>> # each ∎ represents a count of 1
>> 790.0000 - 791.5000 [ 2]: ∎∎
>> 791.5000 - 793.0000 [ 2]: ∎∎
>> 793.0000 - 794.5000 [ 2]: ∎∎
>> 794.5000 - 796.0000 [ 1]: ∎
>> 796.0000 - 797.5000 [ 0]:
>> 797.5000 - 799.0000 [ 1]: ∎
>> 799.0000 - 800.5000 [ 0]:
>> 800.5000 - 802.0000 [ 0]:
>> 802.0000 - 803.5000 [ 0]:
>> 803.5000 - 805.0000 [ 1]: ∎
>>
>>
>> With thermal pressure:
>>
>> # NumSamples = 9; Min = 933.00; Max = 960.00
>> # Mean = 940.777778; Variance = 64.172840; SD = 8.010795; Median 937.000000
>> # each ∎ represents a count of 1
>> 933.0000 - 935.7000 [ 3]: ∎∎∎
>> 935.7000 - 938.4000 [ 2]: ∎∎
>> 938.4000 - 941.1000 [ 2]: ∎∎
>> 941.1000 - 943.8000 [ 0]:
>> 943.8000 - 946.5000 [ 0]:
>> 946.5000 - 949.2000 [ 1]: ∎
>> 949.2000 - 951.9000 [ 0]:
>> 951.9000 - 954.6000 [ 0]:
>> 954.6000 - 957.3000 [ 0]:
>> 957.3000 - 960.0000 [ 1]: ∎
>>
>
> Interesting! If I'm interpreting these correctly there seems to be
> significant improvement when applying thermal pressure.
>
> I'm not familiar with glmark2, can you tell me more about the process
> and the work that the benchmark does?
glmark2 is a 3D benchmark. I ran it without parameters, so all tests are
run. At the end, it gives a score which are the values given above.
> I assume this is a GPU benchmark,
> but not knowing more about it I fail to see the correlation between
> applying thermal pressure to CPU capacities and the improvement of GPU
> performance.
> Do you happen to know more about the behaviour that resulted in these
> benchmark scores?
My hypothesis is glmark2 makes the GPU to contribute a lot to the
heating effect, thus increasing the temperature to the CPU close to it.
--
<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
next prev parent reply other threads:[~2019-10-31 11:54 UTC|newest]
Thread overview: 51+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-10-22 20:34 [Patch v4 0/6] Introduce Thermal Pressure Thara Gopinath
2019-10-22 20:34 ` [Patch v4 1/6] sched/pelt.c: Add support to track thermal pressure Thara Gopinath
2019-10-31 9:47 ` Ionela Voinescu
2019-10-22 20:34 ` [Patch v4 2/6] sched: Add infrastructure to store and update instantaneous " Thara Gopinath
2019-10-28 15:21 ` Peter Zijlstra
2019-10-30 21:37 ` Thara Gopinath
2019-11-01 12:17 ` Dietmar Eggemann
2019-11-01 20:57 ` Thara Gopinath
2019-11-04 17:29 ` Dietmar Eggemann
2019-11-04 17:34 ` Vincent Guittot
2019-11-04 17:41 ` Dietmar Eggemann
2019-11-04 17:48 ` Vincent Guittot
2019-10-22 20:34 ` [Patch v4 3/6] sched/fair: Enable CFS periodic tick to update " Thara Gopinath
2019-10-28 15:24 ` Peter Zijlstra
2019-10-28 15:27 ` Peter Zijlstra
2019-10-30 21:41 ` Thara Gopinath
2019-10-31 16:11 ` Dietmar Eggemann
2019-10-31 16:46 ` Thara Gopinath
2019-10-22 20:34 ` [Patch v4 4/6] sched/fair: update cpu_capcity to reflect " Thara Gopinath
2019-10-23 12:28 ` Qais Yousef
2019-10-28 15:30 ` Peter Zijlstra
2019-10-31 10:53 ` Qais Yousef
2019-10-31 15:38 ` Dietmar Eggemann
2019-10-31 15:48 ` Vincent Guittot
2019-10-31 16:17 ` Dietmar Eggemann
2019-10-31 16:31 ` Vincent Guittot
2019-10-31 16:44 ` Dietmar Eggemann
2019-10-31 16:03 ` Thara Gopinath
2019-10-31 16:56 ` Qais Yousef
2019-10-22 20:34 ` [Patch v4 5/6] thermal/cpu-cooling: Update thermal pressure in case of a maximum frequency capping Thara Gopinath
2019-10-28 15:33 ` Peter Zijlstra
2019-10-31 16:29 ` Dietmar Eggemann
2019-10-31 16:38 ` Vincent Guittot
2019-11-01 15:47 ` Ionela Voinescu
2019-11-01 21:04 ` Thara Gopinath
2019-11-04 14:41 ` Ionela Voinescu
2019-10-31 16:46 ` Thara Gopinath
2019-10-22 20:34 ` [Patch v4 6/6] sched: thermal: Enable tuning of decay period Thara Gopinath
2019-10-28 15:42 ` Peter Zijlstra
2019-11-04 16:12 ` Ionela Voinescu
2019-11-05 20:26 ` Thara Gopinath
2019-11-05 21:29 ` Ionela Voinescu
2019-10-29 15:34 ` [Patch v4 0/6] Introduce Thermal Pressure Daniel Lezcano
2019-10-31 10:07 ` Ionela Voinescu
2019-10-31 11:54 ` Daniel Lezcano [this message]
2019-10-31 12:57 ` Ionela Voinescu
2019-10-31 17:48 ` Daniel Lezcano
2019-10-31 9:44 ` Ionela Voinescu
2019-10-31 16:41 ` Thara Gopinath
2019-10-31 16:52 ` Thara Gopinath
2019-11-05 21:04 ` Ionela Voinescu
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=2009bac3-405a-c60e-a1dd-191625ff3fc5@linaro.org \
--to=daniel.lezcano@linaro.org \
--cc=amit.kachhap@gmail.com \
--cc=edubezval@gmail.com \
--cc=ionela.voinescu@arm.com \
--cc=javi.merino@kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=peterz@infradead.org \
--cc=qperret@google.com \
--cc=rui.zhang@intel.com \
--cc=thara.gopinath@linaro.org \
--cc=vincent.guittot@linaro.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).