From: Lukasz Luba <l.luba@partner.samsung.com>
To: Thara Gopinath <thara.gopinath@linaro.org>, linux-kernel@vger.kernel.org
Cc: mingo@redhat.com, peterz@infradead.org, rui.zhang@intel.com,
gregkh@linuxfoundation.org, rafael@kernel.org,
amit.kachhap@gmail.com, viresh.kumar@linaro.org,
javi.merino@kernel.org, edubezval@gmail.com,
daniel.lezcano@linaro.org, linux-pm@vger.kernel.org,
quentin.perret@arm.com, ionela.voinescu@arm.com,
vincent.guittot@linaro.org,
Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
Subject: Re: [RFC PATCH 0/7] Introduce thermal pressure
Date: Thu, 11 Oct 2018 13:10:23 +0200 [thread overview]
Message-ID: <20181011111025eucas1p2125db99d798a60a8e38da97c2a1c7436~ciWHHd0YW0102601026eucas1p2b@eucas1p2.samsung.com> (raw)
In-Reply-To: <5BBE3751.7000908@linaro.org>
On 10/10/2018 07:30 PM, Thara Gopinath wrote:
> Hello Lukasz,
>
> On 10/10/2018 11:35 AM, Lukasz Luba wrote:
>> Hi Thara,
>>
>> I have run it on Exynos5433 mainline.
>> When it is enabled with step_wise thermal governor,
>> some of my tests are showing ~30-50% regression (i.e. hackbench),
>> dhrystone ~10%.
>
> That is interesting. If I understand correctly, dhrystone spawns 16
> threads or so and floods the system. In "theory", such a test should not
> see any performance improvement and degradation. What is the thermal
> activity like in your system? I will try running one of these tests on
> hikey960.
I use this dhrystone implementation:
https://github.com/Keith-S-Thompson/dhrystone/blob/master/v2.2/dry.c
It does not span new threads/processes and I pinned it to a single cpu.
My thermal setup is probably different than yours.
You have (on hikey960) probably 1 sensor for whole SoC and one thermal
zone (if it is this mainline file:
arch/arm64/boot/dts/hisilicon/hi3660.dtsi).
This thermal zone has two cooling devices - two clusters with dvfs.
Your temperature signal read out from that sensor is probably much
smoother. When you have sensor inside cluster, the rising factor
can be even 20deg/s (for big cores).
In my case, there are 4 thermal zones, each cluster has it's private
sensor and thermal zone. There is no 'SoC sensor' or 'PCB sensor',
which is recommended for IPA.
>>
>> Could you tell me which thermal governor was used in your case?
>> Please also share the name of that benchmark, i will give it a try.
>> Is it single threaded compute-intensive?
>
> Step-wise governor.
> I use aobench which is part of phoronix-test-suite.
>
> Regards
> Thara
>
I have built this aobench and run it pinned to single big cpu:
time taskset -c 4 ./aobench
The results:
3min-5:30min [mainline]
5:15min-5:50min [+patchset]
The idea is definitely worth to investigate further.
Regards,
Lukasz
next prev parent reply other threads:[~2018-10-11 11:10 UTC|newest]
Thread overview: 67+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <CGME20181009162509epcas1p4fdd2e23039caa24586a4a52c6d2e7336@epcas1p4.samsung.com>
2018-10-09 16:24 ` [RFC PATCH 0/7] Introduce thermal pressure Thara Gopinath
2018-10-09 16:24 ` [RFC PATCH 1/7] sched/pelt.c: Add option to make load and util calculations frequency invariant Thara Gopinath
2018-10-09 16:24 ` [RFC PATCH 2/7] sched/pelt.c: Add support to track thermal pressure Thara Gopinath
2018-10-09 16:24 ` [RFC PATCH 3/7] sched: Add infrastructure to store and update instantaneous " Thara Gopinath
2018-10-09 16:24 ` [RFC PATCH 4/7] sched: Initialize per cpu thermal pressure structure Thara Gopinath
2018-10-09 16:25 ` [RFC PATCH 5/7] sched/fair: Enable CFS periodic tick to update thermal pressure Thara Gopinath
2018-12-04 15:43 ` Vincent Guittot
2018-10-09 16:25 ` [RFC PATCH 6/7] sched/fair: update cpu_capcity to reflect " Thara Gopinath
2018-10-10 5:57 ` Javi Merino
2018-10-10 14:22 ` Thara Gopinath
2018-10-09 16:25 ` [RFC PATCH 7/7] thermal/cpu-cooling: Update thermal pressure in case of a maximum frequency capping Thara Gopinath
2018-10-10 5:44 ` [RFC PATCH 0/7] Introduce thermal pressure Javi Merino
2018-10-10 14:15 ` Thara Gopinath
2018-10-10 6:17 ` Ingo Molnar
2018-10-10 8:29 ` Quentin Perret
2018-10-10 8:50 ` Vincent Guittot
2018-10-10 9:55 ` Quentin Perret
2018-10-10 10:14 ` Vincent Guittot
2018-10-10 10:36 ` Quentin Perret
2018-10-10 12:04 ` Vincent Guittot
2018-10-10 12:23 ` Juri Lelli
2018-10-10 12:34 ` Vincent Guittot
2018-10-10 12:50 ` Juri Lelli
2018-10-10 13:08 ` Vincent Guittot
2018-10-10 13:34 ` Juri Lelli
2018-10-10 13:38 ` Vincent Guittot
2018-10-10 17:08 ` Thara Gopinath
2018-10-10 13:11 ` Quentin Perret
2018-10-10 13:05 ` Quentin Perret
2018-10-10 13:27 ` Vincent Guittot
2018-10-10 13:47 ` Quentin Perret
2018-10-10 15:19 ` Vincent Guittot
2018-10-10 16:15 ` Ionela Voinescu
2018-10-10 17:03 ` Thara Gopinath
2018-10-10 15:43 ` Thara Gopinath
2018-10-16 7:33 ` Ingo Molnar
2018-10-16 9:28 ` Lukasz Luba
2018-10-17 16:21 ` Thara Gopinath
2018-10-18 6:48 ` Ingo Molnar
2018-10-18 7:08 ` Rafael J. Wysocki
2018-10-18 7:50 ` Ingo Molnar
2018-10-18 8:14 ` Rafael J. Wysocki
2018-10-18 9:35 ` [PATCH 1/2] sched/cpufreq: Reorganize the cpufreq files Daniel Lezcano
2018-10-18 9:35 ` [PATCH 2/2] sched/cpufreq: Add the SPDX tags Daniel Lezcano
2018-10-18 9:42 ` [PATCH 1/2] sched/cpufreq: Reorganize the cpufreq files Rafael J. Wysocki
2018-10-18 9:54 ` Daniel Lezcano
2018-10-18 10:06 ` Rafael J. Wysocki
2018-10-18 10:13 ` Daniel Lezcano
2018-10-18 9:45 ` Daniel Lezcano
2018-10-19 5:24 ` kbuild test robot
2018-10-19 5:52 ` kbuild test robot
2018-10-18 9:44 ` [PATCH V2 " Daniel Lezcano
2018-10-18 9:44 ` [PATCH V2 2/2] sched/cpufreq: Add the SPDX tags Daniel Lezcano
2018-10-18 16:17 ` [RFC PATCH 0/7] Introduce thermal pressure Thara Gopinath
2018-10-19 8:02 ` Ingo Molnar
2018-10-19 11:29 ` Valentin Schneider
2018-10-10 15:35 ` Lukasz Luba
2018-10-10 16:54 ` Daniel Lezcano
2018-10-11 7:35 ` Lukasz Luba
2018-10-11 8:23 ` Daniel Lezcano
2018-10-12 9:37 ` Lukasz Luba
2018-10-10 17:30 ` Thara Gopinath
2018-10-11 11:10 ` Lukasz Luba [this message]
2018-10-16 17:11 ` Vincent Guittot
2018-10-17 16:24 ` Thara Gopinath
2018-10-18 8:00 ` Lukasz Luba
2018-10-18 8:12 ` Lukasz Luba
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='20181011111025eucas1p2125db99d798a60a8e38da97c2a1c7436~ciWHHd0YW0102601026eucas1p2b@eucas1p2.samsung.com' \
--to=l.luba@partner.samsung.com \
--cc=amit.kachhap@gmail.com \
--cc=b.zolnierkie@samsung.com \
--cc=daniel.lezcano@linaro.org \
--cc=edubezval@gmail.com \
--cc=gregkh@linuxfoundation.org \
--cc=ionela.voinescu@arm.com \
--cc=javi.merino@kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-pm@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=peterz@infradead.org \
--cc=quentin.perret@arm.com \
--cc=rafael@kernel.org \
--cc=rui.zhang@intel.com \
--cc=thara.gopinath@linaro.org \
--cc=vincent.guittot@linaro.org \
--cc=viresh.kumar@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).