From: Kajetan Puchalski <kajetan.puchalski@arm.com>
To: Peter Zijlstra <peterz@infradead.org>
Cc: Jian-Min Liu <jian-min.liu@mediatek.com>,
Dietmar Eggemann <dietmar.eggemann@arm.com>,
Ingo Molnar <mingo@kernel.org>,
Vincent Guittot <vincent.guittot@linaro.org>,
Morten Rasmussen <morten.rasmussen@arm.com>,
Vincent Donnefort <vdonnefort@google.com>,
Quentin Perret <qperret@google.com>,
Patrick Bellasi <patrick.bellasi@matbug.net>,
Abhijeet Dharmapurikar <adharmap@quicinc.com>,
Qais Yousef <qais.yousef@arm.com>,
linux-kernel@vger.kernel.org,
Jonathan JMChen <jonathan.jmchen@mediatek.com>
Subject: Re: [RFC PATCH 0/1] sched/pelt: Change PELT halflife at runtime
Date: Thu, 29 Sep 2022 15:41:47 +0100 [thread overview]
Message-ID: <YzWuq5ShtJC6KWqe@e126311.manchester.arm.com> (raw)
In-Reply-To: <YzV/yT6OYMgaq0kD@hirez.programming.kicks-ass.net>
On Thu, Sep 29, 2022 at 01:21:45PM +0200, Peter Zijlstra wrote:
> On Thu, Sep 29, 2022 at 12:10:17PM +0100, Kajetan Puchalski wrote:
>
> > Overall, the problem being solved here is that based on our testing the
> > PELT half life can occasionally be too slow to keep up in scenarios
> > where many frames need to be rendered quickly, especially on high-refresh
> > rate phones and similar devices.
>
> But it is a problem of DVFS not ramping up quick enough; or of the
> load-balancer not reacting to the increase in load, or what aspect
> controlled by PELT is responsible for the improvement seen?
Based on all the tests we've seen, jankbench or otherwise, the
improvement can mainly be attributed to the faster ramp up of frequency
caused by the shorter PELT window while using schedutil. Alongside that
the signals rising faster also mean that the task would get migrated
faster to bigger CPUs on big.LITTLE systems which improves things too
but it's mostly the frequency aspect of it.
To establish that this benchmark is sensitive to frequency I ran some
tests using the 'performance' cpufreq governor.
Max frame duration (ms)
+------------------+-------------+----------+
| kernel | iteration | value |
|------------------+-------------+----------|
| pelt_1 | 10 | 157.426 |
| pelt_4 | 10 | 85.2713 |
| performance | 10 | 40.9308 |
+------------------+-------------+----------+
Mean frame duration (ms)
+---------------+------------------+---------+-------------+
| variable | kernel | value | perc_diff |
|---------------+------------------+---------+-------------|
| mean_duration | pelt_1 | 14.6 | 0.0% |
| mean_duration | pelt_4 | 14.5 | -0.58% |
| mean_duration | performance | 4.4 | -69.75% |
+---------------+------------------+---------+-------------+
Jank percentage
+------------+------------------+---------+-------------+
| variable | kernel | value | perc_diff |
|------------+------------------+---------+-------------|
| jank_perc | pelt_1 | 2.1 | 0.0% |
| jank_perc | pelt_4 | 2 | -3.46% |
| jank_perc | performance | 0.1 | -97.25% |
+------------+------------------+---------+-------------+
As you can see, bumping up frequency can hugely improve the results
here. This is what's happening when we decrease the PELT window, just on
a much smaller and not as drastic scale. It also explains specifically
where the increased power usage is coming from.
next prev parent reply other threads:[~2022-09-29 14:42 UTC|newest]
Thread overview: 61+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-08-29 5:54 Dietmar Eggemann
2022-08-29 5:54 ` [RFC PATCH 1/1] sched/pelt: Introduce PELT multiplier Dietmar Eggemann
2022-08-29 8:08 ` Peter Zijlstra
2022-08-29 10:02 ` Peter Zijlstra
2022-08-29 10:13 ` Vincent Guittot
2022-08-29 14:23 ` Quentin Perret
2022-08-29 14:34 ` Peter Zijlstra
2022-08-29 15:31 ` Quentin Perret
2022-08-29 15:48 ` Quentin Perret
2022-09-02 7:53 ` Dietmar Eggemann
2022-09-02 8:45 ` Peter Zijlstra
2022-09-06 5:49 ` Vincent Guittot
2022-09-08 6:50 ` Dietmar Eggemann
2022-09-02 7:53 ` Dietmar Eggemann
2022-09-02 8:45 ` Peter Zijlstra
2022-09-20 14:07 ` [RFC PATCH 0/1] sched/pelt: Change PELT halflife at runtime Jian-Min Liu
2022-09-28 17:09 ` Dietmar Eggemann
2022-09-29 9:47 ` Peter Zijlstra
2022-09-29 11:07 ` Dietmar Eggemann
2022-09-29 11:10 ` Kajetan Puchalski
2022-09-29 11:21 ` Peter Zijlstra
2022-09-29 14:41 ` Kajetan Puchalski [this message]
2022-10-03 22:57 ` Wei Wang
2022-10-04 9:33 ` Dietmar Eggemann
2022-10-05 16:57 ` Wei Wang
2022-11-07 13:41 ` Peter Zijlstra
2022-11-08 19:48 ` Qais Yousef
2022-11-09 15:49 ` Peter Zijlstra
2022-11-10 13:25 ` Qais Yousef
2023-02-07 10:29 ` Dietmar Eggemann
2023-02-09 16:16 ` Vincent Guittot
2023-02-17 13:54 ` Dietmar Eggemann
2023-02-20 13:54 ` Vincent Guittot
2023-02-21 9:29 ` Vincent Guittot
2023-02-22 20:28 ` Dietmar Eggemann
2023-03-01 10:24 ` Vincent Guittot
2023-02-22 20:13 ` Dietmar Eggemann
2023-03-02 19:36 ` Dietmar Eggemann
2023-02-20 10:13 ` Peter Zijlstra
2023-02-20 13:39 ` Vincent Guittot
2023-02-23 15:37 ` Qais Yousef
2023-03-01 10:39 ` Vincent Guittot
2023-03-01 17:24 ` Qais Yousef
2023-03-02 8:00 ` Vincent Guittot
2023-03-02 19:39 ` Dietmar Eggemann
2023-03-06 19:11 ` Qais Yousef
2023-03-07 13:22 ` Vincent Guittot
2023-03-11 16:55 ` Qais Yousef
2023-03-23 16:29 ` Dietmar Eggemann
2023-04-03 14:45 ` Qais Yousef
2023-04-06 15:58 ` Dietmar Eggemann
2023-04-11 17:51 ` Qais Yousef
2022-11-09 15:18 ` Lukasz Luba
2022-11-10 11:16 ` Dietmar Eggemann
2022-11-10 13:05 ` Peter Zijlstra
2022-11-10 14:59 ` Dietmar Eggemann
2022-11-10 17:51 ` Peter Zijlstra
2022-11-30 18:14 ` Dietmar Eggemann
2022-12-01 13:37 ` Kajetan Puchalski
2022-11-10 12:45 ` Kajetan Puchalski
2022-11-07 9:41 ` Jian-Min Liu (劉建旻)
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=YzWuq5ShtJC6KWqe@e126311.manchester.arm.com \
--to=kajetan.puchalski@arm.com \
--cc=adharmap@quicinc.com \
--cc=dietmar.eggemann@arm.com \
--cc=jian-min.liu@mediatek.com \
--cc=jonathan.jmchen@mediatek.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@kernel.org \
--cc=morten.rasmussen@arm.com \
--cc=patrick.bellasi@matbug.net \
--cc=peterz@infradead.org \
--cc=qais.yousef@arm.com \
--cc=qperret@google.com \
--cc=vdonnefort@google.com \
--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
all inboxes | Powered by JetHome®