From: Quentin Perret <quentin.perret@arm.com>
To: "Rafael J. Wysocki" <rafael@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>,
"Rafael J. Wysocki" <rjw@rjwysocki.net>,
Linux PM <linux-pm@vger.kernel.org>,
LKML <linux-kernel@vger.kernel.org>,
Viresh Kumar <viresh.kumar@linaro.org>,
Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>,
Chen Yu <yu.c.chen@intel.com>,
Gabriele Mazzotta <gabriele.mzt@gmail.com>
Subject: Re: [RFT][Update][PATCH 2/2] cpufreq: intel_pstate: Update max CPU frequency on global turbo changes
Date: Tue, 5 Mar 2019 17:37:48 +0000 [thread overview]
Message-ID: <20190305173746.p32xolcpueudlzwn@queper01-lin> (raw)
In-Reply-To: <CAJZ5v0hYU763Jx0Ku0HsNMd261z7E0PhZ88_PH6MT=OLYYUAaQ@mail.gmail.com>
On Tuesday 05 Mar 2019 at 18:02:25 (+0100), Rafael J. Wysocki wrote:
> But that 128 needs to be compared to
>
> (SCHED_CAPACITY_SCALE * cpuinfo.min_freq) / cpuinfo.max_freq
>
> so with SCHED_CAPACITY_SCALE equal to 1024 this means max_freq 8x
> higher than min_freq. That is not totally unreasonable IMO and
> because sg_cpu->iowait_boost grows exponentially, the difference
> between 8x and, say, 4x is one iteration.
>
> > The first steps will all be below the min freq, so they'll just be
> > transparent, while right now the iowait boost kicks in much faster :/
>
> There can be one iteration of a difference this way or that way AFAICS
> and I'm not even sure how much of a performance difference that makes
> in practice.
Yeah I don't expect that to have a huge impact TBH but it'd be nice to
actually get numbers to verify that, that's all I'm saying :-)
You have 'funny' platforms like Juno r0 out there where the min/max
frequencies are 450MHz/850Mhz. In this case, starting from 128 you'll
need 3 wake-ups to reach what is currently the starting point. I'm not
sure if the impact is visible or not, but it's worth checking.
> OTOH I fundamentally don't see why the iowait boost should ramp up
> faster on CPUs having a higher max_freq to min_freq ratio. Say you
> have two platforms, both with max_freq of 2 GHz and with min_freq
> equal to 250 MHz and 500 MHz, respectively. The ratios in question
> will be 8 and 4 then, so the first one will reliably react 50% slower
> to iowait than the second one for no particular reason at all.
>
> > OTOH, you also have platforms like the recent Snapdragons with 30+ OPPs,
> > and for them starting at 128 will speed things up.
> >
> > So maybe what you want is to start at max(min, 128) ?
>
> That's not just min, though, or is it?
I'm not sure to get the question, so just to make sure it's clearer, I
was suggesting to do something along the lines of:
sg_cpu->min = max(min_freq * 1024 / max_freq, 128);
That basically just prevents you from starting too low -- some boards,
unlike juno, have tons of OPPs on the lower end of the curve so these
might benefit from getting a higher starting point. But then perhaps
this is in fact a good illustration of the issue of having different
ramp-up speeds depending on the min_freq so ... :-)
Thanks,
Quentin
next prev parent reply other threads:[~2019-03-05 17:37 UTC|newest]
Thread overview: 35+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-03-01 12:43 [RFT][PATCH 0/2] cpufreq: intel_pstate: Handle _PPC updates on global turbo disable/enable Rafael J. Wysocki
2019-03-01 12:45 ` [RFT][PATCH 1/2] cpufreq: intel_pstate: Driver-specific handling of _PPC updates Rafael J. Wysocki
2019-03-01 12:47 ` [RFT][PATCH 2/2] cpufreq: intel_pstate: Update max CPU frequency on global turbo changes Rafael J. Wysocki
2019-03-01 12:57 ` [RFT][Update][PATCH " Rafael J. Wysocki
2019-03-04 14:39 ` Yu Chen
2019-03-05 10:42 ` Quentin Perret
2019-03-05 10:50 ` Rafael J. Wysocki
2019-03-05 10:58 ` Rafael J. Wysocki
2019-03-05 11:44 ` Peter Zijlstra
2019-03-05 11:52 ` Rafael J. Wysocki
2019-03-05 12:00 ` Quentin Perret
2019-03-05 12:24 ` Peter Zijlstra
2019-03-05 17:02 ` Rafael J. Wysocki
2019-03-05 17:37 ` Quentin Perret [this message]
2019-03-06 10:05 ` Rafael J. Wysocki
2019-03-07 11:02 ` Quentin Perret
2019-03-07 11:23 ` Peter Zijlstra
2019-03-07 11:49 ` Quentin Perret
2019-03-07 11:25 ` Rafael J. Wysocki
2019-03-07 11:59 ` Quentin Perret
2019-03-05 11:01 ` Quentin Perret
2019-03-01 17:39 ` [RFT][PATCH 0/2] cpufreq: intel_pstate: Handle _PPC updates on global turbo disable/enable Srinivas Pandruvada
2019-03-02 10:30 ` Yu Chen
2019-03-02 16:24 ` Srinivas Pandruvada
2019-03-03 17:03 ` Rafael J. Wysocki
2019-03-03 21:20 ` Srinivas Pandruvada
2019-03-03 21:51 ` Rafael J. Wysocki
2019-03-04 4:06 ` Srinivas Pandruvada
2019-03-04 9:41 ` Rafael J. Wysocki
2019-03-04 18:06 ` Srinivas Pandruvada
2019-03-04 21:57 ` Rafael J. Wysocki
2019-03-04 23:04 ` Srinivas Pandruvada
2019-03-05 8:40 ` Rafael J. Wysocki
2019-03-03 22:42 ` Gabriele Mazzotta
2019-03-04 9:58 ` Rafael J. Wysocki
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=20190305173746.p32xolcpueudlzwn@queper01-lin \
--to=quentin.perret@arm.com \
--cc=gabriele.mzt@gmail.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-pm@vger.kernel.org \
--cc=peterz@infradead.org \
--cc=rafael@kernel.org \
--cc=rjw@rjwysocki.net \
--cc=srinivas.pandruvada@linux.intel.com \
--cc=viresh.kumar@linaro.org \
--cc=yu.c.chen@intel.com \
/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).