From: Quentin Perret <quentin.perret@arm.com>
To: Peter Zijlstra <peterz@infradead.org>
Cc: Viresh Kumar <viresh.kumar@linaro.org>,
rjw@rjwysocki.net, linux-kernel@vger.kernel.org,
linux-pm@vger.kernel.org, gregkh@linuxfoundation.org,
mingo@redhat.com, dietmar.eggemann@arm.com,
morten.rasmussen@arm.com, chris.redpath@arm.com,
patrick.bellasi@arm.com, valentin.schneider@arm.com,
vincent.guittot@linaro.org, thara.gopinath@linaro.org,
tkjos@google.com, joel@joelfernandes.org, smuckle@google.com,
adharmap@codeaurora.org, skannan@codeaurora.org,
pkondeti@codeaurora.org, juri.lelli@redhat.com,
edubezval@gmail.com, srinivas.pandruvada@linux.intel.com,
currojerez@riseup.net, javi.merino@kernel.org
Subject: Re: [PATCH v9 02/15] sched/cpufreq: Prepare schedutil for Energy Aware Scheduling
Date: Tue, 20 Nov 2018 15:53:05 +0000 [thread overview]
Message-ID: <20181120155302.guvfvxdwbh3ztw6x@queper01-lin> (raw)
In-Reply-To: <20181120152514.GD2113@hirez.programming.kicks-ass.net>
On Tuesday 20 Nov 2018 at 16:25:14 (+0100), Peter Zijlstra wrote:
> On Tue, Nov 20, 2018 at 10:16:02AM +0530, Viresh Kumar wrote:
> > On 19-11-18, 14:18, Quentin Perret wrote:
> > > @@ -223,20 +222,33 @@ static unsigned long sugov_get_util(struct sugov_cpu *sg_cpu)
> >
> > > - if ((util + cpu_util_dl(rq)) >= max)
> > > - return max;
> > > + if (type == FREQUENCY_UTIL) {
> > > + /*
> > > + * For frequency selection we do not make cpu_util_dl() a
> > > + * permanent part of this sum because we want to use
> > > + * cpu_bw_dl() later on, but we need to check if the
> > > + * CFS+RT+DL sum is saturated (ie. no idle time) such
> > > + * that we select f_max when there is no idle time.
> > > + *
> > > + * NOTE: numerical errors or stop class might cause us
> > > + * to not quite hit saturation when we should --
> > > + * something for later.
> > > + */
> > > +
> > > + if ((util + cpu_util_dl(rq)) >= max)
> > > + return max;
> > > + } else {
> > > + /*
> > > + * OTOH, for energy computation we need the estimated
> > > + * running time, so include util_dl and ignore dl_bw.
> > > + */
> > > + util += cpu_util_dl(rq);
> > > + if (util >= max)
> > > + return max;
> > > + }
> >
> > Maybe write above as:
> >
> > dl_util = cpu_util_dl(rq);
> >
> > if ((util + dl_util) >= max)
> > return max;
> >
> > if (type != FREQUENCY_UTIL)
> > util += dl_util;
> >
> >
> > as both the if/else parts were doing almost the same thing.
>
> A little like so ?
>
> --- a/kernel/sched/cpufreq_schedutil.c
> +++ b/kernel/sched/cpufreq_schedutil.c
> @@ -201,8 +201,8 @@ static unsigned int get_next_freq(struct
> unsigned long schedutil_freq_util(int cpu, unsigned long util_cfs,
> unsigned long max, enum schedutil_type type)
> {
> + unsigned long dl_util, util, irq;
> struct rq *rq = cpu_rq(cpu);
> - unsigned long util, irq;
>
> if (type == FREQUENCY_UTIL && rt_rq_is_runnable(&rq->rt))
> return max;
> @@ -225,30 +225,26 @@ unsigned long schedutil_freq_util(int cp
> util = util_cfs;
> util += cpu_util_rt(rq);
>
> - if (type == FREQUENCY_UTIL) {
> - /*
> - * For frequency selection we do not make cpu_util_dl() a
> - * permanent part of this sum because we want to use
> - * cpu_bw_dl() later on, but we need to check if the
> - * CFS+RT+DL sum is saturated (ie. no idle time) such
> - * that we select f_max when there is no idle time.
> - *
> - * NOTE: numerical errors or stop class might cause us
> - * to not quite hit saturation when we should --
> - * something for later.
> - */
> -
> - if ((util + cpu_util_dl(rq)) >= max)
> - return max;
> - } else {
> - /*
> - * OTOH, for energy computation we need the estimated
> - * running time, so include util_dl and ignore dl_bw.
> - */
> - util += cpu_util_dl(rq);
> - if (util >= max)
> - return max;
> - }
> + dl_util = cpu_util_dl(rq);
> +
> + /*
> + * NOTE: numerical errors or stop class might cause us to not quite hit
> + * saturation when we should -- something for later.
> + */
> + if (util + dl_util > max)
> + return max;
> +
> + /*
> + * For frequency selection we do not make cpu_util_dl() a permanent
> + * part of this sum because we want to use cpu_bw_dl() later on, but we
> + * need to check if the CFS+RT+DL sum is saturated (ie. no idle time)
> + * such that we select f_max when there is no idle time.
We probably want move that paragraph to the comment above no ? Other
than that, the change LGTM.
> + *
> + * OTOH, for energy computation we need the estimated running time, so
> + * do include util_dl and ignore dl_bw.
> + */
> + if (type == ENERGY_UTIL)
> + util += dl_util;
>
> /*
> * There is still idle time; further improve the number by using the
> @@ -262,21 +258,18 @@ unsigned long schedutil_freq_util(int cp
> util = scale_irq_capacity(util, irq, max);
> util += irq;
>
> - if (type == FREQUENCY_UTIL) {
> - /*
> - * Bandwidth required by DEADLINE must always be granted
> - * while, for FAIR and RT, we use blocked utilization of
> - * IDLE CPUs as a mechanism to gracefully reduce the
> - * frequency when no tasks show up for longer periods of
> - * time.
> - *
> - * Ideally we would like to set bw_dl as min/guaranteed
> - * freq and util + bw_dl as requested freq. However,
> - * cpufreq is not yet ready for such an interface. So,
> - * we only do the latter for now.
> - */
> + /*
> + * Bandwidth required by DEADLINE must always be granted while, for
> + * FAIR and RT, we use blocked utilization of IDLE CPUs as a mechanism
> + * to gracefully reduce the frequency when no tasks show up for longer
> + * periods of time.
> + *
> + * Ideally we would like to set bw_dl as min/guaranteed freq and util +
> + * bw_dl as requested freq. However, cpufreq is not yet ready for such
> + * an interface. So, we only do the latter for now.
> + */
> + if (type == FREQUENCY_UTIL)
> util += cpu_bw_dl(rq);
> - }
>
> return min(max, util);
> }
Thanks,
Quentin
next prev parent reply other threads:[~2018-11-20 15:53 UTC|newest]
Thread overview: 35+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-11-19 14:18 [PATCH v9 00/15] Energy Aware Scheduling Quentin Perret
2018-11-19 14:18 ` [PATCH v9 01/15] sched: Relocate arch_scale_cpu_capacity Quentin Perret
2018-11-19 14:18 ` [PATCH v9 02/15] sched/cpufreq: Prepare schedutil for Energy Aware Scheduling Quentin Perret
2018-11-20 4:46 ` Viresh Kumar
2018-11-20 15:25 ` Peter Zijlstra
2018-11-20 15:53 ` Quentin Perret [this message]
2018-11-19 14:18 ` [PATCH v9 03/15] PM: Introduce an Energy Model management framework Quentin Perret
2018-11-19 14:18 ` [PATCH v9 04/15] PM / EM: Expose the Energy Model in sysfs Quentin Perret
2018-11-19 14:18 ` [PATCH v9 05/15] sched/topology: Reference the Energy Model of CPUs when available Quentin Perret
2018-11-19 14:18 ` [PATCH v9 06/15] sched/topology: Lowest CPU asymmetry sched_domain level pointer Quentin Perret
2018-11-19 14:18 ` [PATCH v9 07/15] sched/topology: Disable EAS on inappropriate platforms Quentin Perret
2018-11-19 14:18 ` [PATCH v9 08/15] sched/topology: Make Energy Aware Scheduling depend on schedutil Quentin Perret
2018-11-22 14:04 ` Peter Zijlstra
2018-11-22 15:49 ` Rafael J. Wysocki
2018-11-22 15:56 ` Quentin Perret
2018-11-19 14:18 ` [PATCH v9 09/15] sched: Introduce sched_energy_present static key Quentin Perret
2018-11-21 13:08 ` Peter Zijlstra
2018-11-21 15:14 ` Quentin Perret
2018-11-22 9:17 ` Quentin Perret
2018-11-22 9:32 ` Quentin Perret
2018-11-22 10:25 ` Peter Zijlstra
2018-11-22 15:25 ` Quentin Perret
2018-11-22 15:51 ` Rafael J. Wysocki
2018-11-22 15:55 ` Quentin Perret
2018-11-19 14:18 ` [PATCH v9 10/15] sched: Introduce a sysctl for Energy Aware Scheduling Quentin Perret
2018-11-19 14:18 ` [PATCH v9 11/15] sched/fair: Clean-up update_sg_lb_stats parameters Quentin Perret
2018-11-19 14:18 ` [PATCH v9 12/15] sched: Add over-utilization/tipping point indicator Quentin Perret
2018-11-19 14:18 ` [PATCH v9 13/15] sched/fair: Introduce an energy estimation helper function Quentin Perret
2018-11-21 14:28 ` Peter Zijlstra
2018-11-21 16:05 ` Quentin Perret
2018-11-22 13:56 ` Peter Zijlstra
2018-11-19 14:18 ` [PATCH v9 14/15] sched/fair: Select an energy-efficient CPU on task wake-up Quentin Perret
2018-11-19 14:18 ` [PATCH v9 15/15] OPTIONAL: cpufreq: dt: Register an Energy Model Quentin Perret
2018-11-20 6:19 ` Viresh Kumar
2018-11-20 10:01 ` Quentin Perret
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=20181120155302.guvfvxdwbh3ztw6x@queper01-lin \
--to=quentin.perret@arm.com \
--cc=adharmap@codeaurora.org \
--cc=chris.redpath@arm.com \
--cc=currojerez@riseup.net \
--cc=dietmar.eggemann@arm.com \
--cc=edubezval@gmail.com \
--cc=gregkh@linuxfoundation.org \
--cc=javi.merino@kernel.org \
--cc=joel@joelfernandes.org \
--cc=juri.lelli@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-pm@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=morten.rasmussen@arm.com \
--cc=patrick.bellasi@arm.com \
--cc=peterz@infradead.org \
--cc=pkondeti@codeaurora.org \
--cc=rjw@rjwysocki.net \
--cc=skannan@codeaurora.org \
--cc=smuckle@google.com \
--cc=srinivas.pandruvada@linux.intel.com \
--cc=thara.gopinath@linaro.org \
--cc=tkjos@google.com \
--cc=valentin.schneider@arm.com \
--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).