From: Peter Zijlstra <peterz@infradead.org>
To: Viresh Kumar <viresh.kumar@linaro.org>
Cc: Vincent Guittot <vincent.guittot@linaro.org>,
mingo@kernel.org, linux-kernel@vger.kernel.org,
rjw@rjwysocki.net, juri.lelli@redhat.com,
dietmar.eggemann@arm.com, Morten.Rasmussen@arm.com,
valentin.schneider@arm.com, patrick.bellasi@arm.com,
joel@joelfernandes.org, daniel.lezcano@linaro.org,
quentin.perret@arm.com, luca.abeni@santannapisa.it,
claudio@evidence.eu.com, Ingo Molnar <mingo@redhat.com>
Subject: Re: [PATCH 07/11] cpufreq/schedutil: take into account interrupt
Date: Fri, 6 Jul 2018 11:14:29 +0200 [thread overview]
Message-ID: <20180706091429.GJ2494@hirez.programming.kicks-ass.net> (raw)
In-Reply-To: <20180706060033.rcgzfs6pouqssiqh@vireshk-i7>
On Fri, Jul 06, 2018 at 11:30:33AM +0530, Viresh Kumar wrote:
> On 28-06-18, 17:45, Vincent Guittot wrote:
> > The time spent under interrupt can be significant but it is not reflected
> > in the utilization of CPU when deciding to choose an OPP. Now that we have
> > access to this metric, schedutil can take it into account when selecting
> > the OPP for a CPU.
> > rqs utilization don't see the time spend under interrupt context and report
> > their value in the normal context time window. We need to compensate this when
> > adding interrupt utilization
> >
> > The CPU utilization is :
> > irq util_avg + (1 - irq util_avg / max capacity ) * /Sum rq util_avg
> >
> > A test with iperf on hikey (octo arm64) gives:
> > iperf -c server_address -r -t 5
> >
> > w/o patch w/ patch
> > Tx 276 Mbits/sec 304 Mbits/sec +10%
> > Rx 299 Mbits/sec 328 Mbits/sec +09%
> >
> > 8 iterations
> > stdev is lower than 1%
> > Only WFI idle state is enable (shallowest diel state)
Also s/diel/idle/
> > + /*
> > + * Interrupt time is not seen by rqs utilization nso we can compare
>
> nso ?
>
> > + * them with the CPU capacity
> > + */
Already fixed ;-)
next prev parent reply other threads:[~2018-07-06 9:14 UTC|newest]
Thread overview: 44+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-06-28 15:45 [PATCH v7 00/11] track CPU utilization Vincent Guittot
2018-06-28 15:45 ` [PATCH 01/11] sched/pelt: Move pelt related code in a dedicated file Vincent Guittot
2018-07-15 23:26 ` [tip:sched/core] sched/pelt: Move PELT " tip-bot for Vincent Guittot
2018-06-28 15:45 ` [PATCH 02/11] sched/rt: add rt_rq utilization tracking Vincent Guittot
2018-07-15 23:27 ` [tip:sched/core] sched/rt: Add " tip-bot for Vincent Guittot
2018-06-28 15:45 ` [PATCH 03/11] cpufreq/schedutil: use rt " Vincent Guittot
2018-07-06 5:56 ` Viresh Kumar
2018-07-15 23:27 ` [tip:sched/core] cpufreq/schedutil: Use RT " tip-bot for Vincent Guittot
2018-06-28 15:45 ` [PATCH 04/11] sched/dl: add dl_rq " Vincent Guittot
2018-07-15 23:28 ` [tip:sched/core] sched/dl: Add " tip-bot for Vincent Guittot
2018-06-28 15:45 ` [PATCH 05/11] cpufreq/schedutil: use dl " Vincent Guittot
2018-07-06 5:59 ` Viresh Kumar
2018-07-15 23:28 ` [tip:sched/core] cpufreq/schedutil: Use DL " tip-bot for Vincent Guittot
2018-06-28 15:45 ` [PATCH 06/11] sched/irq: add irq " Vincent Guittot
2018-07-15 23:29 ` [tip:sched/core] sched/irq: Add IRQ " tip-bot for Vincent Guittot
2018-07-26 3:09 ` [PATCH 06/11] sched/irq: add irq " Wanpeng Li
2018-07-30 16:43 ` Vincent Guittot
2018-07-31 3:32 ` Wanpeng Li
2018-07-31 8:21 ` Vincent Guittot
2018-06-28 15:45 ` [PATCH 07/11] cpufreq/schedutil: take into account interrupt Vincent Guittot
2018-07-06 6:00 ` Viresh Kumar
2018-07-06 9:14 ` Peter Zijlstra [this message]
2018-07-06 9:21 ` Vincent Guittot
2018-07-15 23:29 ` [tip:sched/core] cpufreq/schedutil: Take time spent in interrupts into account tip-bot for Vincent Guittot
2018-06-28 15:45 ` [PATCH 08/11] sched: schedutil: remove sugov_aggregate_util() Vincent Guittot
2018-07-06 6:02 ` Viresh Kumar
2018-07-15 23:30 ` [tip:sched/core] sched/cpufreq: Remove sugov_aggregate_util() tip-bot for Vincent Guittot
2018-06-28 15:45 ` [PATCH 09/11] sched: use pelt for scale_rt_capacity() Vincent Guittot
2018-07-15 22:15 ` Ingo Molnar
2018-07-15 22:46 ` Joe Perches
2018-07-16 11:24 ` Vincent Guittot
2018-07-16 11:39 ` Ingo Molnar
2018-07-15 23:32 ` [tip:sched/core] sched/core: Use PELT " tip-bot for Vincent Guittot
2018-06-28 15:45 ` [PATCH 10/11] sched: remove rt_avg code Vincent Guittot
2018-07-15 23:33 ` [tip:sched/core] sched/core: Remove the " tip-bot for Vincent Guittot
2018-06-28 15:45 ` [PATCH 11/11] proc/sched: remove unused sched_time_avg_ms Vincent Guittot
2018-06-28 15:51 ` Luis R. Rodriguez
2018-06-29 5:49 ` Vincent Guittot
2018-07-15 23:33 ` [tip:sched/core] sched/sysctl: Remove unused sched_time_avg_ms sysctl tip-bot for Vincent Guittot
2018-07-05 12:36 ` [PATCH v7 00/11] track CPU utilization Peter Zijlstra
2018-07-05 13:32 ` Vincent Guittot
2018-07-06 6:05 ` Viresh Kumar
2018-07-06 9:18 ` Peter Zijlstra
2018-07-15 23:34 ` [tip:sched/core] sched/cpufreq: Clarify sugov_get_util() tip-bot for Peter Zijlstra
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=20180706091429.GJ2494@hirez.programming.kicks-ass.net \
--to=peterz@infradead.org \
--cc=Morten.Rasmussen@arm.com \
--cc=claudio@evidence.eu.com \
--cc=daniel.lezcano@linaro.org \
--cc=dietmar.eggemann@arm.com \
--cc=joel@joelfernandes.org \
--cc=juri.lelli@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=luca.abeni@santannapisa.it \
--cc=mingo@kernel.org \
--cc=mingo@redhat.com \
--cc=patrick.bellasi@arm.com \
--cc=quentin.perret@arm.com \
--cc=rjw@rjwysocki.net \
--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
all inboxes | Powered by JetHome®