[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20180706091429.GJ2494@hirez.programming.kicks-ass.net>
Date: Fri, 6 Jul 2018 11:14:29 +0200
From: Peter Zijlstra <peterz@...radead.org>
To: Viresh Kumar <viresh.kumar@...aro.org>
Cc: Vincent Guittot <vincent.guittot@...aro.org>, mingo@...nel.org,
linux-kernel@...r.kernel.org, rjw@...ysocki.net,
juri.lelli@...hat.com, dietmar.eggemann@....com,
Morten.Rasmussen@....com, valentin.schneider@....com,
patrick.bellasi@....com, joel@...lfernandes.org,
daniel.lezcano@...aro.org, quentin.perret@....com,
luca.abeni@...tannapisa.it, claudio@...dence.eu.com,
Ingo Molnar <mingo@...hat.com>
Subject: Re: [PATCH 07/11] cpufreq/schedutil: take into account interrupt
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 ;-)
Powered by blists - more mailing lists