From: Peter Zijlstra <peterz@infradead.org>
To: Frederic Weisbecker <frederic@kernel.org>
Cc: Ingo Molnar <mingo@kernel.org>,
LKML <linux-kernel@vger.kernel.org>,
Jacek Anaszewski <jacek.anaszewski@gmail.com>,
Wanpeng Li <wanpengli@tencent.com>, Pavel Machek <pavel@ucw.cz>,
Benjamin Herrenschmidt <benh@kernel.crashing.org>,
Thomas Gleixner <tglx@linutronix.de>,
Yauheni Kaliuta <yauheni.kaliuta@redhat.com>,
"Rafael J . Wysocki" <rjw@rjwysocki.net>,
Viresh Kumar <viresh.kumar@linaro.org>,
Rik van Riel <riel@surriel.com>
Subject: Re: [PATCH 3/9] sched/vtime: Handle nice updates under vtime
Date: Fri, 15 Nov 2019 11:18:31 +0100 [thread overview]
Message-ID: <20191115101831.GW5671@hirez.programming.kicks-ass.net> (raw)
In-Reply-To: <20191115101648.GC4131@hirez.programming.kicks-ass.net>
On Fri, Nov 15, 2019 at 11:16:48AM +0100, Peter Zijlstra wrote:
> On Wed, Nov 06, 2019 at 04:08:01AM +0100, Frederic Weisbecker wrote:
> > The cputime niceness is determined while checking the target's nice value
> > at cputime accounting time. Under vtime this happens on context switches,
> > user exit and guest exit. But nice value updates while the target is
> > running are not taken into account.
> >
> > So if a task runs tickless for 10 seconds in userspace but it has been
> > reniced after 5 seconds from -1 (not nice) to 1 (nice), on user exit
> > vtime will account the whole 10 seconds as CPUTIME_NICE because it only
> > sees the latest nice value at accounting time which is 1 here. Yet it's
> > wrong, 5 seconds should be accounted as CPUTIME_USER and 5 seconds as
> > CPUTIME_NICE.
> >
> > In order to solve this, we now cover nice updates withing three cases:
> >
> > * If the nice updater is the current task, although we are in kernel
> > mode there can be pending user or guest time in the cache to flush
> > under the prior nice state. Account these if any. Also toggle the
> > vtime nice flag for further user/guest cputime accounting.
> >
> > * If the target runs on a different CPU, we interrupt it with an IPI to
> > update the vtime state in place. If the task is running in user or
> > guest, the pending cputime is accounted under the prior nice state.
> > Then the vtime nice flag is toggled for further user/guest cputime
> > accounting.
>
> But but but, I thought the idea was to _never_ send interrupts to
> NOHZ_FULL cpus ?!?
That is, isn't the cure worse than the problem? I mean, who bloody cares
about silly accounting crud more than not getting interrupts on their
NOHZ_FULL cpus.
next prev parent reply other threads:[~2019-11-15 10:18 UTC|newest]
Thread overview: 16+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-11-06 3:07 [PATCH 0/9] sched/nohz: Make the rest of kcpustat vtime aware Frederic Weisbecker
2019-11-06 3:07 ` [PATCH 1/9] sched/cputime: Allow to pass cputime index on user/guest accounting Frederic Weisbecker
2019-11-06 3:08 ` [PATCH 2/9] sched/cputime: Standardize the kcpustat index based accounting functions Frederic Weisbecker
2019-11-06 3:08 ` [PATCH 3/9] sched/vtime: Handle nice updates under vtime Frederic Weisbecker
2019-11-15 10:14 ` Peter Zijlstra
2019-11-15 10:16 ` Peter Zijlstra
2019-11-15 10:18 ` Peter Zijlstra [this message]
2019-11-15 15:27 ` Frederic Weisbecker
2019-11-18 13:04 ` Peter Zijlstra
2019-11-06 3:08 ` [PATCH 4/9] sched/cputime: Support other fields on kcpustat_field() Frederic Weisbecker
2019-11-06 3:08 ` [PATCH 5/9] sched/vtime: Bring all-in-one kcpustat accessor for vtime fields Frederic Weisbecker
2019-11-06 3:08 ` [PATCH 6/9] procfs: Use all-in-one vtime aware kcpustat accessor Frederic Weisbecker
2019-11-06 3:08 ` [PATCH 7/9] cpufreq: Use vtime aware kcpustat accessors for user time Frederic Weisbecker
2019-11-06 3:08 ` [PATCH 8/9] leds: Use all-in-one vtime aware kcpustat accessor Frederic Weisbecker
2019-11-06 3:08 ` [PATCH 9/9] rackmeter: Use " Frederic Weisbecker
2019-11-14 15:25 ` [PATCH 0/9] sched/nohz: Make the rest of kcpustat vtime aware Frederic Weisbecker
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=20191115101831.GW5671@hirez.programming.kicks-ass.net \
--to=peterz@infradead.org \
--cc=benh@kernel.crashing.org \
--cc=frederic@kernel.org \
--cc=jacek.anaszewski@gmail.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@kernel.org \
--cc=pavel@ucw.cz \
--cc=riel@surriel.com \
--cc=rjw@rjwysocki.net \
--cc=tglx@linutronix.de \
--cc=viresh.kumar@linaro.org \
--cc=wanpengli@tencent.com \
--cc=yauheni.kaliuta@redhat.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).