All of lore.kernel.org
 help / color / mirror / Atom feed
From: Yury Norov <ynorov@nvidia.com>
To: Shrikanth Hegde <sshegde@linux.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>,
	Ingo Molnar <mingo@redhat.com>, Thomas Gleixner <tglx@kernel.org>,
	Juri Lelli <juri.lelli@redhat.com>,
	Vincent Guittot <vincent.guittot@linaro.org>,
	Yury Norov <yury.norov@gmail.com>,
	"Rafael J. Wysocki" <rafael@kernel.org>,
	Alexander Gordeev <agordeev@linux.ibm.com>,
	Andrea Righi <arighi@nvidia.com>, Ben Segall <bsegall@google.com>,
	Christian Borntraeger <borntraeger@linux.ibm.com>,
	Danilo Krummrich <dakr@kernel.org>,
	Dietmar Eggemann <dietmar.eggemann@arm.com>,
	Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
	Heiko Carstens <hca@linux.ibm.com>,
	Ilya Leoshkevich <iii@linux.ibm.com>,
	Johan Hovold <johan@kernel.org>, Jonathan Corbet <corbet@lwn.net>,
	K Prateek Nayak <kprateek.nayak@amd.com>,
	Maxim Kuvyrkov <maxim.kuvyrkov@grdncc.com>,
	Mel Gorman <mgorman@suse.de>, Mete Durlu <meted@linux.ibm.com>,
	Randy Dunlap <rdunlap@infradead.org>,
	Rasmus Villemoes <linux@rasmusvillemoes.dk>,
	Shuah Khan <skhan@linuxfoundation.org>,
	Steven Rostedt <rostedt@goodmis.org>,
	Sven Schnelle <svens@linux.ibm.com>,
	Valentin Schneider <vschneid@redhat.com>,
	Vasily Gorbik <gor@linux.ibm.com>,
	linux-kernel@vger.kernel.org, linux-doc@vger.kernel.org,
	driver-core@lists.linux.dev, linux-s390@vger.kernel.org
Subject: Re: [PATCH 6/7] virt: steal_governor: restart sampling immediately after CPU hotplug
Date: Thu, 19 Nov 2026 12:39:21 -0500	[thread overview]
Message-ID: <av80SflNuKlReSEO@yury> (raw)
In-Reply-To: <37a30a91-bd86-4dbb-ad12-8cbb509f7c4c@linux.ibm.com>

On Thu, Nov 19, 2026 at 11:36:46AM +0530, Shrikanth Hegde wrote:
> Hi Yury.
> 
> On 11/14/26 12:12 AM, Yury Norov wrote:
> > CPU hotplug between samples can distort the calculated steal ratio because
> > the governor divides accumulated steal time by the current active CPU
> > count, even when that count changed during the sampling interval.
> > 
> > For example, assume a constant 3% steal rate on each CPU, with four active
> > CPUs for 900ms followed by two active CPUs for 100ms. The accumulated
> > steal time is:
> > 
> >      4 * 900ms * 3% + 2 * 100ms * 3% = 108ms + 6ms = 114ms
> 
> 
> This example is not realistic. If you had 3% steal with 4 CPUs, and if they become 2,
> your steal time will definitely increase. It will likely double. So
> governor likely calculates 6%.

You say it's not realistic, and then you confirm the math. So
realistic or not?

On my VM, there are 4 or 8 vCPUs, and the steal time hovers around 3%
normally. Offlining half of them triggers steal governor pretty
consistently.
 
> But yes, you can have realistic examples, where governor may calculate
> the values which goes slightly above or below. But IMHO those examples are very
> limited. Even in the above examples, the steal governor was supposed to trigger
> high threshold since the steal time with 2 CPUs is 6%. So if not now, in the next
> delta it would have triggered it anyways.

Sorry, I don't understand this. The governor is not supposed to
trigger decrease_preferred_cpus() on offline event. If some system
event skews steal ratio, the governor must adjust to that, or simply
skip the iteration. This patch implements the 2nd approach, which is
simpler IMO.

> Some examples are really corner cases. Maybe like
> 
> 60 CPUs 3% steal, and then 40 CPUs 5.1% steal = 4.55%
> (Below threshold, but should have been high). One interval missed. But if you see
> large duration was in low threshold, so it is agreeable to miss it.

Don't understand this either. Can you elaborate on your case and math
please?
 
> > The elapsed time is 1000ms. Using the final count of two active CPUs, the
> > governor calculates:
> > 
> >      114ms / (2 * 1000ms) = 5.7%
> > 
> > This exceeds the default 5% high threshold, even though the actual steal
> > rate stayed at 3%. Using the CPU counts over the whole interval gives:
> > 
> >      114ms / (4 * 900ms + 2 * 100ms) = 3%
> > 
> > Checking num_online_cpus() doesn't account for cases where CPUs go online
> > and offline such that the total number of online CPUs doesn't change. So,
> > implement the sampling restart on hotplug event.
> > 
> 
> I am not sure if we really need to stress about hotplug cases. IIUC, when a user
> does hotplug, systems are usually idle. (Atleast that is what we have observed in
> real life use cases). And hotplug is really user driven, so user knows system is going
> through some transitions and will be stable soon.

The follow-up series brings a real counter example: Android daemon
running on Qualcomm SoC offlines CPUs on thermal event. So, it's
automatic and the offlined CPU is likely not idling.

Thanks,
Yury

  reply	other threads:[~2026-11-19 17:39 UTC|newest]

Thread overview: 33+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-11-13 18:42 [PATCH 0/7] Harden preferred CPUs management Yury Norov
2026-11-13 18:42 ` [PATCH 1/7] cpumask: add reset_preferred_cpumask() helper Yury Norov
2026-11-13 18:55   ` sashiko-bot
2026-11-13 18:42 ` [PATCH 2/7] sched: restore preferred CPUs when hotplug removes the last one Yury Norov
2026-11-13 19:12   ` sashiko-bot
2026-11-19  6:13   ` Shrikanth Hegde
2026-11-19 16:46     ` Yury Norov
2026-11-13 18:42 ` [PATCH 3/7] virt: steal_governor: remove the minimum elapsed-time check Yury Norov
2026-11-13 18:56   ` sashiko-bot
2026-11-13 18:42 ` [PATCH 4/7] virt: steal_governor: serialize sampling against CPU hotplug Yury Norov
2026-11-13 19:03   ` sashiko-bot
2026-11-19  6:22   ` Shrikanth Hegde
2026-11-19 16:50     ` Yury Norov
2026-11-20  8:38       ` Shrikanth Hegde
2026-11-20 15:35         ` Yury Norov
2026-11-13 18:42 ` [PATCH 5/7] virt: steal_governor: warn on unexpected preferred mask states Yury Norov
2026-11-13 19:06   ` sashiko-bot
2026-11-13 18:42 ` [PATCH 6/7] virt: steal_governor: restart sampling immediately after CPU hotplug Yury Norov
2026-11-13 19:21   ` sashiko-bot
2026-11-16  2:13   ` Yury Norov
2026-11-19  6:06   ` Shrikanth Hegde
2026-11-19 17:39     ` Yury Norov [this message]
2026-11-20  8:50       ` Shrikanth Hegde
2026-11-20 15:36         ` Yury Norov
2026-11-13 18:42 ` [PATCH 7/7] cpu: make preferred CPU policy writers mutually exclusive Yury Norov
2026-11-13 19:25   ` sashiko-bot
2026-11-19  6:10   ` Shrikanth Hegde
2026-11-19 17:47     ` Yury Norov
2026-11-20 15:38   ` Peter Zijlstra
2026-11-20 15:59     ` Yury Norov
2026-11-20 16:09       ` Peter Zijlstra
2026-11-20 16:25         ` Yury Norov
2026-11-20 16:26           ` Yury Norov

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=av80SflNuKlReSEO@yury \
    --to=ynorov@nvidia.com \
    --cc=agordeev@linux.ibm.com \
    --cc=arighi@nvidia.com \
    --cc=borntraeger@linux.ibm.com \
    --cc=bsegall@google.com \
    --cc=corbet@lwn.net \
    --cc=dakr@kernel.org \
    --cc=dietmar.eggemann@arm.com \
    --cc=driver-core@lists.linux.dev \
    --cc=gor@linux.ibm.com \
    --cc=gregkh@linuxfoundation.org \
    --cc=hca@linux.ibm.com \
    --cc=iii@linux.ibm.com \
    --cc=johan@kernel.org \
    --cc=juri.lelli@redhat.com \
    --cc=kprateek.nayak@amd.com \
    --cc=linux-doc@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-s390@vger.kernel.org \
    --cc=linux@rasmusvillemoes.dk \
    --cc=maxim.kuvyrkov@grdncc.com \
    --cc=meted@linux.ibm.com \
    --cc=mgorman@suse.de \
    --cc=mingo@redhat.com \
    --cc=peterz@infradead.org \
    --cc=rafael@kernel.org \
    --cc=rdunlap@infradead.org \
    --cc=rostedt@goodmis.org \
    --cc=skhan@linuxfoundation.org \
    --cc=sshegde@linux.ibm.com \
    --cc=svens@linux.ibm.com \
    --cc=tglx@kernel.org \
    --cc=vincent.guittot@linaro.org \
    --cc=vschneid@redhat.com \
    --cc=yury.norov@gmail.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.