From: Peter Zijlstra <peterz@infradead.org>
To: "Joel Fernandes (Google)" <joel@joelfernandes.org>
Cc: linux-kernel@vger.kernel.org, Ingo Molnar <mingo@redhat.com>,
Juri Lelli <juri.lelli@redhat.com>,
Vincent Guittot <vincent.guittot@linaro.org>,
Dietmar Eggemann <dietmar.eggemann@arm.com>,
Steven Rostedt <rostedt@goodmis.org>,
Ben Segall <bsegall@google.com>, Mel Gorman <mgorman@suse.de>,
Daniel Bristot de Oliveira <bristot@redhat.com>,
Valentin Schneider <vschneid@redhat.com>,
Vineeth Pillai <vineethrp@google.com>,
Suleiman Souhlal <suleiman@google.com>,
Hsin Yi <hsinyi@google.com>,
Frederic Weisbecker <frederic@kernel.org>,
"Paul E . McKenney" <paulmck@kernel.org>
Subject: Re: [PATCH RFC] sched/fair: Avoid unnecessary IPIs for ILB
Date: Fri, 6 Oct 2023 22:01:29 +0200 [thread overview]
Message-ID: <20231006200129.GJ36277@noisy.programming.kicks-ass.net> (raw)
In-Reply-To: <20231005161727.1855004-1-joel@joelfernandes.org>
On Thu, Oct 05, 2023 at 04:17:26PM +0000, Joel Fernandes (Google) wrote:
> From: Vineeth Pillai <vineethrp@google.com>
>
> Whenever a CPU stops its tick, it now requires another idle CPU to handle the
> balancing for it because it can't perform its own periodic load balancing.
> This means it might need to update 'nohz.next_balance' to 'rq->next_balance' if
> the upcoming nohz-idle load balancing is too distant in the future. This update
> process is done by triggering an ILB, as the general ILB handler
> (_nohz_idle_balance) that manages regular nohz balancing also refreshes
> 'nohz.next_balance' by looking at the 'rq->next_balance' of all other idle CPUs
> and selecting the smallest value.
>
> Triggering this ILB can be achieved by setting the NOHZ_NEXT_KICK flag. This
> primarily results in the ILB handler updating 'nohz.next_balance' while
> possibly not doing any load balancing at all. However, sending an IPI merely to
> refresh 'nohz.next_balance' seems excessive, and there ought to be a more
> efficient method to update 'nohz.next_balance' from the local CPU.
>
> Fortunately, there already exists a mechanism to directly invoke the ILB
> handler (_nohz_idle_balance) without initiating an IPI. It's accomplished by
> setting the NOHZ_NEWILB_KICK flag. This flag is set during regular "newly idle"
> balancing and solely exists to update a CPU's blocked load if it couldn't pull
> more tasks during regular "newly idle balancing" - and it does so without
> having to send any IPIs. Once the flag is set, the ILB handler is called
> directly from do_idle()-> nohz_run_idle_balance(). While its goal is to update
> the blocked load without an IPI, in our situation, we aim to refresh
> 'nohz.next_balance' without an IPI but we can piggy back on this.
>
> So in this patch, we reuse this mechanism by also setting the NOHZ_NEXT_KICK to
> indicate nohz.next_balance needs an update via this direct call shortcut. Note
> that we set this flag without knowledge that the tick is about to be stopped,
> because at the point we do it, we have no way of knowing that. However we do
> know that the CPU is about to enter idle. In our testing, the reduction in IPIs
> is well worth updating nohz.next_balance a few more times.
>
> Also just to note, without this patch we observe the following pattern:
>
> 1. A CPU is about to stop its tick.
> 2. It sets nohz.needs_update to 1.
> 3. It then stops its tick and goes idle.
> 4. The scheduler tick on another CPU checks this flag and decides an ILB kick is needed.
> 5. The ILB CPU ends up being the one that just stopped its tick!
> 6. This results in an IPI to the tick-stopped CPU which ends up waking it up
> and disturbing it!
>
> Testing shows a considerable reduction in IPIs when doing this:
>
> Running "cyclictest -i 100 -d 100 --latency=1000 -t -m" on a 4vcpu VM
> the IPI call count profiled over 10s period is as follows:
> without fix: ~10500
> with fix: ~1000
>
> Fixes: 7fd7a9e0caba ("sched/fair: Trigger nohz.next_balance updates when a CPU goes NOHZ-idle")
Hurm.. does this really warrant a Fixes tag? Afaict nothing is currently
broken -- this is a pure optimization question, no?
next prev parent reply other threads:[~2023-10-06 20:01 UTC|newest]
Thread overview: 20+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-10-05 16:17 [PATCH RFC] sched/fair: Avoid unnecessary IPIs for ILB Joel Fernandes (Google)
2023-10-06 10:51 ` Ingo Molnar
2023-10-06 16:32 ` Joel Fernandes
2023-10-08 17:35 ` Joel Fernandes
2023-10-09 18:33 ` Vineeth Pillai
2023-10-10 7:15 ` Vincent Guittot
2023-10-10 19:32 ` Joel Fernandes
2023-10-06 13:46 ` Vincent Guittot
2023-10-06 16:46 ` Joel Fernandes
2023-10-06 19:18 ` Shrikanth Hegde
2023-10-06 20:10 ` Shrikanth Hegde
2023-10-08 16:50 ` Joel Fernandes
2023-10-06 21:20 ` Vineeth Pillai
2023-10-08 16:46 ` Joel Fernandes
2023-10-06 20:01 ` Peter Zijlstra [this message]
2023-10-08 16:39 ` Joel Fernandes
2023-10-09 11:25 ` Ingo Molnar
2023-10-09 20:11 ` Steven Rostedt
2023-10-10 17:55 ` Joel Fernandes
2023-10-19 14:56 ` kernel test robot
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=20231006200129.GJ36277@noisy.programming.kicks-ass.net \
--to=peterz@infradead.org \
--cc=bristot@redhat.com \
--cc=bsegall@google.com \
--cc=dietmar.eggemann@arm.com \
--cc=frederic@kernel.org \
--cc=hsinyi@google.com \
--cc=joel@joelfernandes.org \
--cc=juri.lelli@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mgorman@suse.de \
--cc=mingo@redhat.com \
--cc=paulmck@kernel.org \
--cc=rostedt@goodmis.org \
--cc=suleiman@google.com \
--cc=vincent.guittot@linaro.org \
--cc=vineethrp@google.com \
--cc=vschneid@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).