From: Ingo Molnar <mingo@kernel.org>
To: "Joel Fernandes (Google)" <joel@joelfernandes.org>
Cc: linux-kernel@vger.kernel.org, Ingo Molnar <mingo@redhat.com>,
Peter Zijlstra <peterz@infradead.org>,
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 (Google)" <vineeth@bitbyteword.org>,
Suleiman Souhlal <suleiman@google.com>,
Frederic Weisbecker <frederic@kernel.org>,
"Paul E . McKenney" <paulmck@kernel.org>
Subject: Re: [PATCH 3/3] sched: Update ->next_balance correctly during newidle balance
Date: Fri, 20 Oct 2023 09:53:51 +0200 [thread overview]
Message-ID: <ZTIyD8EuhSmF4JFr@gmail.com> (raw)
In-Reply-To: <20231020014031.919742-3-joel@joelfernandes.org>
* Joel Fernandes (Google) <joel@joelfernandes.org> wrote:
> From: "Vineeth Pillai (Google)" <vineeth@bitbyteword.org>
>
> When newidle balancing triggers, we see that it constantly clobbers
> rq->next_balance even when there is no newidle balance happening due to
> the cost estimates. Due to this, we see that periodic load balance
> (rebalance_domains) may trigger way more often when the CPU is going in
> and out of idle at a high rate but is no really idle. Repeatedly
> triggering load balance there is a bad idea as it is a heavy operation.
> It also causes increases in softirq.
>
> Another issue is ->last_balance is not updated after newidle balance
> causing mistakes in the ->next_balance calculations.
>
> Fix by updating last_balance when a newidle load balance actually happens
> and then updating next_balance. This is also how it is done in other load
> balance paths.
>
> Testing shows a significant drop in softirqs when running:
> cyclictest -i 100 -d 100 --latency=1000 -D 5 -t -m -q
>
> Goes from ~6k to ~800.
>
> Cc: Suleiman Souhlal <suleiman@google.com>
> Cc: Steven Rostedt <rostedt@goodmis.org>
> Cc: Frederic Weisbecker <frederic@kernel.org>
> Cc: Paul E. McKenney <paulmck@kernel.org>
> Signed-off-by: Vineeth Pillai (Google) <vineeth@bitbyteword.org>
> Co-developed-by: Joel Fernandes (Google) <joel@joelfernandes.org>
> Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org>
> ---
> kernel/sched/fair.c | 8 ++------
> 1 file changed, 2 insertions(+), 6 deletions(-)
>
> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> index 8e276d12c3cb..b147ad09126a 100644
> --- a/kernel/sched/fair.c
> +++ b/kernel/sched/fair.c
> @@ -12076,11 +12076,7 @@ static int newidle_balance(struct rq *this_rq, struct rq_flags *rf)
>
> if (!READ_ONCE(this_rq->rd->overload) ||
> (sd && this_rq->avg_idle < sd->max_newidle_lb_cost)) {
> -
> - if (sd)
> - update_next_balance(sd, &next_balance);
> rcu_read_unlock();
> -
> goto out;
> }
> rcu_read_unlock();
> @@ -12095,8 +12091,6 @@ static int newidle_balance(struct rq *this_rq, struct rq_flags *rf)
> int continue_balancing = 1;
> u64 domain_cost;
>
> - update_next_balance(sd, &next_balance);
> -
> if (this_rq->avg_idle < curr_cost + sd->max_newidle_lb_cost)
> break;
>
> @@ -12109,6 +12103,8 @@ static int newidle_balance(struct rq *this_rq, struct rq_flags *rf)
> t1 = sched_clock_cpu(this_cpu);
> domain_cost = t1 - t0;
> update_newidle_cost(sd, domain_cost);
> + sd->last_balance = jiffies;
> + update_next_balance(sd, &next_balance);
>
> curr_cost += domain_cost;
> t0 = t1;
Okay, I'm applying patches #2 and #3, without #1: it should be safe
out of order, but let me know if I missed something ...
Thanks,
Ingo
next prev parent reply other threads:[~2023-10-20 7:53 UTC|newest]
Thread overview: 19+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-10-20 1:40 [PATCH 1/3] sched/nohz: Update nohz.next_balance directly without IPIs (v2) Joel Fernandes (Google)
2023-10-20 1:40 ` [PATCH 2/3] sched/nohz: Update comments about NEWILB_KICK Joel Fernandes (Google)
2023-10-20 7:51 ` Ingo Molnar
2023-10-20 8:02 ` [tip: sched/core] " tip-bot2 for Joel Fernandes (Google)
2023-10-20 1:40 ` [PATCH 3/3] sched: Update ->next_balance correctly during newidle balance Joel Fernandes (Google)
2023-10-20 7:53 ` Ingo Molnar [this message]
2023-10-20 13:48 ` Vincent Guittot
2023-10-21 6:50 ` Ingo Molnar
2023-10-20 8:02 ` [tip: sched/core] sched/fair: " tip-bot2 for Vineeth Pillai (Google)
2023-10-20 13:40 ` [PATCH 3/3] sched: " Vincent Guittot
2023-10-20 13:56 ` Ingo Molnar
2023-10-20 15:50 ` Joel Fernandes
2023-10-22 0:28 ` Joel Fernandes
2023-10-26 14:23 ` Vincent Guittot
2023-11-09 10:02 ` Joel Fernandes
2023-11-09 12:31 ` Joel Fernandes
2023-11-14 15:43 ` Vincent Guittot
2023-11-14 17:43 ` Joel Fernandes
2023-10-20 4:17 ` [PATCH 1/3] sched/nohz: Update nohz.next_balance directly without IPIs (v2) Joel Fernandes
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=ZTIyD8EuhSmF4JFr@gmail.com \
--to=mingo@kernel.org \
--cc=bristot@redhat.com \
--cc=bsegall@google.com \
--cc=dietmar.eggemann@arm.com \
--cc=frederic@kernel.org \
--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=peterz@infradead.org \
--cc=rostedt@goodmis.org \
--cc=suleiman@google.com \
--cc=vincent.guittot@linaro.org \
--cc=vineeth@bitbyteword.org \
--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).