From: Vincent Guittot <vincent.guittot@linaro.org>
To: Konstantin Khorenko <khorenko@virtuozzo.com>
Cc: Ingo Molnar <mingo@redhat.com>,
Peter Zijlstra <peterz@infradead.org>,
Juri Lelli <juri.lelli@redhat.com>,
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>,
Alexander Atanasov <alexander.atanasov@virtuozzo.com>,
linux-kernel@vger.kernel.org
Subject: Re: [PATCH v2 RESEND] sched/fair: Do not scan non-movable tasks several times
Date: Fri, 19 Jan 2024 16:49:07 +0100 [thread overview]
Message-ID: <ZaqZ8wXzNvqUH8Jn@vingu-book> (raw)
In-Reply-To: <20240115105052.398761-1-khorenko@virtuozzo.com>
Le lundi 15 janv. 2024 à 13:50:52 (+0300), Konstantin Khorenko a écrit :
> If busiest rq is small, nr_running < SCHED_NR_MIGRATE_BREAK and all
> tasks are not movable, detach_tasks() should not iterate more than tasks
> available in the busiest rq.
>
> Before commit: b0defa7ae03e ("sched/fair: Make sure to try to detach at
> least one movable task"), the (env->loop > env->loop_max) condition
> prevented us from scanning non-movable tasks more than rq size times,
> but after we start checking the LBF_ALL_PINNED flag, the "all tasks are
> not movable" case is under threat.
>
> Note: in case all tasks in the rq could not be moved in detach_tasks()
> we always increase loop_break by SCHED_NR_MIGRATE_BREAK, so we can step
> over loop_max, but i think it's a rare case and does not worth adding
> here extra check for rq->nr_running overlimit.
In this case why not doing the below ? Close to your 1st version
---
kernel/sched/fair.c | 7 +++++++
1 file changed, 7 insertions(+)
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index fce22b4462bb..1dae6cdf8561 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -11344,6 +11344,13 @@ static int load_balance(int this_cpu, struct rq *this_rq,
env.loop_max = min(sysctl_sched_nr_migrate, busiest->nr_running);
more_balance:
+ /*
+ * If busiest rq is small, nr_running < SCHED_NR_MIGRATE_BREAK
+ * and all tasks are not movable, detach_tasks() should not
+ * iterate more than tasks available in rq.
+ */
+ env.loop_break = min(env.loop_break, busiest->nr_running);
+
rq_lock_irqsave(busiest, &rf);
update_rq_clock(busiest);
--
2.34.1
>
> Fixes: b0defa7ae03e ("sched/fair: Make sure to try to detach at least
> one movable task")
>
> Signed-off-by: Konstantin Khorenko <khorenko@virtuozzo.com>
> ---
> kernel/sched/fair.c | 13 +++++++++----
> 1 file changed, 9 insertions(+), 4 deletions(-)
>
> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> index 533547e3c90a..920fb16e6e2f 100644
> --- a/kernel/sched/fair.c
> +++ b/kernel/sched/fair.c
> @@ -11277,7 +11277,6 @@ static int load_balance(int this_cpu, struct rq *this_rq,
> .dst_rq = this_rq,
> .dst_grpmask = group_balance_mask(sd->groups),
> .idle = idle,
> - .loop_break = SCHED_NR_MIGRATE_BREAK,
> .cpus = cpus,
> .fbq_type = all,
> .tasks = LIST_HEAD_INIT(env.tasks),
> @@ -11324,6 +11323,14 @@ static int load_balance(int this_cpu, struct rq *this_rq,
> */
> env.loop_max = min(sysctl_sched_nr_migrate, busiest->nr_running);
>
> +more_balance_reset_break:
> + /*
> + * If busiest rq is small, nr_running < SCHED_NR_MIGRATE_BREAK
> + * and all tasks are not movable, detach_tasks() should not
> + * iterate more than tasks available in rq.
> + */
> + env.loop_break = min(SCHED_NR_MIGRATE_BREAK, busiest->nr_running);
> +
> more_balance:
> rq_lock_irqsave(busiest, &rf);
> update_rq_clock(busiest);
> @@ -11386,13 +11393,12 @@ static int load_balance(int this_cpu, struct rq *this_rq,
> env.dst_cpu = env.new_dst_cpu;
> env.flags &= ~LBF_DST_PINNED;
> env.loop = 0;
> - env.loop_break = SCHED_NR_MIGRATE_BREAK;
>
> /*
> * Go back to "more_balance" rather than "redo" since we
> * need to continue with same src_cpu.
> */
> - goto more_balance;
> + goto more_balance_reset_break;
> }
>
> /*
> @@ -11418,7 +11424,6 @@ static int load_balance(int this_cpu, struct rq *this_rq,
> */
> if (!cpumask_subset(cpus, env.dst_grpmask)) {
> env.loop = 0;
> - env.loop_break = SCHED_NR_MIGRATE_BREAK;
> goto redo;
> }
> goto out_all_pinned;
> --
> 2.39.3
>
prev parent reply other threads:[~2024-01-19 15:49 UTC|newest]
Thread overview: 2+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-01-15 10:50 [PATCH v2 RESEND] sched/fair: Do not scan non-movable tasks several times Konstantin Khorenko
2024-01-19 15:49 ` Vincent Guittot [this message]
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=ZaqZ8wXzNvqUH8Jn@vingu-book \
--to=vincent.guittot@linaro.org \
--cc=alexander.atanasov@virtuozzo.com \
--cc=bristot@redhat.com \
--cc=bsegall@google.com \
--cc=dietmar.eggemann@arm.com \
--cc=juri.lelli@redhat.com \
--cc=khorenko@virtuozzo.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mgorman@suse.de \
--cc=mingo@redhat.com \
--cc=peterz@infradead.org \
--cc=rostedt@goodmis.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).