[<prev] [next>] [day] [month] [year] [list]
Message-ID: <xhsmhle5n9btt.mognet@vschneid-thinkpadt14sgen2i.remote.csb>
Date: Tue, 09 Apr 2024 10:31:26 +0200
From: Valentin Schneider <vschneid@...hat.com>
To: Kyle Meyer <kyle.meyer@....com>, yury.norov@...il.com,
andriy.shevchenko@...ux.intel.com, linux@...musvillemoes.dk,
mingo@...hat.com, peterz@...radead.org, juri.lelli@...hat.com,
vincent.guittot@...aro.org, dietmar.eggemann@....com, rostedt@...dmis.org,
bsegall@...gle.com, mgorman@...e.de, bristot@...hat.com,
linux-kernel@...r.kernel.org
Cc: russ.anderson@....com, dimitri.sivanich@....com, steve.wahl@....com,
Kyle Meyer <kyle.meyer@....com>
Subject: Re: [PATCH 0/2] sched/topology: Optimize topology_span_sane()
On 19/03/24 13:51, Kyle Meyer wrote:
> A soft lockup is being detected in build_sched_domains() on 32 socket
> Sapphire Rapids systems with 3840 processors.
>
> topology_span_sane(), called by build_sched_domains(), checks that each
> processor's non-NUMA scheduling domains are completely equal or
> completely disjoint. If a non-NUMA scheduling domain partially overlaps
> another, scheduling groups can break.
>
> This series adds for_each_cpu_from() as a generic cpumask macro to
> optimize topology_span_sane() by removing duplicate comparisons. The
> total number of comparisons is reduced from N * (N - 1) to
> N * (N - 1) / 2 (per non-NUMA scheduling domain level), decreasing the
> boot time by approximately 20 seconds and preventing the soft lockup on
> the mentioned systems.
>
> Kyle Meyer (2):
> cpumask: Add for_each_cpu_from()
> sched/topology: Optimize topology_span_sane()
I somehow never got 2/2, and it doesn't show up on lore.kernel.org
either. I can see it from Yury's reply and it looks OK to me, but you'll
have to resend it for maintainers to be able to pick it up.
>
> include/linux/cpumask.h | 10 ++++++++++
> kernel/sched/topology.c | 6 ++----
> 2 files changed, 12 insertions(+), 4 deletions(-)
>
> --
> 2.44.0
Powered by blists - more mailing lists