[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <CALOAHbCuYS6gcc4zMT3Pgo1ZcueuCMsTd3xSi-FkhLb3fBU8gA@mail.gmail.com>
Date: Wed, 28 May 2025 10:13:01 +0800
From: Yafang Shao <laoar.shao@...il.com>
To: Michal Koutný <mkoutny@...e.com>
Cc: mingo@...hat.com, peterz@...radead.org, hannes@...xchg.org,
juri.lelli@...hat.com, vincent.guittot@...aro.org, dietmar.eggemann@....com,
rostedt@...dmis.org, bsegall@...gle.com, mgorman@...e.de, vschneid@...hat.com,
surenb@...gle.com, linux-kernel@...r.kernel.org, cgroups@...r.kernel.org,
lkp@...el.com, Eric Dumazet <edumazet@...gle.com>
Subject: Re: [PATCH v9 2/2] sched: Annotate sched_clock_irqtime with __read_mostly
On Tue, May 27, 2025 at 11:33 PM Michal Koutný <mkoutny@...e.com> wrote:
>
> On Sun, May 11, 2025 at 11:08:00AM +0800, Yafang Shao <laoar.shao@...il.com> wrote:
> > Eric reported an issue [0] as follows,
> > : rebalance_domains() can attempt to change sched_balance_running
> > : more than 350,000 times per second on our servers.
> >
> > : If sched_clock_irqtime and sched_balance_running share the
> > : same cache line, we see a very high cost on hosts with 480 threads
> > : dealing with many interrupts.
>
> I'd say this patch could be independent from the "series".
I will send it separately.
>
> > While the rebalance_domains() issue has been resolved [1], we should
> > proactively annotate sched_clock_irqtime with __read_mostly to prevent
> > potential cacheline false sharing. This optimization is particularly
> > justified since sched_clock_irqtime is only modified during TSC instability
> > events.
> >
> > Link: https://lore.kernel.org/all/20250423174634.3009657-1-edumazet@google.com/ [0]
> > Link: https://lore.kernel.org/all/20250416035823.1846307-1-tim.c.chen@linux.intel.com/ [1]
> >
> > Reported-by: Eric Dumazet <edumazet@...gle.com>
> > Debugged-by: Eric Dumazet <edumazet@...gle.com>
> > Signed-off-by: Yafang Shao <laoar.shao@...il.com>
> > Cc: Eric Dumazet <edumazet@...gle.com>
>
> I can say
> Reviewed-by: Michal Koutný <mkoutny@...e.com>
Thanks for the review.
>
> but it'd be good to have also Tested-by: wrt the cache traffic
> reduction.
--
Regards
Yafang
Powered by blists - more mailing lists