Re: [PATCH v9 2/2] sched: Annotate sched_clock_irqtime with __read_mostly

[Yafang Shao]

On Tue, May 27, 2025 at 11:33 PM Michal Koutný <mkoutny@xxxxxxxx> wrote:
>
> On Sun, May 11, 2025 at 11:08:00AM +0800, Yafang Shao <laoar.shao@xxxxxxxxx> 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@xxxxxxxxxx/ [0]
> > Link: https://lore.kernel.org/all/20250416035823.1846307-1-tim.c.chen@xxxxxxxxxxxxxxx/ [1]
> >
> > Reported-by: Eric Dumazet <edumazet@xxxxxxxxxx>
> > Debugged-by: Eric Dumazet <edumazet@xxxxxxxxxx>
> > Signed-off-by: Yafang Shao <laoar.shao@xxxxxxxxx>
> > Cc: Eric Dumazet <edumazet@xxxxxxxxxx>
>
> I can say
> Reviewed-by: Michal Koutný <mkoutny@xxxxxxxx>

Thanks for the review.

>
> but it'd be good to have also Tested-by: wrt the cache traffic
> reduction.


-- 
Regards
Yafang