On Tue, Apr 4, 2023 at 10:13 AM Shakeel Butt <shakeelb@xxxxxxxxxx> wrote:
>
> On Tue, Apr 4, 2023 at 9:53 AM Michal Koutný <mkoutny@xxxxxxxx> wrote:
> >
> > Hello.
> >
> > On Thu, Mar 30, 2023 at 07:17:57PM +0000, Yosry Ahmed <yosryahmed@xxxxxxxxxx> wrote:
> > > static void __mem_cgroup_flush_stats(void)
> > > {
> > > - unsigned long flag;
> > > -
> > > - if (!spin_trylock_irqsave(&stats_flush_lock, flag))
> > > + /*
> > > + * We always flush the entire tree, so concurrent flushers can just
> > > + * skip. This avoids a thundering herd problem on the rstat global lock
> > > + * from memcg flushers (e.g. reclaim, refault, etc).
> > > + */
> > > + if (atomic_read(&stats_flush_ongoing) ||
> > > + atomic_xchg(&stats_flush_ongoing, 1))
> > > return;
> >
> > I'm curious about why this instead of
> >
> > if (atomic_xchg(&stats_flush_ongoing, 1))
> > return;
> >
> > Is that some microarchitectural cleverness?
> >
>
> Yes indeed it is. Basically we want to avoid unconditional cache
> dirtying. This pattern is also used at other places in the kernel like
> qspinlock.
Oh also take a look at
https://lore.kernel.org/all/20230404052228.15788-1-feng.tang@xxxxxxxxx/
