Re: [PATCH] thp: reduce usage of huge zero page's atomic counter

From: Andrew Morton
Date: Tue Aug 30 2016 - 01:19:10 EST


On Tue, 30 Aug 2016 10:44:21 +0530 Anshuman Khandual <khandual@xxxxxxxxxxxxxxxxxx> wrote:

> On 08/30/2016 04:20 AM, Andrew Morton wrote:
> > On Mon, 29 Aug 2016 14:31:20 +0800 Aaron Lu <aaron.lu@xxxxxxxxx> wrote:
> >
> >> >
> >> > The global zero page is used to satisfy an anonymous read fault. If
> >> > THP(Transparent HugePage) is enabled then the global huge zero page is used.
> >> > The global huge zero page uses an atomic counter for reference counting
> >> > and is allocated/freed dynamically according to its counter value.
> >> >
> >> > CPU time spent on that counter will greatly increase if there are
> >> > a lot of processes doing anonymous read faults. This patch proposes a
> >> > way to reduce the access to the global counter so that the CPU load
> >> > can be reduced accordingly.
> >> >
> >> > To do this, a new flag of the mm_struct is introduced: MMF_USED_HUGE_ZERO_PAGE.
> >> > With this flag, the process only need to touch the global counter in
> >> > two cases:
> >> > 1 The first time it uses the global huge zero page;
> >> > 2 The time when mm_user of its mm_struct reaches zero.
> >> >
> >> > Note that right now, the huge zero page is eligible to be freed as soon
> >> > as its last use goes away. With this patch, the page will not be
> >> > eligible to be freed until the exit of the last process from which it
> >> > was ever used.
> >> >
> >> > And with the use of mm_user, the kthread is not eligible to use huge
> >> > zero page either. Since no kthread is using huge zero page today, there
> >> > is no difference after applying this patch. But if that is not desired,
> >> > I can change it to when mm_count reaches zero.
>
> > I suppose we could simply never free the zero huge page - if some
> > process has used it in the past, others will probably use it in the
> > future. One wonders how useful this optimization is...
>
> Yeah, what prevents us from doing away with this lock altogether and
> keep one zero filled huge page (after a process has used it once) for
> ever to be mapped across all the read faults ? A 16MB / 2MB huge page
> is too much of memory loss on a THP enabled system ? We can also save
> on allocation time.

Sounds OK to me. But only if it makes a useful performance benefit to
something that someone cares about!

otoh, that patch is simple enough...