Received-SPF: pass (google.com: domain of linux-kernel+bounces-77492-linux.lists.archive=gmail.com@vger.kernel.org designates 139.178.88.99 as permitted sender) client-ip=139.178.88.99;
Precedence: bulk
MIME-Version: 1.0
References: <20240102184633.748113-1-urezki@gmail.com> <ZdcHXFMq0cwmVKfM@pc636>
In-Reply-To: <ZdcHXFMq0cwmVKfM@pc636>
From: Pedro Falcato <pedro.falcato@gmail.com>
Date: Thu, 22 Feb 2024 23:15:59 +0000
Message-ID: <CAKbZUD3+PJUoXee3MNvToy1zRnDoPoPqMjNAf5_87Uh-u2377w@mail.gmail.com>
Subject: Re: [PATCH v3 00/11] Mitigate a vmap lock contention v3
To: Uladzislau Rezki <urezki@gmail.com>
Cc: Matthew Wilcox <willy@infradead.org>, Mel Gorman <mgorman@suse.de>, 
	kirill.shutemov@linux.intel.com, Vishal Moola <vishal.moola@gmail.com>, 
	Andrew Morton <akpm@linux-foundation.org>, LKML <linux-kernel@vger.kernel.org>, 
	Baoquan He <bhe@redhat.com>, Lorenzo Stoakes <lstoakes@gmail.com>, 
	Christoph Hellwig <hch@infradead.org>, "Liam R . Howlett" <Liam.Howlett@oracle.com>, 
	Dave Chinner <david@fromorbit.com>, "Paul E . McKenney" <paulmck@kernel.org>, 
	Joel Fernandes <joel@joelfernandes.org>, Oleksiy Avramchenko <oleksiy.avramchenko@sony.com>, 
	linux-mm@kvack.org
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable

Hi,

On Thu, Feb 22, 2024 at 8:35=E2=80=AFAM Uladzislau Rezki <urezki@gmail.com>=
 wrote:
>
> Hello, Folk!
>
>[...]
> pagetable_alloc - gets increased as soon as a higher pressure is applied =
by
> increasing number of workers. Running same number of jobs on a next run
> does not increase it and stays on same level as on previous.
>
> /**
>  * pagetable_alloc - Allocate pagetables
>  * @gfp:    GFP flags
>  * @order:  desired pagetable order
>  *
>  * pagetable_alloc allocates memory for page tables as well as a page tab=
le
>  * descriptor to describe that memory.
>  *
>  * Return: The ptdesc describing the allocated page tables.
>  */
> static inline struct ptdesc *pagetable_alloc(gfp_t gfp, unsigned int orde=
r)
> {
>         struct page *page =3D alloc_pages(gfp | __GFP_COMP, order);
>
>         return page_ptdesc(page);
> }
>
> Could you please comment on it? Or do you have any thought? Is it expecte=
d?
> Is a page-table ever shrink?

It's my understanding that the vunmap_range helpers don't actively
free page tables, they just clear PTEs. munmap does free them in
mmap.c:free_pgtables, maybe something could be worked up for vmalloc
too.
I would not be surprised if the memory increase you're seeing is more
or less correlated to the maximum vmalloc footprint throughout the
whole test.

--=20
Pedro