Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
MIME-Version: 1.0
References: <CAHbLzkq5rSHUSbHegM5mURytS7nEDyHHbxOYn8DaBwYB0qGocw@mail.gmail.com>
 <20200710141827.netxb2rimpge4qkd@box>
In-Reply-To: <20200710141827.netxb2rimpge4qkd@box>
From:   Yang Shi <shy828301@gmail.com>
Date:   Fri, 10 Jul 2020 10:32:24 -0700
Message-ID: <CAHbLzkq+Rs9662FA+vChBt5it2SRXS0QiwG0Rx8m+BZFad6uyA@mail.gmail.com>
Subject: Re: [RFC] Kill THP deferred split queue?
To:     "Kirill A. Shutemov" <kirill@shutemov.name>
Cc:     "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>,
        Linux MM <linux-mm@kvack.org>,
        Linux Kernel Mailing List <linux-kernel@vger.kernel.org>
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On Fri, Jul 10, 2020 at 7:18 AM Kirill A. Shutemov <kirill@shutemov.name> w=
rote:
>
> On Tue, Jul 07, 2020 at 11:00:16AM -0700, Yang Shi wrote:
> > Hi folks,
> >
> > The THP deferred split queue is used to store PTE mapped THP (i.e.
> > partial unmapped THP) then they will get split by deferred split
> > shrinker when memory pressure kicks in.
> >
> > Now the page reclaim could handle such cases nicely without calling
> > the shrinker. Since the THPs on deferred split queue is not PMD mapped
> > so they will be split unconditionally, then the unmapped sub pages
> > would get freed. Please see the below code snippet:
> >
> >                              if (PageTransHuge(page)) {
> >                                         /* cannot split THP, skip it */
> >                                         if (!can_split_huge_page(page, =
NULL))
> >                                                 goto activate_locked;
> >                                         /*
> >                                          * Split pages without a PMD ma=
p right
> >                                          * away. Chances are some or al=
l of the
> >                                          * tail pages can be freed with=
out IO.
> >                                          */
> >                                         if (!compound_mapcount(page) &&
> >                                             split_huge_page_to_list(pag=
e,
> >                                                                     pag=
e_list))
> >                                                 goto activate_locked;
> >                                 }
> >
> > Then the unmapped pages will be moved to free_list by
> > move_pages_to_lru() called by shrink_inactive_list(). The mapped sub
> > pages will be kept on LRU. So, it does exactly the same thing as
> > deferred split shrinker and at the exact same timing.
> >
> > The only benefit of shrinker is they can be split and freed via "echo
> > 2 > /proc/sys/vm/drop_caches=E2=80=9D, but I'm not sure how many people=
 rely
> > on this?
> >
> > The benefit of killing deferred split queue is code simplification.
> >
> > Any comment is welcome.
>
> The point of handing it in shrinker is that these pages have to be droppe=
d
> before anything potentially useful get reclaimed. If the compound page ha=
s
> any active PTEs you are unlikely to reach it during normal reclaim.

Thanks. Yes, it looks so. We can't tell if the THP has inactive PTEs
or not easily via page_referenced(). It looks the whole THP would be
treated as active as long as one subpage is active.

>
> --
>  Kirill A. Shutemov