Received-SPF: pass (google.com: domain of linux-kernel+bounces-132398-linux.lists.archive=gmail.com@vger.kernel.org designates 147.75.80.249 as permitted sender) client-ip=147.75.80.249;
Precedence: bulk
MIME-Version: 1.0
References: <20240327144537.4165578-1-ryan.roberts@arm.com>
 <20240327144537.4165578-6-ryan.roberts@arm.com> <CAGsJ_4x40DxoukgRuEt3OKP7dESj3w+HXz=dHYR+PH8LjtCnEA@mail.gmail.com>
 <63c9caf4-3af4-4149-b3c2-e677788cb11f@arm.com>
In-Reply-To: <63c9caf4-3af4-4149-b3c2-e677788cb11f@arm.com>
From: Barry Song <21cnbao@gmail.com>
Date: Fri, 5 Apr 2024 17:06:03 +1300
Message-ID: <CAGsJ_4xocWy7PyHbgWhaK1gQeHADMAng3cFtnPHFW4MGB7qkBA@mail.gmail.com>
Subject: Re: [PATCH v5 5/6] mm: vmscan: Avoid split during shrink_folio_list()
To: Ryan Roberts <ryan.roberts@arm.com>
Cc: Andrew Morton <akpm@linux-foundation.org>, David Hildenbrand <david@redhat.com>, 
	Matthew Wilcox <willy@infradead.org>, Huang Ying <ying.huang@intel.com>, Gao Xiang <xiang@kernel.org>, 
	Yu Zhao <yuzhao@google.com>, Yang Shi <shy828301@gmail.com>, Michal Hocko <mhocko@suse.com>, 
	Kefeng Wang <wangkefeng.wang@huawei.com>, Chris Li <chrisl@kernel.org>, 
	Lance Yang <ioworker0@gmail.com>, linux-mm@kvack.org, linux-kernel@vger.kernel.org, 
	Barry Song <v-songbaohua@oppo.com>
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable

On Wed, Apr 3, 2024 at 2:10=E2=80=AFAM Ryan Roberts <ryan.roberts@arm.com> =
wrote:
>
> On 28/03/2024 08:18, Barry Song wrote:
> > On Thu, Mar 28, 2024 at 3:45=E2=80=AFAM Ryan Roberts <ryan.roberts@arm.=
com> wrote:
> >>
> >> Now that swap supports storing all mTHP sizes, avoid splitting large
> >> folios before swap-out. This benefits performance of the swap-out path
> >> by eliding split_folio_to_list(), which is expensive, and also sets us
> >> up for swapping in large folios in a future series.
> >>
> >> If the folio is partially mapped, we continue to split it since we wan=
t
> >> to avoid the extra IO overhead and storage of writing out pages
> >> uneccessarily.
> >>
> >> Reviewed-by: David Hildenbrand <david@redhat.com>
> >> Reviewed-by: Barry Song <v-songbaohua@oppo.com>
> >> Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
> >> ---
> >>  mm/vmscan.c | 9 +++++----
> >>  1 file changed, 5 insertions(+), 4 deletions(-)
> >>
> >> diff --git a/mm/vmscan.c b/mm/vmscan.c
> >> index 00adaf1cb2c3..293120fe54f3 100644
> >> --- a/mm/vmscan.c
> >> +++ b/mm/vmscan.c
> >> @@ -1223,11 +1223,12 @@ static unsigned int shrink_folio_list(struct l=
ist_head *folio_list,
> >>                                         if (!can_split_folio(folio, NU=
LL))
> >>                                                 goto activate_locked;
> >>                                         /*
> >> -                                        * Split folios without a PMD =
map right
> >> -                                        * away. Chances are some or a=
ll of the
> >> -                                        * tail pages can be freed wit=
hout IO.
> >> +                                        * Split partially mapped foli=
os right
> >> +                                        * away. We can free the unmap=
ped pages
> >> +                                        * without IO.
> >>                                          */
> >> -                                       if (!folio_entire_mapcount(fol=
io) &&
> >> +                                       if (data_race(!list_empty(
> >> +                                               &folio->_deferred_list=
)) &&
> >>                                             split_folio_to_list(folio,
> >>                                                                 folio_=
list))
> >>                                                 goto activate_locked;
> >
> > Hi Ryan,
> >
> > Sorry for bringing up another minor issue at this late stage.
>
> No problem - I'd rather take a bit longer and get it right, rather than r=
ush it
> and get it wrong!
>
> >
> > During the debugging of thp counter patch v2, I noticed the discrepancy=
 between
> > THP_SWPOUT_FALLBACK and THP_SWPOUT.
> >
> > Should we make adjustments to the counter?
>
> Yes, agreed; we want to be consistent here with all the other existing TH=
P
> counters; they only refer to PMD-sized THP. I'll make the change for the =
next
> version.
>
> I guess we will eventually want equivalent counters for per-size mTHP usi=
ng the
> framework you are adding.

Hi Ryan,

Today, I created counters for per-order SWPOUT and SWPOUT_FALLBACK.
I'd appreciate any
suggestions you might have before I submit this as patch 2/2 of my
mTHP counters series.

diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index cc13fa14aa32..762a6d8759b9 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -267,6 +267,8 @@ unsigned long thp_vma_allowable_orders(struct
vm_area_struct *vma,
 enum thp_stat_item {
        THP_STAT_ANON_ALLOC,
        THP_STAT_ANON_ALLOC_FALLBACK,
+       THP_STAT_ANON_SWPOUT,
+       THP_STAT_ANON_SWPOUT_FALLBACK,
        __THP_STAT_COUNT
 };

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index e704b4408181..7f2b5d2852cc 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -554,10 +554,14 @@ static struct kobj_attribute _name##_attr =3D
__ATTR_RO(_name)

 THP_STATE_ATTR(anon_alloc, THP_STAT_ANON_ALLOC);
 THP_STATE_ATTR(anon_alloc_fallback, THP_STAT_ANON_ALLOC_FALLBACK);
+THP_STATE_ATTR(anon_swpout, THP_STAT_ANON_SWPOUT);
+THP_STATE_ATTR(anon_swpout_fallback, THP_STAT_ANON_SWPOUT_FALLBACK);

 static struct attribute *stats_attrs[] =3D {
        &anon_alloc_attr.attr,
        &anon_alloc_fallback_attr.attr,
+       &anon_swpout_attr.attr,
+       &anon_swpout_fallback_attr.attr,
        NULL,
 };

diff --git a/mm/page_io.c b/mm/page_io.c
index a9a7c236aecc..be4f822b39f8 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -212,13 +212,16 @@ int swap_writepage(struct page *page, struct
writeback_control *wbc)

 static inline void count_swpout_vm_event(struct folio *folio)
 {
+       long nr_pages =3D folio_nr_pages(folio);
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
        if (unlikely(folio_test_pmd_mappable(folio))) {
                count_memcg_folio_events(folio, THP_SWPOUT, 1);
                count_vm_event(THP_SWPOUT);
        }
+       if (nr_pages > 0 && nr_pages <=3D HPAGE_PMD_NR)
+               count_thp_state(folio_order(folio), THP_STAT_ANON_SWPOUT);
 #endif
-       count_vm_events(PSWPOUT, folio_nr_pages(folio));
+       count_vm_events(PSWPOUT, nr_pages);
 }

 #if defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP)
diff --git a/mm/vmscan.c b/mm/vmscan.c
index ffc4553c8615..b7c5fbd830b6 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1247,6 +1247,10 @@ static unsigned int shrink_folio_list(struct
list_head *folio_list,
                                                count_vm_event(
                                                        THP_SWPOUT_FALLBACK=
);
                                        }
+                                       if (nr_pages > 0 && nr_pages
<=3D HPAGE_PMD_NR)
+
count_thp_state(folio_order(folio),
+
THP_STAT_ANON_SWPOUT_FALLBACK);
+
 #endif
                                        if (!add_to_swap(folio))
                                                goto activate_locked_split;


Thanks
Barry