Re: [PATCH v5 5/6] mm: vmscan: Avoid split during shrink_folio_list()

From: Barry Song
Date: Tue Apr 02 2024 - 18:54:21 EST


On Wed, Apr 3, 2024 at 2:22 AM Ryan Roberts <ryan.roberts@xxxxxxx> wrote:
>
> On 02/04/2024 14:10, Ryan Roberts wrote:
> > On 28/03/2024 08:18, Barry Song wrote:
> >> On Thu, Mar 28, 2024 at 3:45 AM Ryan Roberts <ryan.roberts@armcom> 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 want
> >>> to avoid the extra IO overhead and storage of writing out pages
> >>> uneccessarily.
> >>>
> >>> Reviewed-by: David Hildenbrand <david@xxxxxxxxxx>
> >>> Reviewed-by: Barry Song <v-songbaohua@xxxxxxxx>
> >>> Signed-off-by: Ryan Roberts <ryan.roberts@xxxxxxx>
> >>> ---
> >>> 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 list_head *folio_list,
> >>> if (!can_split_folio(folio, NULL))
> >>> goto activate_locked;
> >>> /*
> >>> - * Split folios without a PMD map right
> >>> - * away. Chances are some or all of the
> >>> - * tail pages can be freed without IO.
> >>> + * Split partially mapped folios right
> >>> + * away. We can free the unmapped pages
> >>> + * without IO.
> >>> */
> >>> - if (!folio_entire_mapcount(folio) &&
> >>> + 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 rush 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 THP
> > 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 using the
> > framework you are adding.
> >
> >>
> >> diff --git a/mm/vmscan.c b/mm/vmscan.c
> >> index 293120fe54f3..d7856603f689 100644
> >> --- a/mm/vmscan.c
> >> +++ b/mm/vmscan.c
> >> @@ -1241,8 +1241,10 @@ static unsigned int shrink_folio_list(struct
> >> list_head *folio_list,
> >> folio_list))
> >> goto activate_locked;
> >> #ifdef CONFIG_TRANSPARENT_HUGEPAGE
> >> -
> >> count_memcg_folio_events(folio, THP_SWPOUT_FALLBACK, 1);
> >> - count_vm_event(THP_SWPOUT_FALLBACK);
> >> + if (folio_test_pmd_mappable(folio)) {
>
> This doesn't quite work because we have already split the folio here, so this
> will always return false. I've changed it to:
>
> if (nr_pages >= HPAGE_PMD_NR) {

make sense to me.

>
>
> >> +
> >> count_memcg_folio_events(folio, THP_SWPOUT_FALLBACK, 1);
> >> +
> >> count_vm_event(THP_SWPOUT_FALLBACK);
> >> + }
> >> #endif
> >> if (!add_to_swap(folio))
> >> goto activate_locked_split;
> >>
> >>
> >> Because THP_SWPOUT is only for pmd:
> >>
> >> static inline void count_swpout_vm_event(struct folio *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);
> >> }
> >> #endif
> >> count_vm_events(PSWPOUT, folio_nr_pages(folio));
> >> }
> >>
> >> I can provide per-order counters for this in my THP counter patch.
> >>
> >>> --
> >>> 2.25.1
> >>>
> >>

Thanks
Barry