| Message ID | 20240403114032.1162100-6-ryan.roberts@arm.com (mailing list archive) |
|---|---|
| State | New |
| Headers | show |
| Series | Swap-out mTHP without splitting | expand |
On 03.04.24 13:40, Ryan Roberts 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. > > THP_SWPOUT and THP_SWPOUT_FALLBACK counters should continue to count > events only for PMD-mappable folios to avoid user confusion. THP_SWPOUT > already has the appropriate guard. Add a guard for THP_SWPOUT_FALLBACK. > It may be appropriate to add per-size counters in future. > > 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 | 17 +++++++++++------ > 1 file changed, 11 insertions(+), 6 deletions(-) > > diff --git a/mm/vmscan.c b/mm/vmscan.c > index 00adaf1cb2c3..ffc4553c8615 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)) && Please violate the 80 chars rule where reasonable. " Statements longer than 80 columns should be broken into sensible chunks, unless exceeding 80 columns significantly increases readability and does not hide information. " Likely some of that code here should be refactored into readable sub-functions. codingstyle also mentions "The answer to that is that if you need more than 3 levels of indentation, you're screwed anyway, and should fix your program."
On 05/04/2024 11:42, David Hildenbrand wrote: > On 03.04.24 13:40, Ryan Roberts 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. >> >> THP_SWPOUT and THP_SWPOUT_FALLBACK counters should continue to count >> events only for PMD-mappable folios to avoid user confusion. THP_SWPOUT >> already has the appropriate guard. Add a guard for THP_SWPOUT_FALLBACK. >> It may be appropriate to add per-size counters in future. >> >> 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 | 17 +++++++++++------ >> 1 file changed, 11 insertions(+), 6 deletions(-) >> >> diff --git a/mm/vmscan.c b/mm/vmscan.c >> index 00adaf1cb2c3..ffc4553c8615 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)) && > > Please violate the 80 chars rule where reasonable. > > " > Statements longer than 80 columns should be broken into sensible chunks, unless > exceeding 80 columns significantly increases readability and does not hide > information. > " > > > Likely some of that code here should be refactored into readable sub-functions. > > codingstyle also mentions > > "The answer to that is that if you need more than 3 levels of indentation, > you're screwed anyway, and should fix your program." > Boo! :) Yeah, no problem, I'll sort this.
diff --git a/mm/vmscan.c b/mm/vmscan.c index 00adaf1cb2c3..ffc4553c8615 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; @@ -1240,8 +1241,12 @@ 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 (nr_pages >= HPAGE_PMD_NR) { + 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;