From: Barry Song <v-songbaohua@oppo.com> This helps profile the sizes of folios being swapped in. Currently, only mTHP swap-out is being counted. The new interface can be found at: /sys/kernel/mm/transparent_hugepage/hugepages-<size>/stats swpin For example, cat /sys/kernel/mm/transparent_hugepage/hugepages-64kB/stats/swpin 12809 cat /sys/kernel/mm/transparent_hugepage/hugepages-32kB/stats/swpin 4763 Signed-off-by: Barry Song <v-songbaohua@oppo.com> Reviewed-by: Baolin Wang <baolin.wang@linux.alibaba.com> Acked-by: David Hildenbrand <david@redhat.com> Cc: Chris Li <chrisl@kernel.org> Cc: Yosry Ahmed <yosryahmed@google.com> Cc: "Huang, Ying" <ying.huang@intel.com> Cc: Kairui Song <kasong@tencent.com> Cc: Ryan Roberts <ryan.roberts@arm.com> Cc: Kanchana P Sridhar <kanchana.p.sridhar@intel.com> Cc: Usama Arif <usamaarif642@gmail.com> --- -v2: * collect Baolin's reviewed-by and David's acked-by, thanks! * add some examples for the interface in the changelog, Per Huang, Ying. thanks! * add a blank line in doc which was missed in v1. Documentation/admin-guide/mm/transhuge.rst | 4 ++++ include/linux/huge_mm.h | 1 + mm/huge_memory.c | 3 +++ mm/page_io.c | 3 +++ 4 files changed, 11 insertions(+) diff --git a/Documentation/admin-guide/mm/transhuge.rst b/Documentation/admin-guide/mm/transhuge.rst index XXXXXXX..XXXXXXX 100644 --- a/Documentation/admin-guide/mm/transhuge.rst +++ b/Documentation/admin-guide/mm/transhuge.rst @@ -XXX,XX +XXX,XX @@ zswpout is incremented every time a huge page is swapped out to zswap in one piece without splitting. +swpin + is incremented every time a huge page is swapped in from a non-zswap + swap device in one piece. + swpout is incremented every time a huge page is swapped out to a non-zswap swap device in one piece without splitting. diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index XXXXXXX..XXXXXXX 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -XXX,XX +XXX,XX @@ enum mthp_stat_item { MTHP_STAT_ANON_FAULT_FALLBACK, MTHP_STAT_ANON_FAULT_FALLBACK_CHARGE, MTHP_STAT_ZSWPOUT, + MTHP_STAT_SWPIN, MTHP_STAT_SWPOUT, MTHP_STAT_SWPOUT_FALLBACK, MTHP_STAT_SHMEM_ALLOC, diff --git a/mm/huge_memory.c b/mm/huge_memory.c index XXXXXXX..XXXXXXX 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -XXX,XX +XXX,XX @@ DEFINE_MTHP_STAT_ATTR(anon_fault_alloc, MTHP_STAT_ANON_FAULT_ALLOC); DEFINE_MTHP_STAT_ATTR(anon_fault_fallback, MTHP_STAT_ANON_FAULT_FALLBACK); DEFINE_MTHP_STAT_ATTR(anon_fault_fallback_charge, MTHP_STAT_ANON_FAULT_FALLBACK_CHARGE); DEFINE_MTHP_STAT_ATTR(zswpout, MTHP_STAT_ZSWPOUT); +DEFINE_MTHP_STAT_ATTR(swpin, MTHP_STAT_SWPIN); DEFINE_MTHP_STAT_ATTR(swpout, MTHP_STAT_SWPOUT); DEFINE_MTHP_STAT_ATTR(swpout_fallback, MTHP_STAT_SWPOUT_FALLBACK); #ifdef CONFIG_SHMEM @@ -XXX,XX +XXX,XX @@ static struct attribute *anon_stats_attrs[] = { &anon_fault_fallback_charge_attr.attr, #ifndef CONFIG_SHMEM &zswpout_attr.attr, + &swpin_attr.attr, &swpout_attr.attr, &swpout_fallback_attr.attr, #endif @@ -XXX,XX +XXX,XX @@ static struct attribute_group file_stats_attr_grp = { static struct attribute *any_stats_attrs[] = { #ifdef CONFIG_SHMEM &zswpout_attr.attr, + &swpin_attr.attr, &swpout_attr.attr, &swpout_fallback_attr.attr, #endif diff --git a/mm/page_io.c b/mm/page_io.c index XXXXXXX..XXXXXXX 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -XXX,XX +XXX,XX @@ static void sio_read_complete(struct kiocb *iocb, long ret) for (p = 0; p < sio->pages; p++) { struct folio *folio = page_folio(sio->bvec[p].bv_page); + count_mthp_stat(folio_order(folio), MTHP_STAT_SWPIN); count_memcg_folio_events(folio, PSWPIN, folio_nr_pages(folio)); folio_mark_uptodate(folio); folio_unlock(folio); @@ -XXX,XX +XXX,XX @@ static void swap_read_folio_bdev_sync(struct folio *folio, * attempt to access it in the page fault retry time check. */ get_task_struct(current); + count_mthp_stat(folio_order(folio), MTHP_STAT_SWPIN); count_memcg_folio_events(folio, PSWPIN, folio_nr_pages(folio)); count_vm_events(PSWPIN, folio_nr_pages(folio)); submit_bio_wait(&bio); @@ -XXX,XX +XXX,XX @@ static void swap_read_folio_bdev_async(struct folio *folio, bio->bi_iter.bi_sector = swap_folio_sector(folio); bio->bi_end_io = end_swap_bio_read; bio_add_folio_nofail(bio, folio, folio_size(folio), 0); + count_mthp_stat(folio_order(folio), MTHP_STAT_SWPIN); count_memcg_folio_events(folio, PSWPIN, folio_nr_pages(folio)); count_vm_events(PSWPIN, folio_nr_pages(folio)); submit_bio(bio); -- 2.39.3 (Apple Git-146) From: Barry Song <v-songbaohua@oppo.com> This helps profile the sizes of folios being swapped in. Currently, only mTHP swap-out is being counted. The new interface can be found at: /sys/kernel/mm/transparent_hugepage/hugepages-<size>/stats/swpin For example, $ cat /sys/kernel/mm/transparent_hugepage/hugepages-64kB/stats/swpin 12809 $ cat /sys/kernel/mm/transparent_hugepage/hugepages-32kB/stats/swpin 4763 Signed-off-by: Barry Song <v-songbaohua@oppo.com> Reviewed-by: Baolin Wang <baolin.wang@linux.alibaba.com> Acked-by: David Hildenbrand <david@redhat.com> Cc: Chris Li <chrisl@kernel.org> Cc: Yosry Ahmed <yosryahmed@google.com> Cc: "Huang, Ying" <ying.huang@intel.com> Cc: Kairui Song <kasong@tencent.com> Cc: Ryan Roberts <ryan.roberts@arm.com> Cc: Kanchana P Sridhar <kanchana.p.sridhar@intel.com> Cc: Usama Arif <usamaarif642@gmail.com> --- -v3: minor refine changelog per Huang, Ying. thanks! Documentation/admin-guide/mm/transhuge.rst | 4 ++++ include/linux/huge_mm.h | 1 + mm/huge_memory.c | 3 +++ mm/page_io.c | 3 +++ 4 files changed, 11 insertions(+) diff --git a/Documentation/admin-guide/mm/transhuge.rst b/Documentation/admin-guide/mm/transhuge.rst index XXXXXXX..XXXXXXX 100644 --- a/Documentation/admin-guide/mm/transhuge.rst +++ b/Documentation/admin-guide/mm/transhuge.rst @@ -XXX,XX +XXX,XX @@ zswpout is incremented every time a huge page is swapped out to zswap in one piece without splitting. +swpin + is incremented every time a huge page is swapped in from a non-zswap + swap device in one piece. + swpout is incremented every time a huge page is swapped out to a non-zswap swap device in one piece without splitting. diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index XXXXXXX..XXXXXXX 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -XXX,XX +XXX,XX @@ enum mthp_stat_item { MTHP_STAT_ANON_FAULT_FALLBACK, MTHP_STAT_ANON_FAULT_FALLBACK_CHARGE, MTHP_STAT_ZSWPOUT, + MTHP_STAT_SWPIN, MTHP_STAT_SWPOUT, MTHP_STAT_SWPOUT_FALLBACK, MTHP_STAT_SHMEM_ALLOC, diff --git a/mm/huge_memory.c b/mm/huge_memory.c index XXXXXXX..XXXXXXX 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -XXX,XX +XXX,XX @@ DEFINE_MTHP_STAT_ATTR(anon_fault_alloc, MTHP_STAT_ANON_FAULT_ALLOC); DEFINE_MTHP_STAT_ATTR(anon_fault_fallback, MTHP_STAT_ANON_FAULT_FALLBACK); DEFINE_MTHP_STAT_ATTR(anon_fault_fallback_charge, MTHP_STAT_ANON_FAULT_FALLBACK_CHARGE); DEFINE_MTHP_STAT_ATTR(zswpout, MTHP_STAT_ZSWPOUT); +DEFINE_MTHP_STAT_ATTR(swpin, MTHP_STAT_SWPIN); DEFINE_MTHP_STAT_ATTR(swpout, MTHP_STAT_SWPOUT); DEFINE_MTHP_STAT_ATTR(swpout_fallback, MTHP_STAT_SWPOUT_FALLBACK); #ifdef CONFIG_SHMEM @@ -XXX,XX +XXX,XX @@ static struct attribute *anon_stats_attrs[] = { &anon_fault_fallback_charge_attr.attr, #ifndef CONFIG_SHMEM &zswpout_attr.attr, + &swpin_attr.attr, &swpout_attr.attr, &swpout_fallback_attr.attr, #endif @@ -XXX,XX +XXX,XX @@ static struct attribute_group file_stats_attr_grp = { static struct attribute *any_stats_attrs[] = { #ifdef CONFIG_SHMEM &zswpout_attr.attr, + &swpin_attr.attr, &swpout_attr.attr, &swpout_fallback_attr.attr, #endif diff --git a/mm/page_io.c b/mm/page_io.c index XXXXXXX..XXXXXXX 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -XXX,XX +XXX,XX @@ static void sio_read_complete(struct kiocb *iocb, long ret) for (p = 0; p < sio->pages; p++) { struct folio *folio = page_folio(sio->bvec[p].bv_page); + count_mthp_stat(folio_order(folio), MTHP_STAT_SWPIN); count_memcg_folio_events(folio, PSWPIN, folio_nr_pages(folio)); folio_mark_uptodate(folio); folio_unlock(folio); @@ -XXX,XX +XXX,XX @@ static void swap_read_folio_bdev_sync(struct folio *folio, * attempt to access it in the page fault retry time check. */ get_task_struct(current); + count_mthp_stat(folio_order(folio), MTHP_STAT_SWPIN); count_memcg_folio_events(folio, PSWPIN, folio_nr_pages(folio)); count_vm_events(PSWPIN, folio_nr_pages(folio)); submit_bio_wait(&bio); @@ -XXX,XX +XXX,XX @@ static void swap_read_folio_bdev_async(struct folio *folio, bio->bi_iter.bi_sector = swap_folio_sector(folio); bio->bi_end_io = end_swap_bio_read; bio_add_folio_nofail(bio, folio, folio_size(folio), 0); + count_mthp_stat(folio_order(folio), MTHP_STAT_SWPIN); count_memcg_folio_events(folio, PSWPIN, folio_nr_pages(folio)); count_vm_events(PSWPIN, folio_nr_pages(folio)); submit_bio(bio); -- 2.39.3 (Apple Git-146)