Re: [PATCH v10 12/13] khugepaged: add per-order mTHP khugepaged stats
From: Nico Pache
Date: Tue Aug 19 2025 - 10:23:51 EST
On Tue, Aug 19, 2025 at 7:49 AM Nico Pache <npache@xxxxxxxxxx> wrote:
>
> With mTHP support inplace, let add the per-order mTHP stats for
> exceeding NONE, SWAP, and SHARED.
>
> Signed-off-by: Nico Pache <npache@xxxxxxxxxx>
I had git send email error and had to resend this patch (12) and patch
13, but i forgot the in-reply-to
please ignore this one and reply to correct version
https://lore.kernel.org/lkml/20250819141610.626140-1-npache@xxxxxxxxxx/
--in-reply-to=20250819141610.626140-1-npache@xxxxxxxxxx
-- Nico
> ---
> Documentation/admin-guide/mm/transhuge.rst | 17 +++++++++++++++++
> include/linux/huge_mm.h | 3 +++
> mm/huge_memory.c | 7 +++++++
> mm/khugepaged.c | 16 +++++++++++++---
> 4 files changed, 40 insertions(+), 3 deletions(-)
>
> diff --git a/Documentation/admin-guide/mm/transhuge.rst b/Documentation/admin-guide/mm/transhuge.rst
> index 7ccb93e22852..b85547ac4fe9 100644
> --- a/Documentation/admin-guide/mm/transhuge.rst
> +++ b/Documentation/admin-guide/mm/transhuge.rst
> @@ -705,6 +705,23 @@ nr_anon_partially_mapped
> an anonymous THP as "partially mapped" and count it here, even though it
> is not actually partially mapped anymore.
>
> +collapse_exceed_swap_pte
> + The number of anonymous THP which contain at least one swap PTE.
> + Currently khugepaged does not support collapsing mTHP regions that
> + contain a swap PTE.
> +
> +collapse_exceed_none_pte
> + The number of anonymous THP which have exceeded the none PTE threshold.
> + With mTHP collapse, a bitmap is used to gather the state of a PMD region
> + and is then recursively checked from largest to smallest order against
> + the scaled max_ptes_none count. This counter indicates that the next
> + enabled order will be checked.
> +
> +collapse_exceed_shared_pte
> + The number of anonymous THP which contain at least one shared PTE.
> + Currently khugepaged does not support collapsing mTHP regions that
> + contain a shared PTE.
> +
> As the system ages, allocating huge pages may be expensive as the
> system uses memory compaction to copy data around memory to free a
> huge page for use. There are some counters in ``/proc/vmstat`` to help
> diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
> index 4ada5d1f7297..6f1593d0b4b5 100644
> --- a/include/linux/huge_mm.h
> +++ b/include/linux/huge_mm.h
> @@ -144,6 +144,9 @@ enum mthp_stat_item {
> MTHP_STAT_SPLIT_DEFERRED,
> MTHP_STAT_NR_ANON,
> MTHP_STAT_NR_ANON_PARTIALLY_MAPPED,
> + MTHP_STAT_COLLAPSE_EXCEED_SWAP,
> + MTHP_STAT_COLLAPSE_EXCEED_NONE,
> + MTHP_STAT_COLLAPSE_EXCEED_SHARED,
> __MTHP_STAT_COUNT
> };
>
> diff --git a/mm/huge_memory.c b/mm/huge_memory.c
> index 20d005c2c61f..9f0470c3e983 100644
> --- a/mm/huge_memory.c
> +++ b/mm/huge_memory.c
> @@ -639,6 +639,10 @@ DEFINE_MTHP_STAT_ATTR(split_failed, MTHP_STAT_SPLIT_FAILED);
> DEFINE_MTHP_STAT_ATTR(split_deferred, MTHP_STAT_SPLIT_DEFERRED);
> DEFINE_MTHP_STAT_ATTR(nr_anon, MTHP_STAT_NR_ANON);
> DEFINE_MTHP_STAT_ATTR(nr_anon_partially_mapped, MTHP_STAT_NR_ANON_PARTIALLY_MAPPED);
> +DEFINE_MTHP_STAT_ATTR(collapse_exceed_swap_pte, MTHP_STAT_COLLAPSE_EXCEED_SWAP);
> +DEFINE_MTHP_STAT_ATTR(collapse_exceed_none_pte, MTHP_STAT_COLLAPSE_EXCEED_NONE);
> +DEFINE_MTHP_STAT_ATTR(collapse_exceed_shared_pte, MTHP_STAT_COLLAPSE_EXCEED_SHARED);
> +
>
> static struct attribute *anon_stats_attrs[] = {
> &anon_fault_alloc_attr.attr,
> @@ -655,6 +659,9 @@ static struct attribute *anon_stats_attrs[] = {
> &split_deferred_attr.attr,
> &nr_anon_attr.attr,
> &nr_anon_partially_mapped_attr.attr,
> + &collapse_exceed_swap_pte_attr.attr,
> + &collapse_exceed_none_pte_attr.attr,
> + &collapse_exceed_shared_pte_attr.attr,
> NULL,
> };
>
> diff --git a/mm/khugepaged.c b/mm/khugepaged.c
> index c13bc583a368..5a3386043f39 100644
> --- a/mm/khugepaged.c
> +++ b/mm/khugepaged.c
> @@ -594,7 +594,9 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma,
> continue;
> } else {
> result = SCAN_EXCEED_NONE_PTE;
> - count_vm_event(THP_SCAN_EXCEED_NONE_PTE);
> + if (order == HPAGE_PMD_ORDER)
> + count_vm_event(THP_SCAN_EXCEED_NONE_PTE);
> + count_mthp_stat(order, MTHP_STAT_COLLAPSE_EXCEED_NONE);
> goto out;
> }
> }
> @@ -633,10 +635,17 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma,
> * shared may cause a future higher order collapse on a
> * rescan of the same range.
> */
> - if (order != HPAGE_PMD_ORDER || (cc->is_khugepaged &&
> - shared > khugepaged_max_ptes_shared)) {
> + if (order != HPAGE_PMD_ORDER) {
> + result = SCAN_EXCEED_SHARED_PTE;
> + count_mthp_stat(order, MTHP_STAT_COLLAPSE_EXCEED_SHARED);
> + goto out;
> + }
> +
> + if (cc->is_khugepaged &&
> + shared > khugepaged_max_ptes_shared) {
> result = SCAN_EXCEED_SHARED_PTE;
> count_vm_event(THP_SCAN_EXCEED_SHARED_PTE);
> + count_mthp_stat(order, MTHP_STAT_COLLAPSE_EXCEED_SHARED);
> goto out;
> }
> }
> @@ -1084,6 +1093,7 @@ static int __collapse_huge_page_swapin(struct mm_struct *mm,
> * range.
> */
> if (order != HPAGE_PMD_ORDER) {
> + count_mthp_stat(order, MTHP_STAT_COLLAPSE_EXCEED_SWAP);
> pte_unmap(pte);
> mmap_read_unlock(mm);
> result = SCAN_EXCEED_SWAP_PTE;
> --
> 2.50.1
>