On 28/06/2024 14:07, Lance Yang wrote:
> Currently, the split counters in THP statistics no longer include
> PTE-mapped mTHP. Therefore, we propose introducing per-order mTHP split
> counters to monitor the frequency of mTHP splits. This will help developers
> better analyze and optimize system performance.
>
> /sys/kernel/mm/transparent_hugepage/hugepages-<size>/stats
> split
> split_failed
> split_deferred
>
> Signed-off-by: Mingzhe Yang <mingzhe.yang@xxxxxx>
> Signed-off-by: Lance Yang <ioworker0@xxxxxxxxx>
LGTM!
Reviewed-by: Ryan Roberts <ryan.roberts@xxxxxxx>
> ---
> include/linux/huge_mm.h | 3 +++
> mm/huge_memory.c | 19 ++++++++++++++-----
> 2 files changed, 17 insertions(+), 5 deletions(-)
>
> diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
> index 212cca384d7e..cee3c5da8f0e 100644
> --- a/include/linux/huge_mm.h
> +++ b/include/linux/huge_mm.h
> @@ -284,6 +284,9 @@ enum mthp_stat_item {
> MTHP_STAT_FILE_ALLOC,
> MTHP_STAT_FILE_FALLBACK,
> MTHP_STAT_FILE_FALLBACK_CHARGE,
> + MTHP_STAT_SPLIT,
> + MTHP_STAT_SPLIT_FAILED,
> + MTHP_STAT_SPLIT_DEFERRED,
> __MTHP_STAT_COUNT
> };
>
> diff --git a/mm/huge_memory.c b/mm/huge_memory.c
> index c7ce28f6b7f3..a633206375af 100644
> --- a/mm/huge_memory.c
> +++ b/mm/huge_memory.c
> @@ -559,6 +559,9 @@ DEFINE_MTHP_STAT_ATTR(swpout_fallback, MTHP_STAT_SWPOUT_FALLBACK);
> DEFINE_MTHP_STAT_ATTR(file_alloc, MTHP_STAT_FILE_ALLOC);
> DEFINE_MTHP_STAT_ATTR(file_fallback, MTHP_STAT_FILE_FALLBACK);
> DEFINE_MTHP_STAT_ATTR(file_fallback_charge, MTHP_STAT_FILE_FALLBACK_CHARGE);
> +DEFINE_MTHP_STAT_ATTR(split, MTHP_STAT_SPLIT);
> +DEFINE_MTHP_STAT_ATTR(split_failed, MTHP_STAT_SPLIT_FAILED);
> +DEFINE_MTHP_STAT_ATTR(split_deferred, MTHP_STAT_SPLIT_DEFERRED);
>
> static struct attribute *stats_attrs[] = {
> &anon_fault_alloc_attr.attr,
> @@ -569,6 +572,9 @@ static struct attribute *stats_attrs[] = {
> &file_alloc_attr.attr,
> &file_fallback_attr.attr,
> &file_fallback_charge_attr.attr,
> + &split_attr.attr,
> + &split_failed_attr.attr,
> + &split_deferred_attr.attr,
> NULL,
> };
>
> @@ -3068,7 +3074,7 @@ int split_huge_page_to_list_to_order(struct page *page, struct list_head *list,
> XA_STATE_ORDER(xas, &folio->mapping->i_pages, folio->index, new_order);
> struct anon_vma *anon_vma = NULL;
> struct address_space *mapping = NULL;
> - bool is_thp = folio_test_pmd_mappable(folio);
> + int order = folio_order(folio);
> int extra_pins, ret;
> pgoff_t end;
> bool is_hzp;
> @@ -3076,7 +3082,7 @@ int split_huge_page_to_list_to_order(struct page *page, struct list_head *list,
> VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
> VM_BUG_ON_FOLIO(!folio_test_large(folio), folio);
>
> - if (new_order >= folio_order(folio))
> + if (new_order >= order)
> return -EINVAL;
>
> if (folio_test_anon(folio)) {
> @@ -3253,8 +3259,9 @@ int split_huge_page_to_list_to_order(struct page *page, struct list_head *list,
> i_mmap_unlock_read(mapping);
> out:
> xas_destroy(&xas);
> - if (is_thp)
> + if (order >= HPAGE_PMD_ORDER)
> count_vm_event(!ret ? THP_SPLIT_PAGE : THP_SPLIT_PAGE_FAILED);
> + count_mthp_stat(order, !ret ? MTHP_STAT_SPLIT : MTHP_STAT_SPLIT_FAILED);
> return ret;
> }
>
> @@ -3278,13 +3285,14 @@ void deferred_split_folio(struct folio *folio)
> #ifdef CONFIG_MEMCG
> struct mem_cgroup *memcg = folio_memcg(folio);
> #endif
> + int order = folio_order(folio);
> unsigned long flags;
>
> /*
> * Order 1 folios have no space for a deferred list, but we also
> * won't waste much memory by not adding them to the deferred list.
> */
> - if (folio_order(folio) <= 1)
> + if (order <= 1)
> return;
>
> /*
> @@ -3305,8 +3313,9 @@ void deferred_split_folio(struct folio *folio)
>
> spin_lock_irqsave(&ds_queue->split_queue_lock, flags);
> if (list_empty(&folio->_deferred_list)) {
> - if (folio_test_pmd_mappable(folio))
> + if (order >= HPAGE_PMD_ORDER)
> count_vm_event(THP_DEFERRED_SPLIT_PAGE);
> + count_mthp_stat(order, MTHP_STAT_SPLIT_DEFERRED);
> list_add_tail(&folio->_deferred_list, &ds_queue->split_queue);
> ds_queue->split_queue_len++;
> #ifdef CONFIG_MEMCG
