The following data is traced by bpftrace on a desktop system. After
the system has been left idle for 10 minutes upon booting, a lot of
SCAN_PMD_MAPPED or SCAN_NO_PTE_TABLE are observed during a full scan
by khugepaged.
@scan_pmd_status[1]: 1 ## SCAN_SUCCEED
@scan_pmd_status[6]: 2 ## SCAN_EXCEED_SHARED_PTE
@scan_pmd_status[3]: 142 ## SCAN_PMD_MAPPED
@scan_pmd_status[2]: 178 ## SCAN_NO_PTE_TABLE
total progress size: 674 MB
Total time : 419 seconds ## include khugepaged_scan_sleep_millisecs
The khugepaged_scan list save all task that support collapse into hugepage,
as long as the task is not destroyed, khugepaged will not remove it from
the khugepaged_scan list. This exist a phenomenon where task has already
collapsed all memory regions into hugepage, but khugepaged continues to
scan it, which wastes CPU time and invalid, and due to
khugepaged_scan_sleep_millisecs (default 10s) causes a long wait for
scanning a large number of invalid task, so scanning really valid task
is later.
After applying this patch, when the memory is either SCAN_PMD_MAPPED or
SCAN_NO_PTE_TABLE, just skip it, as follow:
@scan_pmd_status[6]: 2
@scan_pmd_status[3]: 147
@scan_pmd_status[2]: 173
total progress size: 45 MB
Total time : 20 seconds
Signed-off-by: Vernon Yang <yanglincheng@kylinos.cn>
---
mm/khugepaged.c | 23 ++++++++++++++++++-----
1 file changed, 18 insertions(+), 5 deletions(-)
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 9f99f61689f8..2b3685b195f5 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -66,7 +66,10 @@ enum scan_result {
static struct task_struct *khugepaged_thread __read_mostly;
static DEFINE_MUTEX(khugepaged_mutex);
-/* default scan 8*HPAGE_PMD_NR ptes (or vmas) every 10 second */
+/*
+ * default scan 8*HPAGE_PMD_NR ptes, pmd_mapped, no_pte_table or vmas
+ * every 10 second.
+ */
static unsigned int khugepaged_pages_to_scan __read_mostly;
static unsigned int khugepaged_pages_collapsed;
static unsigned int khugepaged_full_scans;
@@ -2487,12 +2490,22 @@ static unsigned int khugepaged_scan_mm_slot(unsigned int pages, int *result,
khugepaged_scan.address, &mmap_locked, cc);
}
- if (*result == SCAN_SUCCEED)
- ++khugepaged_pages_collapsed;
-
/* move to next address */
khugepaged_scan.address += HPAGE_PMD_SIZE;
- progress += HPAGE_PMD_NR;
+
+ switch (*result) {
+ case SCAN_NO_PTE_TABLE:
+ case SCAN_PMD_MAPPED:
+ case SCAN_PTE_MAPPED_HUGEPAGE:
+ progress++;
+ break;
+ case SCAN_SUCCEED:
+ ++khugepaged_pages_collapsed;
+ fallthrough;
+ default:
+ progress += HPAGE_PMD_NR;
+ }
+
if (!mmap_locked)
/*
* We released mmap_lock so break loop. Note
--
2.51.0On Mon, Dec 29, 2025 at 1:52 PM Vernon Yang <vernon2gm@gmail.com> wrote:
>
> The following data is traced by bpftrace on a desktop system. After
> the system has been left idle for 10 minutes upon booting, a lot of
> SCAN_PMD_MAPPED or SCAN_NO_PTE_TABLE are observed during a full scan
> by khugepaged.
>
> @scan_pmd_status[1]: 1 ## SCAN_SUCCEED
> @scan_pmd_status[6]: 2 ## SCAN_EXCEED_SHARED_PTE
> @scan_pmd_status[3]: 142 ## SCAN_PMD_MAPPED
> @scan_pmd_status[2]: 178 ## SCAN_NO_PTE_TABLE
> total progress size: 674 MB
> Total time : 419 seconds ## include khugepaged_scan_sleep_millisecs
>
> The khugepaged_scan list save all task that support collapse into hugepage,
> as long as the task is not destroyed, khugepaged will not remove it from
> the khugepaged_scan list. This exist a phenomenon where task has already
> collapsed all memory regions into hugepage, but khugepaged continues to
> scan it, which wastes CPU time and invalid, and due to
> khugepaged_scan_sleep_millisecs (default 10s) causes a long wait for
> scanning a large number of invalid task, so scanning really valid task
> is later.
>
> After applying this patch, when the memory is either SCAN_PMD_MAPPED or
> SCAN_NO_PTE_TABLE, just skip it, as follow:
>
> @scan_pmd_status[6]: 2
> @scan_pmd_status[3]: 147
> @scan_pmd_status[2]: 173
> total progress size: 45 MB
> Total time : 20 seconds
>
> Signed-off-by: Vernon Yang <yanglincheng@kylinos.cn>
> ---
> mm/khugepaged.c | 23 ++++++++++++++++++-----
> 1 file changed, 18 insertions(+), 5 deletions(-)
>
> diff --git a/mm/khugepaged.c b/mm/khugepaged.c
> index 9f99f61689f8..2b3685b195f5 100644
> --- a/mm/khugepaged.c
> +++ b/mm/khugepaged.c
> @@ -66,7 +66,10 @@ enum scan_result {
> static struct task_struct *khugepaged_thread __read_mostly;
> static DEFINE_MUTEX(khugepaged_mutex);
>
> -/* default scan 8*HPAGE_PMD_NR ptes (or vmas) every 10 second */
> +/*
> + * default scan 8*HPAGE_PMD_NR ptes, pmd_mapped, no_pte_table or vmas
> + * every 10 second.
> + */
> static unsigned int khugepaged_pages_to_scan __read_mostly;
> static unsigned int khugepaged_pages_collapsed;
> static unsigned int khugepaged_full_scans;
> @@ -2487,12 +2490,22 @@ static unsigned int khugepaged_scan_mm_slot(unsigned int pages, int *result,
> khugepaged_scan.address, &mmap_locked, cc);
> }
>
> - if (*result == SCAN_SUCCEED)
> - ++khugepaged_pages_collapsed;
> -
> /* move to next address */
> khugepaged_scan.address += HPAGE_PMD_SIZE;
> - progress += HPAGE_PMD_NR;
> +
> + switch (*result) {
> + case SCAN_NO_PTE_TABLE:
> + case SCAN_PMD_MAPPED:
> + case SCAN_PTE_MAPPED_HUGEPAGE:
> + progress++;
> + break;
> + case SCAN_SUCCEED:
> + ++khugepaged_pages_collapsed;
> + fallthrough;
> + default:
> + progress += HPAGE_PMD_NR;
> + }
> +
> if (!mmap_locked)
> /*
> * We released mmap_lock so break loop. Note
> --
> 2.51.0
>
Sorry, this coding has warnings at SCAN_PTE_MAPPED_HUGEPAGE, and the code
will be refactored in the next version. But the core idea is unchanged.
© 2016 - 2026 Red Hat, Inc.