Skip to contentSkip to conversation

khugepaged: add per-order mTHP khugepaged stats

PATCH In review Nico Pache 1 participant 4 messages Aug 19, 2025

Subsystems (5)
lore
Share & tools
lore

Nico Pache

author
#0 lore raw

PATCH v10 12/13 khugepaged: add per-order mTHP khugepaged stats

With mTHP support inplace, let add the per-order mTHP stats for exceeding NONE, SWAP, and SHARED.

---
 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(-)
Documentation/admin-guide/mm/transhuge.rst +17 -0
index 7ccb93e22852..b85547ac4fe9 100644
@@ -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
include/linux/huge_mm.h +3 -0
index 4ada5d1f7297..6f1593d0b4b5 100644
@@ -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
 };
 
mm/huge_memory.c +7 -0
index 20d005c2c61f..9f0470c3e983 100644
@@ -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,
 };
 
mm/khugepaged.c +13 -3
index c13bc583a368..5a3386043f39 100644
@@ -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;
Signature · 1 line
2.50.1
author
#1 lore raw

PATCH v10 13/13 Documentation: mm: update the admin guide for mTHP collapse

Now that we can collapse to mTHPs lets update the admin guide to reflect these changes and provide proper guidence on how to utilize it.

---
 Documentation/admin-guide/mm/transhuge.rst | 19 +++++++++++++------
 1 file changed, 13 insertions(+), 6 deletions(-)
Documentation/admin-guide/mm/transhuge.rst +13 -6
index b85547ac4fe9..1f9e6a32052c 100644
@@ -63,7 +63,7 @@ often.
 THP can be enabled system wide or restricted to certain tasks or even
 memory ranges inside task's address space. Unless THP is completely
 disabled, there is ``khugepaged`` daemon that scans memory and
-collapses sequences of basic pages into PMD-sized huge pages.
+collapses sequences of basic pages into huge pages.
 
 The THP behaviour is controlled via :ref:`sysfs <thp_sysfs>`
 interface and using madvise(2) and prctl(2) system calls.
@@ -149,6 +149,18 @@ hugepage sizes have enabled="never". If enabling multiple hugepage
 sizes, the kernel will select the most appropriate enabled size for a
 given allocation.
 
+khugepaged uses max_ptes_none scaled to the order of the enabled mTHP size
+to determine collapses. When using mTHPs it's recommended to set
+max_ptes_none low-- ideally less than HPAGE_PMD_NR / 2 (255 on 4k page
+size). This will prevent undesired "creep" behavior that leads to
+continuously collapsing to the largest mTHP size; when we collapse, we are
+bringing in new non-zero pages that will, on a subsequent scan, cause the
+max_ptes_none check of the +1 order to always be satisfied. By limiting
+this to less than half the current order, we make sure we don't cause this
+feedback loop. max_ptes_shared and max_ptes_swap have no effect when
+collapsing to a mTHP, and mTHP collapse will fail on shared or swapped out
+pages.
+
 It's also possible to limit defrag efforts in the VM to generate
 anonymous hugepages in case they're not immediately free to madvise
 regions or to never try to defrag memory and simply fallback to regular
@@ -264,11 +276,6 @@ support the following arguments::
 Khugepaged controls
 -------------------
 
-.. note::
-   khugepaged currently only searches for opportunities to collapse to
-   PMD-sized THP and no attempt is made to collapse to other THP
-   sizes.
-
 khugepaged runs usually at low frequency so while one may not want to
 invoke defrag algorithms synchronously during the page faults, it
 should be worth invoking defrag at least in khugepaged. However it's
Signature · 1 line
2.50.1
author
#2 lore raw

Re: [PATCH v10 13/13] Documentation: mm: update the admin guide for mTHP collapse

Quoted 6 lines · Nico Pache

Now that we can collapse to mTHPs lets update the admin guide to reflect these changes and provide proper guidence on how to utilize it.

I had git send email error and had to resend this patch (13), but i forgot the in-reply-to
please ignore this one and reply to correct version

https://lore.kernel.org/lkml/[email protected]/
[email protected]

-- Nico

Quoted 51 lines
---
 Documentation/admin-guide/mm/transhuge.rst | 19 +++++++++++++------
 1 file changed, 13 insertions(+), 6 deletions(-)
Documentation/admin-guide/mm/transhuge.rst +13 -7
index b85547ac4fe9..1f9e6a32052c 100644
@@ -63,7 +63,7 @@ often.
 THP can be enabled system wide or restricted to certain tasks or even
 memory ranges inside task's address space. Unless THP is completely
 disabled, there is ``khugepaged`` daemon that scans memory and
-collapses sequences of basic pages into PMD-sized huge pages.
+collapses sequences of basic pages into huge pages.
 
 The THP behaviour is controlled via :ref:`sysfs <thp_sysfs>`
 interface and using madvise(2) and prctl(2) system calls.
@@ -149,6 +149,18 @@ hugepage sizes have enabled="never". If enabling multiple hugepage
 sizes, the kernel will select the most appropriate enabled size for a
 given allocation.
 
+khugepaged uses max_ptes_none scaled to the order of the enabled mTHP size
+to determine collapses. When using mTHPs it's recommended to set
+max_ptes_none low-- ideally less than HPAGE_PMD_NR / 2 (255 on 4k page
+size). This will prevent undesired "creep" behavior that leads to
+continuously collapsing to the largest mTHP size; when we collapse, we are
+bringing in new non-zero pages that will, on a subsequent scan, cause the
+max_ptes_none check of the +1 order to always be satisfied. By limiting
+this to less than half the current order, we make sure we don't cause this
+feedback loop. max_ptes_shared and max_ptes_swap have no effect when
+collapsing to a mTHP, and mTHP collapse will fail on shared or swapped out
+pages.
+
 It's also possible to limit defrag efforts in the VM to generate
 anonymous hugepages in case they're not immediately free to madvise
 regions or to never try to defrag memory and simply fallback to regular
@@ -264,11 +276,6 @@ support the following arguments::
 Khugepaged controls
 -------------------
 
-.. note::
-   khugepaged currently only searches for opportunities to collapse to
-   PMD-sized THP and no attempt is made to collapse to other THP
-   sizes.
-
 khugepaged runs usually at low frequency so while one may not want to
 invoke defrag algorithms synchronously during the page faults, it
 should be worth invoking defrag at least in khugepaged. However it's
--

2.50.1

author
#3 lore raw
In reply to Nico Pache
Quoted 5 lines · Nico Pache

With mTHP support inplace, let add the per-order mTHP stats for exceeding NONE, SWAP, and SHARED.

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/[email protected]/
[email protected]

-- Nico

Quoted 120 lines
---
 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(-)
Documentation/admin-guide/mm/transhuge.rst +17 -0
index 7ccb93e22852..b85547ac4fe9 100644
@@ -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
include/linux/huge_mm.h +3 -0
index 4ada5d1f7297..6f1593d0b4b5 100644
@@ -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
 };
 
mm/huge_memory.c +7 -0
index 20d005c2c61f..9f0470c3e983 100644
@@ -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,
 };
 
mm/khugepaged.c +13 -4
index c13bc583a368..5a3386043f39 100644
@@ -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