mirrors/linux
2
0
Fork 0
mirror of https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git synced 2026-07-22 02:17:36 -04:00
Code Issues Packages Projects Releases Wiki Activity

mm/khugepaged: add per-order mTHP collapse failure statistics

Browse Source 
Add three new mTHP statistics to track collapse failures for different
orders when encountering swap PTEs, excessive none PTEs, and shared PTEs:

- collapse_exceed_swap_pte: Increment when mTHP collapse fails due to
	encountering a swap PTE.

- collapse_exceed_none_pte: Counts when mTHP collapse fails due to
  	exceeding the none PTE threshold for the given order

- collapse_exceed_shared_pte: Counts when mTHP collapse fails due to
	encountering a shared PTE.

These statistics complement the existing THP_SCAN_EXCEED_* events by
providing per-order granularity for mTHP collapse attempts.  The stats are
exposed via sysfs under
`/sys/kernel/mm/transparent_hugepage/hugepages-*/stats/` for each
supported hugepage size.

As we currently do not support collapsing mTHPs that contain a swap or
shared entry, those statistics keep track of how often we are encountering
failed mTHP collapses due to these restrictions.

We will add support for mTHP collapse for anonymous pages next; lets also
track when this happens at the PMD level within the per-mTHP stats.

Link: https://lore.kernel.org/20260605161422.213817-9-npache@redhat.com
Signed-off-by: Nico Pache <npache@redhat.com>
Reviewed-by: Lorenzo Stoakes <ljs@kernel.org>
Acked-by: David Hildenbrand (Arm) <david@kernel.org>
Reviewed-by: Lance Yang <lance.yang@linux.dev>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Bagas Sanjaya <bagasdotme@gmail.com>
Cc: Baolin Wang <baolin.wang@linux.alibaba.com>
Cc: Barry Song <baohua@kernel.org>
Cc: Brendan Jackman <jackmanb@google.com>
Cc: Byungchul Park <byungchul@sk.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Dev Jain <dev.jain@arm.com>
Cc: Gregory Price <gourry@gourry.net>
Cc: "Huang, Ying" <ying.huang@linux.alibaba.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Jann Horn <jannh@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Joshua Hahn <joshua.hahnjy@gmail.com>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Cc: Liam R. Howlett <liam@infradead.org>
Cc: "Masami Hiramatsu (Google)" <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Nanyong Sun <sunnanyong@huawei.com>
Cc: Pedro Falcato <pfalcato@suse.de>
Cc: Peter Xu <peterx@redhat.com>
Cc: Rafael Aquini <raquini@redhat.com>
Cc: Rakie Kim <rakie.kim@sk.com>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Shivank Garg <shivankg@amd.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Takashi Iwai (SUSE) <tiwai@suse.de>
Cc: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Cc: Usama Arif <usamaarif642@gmail.com>
Cc: Usama Arif <usama.arif@linux.dev>
Cc: Vishal Moola (Oracle) <vishal.moola@gmail.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Wei Yang <richard.weiyang@gmail.com>
Cc: Will Deacon <will@kernel.org>
Cc: Yang Shi <yang@os.amperecomputing.com>
Cc: Zach O'Keefe <zokeefe@google.com>
Cc: Zi Yan <ziy@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
This commit is contained in:
Nico Pache
2026-06-05 10:14:15 -06:00
committed by Andrew Morton
parent 3a460f245f
commit b5b8b329c4
4 changed files with 37 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
Documentation/admin-guide/mm/transhuge.rst
View File

@@ -714,6 +714,20 @@ 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_none_pte
The number of collapse attempts that failed due to exceeding the
max_ptes_none threshold.
collapse_exceed_swap_pte
The number of collapse attempts that failed due to exceeding the
max_ptes_swap threshold. For non-PMD orders this occurs if a mTHP range
contains at least one swap PTE.
collapse_exceed_shared_pte
The number of collapse attempts that failed due to exceeding the
max_ptes_shared threshold. For non-PMD orders this occurs if a mTHP range
contains at least one 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

3
include/linux/huge_mm.h
View File

@@ -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
};

7
mm/huge_memory.c
View File

@@ -720,6 +720,10 @@ 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,
@@ -736,6 +740,9 @@ 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,
};

15
mm/khugepaged.c
View File

@@ -651,7 +651,9 @@ static enum scan_result __collapse_huge_page_isolate(struct vm_area_struct *vma,
if (pte_none_or_zero(pteval)) {
if (++none_or_zero > max_ptes_none) {
result = SCAN_EXCEED_NONE_PTE;
count_vm_event(THP_SCAN_EXCEED_NONE_PTE);
if (is_pmd_order(order))
count_vm_event(THP_SCAN_EXCEED_NONE_PTE);
count_mthp_stat(order, MTHP_STAT_COLLAPSE_EXCEED_NONE);
goto out;
}
continue;
@@ -693,7 +695,9 @@ static enum scan_result __collapse_huge_page_isolate(struct vm_area_struct *vma,
*/
if (++shared > max_ptes_shared) {
result = SCAN_EXCEED_SHARED_PTE;
count_vm_event(THP_SCAN_EXCEED_SHARED_PTE);
if (is_pmd_order(order))
count_vm_event(THP_SCAN_EXCEED_SHARED_PTE);
count_mthp_stat(order, MTHP_STAT_COLLAPSE_EXCEED_SHARED);
goto out;
}
}
@@ -1152,6 +1156,7 @@ static enum scan_result __collapse_huge_page_swapin(struct mm_struct *mm,
* range.
*/
if (!is_pmd_order(order)) {
count_mthp_stat(order, MTHP_STAT_COLLAPSE_EXCEED_SWAP);
pte_unmap(pte);
mmap_read_unlock(mm);
result = SCAN_EXCEED_SWAP_PTE;
@@ -1464,6 +1469,8 @@ static enum scan_result collapse_scan_pmd(struct mm_struct *mm,
if (++none_or_zero > max_ptes_none) {
result = SCAN_EXCEED_NONE_PTE;
count_vm_event(THP_SCAN_EXCEED_NONE_PTE);
count_mthp_stat(HPAGE_PMD_ORDER,
MTHP_STAT_COLLAPSE_EXCEED_NONE);
goto out_unmap;
}
continue;
@@ -1472,6 +1479,8 @@ static enum scan_result collapse_scan_pmd(struct mm_struct *mm,
if (++unmapped > max_ptes_swap) {
result = SCAN_EXCEED_SWAP_PTE;
count_vm_event(THP_SCAN_EXCEED_SWAP_PTE);
count_mthp_stat(HPAGE_PMD_ORDER,
MTHP_STAT_COLLAPSE_EXCEED_SWAP);
goto out_unmap;
}
/*
@@ -1529,6 +1538,8 @@ static enum scan_result collapse_scan_pmd(struct mm_struct *mm,
if (++shared > max_ptes_shared) {
result = SCAN_EXCEED_SHARED_PTE;
count_vm_event(THP_SCAN_EXCEED_SHARED_PTE);
count_mthp_stat(HPAGE_PMD_ORDER,
MTHP_STAT_COLLAPSE_EXCEED_SHARED);
goto out_unmap;
}
}