Skip to contentSkip to conversation

mm: add per-order mTHP swpin counters

PATCH Superseded Barry Song 4 participants 7 messages Oct 26, 2024 – Oct 30, 2024

Subsystems (5)

v1 of 3 Superseded Latest is v3 →

lore
Share & tools
lore

Barry Song

author
#0 lore raw

PATCH 1/1 mm: add per-order mTHP swpin counters

From: Barry Song <[email protected]>

This helps profile the sizes of folios being swapped in. Currently, only mTHP swap-out is being counted.

Cc David Hildenbrand <[email protected]>
Cc Baolin Wang <[email protected]>
Cc Chris Li <[email protected]>
Cc Yosry Ahmed <[email protected]>
Cc "Huang, Ying" <[email protected]>
Cc Kairui Song <[email protected]>
Cc Ryan Roberts <[email protected]>
Cc Kanchana P Sridhar <[email protected]>
Cc Usama Arif <[email protected]>
---
 Documentation/admin-guide/mm/transhuge.rst | 3 +++
 include/linux/huge_mm.h                    | 1 +
 mm/huge_memory.c                           | 3 +++
 mm/page_io.c                               | 3 +++
 4 files changed, 10 insertions(+)
Documentation/admin-guide/mm/transhuge.rst +3 -0
index 2a171ed5206e..203ba7aaf5fc 100644
@@ -533,6 +533,9 @@ anon_fault_fallback_charge
 zswpout
 	is incremented every time a huge page is swapped out to zswap in one
 	piece without splitting.
+swpin
+	is incremented every time a huge page is swapped in from a non-zswap
+	swap device in one piece.
 
 swpout
 	is incremented every time a huge page is swapped out to a non-zswap
include/linux/huge_mm.h +1 -0
index c59e5aa9b081..b94c2e8ee918 100644
@@ -120,6 +120,7 @@ enum mthp_stat_item {
 	MTHP_STAT_ANON_FAULT_FALLBACK,
 	MTHP_STAT_ANON_FAULT_FALLBACK_CHARGE,
 	MTHP_STAT_ZSWPOUT,
+	MTHP_STAT_SWPIN,
 	MTHP_STAT_SWPOUT,
 	MTHP_STAT_SWPOUT_FALLBACK,
 	MTHP_STAT_SHMEM_ALLOC,
mm/huge_memory.c +3 -0
index 830d6aa5bf97..846c1a43f61c 100644
@@ -616,6 +616,7 @@ DEFINE_MTHP_STAT_ATTR(anon_fault_alloc, MTHP_STAT_ANON_FAULT_ALLOC);
 DEFINE_MTHP_STAT_ATTR(anon_fault_fallback, MTHP_STAT_ANON_FAULT_FALLBACK);
 DEFINE_MTHP_STAT_ATTR(anon_fault_fallback_charge, MTHP_STAT_ANON_FAULT_FALLBACK_CHARGE);
 DEFINE_MTHP_STAT_ATTR(zswpout, MTHP_STAT_ZSWPOUT);
+DEFINE_MTHP_STAT_ATTR(swpin, MTHP_STAT_SWPIN);
 DEFINE_MTHP_STAT_ATTR(swpout, MTHP_STAT_SWPOUT);
 DEFINE_MTHP_STAT_ATTR(swpout_fallback, MTHP_STAT_SWPOUT_FALLBACK);
 #ifdef CONFIG_SHMEM
@@ -635,6 +636,7 @@ static struct attribute *anon_stats_attrs[] = {
 	&anon_fault_fallback_charge_attr.attr,
 #ifndef CONFIG_SHMEM
 	&zswpout_attr.attr,
+	&swpin_attr.attr,
 	&swpout_attr.attr,
 	&swpout_fallback_attr.attr,
 #endif
@@ -666,6 +668,7 @@ static struct attribute_group file_stats_attr_grp = {
 static struct attribute *any_stats_attrs[] = {
 #ifdef CONFIG_SHMEM
 	&zswpout_attr.attr,
+	&swpin_attr.attr,
 	&swpout_attr.attr,
 	&swpout_fallback_attr.attr,
 #endif
mm/page_io.c +3 -0
index c69fab5060a1..5d9b6e6cf96c 100644
@@ -487,6 +487,7 @@ static void sio_read_complete(struct kiocb *iocb, long ret)
 		for (p = 0; p < sio->pages; p++) {
 			struct folio *folio = page_folio(sio->bvec[p].bv_page);
 
+			count_mthp_stat(folio_order(folio), MTHP_STAT_SWPIN);
 			count_memcg_folio_events(folio, PSWPIN, folio_nr_pages(folio));
 			folio_mark_uptodate(folio);
 			folio_unlock(folio);
@@ -573,6 +574,7 @@ static void swap_read_folio_bdev_sync(struct folio *folio,
 	 * attempt to access it in the page fault retry time check.
 	 */
 	get_task_struct(current);
+	count_mthp_stat(folio_order(folio), MTHP_STAT_SWPIN);
 	count_memcg_folio_events(folio, PSWPIN, folio_nr_pages(folio));
 	count_vm_events(PSWPIN, folio_nr_pages(folio));
 	submit_bio_wait(&bio);
@@ -589,6 +591,7 @@ static void swap_read_folio_bdev_async(struct folio *folio,
 	bio->bi_iter.bi_sector = swap_folio_sector(folio);
 	bio->bi_end_io = end_swap_bio_read;
 	bio_add_folio_nofail(bio, folio, folio_size(folio), 0);
+	count_mthp_stat(folio_order(folio), MTHP_STAT_SWPIN);
 	count_memcg_folio_events(folio, PSWPIN, folio_nr_pages(folio));
 	count_vm_events(PSWPIN, folio_nr_pages(folio));
 	submit_bio(bio);
Signature · 1 line
2.39.3 (Apple Git-146)
reviewer Reviewed-by on v1 1/1
#1 lore raw
Quoted 5 lines · Barry Song

From: Barry Song <[email protected]>

This helps profile the sizes of folios being swapped in. Currently, only mTHP swap-out is being counted.

Quoted 10 lines
Cc David Hildenbrand <[email protected]>
Cc Baolin Wang <[email protected]>
Cc Chris Li <[email protected]>
Cc Yosry Ahmed <[email protected]>
Cc "Huang, Ying" <[email protected]>
Cc Kairui Song <[email protected]>
Cc Ryan Roberts <[email protected]>
Cc Kanchana P Sridhar <[email protected]>
Cc Usama Arif <[email protected]>

Looks reasonable to me.

Quoted 89 lines
---
  Documentation/admin-guide/mm/transhuge.rst | 3 +++
  include/linux/huge_mm.h                    | 1 +
  mm/huge_memory.c                           | 3 +++
  mm/page_io.c                               | 3 +++
  4 files changed, 10 insertions(+)
Documentation/admin-guide/mm/transhuge.rst +3 -0
index 2a171ed5206e..203ba7aaf5fc 100644
@@ -533,6 +533,9 @@ anon_fault_fallback_charge
  zswpout
  	is incremented every time a huge page is swapped out to zswap in one
  	piece without splitting.
+swpin
+	is incremented every time a huge page is swapped in from a non-zswap
+	swap device in one piece.
 
  swpout
  	is incremented every time a huge page is swapped out to a non-zswap
include/linux/huge_mm.h +1 -0
index c59e5aa9b081..b94c2e8ee918 100644
@@ -120,6 +120,7 @@ enum mthp_stat_item {
  	MTHP_STAT_ANON_FAULT_FALLBACK,
  	MTHP_STAT_ANON_FAULT_FALLBACK_CHARGE,
  	MTHP_STAT_ZSWPOUT,
+	MTHP_STAT_SWPIN,
  	MTHP_STAT_SWPOUT,
  	MTHP_STAT_SWPOUT_FALLBACK,
  	MTHP_STAT_SHMEM_ALLOC,
mm/huge_memory.c +3 -0
index 830d6aa5bf97..846c1a43f61c 100644
@@ -616,6 +616,7 @@ DEFINE_MTHP_STAT_ATTR(anon_fault_alloc, MTHP_STAT_ANON_FAULT_ALLOC);
  DEFINE_MTHP_STAT_ATTR(anon_fault_fallback, MTHP_STAT_ANON_FAULT_FALLBACK);
  DEFINE_MTHP_STAT_ATTR(anon_fault_fallback_charge, MTHP_STAT_ANON_FAULT_FALLBACK_CHARGE);
  DEFINE_MTHP_STAT_ATTR(zswpout, MTHP_STAT_ZSWPOUT);
+DEFINE_MTHP_STAT_ATTR(swpin, MTHP_STAT_SWPIN);
  DEFINE_MTHP_STAT_ATTR(swpout, MTHP_STAT_SWPOUT);
  DEFINE_MTHP_STAT_ATTR(swpout_fallback, MTHP_STAT_SWPOUT_FALLBACK);
  #ifdef CONFIG_SHMEM
@@ -635,6 +636,7 @@ static struct attribute *anon_stats_attrs[] = {
  	&anon_fault_fallback_charge_attr.attr,
  #ifndef CONFIG_SHMEM
  	&zswpout_attr.attr,
+	&swpin_attr.attr,
  	&swpout_attr.attr,
  	&swpout_fallback_attr.attr,
  #endif
@@ -666,6 +668,7 @@ static struct attribute_group file_stats_attr_grp = {
  static struct attribute *any_stats_attrs[] = {
  #ifdef CONFIG_SHMEM
  	&zswpout_attr.attr,
+	&swpin_attr.attr,
  	&swpout_attr.attr,
  	&swpout_fallback_attr.attr,
  #endif
mm/page_io.c +3 -0
index c69fab5060a1..5d9b6e6cf96c 100644
@@ -487,6 +487,7 @@ static void sio_read_complete(struct kiocb *iocb, long ret)
  		for (p = 0; p < sio->pages; p++) {
  			struct folio *folio = page_folio(sio->bvec[p].bv_page);
 
+			count_mthp_stat(folio_order(folio), MTHP_STAT_SWPIN);
  			count_memcg_folio_events(folio, PSWPIN, folio_nr_pages(folio));
  			folio_mark_uptodate(folio);
  			folio_unlock(folio);
@@ -573,6 +574,7 @@ static void swap_read_folio_bdev_sync(struct folio *folio,
  	 * attempt to access it in the page fault retry time check.
  	 */
  	get_task_struct(current);
+	count_mthp_stat(folio_order(folio), MTHP_STAT_SWPIN);
  	count_memcg_folio_events(folio, PSWPIN, folio_nr_pages(folio));
  	count_vm_events(PSWPIN, folio_nr_pages(folio));
  	submit_bio_wait(&bio);
@@ -589,6 +591,7 @@ static void swap_read_folio_bdev_async(struct folio *folio,
  	bio->bi_iter.bi_sector = swap_folio_sector(folio);
  	bio->bi_end_io = end_swap_bio_read;
  	bio_add_folio_nofail(bio, folio, folio_size(folio), 0);
+	count_mthp_stat(folio_order(folio), MTHP_STAT_SWPIN);
  	count_memcg_folio_events(folio, PSWPIN, folio_nr_pages(folio));
  	count_vm_events(PSWPIN, folio_nr_pages(folio));
  	submit_bio(bio);
#2 lore raw
In reply to Barry Song
Quoted 4 lines · Barry Song

From: Barry Song <[email protected]>

This helps profile the sizes of folios being swapped in. Currently, only mTHP swap-out is being counted.

Better to describe the user space interface in patch description?

[snip]

--
Best Regards,
Huang, Ying

author
#3 lore raw
Quoted 10 lines · Ying
Quoted 4 lines · Barry Song

From: Barry Song <[email protected]>

This helps profile the sizes of folios being swapped in. Currently, only mTHP swap-out is being counted.

Better to describe the user space interface in patch description?

Do you mean something as below?

The new interface can be found at:

/sys/kernel/mm/transparent_hugepage/hugepages-<size>/stats
swapin

Quoted 5 lines

[snip]

--
Best Regards,
Huang, Ying

#4 lore raw
Quoted 12 lines · Barry Song
Quoted 10 lines · Ying
Quoted 4 lines · Barry Song

From: Barry Song <[email protected]>

This helps profile the sizes of folios being swapped in. Currently, only mTHP swap-out is being counted.

Better to describe the user space interface in patch description?

Quoted 6 lines

Do you mean something as below?

The new interface can be found at:

/sys/kernel/mm/transparent_hugepage/hugepages-<size>/stats
swapin

Yes. Some example output may be even better.

--
Best Regards,
Huang, Ying

author
#5 lore raw
Quoted 15 lines · Ying
Quoted 12 lines · Barry Song
Quoted 10 lines · Ying
Quoted 4 lines · Barry Song

From: Barry Song <[email protected]>

This helps profile the sizes of folios being swapped in. Currently, only mTHP swap-out is being counted.

Better to describe the user space interface in patch description?

Quoted 8 lines
Quoted 6 lines

Do you mean something as below?

The new interface can be found at:

/sys/kernel/mm/transparent_hugepage/hugepages-<size>/stats
swapin

Yes. Some example output may be even better.

ok. let me add some examples in changelog:

cat /sys/kernel/mm/transparent_hugepage/hugepages-64kB/stats/swpin 12809

cat /sys/kernel/mm/transparent_hugepage/hugepages-32kB/stats/swpin 4763

Quoted 4 lines

--
Best Regards,
Huang, Ying