Skip to contentSkip to conversation

mm/vmscan: reclaim only affects managed_zones

PATCH In review Wei Yang 4 participants 6 messages Mar 29, 2022 – Mar 30, 2022

Subsystems (5)
lore
Share & tools
lore

Wei Yang

author
#0 lore raw

PATCH v2 1/2 mm/vmscan: reclaim only affects managed_zones

As mentioned in commit 6aa303defb74 ("mm, vmscan: only allocate and reclaim from zones with pages managed by the buddy allocator") , reclaim only affects managed_zones.

Let's adjust the code and comment accordingly.

---
 mm/vmscan.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)
mm/vmscan.c +2 -2
index 1f2d79e8c43c..4385b59ef599 100644
@@ -1040,7 +1040,7 @@ static bool skip_throttle_noprogress(pg_data_t *pgdat)
 	for (i = 0; i < MAX_NR_ZONES; i++) {
 		struct zone *zone = pgdat->node_zones + i;
 
-		if (!populated_zone(zone))
+		if (!managed_zone(zone))
 			continue;
 
 		reclaimable += zone_reclaimable_pages(zone);
@@ -3909,7 +3909,7 @@ static bool pgdat_balanced(pg_data_t *pgdat, int order, int highest_zoneidx)
 	}
 
 	/*
-	 * If a node has no populated zone within highest_zoneidx, it does not
+	 * If a node has no managed zone within highest_zoneidx, it does not
 	 * need balancing by definition. This can happen if a zone-restricted
 	 * allocation tries to wake a remote kswapd.
 	 */
Signature · 1 line
2.33.1
author
#1 lore raw

PATCH v2 2/2 mm/vmscan: make sure wakeup_kswapd with managed zone

wakeup_kswapd() only wake up kswapd when the zone is managed.

For two callers of wakeup_kswapd(), they are node perspective.

* wake_all_kswapds
* numamigrate_isolate_page

If we picked up a !managed zone, this is not we expected.

This patch makes sure we pick up a managed zone for wakeup_kswapd(). And it also use managed_zone in migrate_balanced_pgdat() to get the proper zone.

Cc Miaohe Lin <[email protected]>
Cc David Hildenbrand <[email protected]>
Cc "Huang, Ying" <[email protected]>
Cc Mel Gorman <[email protected]>
Cc Oscar Salvador <[email protected]>

---
v2: adjust the usage in migrate_balanced_pgdat()

---
 mm/migrate.c    | 6 +++---
 mm/page_alloc.c | 2 ++
 2 files changed, 5 insertions(+), 3 deletions(-)
mm/migrate.c +3 -3
index 3d60823afd2d..5adc55b5347c 100644
@@ -1971,7 +1971,7 @@ SYSCALL_DEFINE6(move_pages, pid_t, pid, unsigned long, nr_pages,
 #ifdef CONFIG_NUMA_BALANCING
 /*
  * Returns true if this is a safe migration target node for misplaced NUMA
- * pages. Currently it only checks the watermarks which crude
+ * pages. Currently it only checks the watermarks which is crude.
  */
 static bool migrate_balanced_pgdat(struct pglist_data *pgdat,
 				   unsigned long nr_migrate_pages)
@@ -1981,7 +1981,7 @@ static bool migrate_balanced_pgdat(struct pglist_data *pgdat,
 	for (z = pgdat->nr_zones - 1; z >= 0; z--) {
 		struct zone *zone = pgdat->node_zones + z;
 
-		if (!populated_zone(zone))
+		if (!managed_zone(zone))
 			continue;
 
 		/* Avoid waking kswapd by allocating pages_to_migrate pages. */
@@ -2046,7 +2046,7 @@ static int numamigrate_isolate_page(pg_data_t *pgdat, struct page *page)
 		if (!(sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING))
 			return 0;
 		for (z = pgdat->nr_zones - 1; z >= 0; z--) {
-			if (populated_zone(pgdat->node_zones + z))
+			if (managed_zone(pgdat->node_zones + z))
 				break;
 		}
 		wakeup_kswapd(pgdat->node_zones + z, 0, order, ZONE_MOVABLE);
mm/page_alloc.c +2 -0
index 4c0c4ef94ba0..6656c2d06e01 100644
@@ -4674,6 +4674,8 @@ static void wake_all_kswapds(unsigned int order, gfp_t gfp_mask,
 
 	for_each_zone_zonelist_nodemask(zone, z, ac->zonelist, highest_zoneidx,
 					ac->nodemask) {
+		if (!managed_zone(zone))
+			continue;
 		if (last_pgdat != zone->zone_pgdat)
 			wakeup_kswapd(zone, gfp_mask, order, highest_zoneidx);
 		last_pgdat = zone->zone_pgdat;
Signature · 1 line
2.33.1
Reviewed-by on v2 2/2
#2 lore raw

Re: [Patch v2 2/2] mm/vmscan: make sure wakeup_kswapd with managed zone

Quoted 13 lines · Wei Yang

wakeup_kswapd() only wake up kswapd when the zone is managed.

For two callers of wakeup_kswapd(), they are node perspective.

* wake_all_kswapds
* numamigrate_isolate_page

If we picked up a !managed zone, this is not we expected.

This patch makes sure we pick up a managed zone for wakeup_kswapd(). And it also use managed_zone in migrate_balanced_pgdat() to get the proper zone.

Quoted 7 lines
Cc Miaohe Lin <[email protected]>
Cc David Hildenbrand <[email protected]>
Cc "Huang, Ying" <[email protected]>
Cc Mel Gorman <[email protected]>
Cc Oscar Salvador <[email protected]>

LGTM, Thanks!

Quoted 53 lines

---
v2: adjust the usage in migrate_balanced_pgdat()

---
 mm/migrate.c    | 6 +++---
 mm/page_alloc.c | 2 ++
 2 files changed, 5 insertions(+), 3 deletions(-)
mm/migrate.c +3 -3
index 3d60823afd2d..5adc55b5347c 100644
@@ -1971,7 +1971,7 @@ SYSCALL_DEFINE6(move_pages, pid_t, pid, unsigned long, nr_pages,
 #ifdef CONFIG_NUMA_BALANCING
 /*
  * Returns true if this is a safe migration target node for misplaced NUMA
- * pages. Currently it only checks the watermarks which crude
+ * pages. Currently it only checks the watermarks which is crude.
  */
 static bool migrate_balanced_pgdat(struct pglist_data *pgdat,
 				   unsigned long nr_migrate_pages)
@@ -1981,7 +1981,7 @@ static bool migrate_balanced_pgdat(struct pglist_data *pgdat,
 	for (z = pgdat->nr_zones - 1; z >= 0; z--) {
 		struct zone *zone = pgdat->node_zones + z;
 
-		if (!populated_zone(zone))
+		if (!managed_zone(zone))
 			continue;
 
 		/* Avoid waking kswapd by allocating pages_to_migrate pages. */
@@ -2046,7 +2046,7 @@ static int numamigrate_isolate_page(pg_data_t *pgdat, struct page *page)
 		if (!(sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING))
 			return 0;
 		for (z = pgdat->nr_zones - 1; z >= 0; z--) {
-			if (populated_zone(pgdat->node_zones + z))
+			if (managed_zone(pgdat->node_zones + z))
 				break;
 		}
 		wakeup_kswapd(pgdat->node_zones + z, 0, order, ZONE_MOVABLE);
mm/page_alloc.c +2 -0
index 4c0c4ef94ba0..6656c2d06e01 100644
@@ -4674,6 +4674,8 @@ static void wake_all_kswapds(unsigned int order, gfp_t gfp_mask,
 
 	for_each_zone_zonelist_nodemask(zone, z, ac->zonelist, highest_zoneidx,
 					ac->nodemask) {
+		if (!managed_zone(zone))
+			continue;
 		if (last_pgdat != zone->zone_pgdat)
 			wakeup_kswapd(zone, gfp_mask, order, highest_zoneidx);
 		last_pgdat = zone->zone_pgdat;
Reviewed-by on v2 2/2
#3 lore raw

Re: [Patch v2 2/2] mm/vmscan: make sure wakeup_kswapd with managed zone

In reply to Wei Yang
Quoted 7 lines · Wei Yang

wakeup_kswapd() only wake up kswapd when the zone is managed.

For two callers of wakeup_kswapd(), they are node perspective.

* wake_all_kswapds
* numamigrate_isolate_page

Quoted 7 lines

If we picked up a !managed zone, this is not we expected.

This patch makes sure we pick up a managed zone for wakeup_kswapd(). And it also use managed_zone in migrate_balanced_pgdat() to get the proper zone.

Looks good to me. Thanks!

Quoted 60 lines
Cc Miaohe Lin <[email protected]>
Cc David Hildenbrand <[email protected]>
Cc "Huang, Ying" <[email protected]>
Cc Mel Gorman <[email protected]>
Cc Oscar Salvador <[email protected]>

---
v2: adjust the usage in migrate_balanced_pgdat()

---
 mm/migrate.c    | 6 +++---
 mm/page_alloc.c | 2 ++
 2 files changed, 5 insertions(+), 3 deletions(-)
mm/migrate.c +3 -3
index 3d60823afd2d..5adc55b5347c 100644
@@ -1971,7 +1971,7 @@ SYSCALL_DEFINE6(move_pages, pid_t, pid, unsigned long, nr_pages,
 #ifdef CONFIG_NUMA_BALANCING
 /*
  * Returns true if this is a safe migration target node for misplaced NUMA
- * pages. Currently it only checks the watermarks which crude
+ * pages. Currently it only checks the watermarks which is crude.
  */
 static bool migrate_balanced_pgdat(struct pglist_data *pgdat,
 				   unsigned long nr_migrate_pages)
@@ -1981,7 +1981,7 @@ static bool migrate_balanced_pgdat(struct pglist_data *pgdat,
 	for (z = pgdat->nr_zones - 1; z >= 0; z--) {
 		struct zone *zone = pgdat->node_zones + z;
 
-		if (!populated_zone(zone))
+		if (!managed_zone(zone))
 			continue;
 
 		/* Avoid waking kswapd by allocating pages_to_migrate pages. */
@@ -2046,7 +2046,7 @@ static int numamigrate_isolate_page(pg_data_t *pgdat, struct page *page)
 		if (!(sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING))
 			return 0;
 		for (z = pgdat->nr_zones - 1; z >= 0; z--) {
-			if (populated_zone(pgdat->node_zones + z))
+			if (managed_zone(pgdat->node_zones + z))
 				break;
 		}
 		wakeup_kswapd(pgdat->node_zones + z, 0, order, ZONE_MOVABLE);
mm/page_alloc.c +2 -0
index 4c0c4ef94ba0..6656c2d06e01 100644
@@ -4674,6 +4674,8 @@ static void wake_all_kswapds(unsigned int order, gfp_t gfp_mask,
 
 	for_each_zone_zonelist_nodemask(zone, z, ac->zonelist, highest_zoneidx,
 					ac->nodemask) {
+		if (!managed_zone(zone))
+			continue;
 		if (last_pgdat != zone->zone_pgdat)
 			wakeup_kswapd(zone, gfp_mask, order, highest_zoneidx);
 		last_pgdat = zone->zone_pgdat;
Reviewed-by on v2 2/2
#4 lore raw

Re: [Patch v2 2/2] mm/vmscan: make sure wakeup_kswapd with managed zone

In reply to Wei Yang
Quoted 13 lines · Wei Yang

wakeup_kswapd() only wake up kswapd when the zone is managed.

For two callers of wakeup_kswapd(), they are node perspective.

* wake_all_kswapds
* numamigrate_isolate_page

If we picked up a !managed zone, this is not we expected.

This patch makes sure we pick up a managed zone for wakeup_kswapd(). And it also use managed_zone in migrate_balanced_pgdat() to get the proper zone.

Quoted 7 lines
Cc Miaohe Lin <[email protected]>
Cc David Hildenbrand <[email protected]>
Cc "Huang, Ying" <[email protected]>
Cc Mel Gorman <[email protected]>
Cc Oscar Salvador <[email protected]>

^ I'm not so sure about that SOB, actually Andrew should add that. But maybe there is good reason for it that I'm not aware of.

Signature · 3 lines
Thanks,

David / dhildenb
author
#5 lore raw

Re: [Patch v2 2/2] mm/vmscan: make sure wakeup_kswapd with managed zone

Quoted 22 lines · David Hildenbrand
Quoted 13 lines · Wei Yang

wakeup_kswapd() only wake up kswapd when the zone is managed.

For two callers of wakeup_kswapd(), they are node perspective.

* wake_all_kswapds
* numamigrate_isolate_page

If we picked up a !managed zone, this is not we expected.

This patch makes sure we pick up a managed zone for wakeup_kswapd(). And it also use managed_zone in migrate_balanced_pgdat() to get the proper zone.

Quoted 7 lines
Cc Miaohe Lin <[email protected]>
Cc David Hildenbrand <[email protected]>
Cc "Huang, Ying" <[email protected]>
Cc Mel Gorman <[email protected]>
Cc Oscar Salvador <[email protected]>
Quoted 3 lines

^ I'm not so sure about that SOB, actually Andrew should add that. But maybe there is good reason for it that I'm not aware of.

I see Andrew has added this for v1.

Maybe I should remove this since v2 has some minor adjustment to v1. :-)

Quoted 7 lines
Signature · 3 lines
Thanks,

David / dhildenb
Signature · 2 lines
Wei Yang
Help you, Help me