diff mbox series

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

Message ID 20220329010901.1654-2-richard.weiyang@gmail.com (mailing list archive)
State New
Headers show
Series [v2,1/2] mm/vmscan: reclaim only affects managed_zones | expand

Commit Message

Wei Yang March 29, 2022, 1:09 a.m. UTC 
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.

Signed-off-by: Wei Yang <richard.weiyang@gmail.com>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: "Huang, Ying" <ying.huang@intel.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Oscar Salvador <osalvador@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

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

---
 mm/migrate.c    | 6 +++---
 mm/page_alloc.c | 2 ++
 2 files changed, 5 insertions(+), 3 deletions(-)

Comments

Huang, Ying March 29, 2022, 1:26 a.m. UTC | #1 
Wei Yang <richard.weiyang@gmail.com> writes:

> 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.
>
> Signed-off-by: Wei Yang <richard.weiyang@gmail.com>
> Cc: Miaohe Lin <linmiaohe@huawei.com>
> Cc: David Hildenbrand <david@redhat.com>
> Cc: "Huang, Ying" <ying.huang@intel.com>
> Cc: Mel Gorman <mgorman@techsingularity.net>
> Cc: Oscar Salvador <osalvador@suse.de>
> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

LGTM, Thanks!

Reviewed-by: "Huang, Ying" <ying.huang@intel.com>

>
> ---
> v2: adjust the usage in migrate_balanced_pgdat()
>
> ---
>  mm/migrate.c    | 6 +++---
>  mm/page_alloc.c | 2 ++
>  2 files changed, 5 insertions(+), 3 deletions(-)
>
> diff --git a/mm/migrate.c b/mm/migrate.c
> index 3d60823afd2d..5adc55b5347c 100644
> --- a/mm/migrate.c
> +++ b/mm/migrate.c
> @@ -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);
> diff --git a/mm/page_alloc.c b/mm/page_alloc.c
> index 4c0c4ef94ba0..6656c2d06e01 100644
> --- a/mm/page_alloc.c
> +++ b/mm/page_alloc.c
> @@ -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;
Miaohe Lin March 29, 2022, 1:56 a.m. UTC | #2 
On 2022/3/29 9:09, Wei Yang wrote:
> 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.
> 
> Signed-off-by: Wei Yang <richard.weiyang@gmail.com>

Looks good to me. Thanks!

Reviewed-by: Miaohe Lin <linmiaohe@huawei.com>

> Cc: Miaohe Lin <linmiaohe@huawei.com>
> Cc: David Hildenbrand <david@redhat.com>
> Cc: "Huang, Ying" <ying.huang@intel.com>
> Cc: Mel Gorman <mgorman@techsingularity.net>
> Cc: Oscar Salvador <osalvador@suse.de>
> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
> 
> ---
> v2: adjust the usage in migrate_balanced_pgdat()
> 
> ---
>  mm/migrate.c    | 6 +++---
>  mm/page_alloc.c | 2 ++
>  2 files changed, 5 insertions(+), 3 deletions(-)
> 
> diff --git a/mm/migrate.c b/mm/migrate.c
> index 3d60823afd2d..5adc55b5347c 100644
> --- a/mm/migrate.c
> +++ b/mm/migrate.c
> @@ -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);
> diff --git a/mm/page_alloc.c b/mm/page_alloc.c
> index 4c0c4ef94ba0..6656c2d06e01 100644
> --- a/mm/page_alloc.c
> +++ b/mm/page_alloc.c
> @@ -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;
>
David Hildenbrand March 30, 2022, 7:39 a.m. UTC | #3 
On 29.03.22 03:09, Wei Yang wrote:
> 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.
> 
> Signed-off-by: Wei Yang <richard.weiyang@gmail.com>
> Cc: Miaohe Lin <linmiaohe@huawei.com>
> Cc: David Hildenbrand <david@redhat.com>
> Cc: "Huang, Ying" <ying.huang@intel.com>
> Cc: Mel Gorman <mgorman@techsingularity.net>
> Cc: Oscar Salvador <osalvador@suse.de>
> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

^ 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.


Reviewed-by: David Hildenbrand <david@redhat.com>
Wei Yang March 30, 2022, 2:20 p.m. UTC | #4 
On Wed, Mar 30, 2022 at 09:39:42AM +0200, David Hildenbrand wrote:
>On 29.03.22 03:09, Wei Yang wrote:
>> 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.
>> 
>> Signed-off-by: Wei Yang <richard.weiyang@gmail.com>
>> Cc: Miaohe Lin <linmiaohe@huawei.com>
>> Cc: David Hildenbrand <david@redhat.com>
>> Cc: "Huang, Ying" <ying.huang@intel.com>
>> Cc: Mel Gorman <mgorman@techsingularity.net>
>> Cc: Oscar Salvador <osalvador@suse.de>
>> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
>
>^ 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. :-)

>
>Reviewed-by: David Hildenbrand <david@redhat.com>
>
>-- 
>Thanks,
>
>David / dhildenb
diff mbox series

Patch

diff --git a/mm/migrate.c b/mm/migrate.c
index 3d60823afd2d..5adc55b5347c 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -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);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 4c0c4ef94ba0..6656c2d06e01 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -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;