[5/9] mm: don't avoid high-priority reclaim on unreclaimable nodes
diff mbox series

Message ID 20170228214007.5621-6-hannes@cmpxchg.org
State New, archived
Headers show
Series
  • mm: kswapd spinning on unreclaimable nodes - fixes and cleanups
Related show

Commit Message

Johannes Weiner Feb. 28, 2017, 9:40 p.m. UTC
246e87a93934 ("memcg: fix get_scan_count() for small targets") sought
to avoid high reclaim priorities for kswapd by forcing it to scan a
minimum amount of pages when lru_pages >> priority yielded nothing.

b95a2f2d486d ("mm: vmscan: convert global reclaim to per-memcg LRU
lists"), due to switching global reclaim to a round-robin scheme over
all cgroups, had to restrict this forceful behavior to unreclaimable
zones in order to prevent massive overreclaim with many cgroups.

The latter patch effectively neutered the behavior completely for all
but extreme memory pressure. But in those situations we might as well
drop the reclaimers to lower priority levels. Remove the check.

Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
---
 mm/vmscan.c | 19 +++++--------------
 1 file changed, 5 insertions(+), 14 deletions(-)

Comments

Michal Hocko March 1, 2017, 3:21 p.m. UTC | #1
On Tue 28-02-17 16:40:03, Johannes Weiner wrote:
> 246e87a93934 ("memcg: fix get_scan_count() for small targets") sought
> to avoid high reclaim priorities for kswapd by forcing it to scan a
> minimum amount of pages when lru_pages >> priority yielded nothing.
> 
> b95a2f2d486d ("mm: vmscan: convert global reclaim to per-memcg LRU
> lists"), due to switching global reclaim to a round-robin scheme over
> all cgroups, had to restrict this forceful behavior to unreclaimable
> zones in order to prevent massive overreclaim with many cgroups.
> 
> The latter patch effectively neutered the behavior completely for all
> but extreme memory pressure. But in those situations we might as well
> drop the reclaimers to lower priority levels. Remove the check.
> 
> Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>

Acked-by: Michal Hocko <mhocko@suse.com>

> ---
>  mm/vmscan.c | 19 +++++--------------
>  1 file changed, 5 insertions(+), 14 deletions(-)
> 
> diff --git a/mm/vmscan.c b/mm/vmscan.c
> index 911957b66622..46b6223fe7f3 100644
> --- a/mm/vmscan.c
> +++ b/mm/vmscan.c
> @@ -2129,22 +2129,13 @@ static void get_scan_count(struct lruvec *lruvec, struct mem_cgroup *memcg,
>  	int pass;
>  
>  	/*
> -	 * If the zone or memcg is small, nr[l] can be 0.  This
> -	 * results in no scanning on this priority and a potential
> -	 * priority drop.  Global direct reclaim can go to the next
> -	 * zone and tends to have no problems. Global kswapd is for
> -	 * zone balancing and it needs to scan a minimum amount. When
> +	 * If the zone or memcg is small, nr[l] can be 0. When
>  	 * reclaiming for a memcg, a priority drop can cause high
> -	 * latencies, so it's better to scan a minimum amount there as
> -	 * well.
> +	 * latencies, so it's better to scan a minimum amount. When a
> +	 * cgroup has already been deleted, scrape out the remaining
> +	 * cache forcefully to get rid of the lingering state.
>  	 */
> -	if (current_is_kswapd()) {
> -		if (!pgdat_reclaimable(pgdat))
> -			force_scan = true;
> -		if (!mem_cgroup_online(memcg))
> -			force_scan = true;
> -	}
> -	if (!global_reclaim(sc))
> +	if (!global_reclaim(sc) || !mem_cgroup_online(memcg))
>  		force_scan = true;
>  
>  	/* If we have no swap space, do not bother scanning anon pages. */
> -- 
> 2.11.1
Hillf Danton March 2, 2017, 3:31 a.m. UTC | #2
On March 01, 2017 5:40 AM Johannes Weiner wrote:
> 
> 246e87a93934 ("memcg: fix get_scan_count() for small targets") sought
> to avoid high reclaim priorities for kswapd by forcing it to scan a
> minimum amount of pages when lru_pages >> priority yielded nothing.
> 
> b95a2f2d486d ("mm: vmscan: convert global reclaim to per-memcg LRU
> lists"), due to switching global reclaim to a round-robin scheme over
> all cgroups, had to restrict this forceful behavior to unreclaimable
> zones in order to prevent massive overreclaim with many cgroups.
> 
> The latter patch effectively neutered the behavior completely for all
> but extreme memory pressure. But in those situations we might as well
> drop the reclaimers to lower priority levels. Remove the check.
> 
> Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
> ---
>  mm/vmscan.c | 19 +++++--------------
>  1 file changed, 5 insertions(+), 14 deletions(-)
> 
Acked-by: Hillf Danton <hillf.zj@alibaba-inc.com>

Patch
diff mbox series

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 911957b66622..46b6223fe7f3 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2129,22 +2129,13 @@  static void get_scan_count(struct lruvec *lruvec, struct mem_cgroup *memcg,
 	int pass;
 
 	/*
-	 * If the zone or memcg is small, nr[l] can be 0.  This
-	 * results in no scanning on this priority and a potential
-	 * priority drop.  Global direct reclaim can go to the next
-	 * zone and tends to have no problems. Global kswapd is for
-	 * zone balancing and it needs to scan a minimum amount. When
+	 * If the zone or memcg is small, nr[l] can be 0. When
 	 * reclaiming for a memcg, a priority drop can cause high
-	 * latencies, so it's better to scan a minimum amount there as
-	 * well.
+	 * latencies, so it's better to scan a minimum amount. When a
+	 * cgroup has already been deleted, scrape out the remaining
+	 * cache forcefully to get rid of the lingering state.
 	 */
-	if (current_is_kswapd()) {
-		if (!pgdat_reclaimable(pgdat))
-			force_scan = true;
-		if (!mem_cgroup_online(memcg))
-			force_scan = true;
-	}
-	if (!global_reclaim(sc))
+	if (!global_reclaim(sc) || !mem_cgroup_online(memcg))
 		force_scan = true;
 
 	/* If we have no swap space, do not bother scanning anon pages. */