The patch titled
Subject: mm/memcg: add next_mz back to soft limit tree if not reclaimed yet
has been added to the -mm tree. Its filename is
mm-memcg-add-next_mz-back-to-soft-limit-tree-if-not-reclaimed-yet.patch
This patch should soon appear at
https://ozlabs.org/~akpm/mmots/broken-out/mm-memcg-add-next_mz-back-to-soft-limit-tree-if-not-reclaimed-yet.patch
and later at
https://ozlabs.org/~akpm/mmotm/broken-out/mm-memcg-add-next_mz-back-to-soft-limit-tree-if-not-reclaimed-yet.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: Wei Yang <richard.weiyang@xxxxxxxxx>
Subject: mm/memcg: add next_mz back to soft limit tree if not reclaimed yet
When memory reclaim failed for a maximum number of attempts and we bail
out of the reclaim loop, we forgot to put the target mem_cgroup chosen for
next reclaim back to the soft limit tree. This prevented pages in the
mem_cgroup from being reclaimed in the future even though the mem_cgroup
exceeded its soft limit.
Let's say there are two mem_cgroup and both of them exceed the soft limit,
while the first one is more active then the second. Since we add a
mem_cgroup to soft limit tree every 1024 event, the second one just get a
rare chance to be put on soft limit tree even it exceeds the limit.
As time goes on, the first mem_cgroup was kept close to its soft limit due
to reclaim activities, while the memory usage of the second mem_cgroup
keeps growing over the soft limit for a long time due to its relatively
rare occurrence.
This patch adds next_mz back to prevent this scenario.
Link: https://lkml.kernel.org/r/20220312071623.19050-3-richard.weiyang@xxxxxxxxx
Signed-off-by: Wei Yang <richard.weiyang@xxxxxxxxx>
Cc: Michal Hocko <mhocko@xxxxxxxx>
Cc: Roman Gushchin <roman.gushchin@xxxxxxxxx>
Cc: Johannes Weiner <hannes@xxxxxxxxxxx>
Cc: Shakeel Butt <shakeelb@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/memcontrol.c | 7 ++++++-
1 file changed, 6 insertions(+), 1 deletion(-)
--- a/mm/memcontrol.c~mm-memcg-add-next_mz-back-to-soft-limit-tree-if-not-reclaimed-yet
+++ a/mm/memcontrol.c
@@ -3453,8 +3453,13 @@ unsigned long mem_cgroup_soft_limit_recl
loop > MEM_CGROUP_MAX_SOFT_LIMIT_RECLAIM_LOOPS))
break;
} while (!nr_reclaimed);
- if (next_mz)
+ if (next_mz) {
+ spin_lock_irq(&mctz->lock);
+ excess = soft_limit_excess(next_mz->memcg);
+ __mem_cgroup_insert_exceeded(next_mz, mctz, excess);
+ spin_unlock_irq(&mctz->lock);
css_put(&next_mz->memcg->css);
+ }
return nr_reclaimed;
}
_
Patches currently in -mm which might be from richard.weiyang@xxxxxxxxx are
mm-memcg-mem_cgroup_per_node-is-already-set-to-0-on-allocation.patch
mm-memcg-retrieve-parent-memcg-from-cssparent.patch
mm-memcg-set-memcg-after-css-verified-and-got-reference.patch
mm-memcg-set-pos-to-prev-unconditionally.patch
mm-memcg-move-generation-assignment-and-comparison-together.patch
mm-memcg-mz-already-removed-from-rb_tree-in-mem_cgroup_largest_soft_limit_node.patch
mm-memcg-__mem_cgroup_remove_exceeded-could-handle-a-on-tree-mz-properly.patch
mm-memcg-add-next_mz-back-to-soft-limit-tree-if-not-reclaimed-yet.patch
mm-page_alloc-add-same-penalty-is-enough-to-get-round-robin-order.patch
mm-page_alloc-add-penalty-to-local_node.patch
memcg-do-not-tweak-node-in-alloc_mem_cgroup_per_node_info.patch
