The patch titled
Subject: mm: memcg: use larger batches for proactive reclaim
has been added to the -mm mm-unstable branch. Its filename is
mm-memcg-use-larger-batches-for-proactive-reclaim.patch
This patch will shortly appear at
https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/mm-memcg-use-larger-batches-for-proactive-reclaim.patch
This patch will later appear in the mm-unstable branch at
git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
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 via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days
------------------------------------------------------
From: "T.J. Mercier" <tjmercier@xxxxxxxxxx>
Subject: mm: memcg: use larger batches for proactive reclaim
Date: Fri, 2 Feb 2024 23:38:54 +0000
Before 388536ac291 ("mm:vmscan: fix inaccurate reclaim during proactive
reclaim") we passed the number of pages for the reclaim request directly
to try_to_free_mem_cgroup_pages, which could lead to significant
overreclaim. After 0388536ac291 the number of pages was limited to a
maximum 32 (SWAP_CLUSTER_MAX) to reduce the amount of overreclaim.
However such a small batch size caused a regression in reclaim performance
due to many more reclaim start/stop cycles inside memory_reclaim.
Reclaim tries to balance nr_to_reclaim fidelity with fairness across nodes
and cgroups over which the pages are spread. As such, the bigger the
request, the bigger the absolute overreclaim error. Historic in-kernel
users of reclaim have used fixed, small sized requests to approach an
appropriate reclaim rate over time. When we reclaim a user request of
arbitrary size, use decaying batch sizes to manage error while maintaining
reasonable throughput.
root - full reclaim pages/sec time (sec)
pre-0388536ac291 : 68047 10.46
post-0388536ac291 : 13742 inf
(reclaim-reclaimed)/4 : 67352 10.51
/uid_0 - 1G reclaim pages/sec time (sec) overreclaim (MiB)
pre-0388536ac291 : 258822 1.12 107.8
post-0388536ac291 : 105174 2.49 3.5
(reclaim-reclaimed)/4 : 233396 1.12 -7.4
/uid_0 - full reclaim pages/sec time (sec)
pre-0388536ac291 : 72334 7.09
post-0388536ac291 : 38105 14.45
(reclaim-reclaimed)/4 : 72914 6.96
Link: https://lkml.kernel.org/r/20240202233855.1236422-1-tjmercier@xxxxxxxxxx
Fixes: 0388536ac291 ("mm:vmscan: fix inaccurate reclaim during proactive re=
claim")
Signed-off-by: T.J. Mercier <tjmercier@xxxxxxxxxx>
Reviewed-by: Yosry Ahmed <yosryahmed@xxxxxxxxxx>
Acked-by: Johannes Weiner <hannes@xxxxxxxxxxx>
Cc: Michal Hocko <mhocko@xxxxxxxx>
Cc: Roman Gushchin <roman.gushchin@xxxxxxxxx>
Cc: Shakeel Butt <shakeelb@xxxxxxxxxx>
Cc: Muchun Song <songmuchun@xxxxxxxxxxxxx>
Cc: Efly Young <yangyifei03@xxxxxxxxxxxx>
Cc: Michal Koutny <mkoutny@xxxxxxxx>
Cc: Yu Zhao <yuzhao@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/memcontrol.c | 6 ++++--
1 file changed, 4 insertions(+), 2 deletions(-)
--- a/mm/memcontrol.c~mm-memcg-use-larger-batches-for-proactive-reclaim
+++ a/mm/memcontrol.c
@@ -6994,9 +6994,11 @@ static ssize_t memory_reclaim(struct ker
if (!nr_retries)
lru_add_drain_all();
+ /* Will converge on zero, but reclaim enforces a minimum */
+ unsigned long batch_size = (nr_to_reclaim - nr_reclaimed) / 4;
+
reclaimed = try_to_free_mem_cgroup_pages(memcg,
- min(nr_to_reclaim - nr_reclaimed, SWAP_CLUSTER_MAX),
- GFP_KERNEL, reclaim_options);
+ batch_size, GFP_KERNEL, reclaim_options);
if (!reclaimed && !nr_retries--)
return -EAGAIN;
_
Patches currently in -mm which might be from tjmercier@xxxxxxxxxx are
mm-memcg-dont-periodically-flush-stats-when-memcg-is-disabled.patch
mm-memcg-use-larger-batches-for-proactive-reclaim.patch
