The patch titled
Subject: mm: make drop_caches keep reclaiming on all nodes
has been added to the -mm mm-unstable branch. Its filename is
mm-make-drop_caches-keep-reclaiming-on-all-nodes.patch
This patch will shortly appear at
https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/mm-make-drop_caches-keep-reclaiming-on-all-nodes.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: Jan Kara <jack@xxxxxxx>
Subject: mm: make drop_caches keep reclaiming on all nodes
Date: Tue, 15 Nov 2022 13:32:55 +0100
Currently, drop_caches are reclaiming node-by-node, looping on each node
until reclaim could not make progress. This can however leave quite some
slab entries (such as filesystem inodes) unreclaimed if objects say on
node 1 keep objects on node 0 pinned. So move the "loop until no
progress" loop to the node-by-node iteration to retry reclaim also on
other nodes if reclaim on some nodes made progress. This fixes problem
when drop_caches was not reclaiming lots of otherwise perfectly fine to
reclaim inodes.
Link: https://lkml.kernel.org/r/20221115123255.12559-1-jack@xxxxxxx
Signed-off-by: Jan Kara <jack@xxxxxxx>
Reported-by: You Zhou <you.zhou@xxxxxxxxx>
Reported-by: Pengfei Xu <pengfei.xu@xxxxxxxxx>
Tested-by: Pengfei Xu <pengfei.xu@xxxxxxxxx>
Reviewed-by: Shakeel Butt <shakeelb@xxxxxxxxxx>
Cc: Vladimir Davydov <vdavydov.dev@xxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/vmscan.c | 33 ++++++++++++++++++---------------
1 file changed, 18 insertions(+), 15 deletions(-)
--- a/mm/vmscan.c~mm-make-drop_caches-keep-reclaiming-on-all-nodes
+++ a/mm/vmscan.c
@@ -1021,31 +1021,34 @@ out:
return freed;
}
-static void drop_slab_node(int nid)
+static unsigned long drop_slab_node(int nid)
{
- unsigned long freed;
- int shift = 0;
+ unsigned long freed = 0;
+ struct mem_cgroup *memcg = NULL;
+ memcg = mem_cgroup_iter(NULL, NULL, NULL);
do {
- struct mem_cgroup *memcg = NULL;
-
- if (fatal_signal_pending(current))
- return;
+ freed += shrink_slab(GFP_KERNEL, nid, memcg, 0);
+ } while ((memcg = mem_cgroup_iter(NULL, memcg, NULL)) != NULL);
- freed = 0;
- memcg = mem_cgroup_iter(NULL, NULL, NULL);
- do {
- freed += shrink_slab(GFP_KERNEL, nid, memcg, 0);
- } while ((memcg = mem_cgroup_iter(NULL, memcg, NULL)) != NULL);
- } while ((freed >> shift++) > 1);
+ return freed;
}
void drop_slab(void)
{
int nid;
+ int shift = 0;
+ unsigned long freed;
+
+ do {
+ freed = 0;
+ for_each_online_node(nid) {
+ if (fatal_signal_pending(current))
+ return;
- for_each_online_node(nid)
- drop_slab_node(nid);
+ freed += drop_slab_node(nid);
+ }
+ } while ((freed >> shift++) > 1);
}
static int reclaimer_offset(void)
_
Patches currently in -mm which might be from jack@xxxxxxx are
mm-make-drop_caches-keep-reclaiming-on-all-nodes.patch
