[<prev] [next>] [thread-next>] [day] [month] [year] [list]
Message-Id: <1511746650-51945-1-git-send-email-jiang.biao2@zte.com.cn>
Date: Mon, 27 Nov 2017 09:37:30 +0800
From: Jiang Biao <jiang.biao2@....com.cn>
To: akpm@...ux-foundation.org, mhocko@...e.com, hannes@...xchg.org,
hillf.zj@...baba-inc.com, minchan@...nel.org, ying.huang@...el.com,
mgorman@...hsingularity.net
Cc: linux-mm@...ck.org, linux-kernel@...r.kernel.org,
jiang.biao2@....com.cn, zhong.weidong@....com.cn
Subject: [PATCH] mm/vmscan: make do_shrink_slab more robust.
When running ltp stress test for 7*24 hours, the kernel occasionally
complains the following warning continuously,
mb_cache_shrink_scan+0x0/0x3f0 negative objects to delete
nr=-9222526086287711848
mb_cache_shrink_scan+0x0/0x3f0 negative objects to delete
nr=-9222420761333860545
mb_cache_shrink_scan+0x0/0x3f0 negative objects to delete
nr=-9222287677544280360
...
The tracing result shows the freeable(mb_cache_shrink_scan returns)
is -1, which causes the continuous accumulation and overflow of
total_scan.
This patch make do_shrink_slab more robust when
shrinker->count_objects return negative freeable.
Signed-off-by: Jiang Biao <jiang.biao2@....com.cn>
---
mm/vmscan.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/mm/vmscan.c b/mm/vmscan.c
index eb2f031..3ea28f0 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -323,7 +323,7 @@ static unsigned long do_shrink_slab(struct shrink_control *shrinkctl,
long scanned = 0, next_deferred;
freeable = shrinker->count_objects(shrinker, shrinkctl);
- if (freeable == 0)
+ if (freeable <= 0)
return 0;
/*
--
2.7.4
Powered by blists - more mailing lists