[dm-devel] dm bufio: Reduce dm_bufio_lock contention

Michal Hocko mhocko at kernel.org
Wed Aug 1 07:03:12 UTC 2018


On Wed 01-08-18 10:48:00, jing xia wrote:
> We reproduced this issue again and found out the root cause.
> dm_bufio_prefetch() with dm_bufio_lock enters the direct reclaim and
> takes a long time to do the soft_limit_reclaim, because of the huge
> number of memory excess of the memcg.
> Then, all the task who do shrink_slab() wait for  dm_bufio_lock.
> 
> Any suggestions for this?Thanks.

Do not use soft limit?
-- 
Michal Hocko
SUSE Labs




More information about the dm-devel mailing list