From: Michal Hocko <mhocko@suse.com>
To: Tim Chen <tim.c.chen@linux.intel.com>
Cc: Andrew Morton <akpm@linux-foundation.org>,
Johannes Weiner <hannes@cmpxchg.org>,
Vladimir Davydov <vdavydov.dev@gmail.com>,
Dave Hansen <dave.hansen@intel.com>,
Ying Huang <ying.huang@intel.com>,
linux-mm@kvack.org, cgroups@vger.kernel.org,
linux-kernel@vger.kernel.org
Subject: Re: [PATCH v2 2/3] mm: Force update of mem cgroup soft limit tree on usage excess
Date: Wed, 24 Feb 2021 12:53:35 +0100 [thread overview]
Message-ID: <YDY+PydRUGQpHNaJ@dhcp22.suse.cz> (raw)
In-Reply-To: <cf5ca7a1-7965-f307-22e1-e216316904cf@linux.intel.com>
On Mon 22-02-21 11:48:37, Tim Chen wrote:
>
>
> On 2/22/21 11:09 AM, Michal Hocko wrote:
>
> >>
> >> I actually have tried adjusting the threshold but found that it doesn't work well for
> >> the case with unenven memory access frequency between cgroups. The soft
> >> limit for the low memory event cgroup could creep up quite a lot, exceeding
> >> the soft limit by hundreds of MB, even
> >> if I drop the SOFTLIMIT_EVENTS_TARGET from 1024 to something like 8.
> >
> > What was the underlying reason? Higher order allocations?
> >
>
> Not high order allocation.
>
> The reason was because the run away memcg asks for memory much less often, compared
> to the other memcgs in the system. So it escapes the sampling update and
> was not put onto the tree and exceeds the soft limit
> pretty badly. Even if it was put onto the tree and gets page reclaimed below the
> limit, it could escape the sampling the next time it exceeds the soft limit.
I am sorry but I really do not follow. Maybe I am missing something
obvious but the the rate of events (charge/uncharge) shouldn't be really
important. There is no way to exceed the limit without charging memory
(either a new or via task migration in v1 and immigrate_on_move). If you
have SOFTLIMIT_EVENTS_TARGET 8 then you should be 128 * 8 events to
re-evaluate. Huge pages can make the runaway much bigger but how it
would be possible to runaway outside of that bound.
Btw. do we really need SOFTLIMIT_EVENTS_TARGET at all? Why cannot we
just stick with a single threshold? mem_cgroup_update_tree can be made
a effectivelly a noop when there is no soft limit in place so overhead
shouldn't matter for the vast majority of workloads.
--
Michal Hocko
SUSE Labs
next prev parent reply other threads:[~2021-02-24 11:53 UTC|newest]
Thread overview: 35+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-02-17 20:41 [PATCH v2 0/3] Soft limit memory management bug fixes Tim Chen
2021-02-17 20:41 ` [PATCH v2 1/3] mm: Fix dropped memcg from mem cgroup soft limit tree Tim Chen
2021-02-18 8:24 ` Michal Hocko
2021-02-18 18:30 ` Tim Chen
2021-02-18 19:13 ` Michal Hocko
2021-02-18 19:51 ` Tim Chen
2021-02-18 19:13 ` Michal Hocko
2021-03-04 17:35 ` Tim Chen
2021-03-05 9:11 ` Michal Hocko
2021-03-05 19:07 ` Tim Chen
2021-03-08 8:34 ` Michal Hocko
2021-02-17 20:41 ` [PATCH v2 2/3] mm: Force update of mem cgroup soft limit tree on usage excess Tim Chen
2021-02-19 9:11 ` Michal Hocko
2021-02-19 18:59 ` Tim Chen
2021-02-20 16:23 ` Tim Chen
2021-02-22 8:40 ` Michal Hocko
2021-02-22 17:41 ` Tim Chen
2021-02-22 19:09 ` Michal Hocko
2021-02-22 19:23 ` Tim Chen
2021-02-22 19:48 ` Tim Chen
2021-02-24 11:53 ` Michal Hocko [this message]
2021-02-25 22:48 ` Tim Chen
2021-02-26 8:52 ` Michal Hocko
2021-02-27 0:56 ` Tim Chen
2021-03-01 7:39 ` Michal Hocko
2021-02-25 22:25 ` Tim Chen
2021-03-02 6:25 ` [mm] 4f09feb8bf: vm-scalability.throughput -4.3% regression kernel test robot
2021-02-17 20:41 ` [PATCH v2 3/3] mm: Fix missing mem cgroup soft limit tree updates Tim Chen
2021-02-18 5:56 ` Johannes Weiner
2021-02-22 18:38 ` Tim Chen
2021-02-23 15:18 ` Johannes Weiner
2021-02-19 9:16 ` Michal Hocko
2021-02-19 19:28 ` Tim Chen
2021-02-22 8:41 ` Michal Hocko
2021-02-22 17:45 ` Tim Chen
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=YDY+PydRUGQpHNaJ@dhcp22.suse.cz \
--to=mhocko@suse.com \
--cc=akpm@linux-foundation.org \
--cc=cgroups@vger.kernel.org \
--cc=dave.hansen@intel.com \
--cc=hannes@cmpxchg.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=tim.c.chen@linux.intel.com \
--cc=vdavydov.dev@gmail.com \
--cc=ying.huang@intel.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).