From: Tim Chen <tim.c.chen@linux.intel.com>
To: Michal Hocko <mhocko@suse.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: Thu, 25 Feb 2021 14:48:58 -0800 [thread overview]
Message-ID: <b5b1944d-846b-3212-fe4a-f10f5fcb87d7@linux.intel.com> (raw)
In-Reply-To: <YDY+PydRUGQpHNaJ@dhcp22.suse.cz>
On 2/24/21 3:53 AM, Michal Hocko wrote:
> 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.
Michal,
Let's take an extreme case where memcg 1 always generate the
first event and memcg 2 generates the rest of 128*8-1 events
and the pattern repeat. The update tree happens on the 128*8th event
so memcg 1 did not trigger update tree. In this case we will
keep missing memcg 1's event and not put memcg 1 on the tree.
Something like this pattern of memory events
cg1 cg2 cg2 cg2 ....cg2 cg1 cg2 cg2 cg2....cg2 cg1 cg2 .....
^ ^
update tree update tree
Of course in real life the update events are random in nature.
However, due to the low occurrence of memcg 1 event, we can miss
updating it for a long time due to its lower probability of occurrence.
>
> 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.
>
I think there are two limits because the original code wants
memc_cgroup_threshold to be updated more frequently than the
soft_limit_tree. The soft limit tree update is more costly.
Tim
next prev parent reply other threads:[~2021-02-25 23:09 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
2021-02-25 22:48 ` Tim Chen [this message]
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=b5b1944d-846b-3212-fe4a-f10f5fcb87d7@linux.intel.com \
--to=tim.c.chen@linux.intel.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=mhocko@suse.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).