From: "Michal Koutný" <mkoutny@suse.com>
To: Roman Gushchin <guro@fb.com>
Cc: Andrew Morton <akpm@linux-foundation.org>,
Dennis Zhou <dennis@kernel.org>, Tejun Heo <tj@kernel.org>,
Christoph Lameter <cl@linux.com>,
Johannes Weiner <hannes@cmpxchg.org>,
Michal Hocko <mhocko@kernel.org>,
Shakeel Butt <shakeelb@google.com>,
linux-mm@kvack.org, kernel-team@fb.com,
linux-kernel@vger.kernel.org
Subject: Re: [PATCH v3 4/5] mm: memcg: charge memcg percpu memory to the parent cgroup
Date: Tue, 11 Aug 2020 20:32:25 +0200 [thread overview]
Message-ID: <20200811183225.GA62582@blackbook> (raw)
In-Reply-To: <20200811165527.GA1507044@carbon.DHCP.thefacebook.com>
[-- Attachment #1: Type: text/plain, Size: 2118 bytes --]
On Tue, Aug 11, 2020 at 09:55:27AM -0700, Roman Gushchin <guro@fb.com> wrote:
> As I said, there are 2 problems with charging systemd (or a similar daemon):
> 1) It often belongs to the root cgroup.
This doesn't hold for systemd (if we agree that systemd is the most
common case).
> 2) OOMing or failing some random memory allocations is a bad way
> to "communicate" a memory shortage to the daemon.
> What we really want is to prevent creating a huge number of cgroups
There's cgroup.max.descendants for that...
> (including dying cgroups) in some specific sub-tree(s).
...oh, so is this limiting the number of cgroups or limiting resources
used?
> OOMing the daemon or returning -ENOMEM to some random syscalls
> will not help us to reach the goal and likely will bring a bad
> experience to a user.
If we reach the situation when memory for cgroup operations is tight,
it'll disappoint the user either way.
My premise is that a running workload is more valuable than the
accompanying manager.
> In a generic case I don't see how we can charge the cgroup which
> creates cgroups without solving these problems first.
In my understanding, "onbehalveness" is a concept useful for various
kernel threads doing deferred work. Here it's promoted to user processes
managing cgroups.
> And if there is a very special case where we have to limit it,
> we can just add an additional layer:
>
> ` root or delegated root
> ` manager-parent-cgroup-with-a-limit
> ` manager-cgroup (systemd, docker, ...)
> ` [aggregation group(s)]
> ` job-group-1
> ` ...
> ` job-group-n
If the charge goes to the parent of created cgroup (job-cgroup-i here),
then the layer adds nothing. Am I missing something?
> I'd definitely charge the parent cgroup in all similar cases.
(This would mandate the controllers on the unified hierarchy, which is
fine IMO.) Then the order of enabling controllers on a subtree (e.g.
cpu,memory vs memory,cpu) by the manager would yield different charging.
This seems wrong^W confusing to me.
Thanks,
Michal
[-- Attachment #2: Digital signature --]
[-- Type: application/pgp-signature, Size: 833 bytes --]
next prev parent reply other threads:[~2020-08-11 18:32 UTC|newest]
Thread overview: 24+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-06-23 18:45 [PATCH v3 0/5] mm: memcg accounting of percpu memory Roman Gushchin
2020-06-23 18:45 ` [PATCH v3 1/5] percpu: return number of released bytes from pcpu_free_area() Roman Gushchin
2020-06-24 0:58 ` Shakeel Butt
2020-06-23 18:45 ` [PATCH v3 2/5] mm: memcg/percpu: account percpu memory to memory cgroups Roman Gushchin
2020-06-24 1:25 ` Shakeel Butt
2020-06-23 18:45 ` [PATCH v3 3/5] mm: memcg/percpu: per-memcg percpu memory statistics Roman Gushchin
2020-06-24 1:35 ` Shakeel Butt
2020-08-11 15:05 ` Johannes Weiner
2020-06-23 18:45 ` [PATCH v3 4/5] mm: memcg: charge memcg percpu memory to the parent cgroup Roman Gushchin
2020-06-24 1:40 ` Shakeel Butt
2020-06-24 1:49 ` Roman Gushchin
2020-07-29 17:10 ` Michal Koutný
2020-08-07 4:16 ` Andrew Morton
2020-08-07 4:37 ` Roman Gushchin
2020-08-10 19:33 ` Roman Gushchin
2020-08-11 14:47 ` Michal Koutný
2020-08-11 16:55 ` Roman Gushchin
2020-08-11 18:32 ` Michal Koutný [this message]
2020-08-11 19:32 ` Roman Gushchin
2020-08-12 16:28 ` Michal Koutný
2020-08-11 15:27 ` Johannes Weiner
2020-08-11 17:06 ` Roman Gushchin
2020-08-13 9:16 ` Naresh Kamboju
2020-08-13 23:27 ` Stephen Rothwell
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=20200811183225.GA62582@blackbook \
--to=mkoutny@suse.com \
--cc=akpm@linux-foundation.org \
--cc=cl@linux.com \
--cc=dennis@kernel.org \
--cc=guro@fb.com \
--cc=hannes@cmpxchg.org \
--cc=kernel-team@fb.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mhocko@kernel.org \
--cc=shakeelb@google.com \
--cc=tj@kernel.org \
/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).