From: Richard Palethorpe <rpalethorpe@suse.de>
To: ltp@lists.linux.it
Subject: [LTP] [RFC PATCH] mm: memcg/slab: Stop reparented obj_cgroups from charging root
Date: Mon, 19 Oct 2020 09:45:32 +0100 [thread overview]
Message-ID: <87lfg2ob83.fsf@suse.de> (raw)
In-Reply-To: <20201016171502.GA102311@blackbook>
Hello,
Michal Koutn? <mkoutny@suse.com> writes:
> On Fri, Oct 16, 2020 at 10:53:08AM -0400, Johannes Weiner <hannes@cmpxchg.org> wrote:
>> The central try_charge() function charges recursively all the way up
>> to and including the root.
> Except for use_hiearchy=0 (which is the case here as Richard
> wrote). The reparenting is hence somewhat incompatible with
> new_parent.use_hiearchy=0 :-/
>
Yes and it also seems
new_parent.use_hierarch=0 -> new_child.use_hierarchy=0
and
new_parent.use_hierarch=0 -> new_child.use_hierarchy=1
are considered valid on cgroupsV1. The kernel will also allow more
descendants on new_child.use_hierarchy=0, but sets
broken_hierarchy=1. However this will not stop the stack trace occuring
(AFAICT) when the reparenting happens between two descendants.
>> We should clean this up one way or another: either charge the root or
>> don't, but do it consistently.
> I agree this'd be good to unify. One upside of excluding root memcg from
> charging is that users are spared from the charging overhead when memcg
> tree is not created. (Actually, I thought that was the reason for this
> exception.)
>
> Michal
--
Thank you,
Richard.
WARNING: multiple messages have this Message-ID (diff)
From: Richard Palethorpe <rpalethorpe@suse.de>
To: "Michal Koutný" <mkoutny@suse.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>,
Roman Gushchin <guro@fb.com>,
ltp@lists.linux.it, Andrew Morton <akpm@linux-foundation.org>,
Shakeel Butt <shakeelb@google.com>,
Christoph Lameter <cl@linux.com>,
Michal Hocko <mhocko@kernel.org>, Tejun Heo <tj@kernel.org>,
Vlastimil Babka <vbabka@suse.cz>,
linux-mm@kvack.org, linux-kernel@vger.kernel.org
Subject: Re: [RFC PATCH] mm: memcg/slab: Stop reparented obj_cgroups from charging root
Date: Mon, 19 Oct 2020 09:45:32 +0100 [thread overview]
Message-ID: <87lfg2ob83.fsf@suse.de> (raw)
In-Reply-To: <20201016171502.GA102311@blackbook>
Hello,
Michal Koutný <mkoutny@suse.com> writes:
> On Fri, Oct 16, 2020 at 10:53:08AM -0400, Johannes Weiner <hannes@cmpxchg.org> wrote:
>> The central try_charge() function charges recursively all the way up
>> to and including the root.
> Except for use_hiearchy=0 (which is the case here as Richard
> wrote). The reparenting is hence somewhat incompatible with
> new_parent.use_hiearchy=0 :-/
>
Yes and it also seems
new_parent.use_hierarch=0 -> new_child.use_hierarchy=0
and
new_parent.use_hierarch=0 -> new_child.use_hierarchy=1
are considered valid on cgroupsV1. The kernel will also allow more
descendants on new_child.use_hierarchy=0, but sets
broken_hierarchy=1. However this will not stop the stack trace occuring
(AFAICT) when the reparenting happens between two descendants.
>> We should clean this up one way or another: either charge the root or
>> don't, but do it consistently.
> I agree this'd be good to unify. One upside of excluding root memcg from
> charging is that users are spared from the charging overhead when memcg
> tree is not created. (Actually, I thought that was the reason for this
> exception.)
>
> Michal
--
Thank you,
Richard.
next prev parent reply other threads:[~2020-10-19 8:45 UTC|newest]
Thread overview: 91+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-10-14 19:07 [LTP] [RFC PATCH] mm: memcg/slab: Stop reparented obj_cgroups from charging root Richard Palethorpe
2020-10-14 19:07 ` Richard Palethorpe
2020-10-14 20:08 ` [LTP] " Roman Gushchin
2020-10-14 20:08 ` Roman Gushchin
2020-10-16 5:40 ` [LTP] " Richard Palethorpe
2020-10-16 5:40 ` Richard Palethorpe
2020-10-16 6:32 ` [LTP] [PATCH v2] " Richard Palethorpe
2020-10-16 9:47 ` [LTP] [RFC PATCH] " Michal =?unknown-8bit?q?Koutn=C3=BD?=
2020-10-16 9:47 ` Michal Koutný
2020-10-16 10:41 ` [LTP] " Richard Palethorpe
2020-10-16 10:41 ` Richard Palethorpe
2020-10-16 15:05 ` [LTP] " Richard Palethorpe
2020-10-16 15:05 ` Richard Palethorpe
2020-10-16 17:26 ` [LTP] " Michal =?unknown-8bit?q?Koutn=C3=BD?=
2020-10-16 17:26 ` Michal Koutný
2020-10-16 14:53 ` [LTP] " Johannes Weiner
2020-10-16 14:53 ` Johannes Weiner
2020-10-16 17:02 ` [LTP] " Roman Gushchin
2020-10-16 17:02 ` Roman Gushchin
2020-10-16 17:15 ` [LTP] " Michal =?unknown-8bit?q?Koutn=C3=BD?=
2020-10-16 17:15 ` Michal Koutný
2020-10-19 8:45 ` Richard Palethorpe [this message]
2020-10-19 8:45 ` Richard Palethorpe
2020-10-19 9:58 ` [LTP] [PATCH v3] " Richard Palethorpe
2020-10-19 9:58 ` Richard Palethorpe
2020-10-19 16:58 ` [LTP] " Shakeel Butt
2020-10-19 16:58 ` Shakeel Butt
2020-10-20 5:52 ` [LTP] " Richard Palethorpe
2020-10-20 5:52 ` Richard Palethorpe
2020-10-20 13:49 ` [LTP] " Richard Palethorpe
2020-10-20 13:49 ` Richard Palethorpe
2020-10-20 16:56 ` [LTP] " Shakeel Butt
2020-10-20 16:56 ` Shakeel Butt
2020-10-21 20:32 ` [LTP] " Roman Gushchin
2020-10-21 20:32 ` Roman Gushchin
2020-10-20 17:24 ` [LTP] " Michal =?unknown-8bit?q?Koutn=C3=BD?=
2020-10-20 17:24 ` Michal Koutný
2020-10-22 7:04 ` [LTP] " Richard Palethorpe
2020-10-22 7:04 ` Richard Palethorpe
2020-10-22 12:28 ` [LTP] [PATCH v4] " Richard Palethorpe
2020-10-22 12:28 ` Richard Palethorpe
2020-10-22 16:37 ` [LTP] " Shakeel Butt
2020-10-22 16:37 ` Shakeel Butt
2020-10-22 17:25 ` [LTP] " Roman Gushchin
2020-10-22 17:25 ` Roman Gushchin
2020-10-22 23:59 ` [LTP] " Shakeel Butt
2020-10-22 23:59 ` Shakeel Butt
2020-10-23 0:40 ` [LTP] " Roman Gushchin
2020-10-23 0:40 ` Roman Gushchin
2020-10-23 15:44 ` [LTP] " Johannes Weiner
2020-10-23 15:44 ` Johannes Weiner
2020-10-23 16:41 ` [LTP] " Shakeel Butt
2020-10-23 16:41 ` Shakeel Butt
2020-10-26 7:32 ` [LTP] " Richard Palethorpe
2020-10-26 7:32 ` Richard Palethorpe
2020-10-26 23:14 ` [LTP] " Roman Gushchin
2020-10-26 23:14 ` Roman Gushchin
2020-10-19 22:28 ` [LTP] [RFC PATCH] " Roman Gushchin
2020-10-19 22:28 ` Roman Gushchin
2020-10-20 6:04 ` [LTP] " Richard Palethorpe
2020-10-20 6:04 ` Richard Palethorpe
2020-10-20 12:02 ` [LTP] " Richard Palethorpe
2020-10-20 12:02 ` Richard Palethorpe
2020-10-20 14:48 ` [LTP] " Richard Palethorpe
2020-10-20 14:48 ` Richard Palethorpe
2020-10-20 16:27 ` [LTP] " Michal =?unknown-8bit?q?Koutn=C3=BD?=
2020-10-20 16:27 ` Michal Koutný
2020-10-20 17:07 ` [LTP] " Roman Gushchin
2020-10-20 17:07 ` Roman Gushchin
2020-10-20 18:18 ` [LTP] " Johannes Weiner
2020-10-20 18:18 ` Johannes Weiner
2020-10-21 19:33 ` [LTP] " Roman Gushchin
2020-10-21 19:33 ` Roman Gushchin
2020-10-23 16:30 ` [LTP] " Johannes Weiner
2020-10-23 16:30 ` Johannes Weiner
2020-11-10 1:27 ` [LTP] " Roman Gushchin
2020-11-10 1:27 ` Roman Gushchin
2020-11-10 15:11 ` [LTP] " Shakeel Butt
2020-11-10 15:11 ` Shakeel Butt
2020-11-10 19:13 ` [LTP] " Roman Gushchin
2020-11-10 19:13 ` Roman Gushchin
2020-11-20 17:46 ` [LTP] " Michal =?unknown-8bit?q?Koutn=C3=BD?=
2020-11-20 17:46 ` Michal Koutný
2020-11-03 13:22 ` [LTP] " Michal Hocko
2020-11-03 13:22 ` Michal Hocko
2020-11-03 21:30 ` [LTP] " Roman Gushchin
2020-11-03 21:30 ` Roman Gushchin
2020-10-20 16:55 ` [LTP] " Shakeel Butt
2020-10-20 16:55 ` Shakeel Butt
2020-10-20 17:17 ` [LTP] " Roman Gushchin
2020-10-20 17:17 ` Roman Gushchin
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=87lfg2ob83.fsf@suse.de \
--to=rpalethorpe@suse.de \
--cc=ltp@lists.linux.it \
/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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.