From: Tejun Heo <tj@kernel.org>
To: Michal Hocko <mhocko@suse.cz>
Cc: hannes@cmpxchg.org, bsingharora@gmail.com,
cgroups@vger.kernel.org, linux-mm@kvack.org, lizefan@huawei.com
Subject: Re: [PATCH 3/3] memcg: simplify mem_cgroup_reclaim_iter
Date: Wed, 5 Jun 2013 02:03:26 -0700 [thread overview]
Message-ID: <20130605090326.GC7990@mtj.dyndns.org> (raw)
In-Reply-To: <20130605085531.GG15997@dhcp22.suse.cz>
Hey,
On Wed, Jun 05, 2013 at 10:55:31AM +0200, Michal Hocko wrote:
> > Yeah, that's true. I just wanna avoid the barrier dancing. Only one
> > of the ancestors can cache a memcg, right?
>
> No. All of them on the way up hierarchy. Basically each parent which
> ever triggered the reclaim caches reclaimers.
Oh, I meant only the ancestors can cache a memcg, so yeap.
> > Walking up the tree scanning for cached ones and putting them should
> > work? Is that what you were suggesting?
>
> That was my first version of the patch I linked in the previous email.
Yeah, indeed. Johannes, what do you think? Between the recent cgroup
iterator update and xchg(), we don't need the weak referencing and
it's just wrong to have that level of complexity in memcg proper.
Thanks.
--
tejun
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
next prev parent reply other threads:[~2013-06-05 9:03 UTC|newest]
Thread overview: 42+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-06-04 0:44 [PATCHSET] memcg: fix and reimplement iterator Tejun Heo
2013-06-04 0:44 ` [PATCH 1/3] memcg: fix subtle memory barrier bug in mem_cgroup_iter() Tejun Heo
2013-06-04 13:03 ` Michal Hocko
2013-06-04 13:58 ` Johannes Weiner
2013-06-04 15:29 ` Michal Hocko
2013-06-04 0:44 ` [PATCH 2/3] memcg: restructure mem_cgroup_iter() Tejun Heo
2013-06-04 13:21 ` Michal Hocko
2013-06-04 20:51 ` Tejun Heo
2013-06-04 0:44 ` [PATCH 3/3] memcg: simplify mem_cgroup_reclaim_iter Tejun Heo
2013-06-04 13:18 ` Michal Hocko
2013-06-04 20:50 ` Tejun Heo
2013-06-04 21:28 ` Michal Hocko
2013-06-04 21:55 ` Tejun Heo
2013-06-05 7:30 ` Michal Hocko
2013-06-05 8:20 ` Tejun Heo
2013-06-05 8:36 ` Michal Hocko
2013-06-05 8:44 ` Tejun Heo
2013-06-05 8:55 ` Michal Hocko
2013-06-05 9:03 ` Tejun Heo [this message]
2013-06-05 14:39 ` Johannes Weiner
2013-06-05 14:50 ` Johannes Weiner
2013-06-05 14:56 ` Michal Hocko
2013-06-05 17:22 ` Tejun Heo
2013-06-05 19:45 ` Johannes Weiner
2013-06-05 20:06 ` Tejun Heo
2013-06-05 21:17 ` Johannes Weiner
2013-06-05 22:20 ` Tejun Heo
2013-06-05 22:27 ` Tejun Heo
2013-06-06 11:50 ` Michal Hocko
2013-06-07 0:52 ` Tejun Heo
2013-06-07 7:37 ` Michal Hocko
2013-06-07 23:25 ` Tejun Heo
2013-06-10 8:02 ` Michal Hocko
2013-06-10 19:54 ` Tejun Heo
2013-06-10 20:48 ` Michal Hocko
2013-06-10 23:13 ` Tejun Heo
2013-06-11 7:27 ` Michal Hocko
2013-06-11 7:44 ` Tejun Heo
2013-06-11 7:55 ` Michal Hocko
2013-06-11 8:00 ` Tejun Heo
2013-06-04 21:40 ` Johannes Weiner
2013-06-04 21:49 ` Tejun Heo
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=20130605090326.GC7990@mtj.dyndns.org \
--to=tj@kernel.org \
--cc=bsingharora@gmail.com \
--cc=cgroups@vger.kernel.org \
--cc=hannes@cmpxchg.org \
--cc=linux-mm@kvack.org \
--cc=lizefan@huawei.com \
--cc=mhocko@suse.cz \
/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).