From: Roman Gushchin <guro@fb.com>
To: Wei Yang <richard.weiyang@gmail.com>
Cc: <hannes@cmpxchg.org>, <mhocko@kernel.org>,
<vdavydov.dev@gmail.com>, <akpm@linux-foundation.org>,
<shakeelb@google.com>, <vbabka@suse.cz>, <willy@infradead.org>,
<songmuchun@bytedance.com>, <shy828301@gmail.com>,
<surenb@google.com>, <linux-kernel@vger.kernel.org>,
<cgroups@vger.kernel.org>, <linux-mm@kvack.org>
Subject: Re: [PATCH 4/4] mm/memcg: refine mem_cgroup_threshold_ary->current_threshold calculation
Date: Tue, 11 Jan 2022 10:23:41 -0800 [thread overview]
Message-ID: <Yd3LLalWzPy17PmR@carbon.dhcp.thefacebook.com> (raw)
In-Reply-To: <20220111010302.8864-4-richard.weiyang@gmail.com>
On Tue, Jan 11, 2022 at 01:03:02AM +0000, Wei Yang wrote:
> mem_cgroup_threshold_ary->current_threshold points to the last entry
> who's threshold is less or equal to usage.
>
> Instead of iterating entries to get the correct index, we can leverage
> primary->current_threshold to get it. If the threshold added is less or
> equal to usage, current_threshold should increase by one. Otherwise, it
> doesn't change.
How big is usually an array of thresholds? If it's not huge, likely
any savings won't be really noticeable (it's not a hot path and there
is an rc_synchronize() below).
So I agree with Michal that a better justification is really needed.
Thanks!
next prev parent reply other threads:[~2022-01-11 18:24 UTC|newest]
Thread overview: 30+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-01-11 1:02 [PATCH 1/4] mm/memcg: use NUMA_NO_NODE to indicate allocation from unspecified node Wei Yang
2022-01-11 1:03 ` [PATCH 2/4] mm/memcg: mem_cgroup_per_node is already set to 0 on allocation Wei Yang
2022-01-11 2:25 ` Muchun Song
2022-01-11 8:41 ` Michal Hocko
2022-01-11 18:06 ` Roman Gushchin
2022-01-14 11:08 ` Mike Rapoport
2022-01-16 19:24 ` Shakeel Butt
2022-01-11 1:03 ` [PATCH 3/4] mm/memcg: retrieve parent memcg from css.parent Wei Yang
2022-01-11 3:12 ` Muchun Song
2022-01-11 8:43 ` Michal Hocko
2022-01-11 18:09 ` Roman Gushchin
2022-01-12 0:24 ` Wei Yang
2022-01-16 19:54 ` Shakeel Butt
2022-01-11 1:03 ` [PATCH 4/4] mm/memcg: refine mem_cgroup_threshold_ary->current_threshold calculation Wei Yang
2022-01-11 8:44 ` Michal Hocko
2022-01-11 18:23 ` Roman Gushchin [this message]
2022-01-12 0:25 ` Wei Yang
2022-01-11 2:23 ` [PATCH 1/4] mm/memcg: use NUMA_NO_NODE to indicate allocation from unspecified node Muchun Song
2022-01-11 8:40 ` Michal Hocko
2022-01-12 0:46 ` Wei Yang
2022-01-12 8:56 ` Michal Hocko
2022-01-14 0:29 ` Wei Yang
2022-01-14 8:51 ` Michal Hocko
2022-01-15 22:10 ` Wei Yang
2022-01-16 19:23 ` Shakeel Butt
2022-01-11 18:05 ` Roman Gushchin
2022-01-14 11:07 ` Mike Rapoport
2022-01-31 1:47 ` Wei Yang
2022-01-31 22:36 ` Andrew Morton
2022-02-01 0:42 ` Wei Yang
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=Yd3LLalWzPy17PmR@carbon.dhcp.thefacebook.com \
--to=guro@fb.com \
--cc=akpm@linux-foundation.org \
--cc=cgroups@vger.kernel.org \
--cc=hannes@cmpxchg.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mhocko@kernel.org \
--cc=richard.weiyang@gmail.com \
--cc=shakeelb@google.com \
--cc=shy828301@gmail.com \
--cc=songmuchun@bytedance.com \
--cc=surenb@google.com \
--cc=vbabka@suse.cz \
--cc=vdavydov.dev@gmail.com \
--cc=willy@infradead.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).