From: Michal Hocko <mhocko@suse.com>
To: Huan Yang <link@vivo.com>
Cc: "Huang, Ying" <ying.huang@intel.com>, Tejun Heo <tj@kernel.org>,
Zefan Li <lizefan.x@bytedance.com>,
Johannes Weiner <hannes@cmpxchg.org>,
Jonathan Corbet <corbet@lwn.net>,
Roman Gushchin <roman.gushchin@linux.dev>,
Shakeel Butt <shakeelb@google.com>,
Muchun Song <muchun.song@linux.dev>,
Andrew Morton <akpm@linux-foundation.org>,
David Hildenbrand <david@redhat.com>,
Matthew Wilcox <willy@infradead.org>,
Kefeng Wang <wangkefeng.wang@huawei.com>,
Peter Xu <peterx@redhat.com>,
"Vishal Moola (Oracle)" <vishal.moola@gmail.com>,
Yosry Ahmed <yosryahmed@google.com>,
Liu Shixin <liushixin2@huawei.com>,
Hugh Dickins <hughd@google.com>,
cgroups@vger.kernel.org, linux-doc@vger.kernel.org,
linux-kernel@vger.kernel.org, linux-mm@kvack.org,
opensource.kernel@vivo.com
Subject: Re: [RFC 0/4] Introduce unbalance proactive reclaim
Date: Fri, 10 Nov 2023 13:32:31 +0100 [thread overview]
Message-ID: <ZU4i36tKnyXZ8lZD@tiehlicka> (raw)
In-Reply-To: <78128117-ce70-47ef-b7fd-10c772b1c933@vivo.com>
On Fri 10-11-23 14:21:17, Huan Yang wrote:
[...]
> > BTW: how do you know the number of pages to be reclaimed proactively in
> > memcg proactive reclaiming based solution?
>
> One point here is that we are not sure how long the frozen application
> will be opened, it could be 10 minutes, an hour, or even days. So we
> need to predict and try, gradually reclaim anonymous pages in
> proportion, preferably based on the LRU algorithm. For example, if
> the application has been frozen for 10 minutes, reclaim 5% of
> anonymous pages; 30min:25%anon, 1hour:75%, 1day:100%. It is even more
> complicated as it requires adding a mechanism for predicting failure
> penalties.
Why would make your reclaiming decisions based on time rather than the
actual memory demand? I can see how a pro-active reclaim could make a
head room for an unexpected memory pressure but applying more pressure
just because of inactivity sound rather dubious to me TBH. Why cannot
you simply wait for the external memory pressure (e.g. from kswapd) to
deal with that based on the demand?
--
Michal Hocko
SUSE Labs
next prev parent reply other threads:[~2023-11-10 12:32 UTC|newest]
Thread overview: 58+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-11-08 6:58 Huan Yang
2023-11-08 6:58 ` [PATCH 1/4] mm: vmscan: LRU unbalance cgroup reclaim Huan Yang
2023-11-08 6:58 ` [PATCH 2/4] mm: multi-gen LRU: MGLRU unbalance reclaim Huan Yang
2023-11-08 12:34 ` kernel test robot
2023-11-09 11:08 ` kernel test robot
2023-12-04 6:53 ` Dan Carpenter
2023-11-08 6:58 ` [PATCH 3/4] mm: memcg: implement unbalance proactive reclaim Huan Yang
2023-11-08 6:58 ` [PATCH 4/4] mm: memcg: apply proactive reclaim into cgroupv1 Huan Yang
2023-11-08 21:06 ` kernel test robot
2023-11-08 7:35 ` [RFC 0/4] Introduce unbalance proactive reclaim Huang, Ying
2023-11-08 7:53 ` Huan Yang
2023-11-08 8:09 ` Huang, Ying
2023-11-08 8:14 ` Yosry Ahmed
2023-11-08 8:21 ` Huan Yang
2023-11-08 9:00 ` Yosry Ahmed
2023-11-08 9:05 ` Huan Yang
2023-11-08 8:00 ` Yosry Ahmed
2023-11-08 8:26 ` Huan Yang
2023-11-08 8:59 ` Yosry Ahmed
2023-11-08 9:12 ` Huan Yang
2023-11-08 14:06 ` Michal Hocko
2023-11-09 1:56 ` Huan Yang
2023-11-09 3:15 ` Huang, Ying
2023-11-09 3:38 ` Huan Yang
2023-11-09 9:57 ` Michal Hocko
2023-11-09 10:29 ` Huan Yang
2023-11-09 10:39 ` Michal Hocko
2023-11-09 10:50 ` Huan Yang
2023-11-09 12:40 ` Michal Hocko
2023-11-09 13:07 ` Huan Yang
2023-11-09 13:46 ` Michal Hocko
2023-11-10 3:48 ` Huan Yang
2023-11-10 12:24 ` Michal Hocko
2023-11-13 2:17 ` Huan Yang
2023-11-13 6:10 ` Huang, Ying
2023-11-13 6:28 ` Huan Yang
2023-11-13 8:05 ` Huang, Ying
2023-11-13 8:26 ` Huan Yang
2023-11-14 9:54 ` Michal Hocko
2023-11-14 9:56 ` Michal Hocko
2023-11-15 6:52 ` Huang, Ying
2023-11-14 9:50 ` Michal Hocko
2023-11-10 1:19 ` Huang, Ying
2023-11-10 2:44 ` Huan Yang
2023-11-10 4:00 ` Huang, Ying
2023-11-10 6:21 ` Huan Yang
2023-11-10 12:32 ` Michal Hocko [this message]
2023-11-13 1:54 ` Huan Yang
2023-11-14 10:04 ` Michal Hocko
2023-11-14 12:37 ` Huan Yang
2023-11-14 13:03 ` Michal Hocko
2023-11-15 2:11 ` Huan Yang
2023-11-09 9:53 ` Michal Hocko
2023-11-09 10:55 ` Huan Yang
2023-11-09 12:45 ` Michal Hocko
2023-11-09 13:10 ` Huan Yang
2023-11-08 16:14 ` Andrew Morton
2023-11-09 1:58 ` Huan 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=ZU4i36tKnyXZ8lZD@tiehlicka \
--to=mhocko@suse.com \
--cc=akpm@linux-foundation.org \
--cc=cgroups@vger.kernel.org \
--cc=corbet@lwn.net \
--cc=david@redhat.com \
--cc=hannes@cmpxchg.org \
--cc=hughd@google.com \
--cc=link@vivo.com \
--cc=linux-doc@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=liushixin2@huawei.com \
--cc=lizefan.x@bytedance.com \
--cc=muchun.song@linux.dev \
--cc=opensource.kernel@vivo.com \
--cc=peterx@redhat.com \
--cc=roman.gushchin@linux.dev \
--cc=shakeelb@google.com \
--cc=tj@kernel.org \
--cc=vishal.moola@gmail.com \
--cc=wangkefeng.wang@huawei.com \
--cc=willy@infradead.org \
--cc=ying.huang@intel.com \
--cc=yosryahmed@google.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