From: Gregory Price <gourry@gourry.net>
To: Tal Zussman <tz2294@columbia.edu>
Cc: Matthew Wilcox <willy@infradead.org>,
Axel Rasmussen <axelrasmussen@google.com>,
"Lorenzo Stoakes (Oracle)" <ljs@kernel.org>,
Michal Hocko <mhocko@suse.com>,
Andrew Morton <akpm@linux-foundation.org>,
Shakeel Butt <shakeel.butt@linux.dev>,
lsf-pc@lists.linux-foundation.org,
Johannes Weiner <hannes@cmpxchg.org>,
David Hildenbrand <david@kernel.org>,
Qi Zheng <zhengqi.arch@bytedance.com>,
Chen Ridong <chenridong@huaweicloud.com>,
Emil Tsalapatis <emil@etsalapatis.com>,
Alexei Starovoitov <ast@kernel.org>,
Yuanchu Xie <yuanchu@google.com>, Wei Xu <weixugc@google.com>,
Kairui Song <ryncsn@gmail.com>, Nhat Pham <nphamcs@gmail.com>,
Barry Song <21cnbao@gmail.com>,
David Stevens <stevensd@google.com>,
Vernon Yang <vernon2gm@gmail.com>,
David Rientjes <rientjes@google.com>,
Kalesh Singh <kaleshsingh@google.com>,
wangzicheng <wangzicheng@honor.com>,
"T . J . Mercier" <tjmercier@google.com>,
Baolin Wang <baolin.wang@linux.alibaba.com>,
Suren Baghdasaryan <surenb@google.com>,
Meta kernel team <kernel-team@meta.com>,
bpf@vger.kernel.org, linux-mm@kvack.org,
linux-kernel@vger.kernel.org
Subject: Re: [LSF/MM/BPF TOPIC] Towards Unified and Extensible Memory Reclaim (reclaim_ext)
Date: Fri, 27 Mar 2026 14:43:34 -0500 [thread overview]
Message-ID: <acbd5lKEh8xa1IQk@gourry-fedora-PF4VCD3F> (raw)
In-Reply-To: <6f40c513-af3e-45b6-9000-c61494a23bd3@columbia.edu>
On Fri, Mar 27, 2026 at 03:12:16PM -0400, Tal Zussman wrote:
>
> It's been well-known in the academic realm for a while that there isn't
> really a "one-size-fits-all" policy that works *best* for all workloads.
> Yes, you can make a general policy that works *well*, but if you really care
> about a workload's performance and want to squeeze out the last 10-20% (or
> more) of performance, you need to be able to (1) experiment and (2) take
> advantage of application-level insights. Being able to extend reclaim (in
> our case with eBPF) enables that.
>
This just makes me think going all the way to reclaim_ext and re-writing
MGLRU as an eBPF extension in an effort to simplify the code/maintenance
and keep what works working is the least-worst option.
But this is a naive take, i'm sure making that interface stable would be
even worse than just maintaining both LRU/MGLRU.
~Gregory
next prev parent reply other threads:[~2026-03-27 19:43 UTC|newest]
Thread overview: 41+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-03-25 21:06 Shakeel Butt
2026-03-26 0:10 ` T.J. Mercier
2026-03-26 2:05 ` Andrew Morton
2026-03-26 7:03 ` Michal Hocko
2026-03-26 8:02 ` Lorenzo Stoakes (Oracle)
2026-03-26 12:37 ` Kairui Song
2026-03-26 13:13 ` Lorenzo Stoakes (Oracle)
2026-03-26 13:42 ` David Hildenbrand (Arm)
2026-03-26 13:45 ` Lorenzo Stoakes (Oracle)
2026-03-26 16:02 ` Lorenzo Stoakes (Oracle)
2026-03-26 20:02 ` Axel Rasmussen
2026-03-26 20:30 ` Gregory Price
2026-03-26 20:47 ` Axel Rasmussen
2026-03-27 3:43 ` Matthew Wilcox
2026-03-27 19:12 ` Tal Zussman
2026-03-27 19:43 ` Gregory Price [this message]
2026-03-27 8:07 ` [Lsf-pc] " Vlastimil Babka
2026-03-27 9:29 ` Lorenzo Stoakes (Oracle)
2026-03-26 12:06 ` Kairui Song
2026-03-26 12:31 ` Lorenzo Stoakes (Oracle)
2026-03-26 13:17 ` Kairui Song
2026-03-26 13:26 ` Lorenzo Stoakes (Oracle)
2026-03-26 13:21 ` Shakeel Butt
2026-03-26 7:12 ` Michal Hocko
2026-03-26 13:44 ` Shakeel Butt
2026-03-26 15:24 ` Michal Hocko
2026-03-26 18:21 ` Shakeel Butt
2026-03-26 7:18 ` wangzicheng
2026-03-26 11:43 ` Lorenzo Stoakes (Oracle)
2026-03-26 15:24 ` Gregory Price
2026-03-26 15:35 ` Lorenzo Stoakes (Oracle)
2026-03-26 16:32 ` Gregory Price
2026-03-26 16:40 ` Lorenzo Stoakes (Oracle)
2026-03-27 19:53 ` Johannes Weiner
2026-04-07 11:36 ` Lorenzo Stoakes
2026-04-07 16:56 ` Gregory Price
2026-04-07 17:30 ` Lorenzo Stoakes
2026-04-07 17:52 ` Johannes Weiner
2026-04-07 18:37 ` Gregory Price
2026-04-08 6:48 ` Lorenzo Stoakes
2026-03-26 18:49 ` Shakeel Butt
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=acbd5lKEh8xa1IQk@gourry-fedora-PF4VCD3F \
--to=gourry@gourry.net \
--cc=21cnbao@gmail.com \
--cc=akpm@linux-foundation.org \
--cc=ast@kernel.org \
--cc=axelrasmussen@google.com \
--cc=baolin.wang@linux.alibaba.com \
--cc=bpf@vger.kernel.org \
--cc=chenridong@huaweicloud.com \
--cc=david@kernel.org \
--cc=emil@etsalapatis.com \
--cc=hannes@cmpxchg.org \
--cc=kaleshsingh@google.com \
--cc=kernel-team@meta.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=ljs@kernel.org \
--cc=lsf-pc@lists.linux-foundation.org \
--cc=mhocko@suse.com \
--cc=nphamcs@gmail.com \
--cc=rientjes@google.com \
--cc=ryncsn@gmail.com \
--cc=shakeel.butt@linux.dev \
--cc=stevensd@google.com \
--cc=surenb@google.com \
--cc=tjmercier@google.com \
--cc=tz2294@columbia.edu \
--cc=vernon2gm@gmail.com \
--cc=wangzicheng@honor.com \
--cc=weixugc@google.com \
--cc=willy@infradead.org \
--cc=yuanchu@google.com \
--cc=zhengqi.arch@bytedance.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