From: Shakeel Butt <shakeel.butt@linux.dev>
To: Davidlohr Bueso <dave@stgolabs.net>
Cc: akpm@linux-foundation.org, mhocko@kernel.org, hannes@cmpxchg.org,
roman.gushchin@linux.dev, yosryahmed@google.com,
linux-mm@kvack.org, linux-kernel@vger.kernel.org
Subject: Re: [PATCH 4/4] mm: introduce per-node proactive reclaim interface
Date: Thu, 17 Jul 2025 15:28:16 -0700 [thread overview]
Message-ID: <6utnw5xyyjqo7o3bsn3s2vp5hfl7ujt4hiyluodhdw4mmzgr22@4vxkkw2kb57y> (raw)
In-Reply-To: <20250623185851.830632-5-dave@stgolabs.net>
On Mon, Jun 23, 2025 at 11:58:51AM -0700, Davidlohr Bueso wrote:
> This adds support for allowing proactive reclaim in general on a
> NUMA system. A per-node interface extends support for beyond a
> memcg-specific interface, respecting the current semantics of
> memory.reclaim: respecting aging LRU and not supporting
> artificially triggering eviction on nodes belonging to non-bottom
> tiers.
>
> This patch allows userspace to do:
>
> echo "512M swappiness=10" > /sys/devices/system/node/nodeX/reclaim
>
> One of the premises for this is to semantically align as best as
> possible with memory.reclaim. During a brief time memcg did
> support nodemask until 55ab834a86a9 (Revert "mm: add nodes=
> arg to memory.reclaim"), for which semantics around reclaim
> (eviction) vs demotion were not clear, rendering charging
> expectations to be broken.
>
> With this approach:
>
> 1. Users who do not use memcg can benefit from proactive reclaim.
> The memcg interface is not NUMA aware and there are usecases that
> are focusing on NUMA balancing rather than workload memory footprint.
>
> 2. Proactive reclaim on top tiers will trigger demotion, for which
> memory is still byte-addressable. Reclaiming on the bottom nodes
> will trigger evicting to swap (the traditional sense of reclaim).
> This follows the semantics of what is today part of the aging process
> on tiered memory, mirroring what every other form of reclaim does
> (reactive and memcg proactive reclaim). Furthermore per-node proactive
> reclaim is not as susceptible to the memcg charging problem mentioned
> above.
>
> 3. Unlike the nodes= arg, this interface avoids confusing semantics,
> such as what exactly the user wants when mixing top-tier and low-tier
> nodes in the nodemask. Further per-node interface is less exposed to
> "free up memory in my container" usecases, where eviction is intended.
>
> 4. Users that *really* want to free up memory can use proactive reclaim
> on nodes knowingly to be on the bottom tiers to force eviction in a
> natural way - higher access latencies are still better than swap.
> If compelled, while no guarantees and perhaps not worth the effort,
> users could also also potentially follow a ladder-like approach to
> eventually free up the memory. Alternatively, perhaps an 'evict' option
> could be added to the parameters for both memory.reclaim and per-node
> interfaces to force this action unconditionally.
>
> Signed-off-by: Davidlohr Bueso <dave@stgolabs.net>
After Roman's suggestion, you can add:
Acked-by: Shakeel Butt <shakeel.butt@linux.dev>
next prev parent reply other threads:[~2025-07-17 22:28 UTC|newest]
Thread overview: 28+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-06-23 18:58 [PATCH -next v2 0/4] mm: per-node proactive reclaim Davidlohr Bueso
2025-06-23 18:58 ` [PATCH 1/4] mm/vmscan: respect psi_memstall region in node reclaim Davidlohr Bueso
2025-06-25 17:08 ` Shakeel Butt
2025-07-17 1:44 ` Roman Gushchin
2025-06-23 18:58 ` [PATCH 2/4] mm/memcg: make memory.reclaim interface generic Davidlohr Bueso
2025-06-23 21:45 ` Andrew Morton
2025-06-23 23:36 ` Davidlohr Bueso
2025-06-24 18:26 ` Klara Modin
2025-07-17 1:58 ` Roman Gushchin
2025-07-17 16:35 ` Davidlohr Bueso
2025-07-17 22:17 ` Shakeel Butt
2025-07-17 22:52 ` Andrew Morton
2025-07-17 23:56 ` Davidlohr Bueso
2025-07-18 0:17 ` Shakeel Butt
2025-06-23 18:58 ` [PATCH 3/4] mm/vmscan: make __node_reclaim() more generic Davidlohr Bueso
2025-07-17 2:03 ` Roman Gushchin
2025-07-17 22:25 ` Shakeel Butt
2025-06-23 18:58 ` [PATCH 4/4] mm: introduce per-node proactive reclaim interface Davidlohr Bueso
2025-06-25 23:10 ` Shakeel Butt
2025-06-27 19:07 ` SeongJae Park
2025-07-17 2:46 ` Roman Gushchin
2025-07-17 16:26 ` Davidlohr Bueso
2025-07-17 22:46 ` Andrew Morton
[not found] ` <20250717064925.2304-1-hdanton@sina.com>
2025-07-17 7:39 ` Michal Hocko
2025-07-17 22:28 ` Shakeel Butt [this message]
2025-06-23 21:50 ` [PATCH -next v2 0/4] mm: per-node proactive reclaim Andrew Morton
2025-07-16 0:24 ` Andrew Morton
2025-07-16 15:15 ` 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=6utnw5xyyjqo7o3bsn3s2vp5hfl7ujt4hiyluodhdw4mmzgr22@4vxkkw2kb57y \
--to=shakeel.butt@linux.dev \
--cc=akpm@linux-foundation.org \
--cc=dave@stgolabs.net \
--cc=hannes@cmpxchg.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mhocko@kernel.org \
--cc=roman.gushchin@linux.dev \
--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