linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Gregory Price <gourry@gourry.net>
To: Byungchul Park <byungchul@sk.com>
Cc: Matthew Wilcox <willy@infradead.org>,
	Hyeonggon Yoo <42.hyeyoo@gmail.com>,
	lsf-pc@lists.linux-foundation.org, linux-mm@kvack.org,
	linux-cxl@vger.kernel.org, Honggyu Kim <honggyu.kim@sk.com>,
	kernel_team@skhynix.com
Subject: Re: [LSF/MM/BPF TOPIC] Restricting or migrating unmovable kernel allocations from slow tier
Date: Fri, 7 Feb 2025 04:27:35 -0500	[thread overview]
Message-ID: <Z6XSB3RcRpUWTcOg@gourry-fedora-PF4VCD3F> (raw)
In-Reply-To: <Z6XLCeU0vjIOYGKe@gourry-fedora-PF4VCD3F>

On Fri, Feb 07, 2025 at 03:57:45AM -0500, Gregory Price wrote:
> On Fri, Feb 07, 2025 at 04:20:24PM +0900, Byungchul Park wrote:
> 
> My thoughts here are that memory tiering is the wrong tool for the
> problem you are trying to solve.
> 
> Maybe there's a world in which we propose a ZONE_MEMDESC which is
> exclusively used for `struct page` for a node. 
> 
> At least then you could design CXL capacities *around* that.
>

Dumb question time

Is this maybe not an entirely horrible idea?  Even at 16-byte page
structs we use 4GB-per-1TB of capacity.

Maybe a memory device providing additional capacity SHOULD be made
(given the option?) to service its own struct pages - but maintain
some control over hot-plug-ability?

At least it could tear down all the ZONE_MOVABLE regions and finally
release the MEMDESC region when finished.

Seems too obvious to have not been proposed already. :shrug:

~Gregory


  reply	other threads:[~2025-02-07  9:27 UTC|newest]

Thread overview: 27+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-02-01 13:29 Hyeonggon Yoo
2025-02-01 14:04 ` Matthew Wilcox
2025-02-01 15:13   ` Hyeonggon Yoo
2025-02-01 16:30     ` Gregory Price
2025-02-01 18:48       ` Matthew Wilcox
2025-02-03 22:09       ` Dan Williams
2025-02-07  7:20   ` Byungchul Park
2025-02-07  8:57     ` Gregory Price
2025-02-07  9:27       ` Gregory Price [this message]
2025-02-07  9:34       ` Honggyu Kim
2025-02-07  9:54         ` Gregory Price
2025-02-07 10:49           ` Byungchul Park
2025-02-10  2:33           ` Harry (Hyeonggon) Yoo
2025-02-10  3:19             ` Matthew Wilcox
2025-02-10  6:00             ` Gregory Price
2025-02-10  7:17               ` Byungchul Park
2025-02-10 15:47                 ` Gregory Price
2025-02-10 15:55                   ` Matthew Wilcox
2025-02-10 16:06                     ` Gregory Price
2025-02-11  1:53                   ` Byungchul Park
2025-02-21  1:52                   ` Harry Yoo
2025-02-25  4:54                     ` [LSF/MM/BPF TOPIC] Gathering ideas to reduce ZONE_NORMAL cost Byungchul Park
2025-02-25  5:06                   ` [LSF/MM/BPF TOPIC] Restricting or migrating unmovable kernel allocations from slow tier Byungchul Park
2025-03-03 15:55                     ` Gregory Price
2025-02-07 10:14       ` Byungchul Park
2025-02-10  7:02       ` Byungchul Park
2025-02-04  9:59 ` David Hildenbrand

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=Z6XSB3RcRpUWTcOg@gourry-fedora-PF4VCD3F \
    --to=gourry@gourry.net \
    --cc=42.hyeyoo@gmail.com \
    --cc=byungchul@sk.com \
    --cc=honggyu.kim@sk.com \
    --cc=kernel_team@skhynix.com \
    --cc=linux-cxl@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=lsf-pc@lists.linux-foundation.org \
    --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