Linux-mm Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: Gregory Price <gourry@gourry.net>
To: Matthew Wilcox <willy@infradead.org>
Cc: "Ritesh Harjani (IBM)" <ritesh.list@gmail.com>,
	linux-fsdevel <linux-fsdevel@vger.kernel.org>,
	Amir Goldstein <amir73il@gmail.com>,
	Christian Brauner <brauner@kernel.org>, Jan Kara <jack@suse.cz>,
	lsf-pc <lsf-pc@lists.linux-foundation.org>,
	Bharata B Rao <bharata@amd.com>,
	Donet Tom <donettom@linux.ibm.com>,
	Aboorva Devarajan <aboorvad@linux.ibm.com>,
	linux-mm@kvack.org, Ojaswin Mujoo <ojaswin@linux.ibm.com>
Subject: Re: [LSF/MM/BPF BoF Session] Numa-Aware Placement for Page Cache Pages
Date: Sat, 2 May 2026 16:49:51 +0100	[thread overview]
Message-ID: <afYdH4Alu9QA18CO@gourry-fedora-PF4VCD3F> (raw)
In-Reply-To: <afYQz3YJdWB2R-1q@gourry-fedora-PF4VCD3F>

On Sat, May 02, 2026 at 03:57:19PM +0100, Gregory Price wrote:
> On Thu, Apr 30, 2026 at 02:15:19PM +0100, Matthew Wilcox wrote:
> 
> fd = open()
> buf = mmap(fd, ...)
> mbind(buf, device_node)
> /* fault file pages directly onto device memory */
>

maybe more explicitly, something like this

fcntl(fd, F_SET_FILE_NUMA_NODE, gpu_nid); /* pref node */
mbind(addr, size, MPOL_BIND, ..., MOVE_ALL); /* move existing */
madvise(addr, size, MADV_POPULATE_READ); /* fault the rest */


  reply	other threads:[~2026-05-02 15:49 UTC|newest]

Thread overview: 10+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-04-30 11:33 [LSF/MM/BPF BoF Session] Numa-Aware Placement for Page Cache Pages Ritesh Harjani (IBM)
2026-04-30 13:15 ` Matthew Wilcox
2026-04-30 14:43   ` Ritesh Harjani
2026-05-02 14:57   ` Gregory Price
2026-05-02 15:49     ` Gregory Price [this message]
2026-05-03 16:18       ` Ritesh Harjani
2026-05-03 23:48         ` Gregory Price
2026-05-02 23:00     ` Matthew Wilcox
2026-05-03 14:15       ` Gregory Price
2026-04-30 17:32 ` Gregory Price

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=afYdH4Alu9QA18CO@gourry-fedora-PF4VCD3F \
    --to=gourry@gourry.net \
    --cc=aboorvad@linux.ibm.com \
    --cc=amir73il@gmail.com \
    --cc=bharata@amd.com \
    --cc=brauner@kernel.org \
    --cc=donettom@linux.ibm.com \
    --cc=jack@suse.cz \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=lsf-pc@lists.linux-foundation.org \
    --cc=ojaswin@linux.ibm.com \
    --cc=ritesh.list@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