From: menage@google.com
To: linux-mm@kvack.org
Cc: akpm@osdl.org
Subject: [RFC][PATCH 0/1] Node-based reclaim/migration
Date: Tue, 28 Nov 2006 19:06:55 -0800 [thread overview]
Message-ID: <20061129030655.941148000@menage.corp.google.com> (raw)
--
We're trying to use NUMA node isolation as a form of job resource
control at Google, and the existing page migration APIs are all bound
to individual processes and so are a bit clunky to use when you just
want to affect all the pages on a given node.
How about an API to allow userspace to direct page migration (and page
reclaim) on a per-node basis? This patch provides such an API, based
around sysfs; a system call approach would certainly be possible too.
It sort of overlaps with memory hot-unplug, but is simpler since it's
not so bad if we miss a few pages.
Comments? Also, can anyone clarify whether I need any locking when
sacnning the pages in a pgdat? As far as I can see, even with memory
hotplug this number can only increase, not decrease.
Paul
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
next reply other threads:[~2006-11-29 3:06 UTC|newest]
Thread overview: 54+ messages / expand[flat|nested] mbox.gz Atom feed top
2006-11-29 3:06 menage [this message]
2006-11-29 3:06 ` [RFC][PATCH 1/1] Expose per-node reclaim and migration to userspace menage
2006-11-29 6:07 ` Nick Piggin
2006-11-29 21:57 ` Paul Menage
2006-11-30 4:13 ` Christoph Lameter
2006-11-30 4:18 ` Paul Menage
2006-11-30 7:38 ` Nick Piggin
2006-11-30 7:57 ` Paul Menage
2006-11-30 8:26 ` Nick Piggin
2006-11-30 8:39 ` Paul Menage
2006-11-30 8:55 ` Nick Piggin
2006-11-30 9:06 ` Paul Menage
2006-11-30 9:21 ` Nick Piggin
2006-11-30 9:45 ` Paul Menage
2006-11-30 10:15 ` Nick Piggin
2006-11-30 10:40 ` Paul Menage
2006-11-30 11:04 ` Nick Piggin
2006-11-30 11:23 ` Paul Menage
2006-11-30 11:35 ` Nick Piggin
2006-11-30 0:18 ` KAMEZAWA Hiroyuki
2006-11-30 0:25 ` Paul Menage
2006-11-30 0:38 ` KAMEZAWA Hiroyuki
2006-11-30 4:15 ` Christoph Lameter
2006-11-30 4:10 ` Christoph Lameter
2006-11-30 0:31 ` [RFC][PATCH 0/1] Node-based reclaim/migration KAMEZAWA Hiroyuki
2006-11-30 0:31 ` Paul Menage
2006-11-30 4:11 ` KAMEZAWA Hiroyuki
2006-11-30 4:17 ` Christoph Lameter
2006-11-30 10:45 ` Paul Menage
2006-11-30 11:12 ` KAMEZAWA Hiroyuki
2006-11-30 11:25 ` Paul Menage
2006-11-30 12:18 ` KAMEZAWA Hiroyuki
2006-11-30 18:28 ` Christoph Lameter
2006-11-30 18:35 ` Paul Menage
2006-11-30 18:39 ` Christoph Lameter
2006-11-30 19:09 ` Paul Menage
2006-11-30 19:42 ` Christoph Lameter
2006-11-30 19:53 ` Paul Menage
2006-11-30 20:00 ` Christoph Lameter
2006-11-30 20:07 ` Paul Menage
2006-11-30 20:15 ` Christoph Lameter
2006-11-30 21:33 ` Paul Menage
2006-11-30 23:41 ` Christoph Lameter
2006-11-30 23:48 ` Paul Menage
2006-12-01 2:23 ` Christoph Lameter
2006-12-01 19:32 ` Paul Menage
2006-12-01 19:56 ` Christoph Lameter
2006-12-01 2:44 ` KAMEZAWA Hiroyuki
2006-12-01 2:43 ` Christoph Lameter
2006-12-01 2:59 ` KAMEZAWA Hiroyuki
2006-12-01 2:44 ` Christoph Lameter
2006-12-01 3:10 ` KAMEZAWA Hiroyuki
2006-12-01 5:28 ` Christoph Lameter
2006-11-30 4:04 ` Christoph Lameter
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=20061129030655.941148000@menage.corp.google.com \
--to=menage@google.com \
--cc=akpm@osdl.org \
--cc=linux-mm@kvack.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