From: Christoph Lameter <clameter@sgi.com>
To: Mel Gorman <mel@skynet.ie>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>,
linux-mm@kvack.org, akpm@linux-foundation.org, riel@redhat.com,
balbir@linux.vnet.ibm.com, andrea@suse.de,
a.p.zijlstra@chello.nl, eric.whitney@hp.com, npiggin@suse.de
Subject: Re: [PATCH/RFC 6/14] Reclaim Scalability: "No Reclaim LRU Infrastructure"
Date: Tue, 18 Sep 2007 12:45:02 -0700 (PDT) [thread overview]
Message-ID: <Pine.LNX.4.64.0709181242240.3714@schroedinger.engr.sgi.com> (raw)
In-Reply-To: <20070918095443.GA2035@skynet.ie>
On Tue, 18 Sep 2007, Mel Gorman wrote:
> > Also the ramfs/shmem pages. There
> > may be uses though that require a page to stay put because it is used for
> > some nefarious I/O purpose by a driver. RDMA comes to mind.
>
> Yeah :/
>
> > Maybe we need
> > some additional option that works like MLOCK but forbids migration.
>
> The problem with RDMA that I recall is that we don't know at allocation
> time that they may be unmovable sometimes in the future. I didn't think
> of a way around that problem.
The current way that we have around the problem is to increase the page
count. With that all attempts to unmap the page by migration or otherwise
fail and the page stays put.
RDMA is probably only temporarily pinning these while I/O is in progress?.
Our applications (XPMEM)
may pins them for good.
> > Those
> > would then be unreclaimable and not __GFP_MOVABLE. I know some of our
> > applications create huge amount of these.
> >
>
> Can you think of a way that pages that will be later pinned by something
> like RDMA can be identified in advance?
No. Nor in our XPMEM situation. We could move them at the point when they
are pinned to another section?
--
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 prev parent reply other threads:[~2007-09-18 19:45 UTC|newest]
Thread overview: 77+ messages / expand[flat|nested] mbox.gz Atom feed top
2007-09-14 20:53 [PATCH/RFC 0/14] Page Reclaim Scalability Lee Schermerhorn
2007-09-14 20:54 ` [PATCH/RFC 1/14] Reclaim Scalability: Convert anon_vma lock to read/write lock Lee Schermerhorn
2007-09-17 11:02 ` Mel Gorman
2007-09-18 2:41 ` KAMEZAWA Hiroyuki
2007-09-18 11:01 ` Mel Gorman
2007-09-18 14:57 ` Rik van Riel
2007-09-18 15:37 ` Lee Schermerhorn
2007-09-18 20:17 ` Lee Schermerhorn
2007-09-20 10:19 ` Mel Gorman
2007-09-14 20:54 ` [PATCH/RFC 2/14] Reclaim Scalability: convert inode i_mmap_lock to reader/writer lock Lee Schermerhorn
2007-09-17 12:53 ` Mel Gorman
2007-09-20 1:24 ` Andrea Arcangeli
2007-09-20 14:10 ` Lee Schermerhorn
2007-09-20 14:16 ` Andrea Arcangeli
2007-09-14 20:54 ` [PATCH/RFC 3/14] Reclaim Scalability: move isolate_lru_page() to vmscan.c Lee Schermerhorn
2007-09-14 21:34 ` Peter Zijlstra
2007-09-15 1:55 ` Rik van Riel
2007-09-17 14:11 ` Lee Schermerhorn
2007-09-17 9:20 ` Balbir Singh
2007-09-17 19:19 ` Lee Schermerhorn
2007-09-14 20:54 ` [PATCH/RFC 4/14] Reclaim Scalability: Define page_anon() function Lee Schermerhorn
2007-09-15 2:00 ` Rik van Riel
2007-09-17 13:19 ` Mel Gorman
2007-09-18 1:58 ` KAMEZAWA Hiroyuki
2007-09-18 2:27 ` Rik van Riel
2007-09-18 2:40 ` KAMEZAWA Hiroyuki
2007-09-18 15:04 ` Lee Schermerhorn
2007-09-18 19:41 ` Christoph Lameter
2007-09-19 0:30 ` KAMEZAWA Hiroyuki
2007-09-19 16:58 ` Lee Schermerhorn
2007-09-20 0:56 ` KAMEZAWA Hiroyuki
2007-09-14 20:54 ` [PATCH/RFC 5/14] Reclaim Scalability: Use an indexed array for LRU variables Lee Schermerhorn
2007-09-17 13:40 ` Mel Gorman
2007-09-17 14:17 ` Lee Schermerhorn
2007-09-17 14:39 ` Lee Schermerhorn
2007-09-17 18:58 ` Balbir Singh
2007-09-17 19:12 ` Lee Schermerhorn
2007-09-17 19:36 ` Balbir Singh
2007-09-17 19:36 ` Rik van Riel
2007-09-17 20:21 ` Balbir Singh
2007-09-17 21:01 ` Rik van Riel
2007-09-14 20:54 ` [PATCH/RFC 6/14] Reclaim Scalability: "No Reclaim LRU Infrastructure" Lee Schermerhorn
2007-09-14 22:47 ` Christoph Lameter
2007-09-17 15:17 ` Lee Schermerhorn
2007-09-17 18:41 ` Christoph Lameter
2007-09-18 9:54 ` Mel Gorman
2007-09-18 19:45 ` Christoph Lameter [this message]
2007-09-19 11:11 ` Mel Gorman
2007-09-19 18:03 ` Christoph Lameter
2007-09-19 6:00 ` Balbir Singh
2007-09-19 14:47 ` Lee Schermerhorn
2007-09-14 20:54 ` [PATCH/RFC 7/14] Reclaim Scalability: Non-reclaimable page statistics Lee Schermerhorn
2007-09-17 1:56 ` Rik van Riel
2007-09-14 20:54 ` [PATCH/RFC 8/14] Reclaim Scalability: Ram Disk Pages are non-reclaimable Lee Schermerhorn
2007-09-17 1:57 ` Rik van Riel
2007-09-17 14:40 ` Lee Schermerhorn
2007-09-17 18:42 ` Christoph Lameter
2007-09-14 20:54 ` [PATCH/RFC 9/14] Reclaim Scalability: SHM_LOCKED pages are nonreclaimable Lee Schermerhorn
2007-09-17 2:18 ` Rik van Riel
2007-09-14 20:55 ` [PATCH/RFC 10/14] Reclaim Scalability: track anon_vma "related vmas" Lee Schermerhorn
2007-09-17 2:52 ` Rik van Riel
2007-09-17 15:52 ` Lee Schermerhorn
2007-09-14 20:55 ` [PATCH/RFC 11/14] Reclaim Scalability: swap backed pages are nonreclaimable when no swap space available Lee Schermerhorn
2007-09-17 2:53 ` Rik van Riel
2007-09-18 17:46 ` Lee Schermerhorn
2007-09-18 20:01 ` Rik van Riel
2007-09-19 14:55 ` Lee Schermerhorn
2007-09-18 2:59 ` KAMEZAWA Hiroyuki
2007-09-18 15:47 ` Lee Schermerhorn
2007-09-14 20:55 ` [PATCH/RFC 12/14] Reclaim Scalability: Non-reclaimable Mlock'ed pages Lee Schermerhorn
2007-09-14 20:55 ` [PATCH/RFC 13/14] Reclaim Scalability: Handle Mlock'ed pages during map/unmap and truncate Lee Schermerhorn
2007-09-14 20:55 ` [PATCH/RFC 14/14] Reclaim Scalability: cull non-reclaimable anon pages in fault path Lee Schermerhorn
2007-09-14 21:11 ` [PATCH/RFC 0/14] Page Reclaim Scalability Peter Zijlstra
2007-09-14 21:42 ` Linus Torvalds
2007-09-14 22:02 ` Peter Zijlstra
2007-09-15 0:07 ` Linus Torvalds
2007-09-17 6:44 ` Balbir Singh
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=Pine.LNX.4.64.0709181242240.3714@schroedinger.engr.sgi.com \
--to=clameter@sgi.com \
--cc=Lee.Schermerhorn@hp.com \
--cc=a.p.zijlstra@chello.nl \
--cc=akpm@linux-foundation.org \
--cc=andrea@suse.de \
--cc=balbir@linux.vnet.ibm.com \
--cc=eric.whitney@hp.com \
--cc=linux-mm@kvack.org \
--cc=mel@skynet.ie \
--cc=npiggin@suse.de \
--cc=riel@redhat.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