From: Peter Zijlstra <peterz@infradead.org>
To: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Andrew Morton <akpm@linux-foundation.org>,
David Howells <dhowells@redhat.com>,
torvalds@linux-foundation.org, Enrik.Berkhan@ge.com,
uclinux-dev@uclinux.org, linux-kernel@vger.kernel.org
Subject: Re: [PATCH] NOMMU: Pages allocated to a ramfs inode's pagecache may get wrongly discarded
Date: Fri, 13 Mar 2009 08:57:16 +0100 [thread overview]
Message-ID: <1236931036.5188.80.camel@laptop> (raw)
In-Reply-To: <20090313105618.43DF.A69D9226@jp.fujitsu.com>
On Fri, 2009-03-13 at 11:03 +0900, KOSAKI Motohiro wrote:
> Hi
>
> > > Which as Peter points out:
> > >
> > > The ramfs stuff is rather icky in that it adds the pages to the aging
> > > list, marks them dirty, but does not provide a writeout method.
> > >
> > > This will make the paging code scan over them (continuously) trying to
> > > clean them, failing that (lack of writeout method) and putting them back
> > > on the list.
> > >
> > > Not requiring the pages to be added to the LRU would be a really good idea.
> > > They are not discardable, be it in MMU or NOMMU mode, except when the inode
> > > itself is discarded.
> >
> > Yep, these pages shouldn't be on the LRU at all. I guess that will
> > require some tweaks to core filemap.c code.
>
> IMHO, UNEVICTABLE_LRU already does lru isolation.
> only rest prblem is, getting rid of "depends on MMU" line in mm/Kconfig.
>
> Am I missing anything?
Yes, the need to take something off that shouldn't be there to begin
with.
next prev parent reply other threads:[~2009-03-13 7:58 UTC|newest]
Thread overview: 101+ messages / expand[flat|nested] mbox.gz Atom feed top
2009-03-11 15:30 [PATCH] NOMMU: Pages allocated to a ramfs inode's pagecache may get wrongly discarded David Howells
2009-03-11 17:26 ` Johannes Weiner
2009-03-11 22:03 ` Andrew Morton
2009-03-11 22:03 ` Andrew Morton
2009-03-11 22:36 ` Johannes Weiner
2009-03-11 22:36 ` Johannes Weiner
2009-03-12 0:02 ` Andrew Morton
2009-03-12 0:02 ` Andrew Morton
2009-03-12 0:35 ` Minchan Kim
2009-03-12 0:35 ` Minchan Kim
2009-03-12 1:04 ` KOSAKI Motohiro
2009-03-12 1:04 ` KOSAKI Motohiro
2009-03-12 1:52 ` Minchan Kim
2009-03-12 1:52 ` Minchan Kim
2009-03-12 1:56 ` Minchan Kim
2009-03-12 1:56 ` Minchan Kim
2009-03-12 2:00 ` KOSAKI Motohiro
2009-03-12 2:00 ` KOSAKI Motohiro
2009-03-12 2:11 ` Minchan Kim
2009-03-12 2:11 ` Minchan Kim
2009-03-12 12:19 ` Robin Getz
2009-03-12 12:19 ` Robin Getz
2009-03-12 17:55 ` [uClinux-dev] " Jamie Lokier
2009-03-12 17:55 ` Jamie Lokier
2009-03-13 11:53 ` David Howells
2009-03-13 11:53 ` David Howells
2009-03-13 22:49 ` Johannes Weiner
2009-03-13 22:49 ` Johannes Weiner
2009-03-13 17:33 ` [PATCH 0/2] Make the Unevictable LRU available on NOMMU David Howells
2009-03-13 17:33 ` David Howells
2009-03-13 17:33 ` [PATCH 1/2] NOMMU: There is no mlock() for NOMMU, so don't provide the bits David Howells
2009-03-13 17:33 ` David Howells
2009-03-14 11:17 ` KOSAKI Motohiro
2009-03-14 11:17 ` KOSAKI Motohiro
2009-03-13 17:33 ` [PATCH 2/2] NOMMU: Make CONFIG_UNEVICTABLE_LRU available when CONFIG_MMU=n David Howells
2009-03-13 17:33 ` David Howells
2009-03-14 11:17 ` KOSAKI Motohiro
2009-03-14 11:17 ` KOSAKI Motohiro
2009-03-14 0:27 ` [PATCH 0/2] Make the Unevictable LRU available on NOMMU Minchan Kim
2009-03-14 0:27 ` Minchan Kim
2009-03-20 16:08 ` Lee Schermerhorn
2009-03-20 16:08 ` Lee Schermerhorn
2009-03-20 16:24 ` David Howells
2009-03-20 16:24 ` David Howells
2009-03-20 18:30 ` Lee Schermerhorn
2009-03-20 18:30 ` Lee Schermerhorn
2009-03-21 10:20 ` Johannes Weiner
2009-03-21 10:20 ` Johannes Weiner
2009-03-22 20:13 ` [patch 1/3] mm: decouple unevictable lru from mmu Johannes Weiner
2009-03-22 20:13 ` Johannes Weiner
2009-03-22 23:46 ` KOSAKI Motohiro
2009-03-22 23:46 ` KOSAKI Motohiro
2009-03-23 0:14 ` Johannes Weiner
2009-03-23 0:14 ` Johannes Weiner
2009-03-23 10:48 ` David Howells
2009-03-23 10:48 ` David Howells
2009-03-22 20:13 ` [patch 2/3] ramfs-nommu: use generic lru cache Johannes Weiner
2009-03-22 20:13 ` Johannes Weiner
2009-03-23 2:22 ` KOSAKI Motohiro
2009-03-23 2:22 ` KOSAKI Motohiro
2009-03-23 10:40 ` David Howells
2009-03-23 10:40 ` David Howells
2009-03-22 20:13 ` [patch 3/3] mm: keep pages from unevictable mappings off the LRU lists Johannes Weiner
2009-03-22 20:13 ` Johannes Weiner
2009-03-23 0:44 ` Minchan Kim
2009-03-23 0:44 ` Minchan Kim
2009-03-23 2:21 ` KOSAKI Motohiro
2009-03-23 2:21 ` KOSAKI Motohiro
2009-03-23 8:42 ` Johannes Weiner
2009-03-23 8:42 ` Johannes Weiner
2009-03-23 9:01 ` KOSAKI Motohiro
2009-03-23 9:01 ` KOSAKI Motohiro
2009-03-23 9:23 ` KOSAKI Motohiro
2009-03-23 9:23 ` KOSAKI Motohiro
2009-03-26 0:48 ` Johannes Weiner
2009-03-26 0:48 ` Johannes Weiner
2009-03-23 10:53 ` David Howells
2009-03-23 10:53 ` David Howells
2009-03-26 0:01 ` Johannes Weiner
2009-03-26 0:01 ` Johannes Weiner
2009-03-26 8:56 ` KOSAKI Motohiro
2009-03-26 8:56 ` KOSAKI Motohiro
2009-03-26 10:36 ` Johannes Weiner
2009-03-26 10:36 ` Johannes Weiner
2009-03-23 20:07 ` [PATCH 0/2] Make the Unevictable LRU available on NOMMU Lee Schermerhorn
2009-03-23 20:07 ` Lee Schermerhorn
2009-03-12 0:08 ` [PATCH] NOMMU: Pages allocated to a ramfs inode's pagecache may get wrongly discarded Andrew Morton
2009-03-12 7:12 ` Berkhan, Enrik (GE Infra, Oil & Gas)
2009-03-12 11:29 ` [uClinux-dev] " Jamie Lokier
2009-03-12 11:50 ` Peter Zijlstra
2009-03-12 23:20 ` Minchan Kim
2009-03-13 7:56 ` Peter Zijlstra
2009-03-13 9:17 ` Minchan Kim
2009-03-12 12:25 ` David Howells
2009-03-12 19:43 ` Andrew Morton
2009-03-13 2:03 ` KOSAKI Motohiro
2009-03-13 7:57 ` Peter Zijlstra [this message]
2009-03-13 8:15 ` KOSAKI Motohiro
2009-03-13 9:19 ` Minchan Kim
2009-03-13 10:44 ` Johannes Weiner
2009-03-14 14:29 ` KOSAKI Motohiro
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=1236931036.5188.80.camel@laptop \
--to=peterz@infradead.org \
--cc=Enrik.Berkhan@ge.com \
--cc=akpm@linux-foundation.org \
--cc=dhowells@redhat.com \
--cc=kosaki.motohiro@jp.fujitsu.com \
--cc=linux-kernel@vger.kernel.org \
--cc=torvalds@linux-foundation.org \
--cc=uclinux-dev@uclinux.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.