From: David Chinner <dgc@sgi.com>
To: Miklos Szeredi <miklos@szeredi.hu>
Cc: akpm@linux-foundation.org, linux-kernel@vger.kernel.org,
linux-fsdevel@vger.kernel.org
Subject: Re: [patch 3/8] per backing_dev dirty and writeback page accounting
Date: Mon, 12 Mar 2007 17:23:49 +1100 [thread overview]
Message-ID: <20070312062349.GN6095633@melbourne.sgi.com> (raw)
In-Reply-To: <20070306180550.793803735@szeredi.hu>
On Tue, Mar 06, 2007 at 07:04:46PM +0100, Miklos Szeredi wrote:
> From: Andrew Morton <akpm@osdl.org>
>
> [tomoki.sekiyama.qu@hitachi.com: bugfix]
>
> Miklos Szeredi <mszeredi@suse.cz>:
>
> Changes:
> - updated to apply after clear_page_dirty_for_io() race fix
>
> This is needed for
>
> - balance_dirty_pages() deadlock fix
> - fuse dirty page accounting
>
> I have no idea how serious the scalability problems with this are. If
> they are serious, different solutions can probably be found for the
> above, but this is certainly the simplest.
Atomic operations to a single per-backing device from all CPUs at once?
That's a pretty serious scalability issue and it will cause a major
performance regression for XFS.
I'd call this a showstopper right now - maybe you need to look at
something like the ZVC code that Christoph Lameter wrote, perhaps?
Cheers,
Dave.
--
Dave Chinner
Principal Engineer
SGI Australian Software Group
next prev parent reply other threads:[~2007-03-12 6:24 UTC|newest]
Thread overview: 28+ messages / expand[flat|nested] mbox.gz Atom feed top
2007-03-06 18:04 [patch 0/8] VFS/VM patches Miklos Szeredi
2007-03-06 18:04 ` [patch 1/8] fix race in clear_page_dirty_for_io() Miklos Szeredi
2007-03-06 22:25 ` Andrew Morton
2007-03-06 18:04 ` [patch 2/8] update ctime and mtime for mmaped write Miklos Szeredi
2007-03-06 20:32 ` Peter Zijlstra
2007-03-06 21:24 ` Miklos Szeredi
2007-03-06 21:47 ` Peter Zijlstra
2007-03-06 22:00 ` Miklos Szeredi
2007-03-06 22:07 ` Peter Zijlstra
2007-03-06 22:18 ` Miklos Szeredi
2007-03-06 22:28 ` Peter Zijlstra
2007-03-06 22:36 ` Miklos Szeredi
2007-03-06 18:04 ` [patch 3/8] per backing_dev dirty and writeback page accounting Miklos Szeredi
2007-03-12 6:23 ` David Chinner [this message]
2007-03-12 11:40 ` Miklos Szeredi
2007-03-12 21:44 ` David Chinner
2007-03-12 22:36 ` Miklos Szeredi
2007-03-12 23:12 ` David Chinner
2007-03-13 8:21 ` Miklos Szeredi
2007-03-13 22:12 ` David Chinner
2007-03-14 22:09 ` Miklos Szeredi
2007-03-06 18:04 ` [patch 4/8] fix deadlock in balance_dirty_pages Miklos Szeredi
2007-03-06 18:04 ` [patch 5/8] fix deadlock in throttle_vm_writeout Miklos Szeredi
2007-03-06 18:04 ` [patch 6/8] balance dirty pages from loop device Miklos Szeredi
2007-03-06 18:04 ` [patch 7/8] add filesystem subtype support Miklos Szeredi
2007-03-06 18:04 ` [patch 8/8] consolidate generic_writepages and mpage_writepages fix Miklos Szeredi
2007-03-07 20:46 ` Andrew Morton
2007-03-07 21:26 ` Miklos Szeredi
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=20070312062349.GN6095633@melbourne.sgi.com \
--to=dgc@sgi.com \
--cc=akpm@linux-foundation.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=miklos@szeredi.hu \
/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;
as well as URLs for NNTP newsgroup(s).