From: Pekka Enberg <penberg@cs.helsinki.fi>
To: Zach Brown <zab@zabbo.net>
Cc: David Teigland <teigland@redhat.com>,
Pekka Enberg <penberg@gmail.com>,
akpm@osdl.org, linux-kernel@vger.kernel.org,
linux-cluster@redhat.com, mark.fasheh@oracle.com
Subject: Re: GFS
Date: Tue, 09 Aug 2005 17:49:43 +0300 [thread overview]
Message-ID: <1123598983.10790.1.camel@haji.ri.fi> (raw)
In-Reply-To: <42F7A557.3000200@zabbo.net>
On Mon, 2005-08-08 at 11:32 -0700, Zach Brown wrote:
> > Sorry if this is an obvious question but what prevents another thread
> > from doing mmap() before we do the second walk and messing up num_gh?
>
> Nothing, I suspect. OCFS2 has a problem like this, too. It wants a way
> for a file system to serialize mmap/munmap/mremap during file IO. Well,
> more specifically, it wants to make sure that the locks it acquired at
> the start of the IO really cover the buf regions that might fault during
> the IO.. mapping activity during the IO can wreck that.
In addition, the vma walk will become an unmaintainable mess as soon as
someone introduces another mmap() capable fs that needs similar locking.
I am not an expert so could someone please explain why this cannot be
done with a_ops->prepare_write and friends?
Pekka
next prev parent reply other threads:[~2005-08-09 14:59 UTC|newest]
Thread overview: 84+ messages / expand[flat|nested] mbox.gz Atom feed top
2005-08-02 7:18 [PATCH 00/14] GFS David Teigland
2005-08-02 7:45 ` Arjan van de Ven
2005-08-02 14:57 ` Jan Engelhardt
2005-08-02 15:02 ` Arjan van de Ven
2005-08-03 1:00 ` Hans Reiser
2005-08-03 4:07 ` Kyle Moffett
2005-08-03 6:37 ` Jan Engelhardt
2005-08-03 9:09 ` Arjan van de Ven
2005-08-03 3:56 ` David Teigland
2005-08-03 9:17 ` Arjan van de Ven
2005-08-03 10:08 ` David Teigland
2005-08-03 10:37 ` Lars Marowsky-Bree
2005-08-03 18:54 ` Mark Fasheh
2005-08-05 7:14 ` David Teigland
2005-08-05 7:27 ` [Linux-cluster] " Mike Christie
2005-08-05 7:30 ` Mike Christie
2005-08-05 7:34 ` Arjan van de Ven
2005-08-05 9:44 ` David Teigland
2005-08-05 10:07 ` Jörn Engel
2005-08-05 10:31 ` David Teigland
2005-08-05 8:28 ` Jan Engelhardt
2005-08-05 8:34 ` Arjan van de Ven
2005-08-08 6:26 ` David Teigland
2005-08-11 6:06 ` David Teigland
2005-08-11 6:55 ` Arjan van de Ven
2005-08-02 10:16 ` Pekka Enberg
2005-08-03 6:36 ` David Teigland
2005-08-08 14:14 ` GFS Pekka J Enberg
2005-08-08 18:32 ` GFS Zach Brown
2005-08-09 14:49 ` Pekka Enberg [this message]
2005-08-09 17:17 ` GFS Zach Brown
2005-08-09 18:35 ` GFS Pekka J Enberg
2005-08-10 4:48 ` GFS Pekka J Enberg
2005-08-10 7:21 ` GFS Christoph Hellwig
2005-08-10 7:31 ` GFS Pekka J Enberg
2005-08-10 16:26 ` GFS Mark Fasheh
2005-08-10 16:57 ` GFS Pekka J Enberg
2005-08-10 18:21 ` GFS Mark Fasheh
2005-08-10 20:18 ` GFS Pekka J Enberg
2005-08-10 22:07 ` GFS Mark Fasheh
2005-08-11 4:41 ` GFS Pekka J Enberg
2005-08-10 5:59 ` GFS David Teigland
2005-08-10 6:06 ` GFS Pekka J Enberg
2005-08-03 6:44 ` [PATCH 00/14] GFS Pekka Enberg
2005-08-08 9:57 ` David Teigland
2005-08-08 10:00 ` GFS Pekka J Enberg
2005-08-08 10:05 ` [PATCH 00/14] GFS Arjan van de Ven
2005-08-08 10:20 ` Jörn Engel
2005-08-08 10:18 ` GFS Pekka J Enberg
2005-08-08 10:56 ` GFS David Teigland
2005-08-08 10:57 ` GFS Pekka J Enberg
2005-08-08 11:39 ` GFS David Teigland
2005-08-08 10:34 ` GFS Pekka J Enberg
2005-08-09 14:55 ` GFS Pekka J Enberg
2005-08-10 7:40 ` GFS Pekka J Enberg
2005-08-10 7:43 ` GFS Christoph Hellwig
2005-08-09 15:20 ` [PATCH 00/14] GFS Al Viro
2005-08-10 7:03 ` Christoph Hellwig
2005-08-10 10:30 ` Lars Marowsky-Bree
2005-08-10 10:32 ` Christoph Hellwig
2005-08-10 10:34 ` Lars Marowsky-Bree
2005-08-10 10:54 ` Christoph Hellwig
2005-08-10 11:02 ` Lars Marowsky-Bree
2005-08-10 11:05 ` Christoph Hellwig
2005-08-10 11:09 ` Lars Marowsky-Bree
2005-08-10 11:11 ` Christoph Hellwig
2005-08-10 13:26 ` [Linux-cluster] " AJ Lewis
2005-08-10 15:43 ` Kyle Moffett
2005-08-11 8:17 ` GFS - updated patches David Teigland
2005-08-11 8:21 ` [Linux-cluster] " Michael
2005-08-11 8:46 ` David Teigland
2005-08-11 8:49 ` Michael
2005-08-11 8:32 ` Arjan van de Ven
2005-08-11 8:50 ` David Teigland
2005-08-11 8:50 ` Arjan van de Ven
2005-08-11 9:16 ` David Teigland
2005-08-11 10:04 ` Pekka Enberg
2005-08-11 9:54 ` [Linux-cluster] " Michael
2005-08-11 10:00 ` Pekka Enberg
2005-08-11 7:10 GFS Pekka J Enberg
2005-08-11 16:33 ` GFS Zach Brown
2005-08-11 16:35 ` GFS Christoph Hellwig
2005-08-11 16:39 ` GFS Zach Brown
2005-08-11 16:44 ` GFS Pekka Enberg
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=1123598983.10790.1.camel@haji.ri.fi \
--to=penberg@cs.helsinki.fi \
--cc=akpm@osdl.org \
--cc=linux-cluster@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mark.fasheh@oracle.com \
--cc=penberg@gmail.com \
--cc=teigland@redhat.com \
--cc=zab@zabbo.net \
/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
all inboxes | Powered by JetHome®