From: Andreas Dilger <adilger@clusterfs.com>
To: Christoph Hellwig <hch@infradead.org>,
marcelo@connectiva.com.br, trond.myklebust@fys.uio.no,
linux-kernel@vger.kernel.org
Subject: Re: ->direct_IO API change in current 2.4 BK
Date: Wed, 9 Jul 2003 10:03:36 -0700 [thread overview]
Message-ID: <20030709100336.H4482@schatzie.adilger.int> (raw)
In-Reply-To: <20030709133109.A23587@infradead.org>; from hch@infradead.org on Wed, Jul 09, 2003 at 01:31:09PM +0100
On Jul 09, 2003 13:31 +0100, Christoph Hellwig wrote:
> I just got a nice XFS oops due to the direct_IO API change in
> 2.4. Guys, this is a STABLE series and APIs are supposed to be exactly
> that, _STABLE_. If you really think O_DIRECT on NFS is soo important
> please add a ->direct_IO2 for NFS like the reiserfs read_inode2 hack.
I would have to agree with that sentiment - we shouldn't change the
API in an "almost compatible" way, although I would have hoped that
compile warnings and/or module symbol versioning would have avoided
a crash.
> But what's the use of it anyway? AFAIK it's mostly for whoracle setups
> that have their data on netapps but that needs a certified vendor kernel
> not mainline..
Actually, it is useful for Lustre to do this, because it allows us to have
a file handle (which, naturally, holds per-file data) at the time the IO is
sent over the wire, instead of the "anonymous" writes that happen now.
This helps us with readahead on the server and other minor improvements.
Cheers, Andreas
--
Andreas Dilger
http://sourceforge.net/projects/ext2resize/
http://www-mddsp.enel.ucalgary.ca/People/adilger/
next prev parent reply other threads:[~2003-07-09 16:50 UTC|newest]
Thread overview: 27+ messages / expand[flat|nested] mbox.gz Atom feed top
2003-07-09 12:31 Christoph Hellwig
2003-07-09 17:03 ` Andreas Dilger [this message]
2003-07-09 17:24 ` Marcelo Tosatti
2003-07-09 17:43 ` Marc-Christian Petersen
2003-07-09 17:46 ` Marcelo Tosatti
2003-07-09 17:55 ` Marc-Christian Petersen
2003-07-09 18:08 ` Marcelo Tosatti
2003-07-09 18:22 ` Marc-Christian Petersen
2003-07-09 19:13 ` Marcelo Tosatti
2003-07-09 19:45 ` Marc-Christian Petersen
2003-07-09 23:43 ` Alan Cox
2003-07-10 0:21 ` Jeff Garzik
2003-07-09 18:33 ` Trond Myklebust
2003-07-09 18:41 ` Marc-Christian Petersen
2003-07-09 18:50 ` Trond Myklebust
2003-07-09 18:55 ` Marc-Christian Petersen
2003-07-09 19:05 ` Jeff Garzik
2003-07-09 19:08 ` Trond Myklebust
2003-07-09 19:17 ` Jeff Garzik
2003-07-09 19:51 ` Trond Myklebust
2003-07-09 21:43 ` Jeff Garzik
2003-07-09 23:42 ` Alan Cox
2003-07-10 0:23 ` Jeff Garzik
2003-07-09 23:40 ` Alan Cox
2003-07-09 18:29 ` Trond Myklebust
2003-07-09 18:51 ` Andreas Dilger
2003-07-09 19:18 ` Jeff Garzik
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=20030709100336.H4482@schatzie.adilger.int \
--to=adilger@clusterfs.com \
--cc=hch@infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=marcelo@connectiva.com.br \
--cc=trond.myklebust@fys.uio.no \
/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®