From: Ingo Molnar <mingo@elte.hu>
To: Nathan Scott <nathans@sgi.com>
Cc: Christoph Hellwig <hch@infradead.org>,
Steven Whitehouse <swhiteho@redhat.com>,
Linus Torvalds <torvalds@osdl.org>,
David Teigland <teigland@redhat.com>,
Patrick Caulfield <pcaulfie@redhat.com>,
Kevin Anderson <kanderso@redhat.com>,
Andrew Morton <akpm@osdl.org>,
linux-kernel@vger.kernel.org
Subject: Re: GFS2 and DLM
Date: Tue, 27 Jun 2006 10:51:24 +0200 [thread overview]
Message-ID: <20060627085124.GA1487@elte.hu> (raw)
In-Reply-To: <20060627184237.A1295371@wobbly.melbourne.sgi.com>
* Nathan Scott <nathans@sgi.com> wrote:
> > and since XFS makes use of KM_SLEEP in 130+ callsites, that means it
> > is in essence using GFP_NOFAIL massively!
>
> Their locations have been carefully audited and understood. The
> original issue here was IRIX being able to do a very good of
> preventing kernel memory allocation failures, which I suspect caused
> the original XFS guys to be fairly relaxed in their handling of memory
> allocation failures. Its caused us no end of pain with the Linux port,
> I assure you.
i know it's a hard problem, and i'm not suggesting at all that this is
easy to fix. Nevertheless there are 130 allocation callsites in XFS that
do implicit GFS_NOFAIL in essence, and 7 callsites in GFS2 that mention
__GFS_NOFAIL explicitly. Ext3 does __GFP_NOFAIL in its journalling code
too. Reiser too.
Ingo
next prev parent reply other threads:[~2006-06-27 8:56 UTC|newest]
Thread overview: 46+ messages / expand[flat|nested] mbox.gz Atom feed top
2006-06-20 12:17 GFS2 and DLM Steven Whitehouse
2006-06-20 12:32 ` Nick Piggin
2006-06-20 12:47 ` Steven Whitehouse
2006-06-20 14:04 ` Nick Piggin
2006-06-20 15:40 ` Steven Whitehouse
2006-06-20 19:55 ` Andrew Morton
2006-06-21 11:20 ` Steven Whitehouse
2006-06-23 14:45 ` Christoph Hellwig
2006-06-26 21:03 ` Ingo Molnar
2006-06-27 7:52 ` Christoph Hellwig
2006-06-20 12:33 ` Christoph Hellwig
2006-06-20 12:55 ` Steven Whitehouse
2006-06-20 15:55 ` Ingo Molnar
2006-06-23 14:49 ` Christoph Hellwig
2006-06-23 20:46 ` Andrew Morton
2006-06-26 20:03 ` Ingo Molnar
2006-06-26 20:12 ` Arjan van de Ven
2006-06-27 7:08 ` Ingo Molnar
2006-06-27 6:33 ` Ingo Molnar
2006-06-27 6:43 ` Arjan van de Ven
2006-06-27 7:07 ` Ingo Molnar
2006-06-27 7:06 ` Andrew Morton
2006-06-27 8:35 ` Ingo Molnar
2006-06-27 8:50 ` Andrew Morton
2006-06-27 9:04 ` Ingo Molnar
2006-06-27 9:23 ` Andrew Morton
2006-07-03 13:40 ` Steven Whitehouse
2006-06-27 8:16 ` Nathan Scott
2006-06-27 8:22 ` Ingo Molnar
2006-06-27 8:41 ` Pekka Enberg
2006-06-27 10:33 ` Ingo Molnar
2006-06-27 8:42 ` Nathan Scott
2006-06-27 8:51 ` Ingo Molnar [this message]
2006-06-23 14:54 ` Christoph Hellwig
2006-06-23 15:54 ` Steven Whitehouse
2006-06-23 15:54 ` Christoph Hellwig
2006-06-23 16:09 ` Steven Whitehouse
2006-06-23 14:55 ` Christoph Hellwig
2006-06-23 14:57 ` Christoph Hellwig
2006-06-23 15:26 ` Steven Whitehouse
2006-06-23 15:00 ` Christoph Hellwig
2006-06-23 16:29 ` Steven Whitehouse
2006-06-23 16:48 ` Christoph Hellwig
2006-06-26 20:58 ` Ingo Molnar
2006-06-27 7:50 ` Christoph Hellwig
2006-06-27 8:31 ` Ingo Molnar
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=20060627085124.GA1487@elte.hu \
--to=mingo@elte.hu \
--cc=akpm@osdl.org \
--cc=hch@infradead.org \
--cc=kanderso@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=nathans@sgi.com \
--cc=pcaulfie@redhat.com \
--cc=swhiteho@redhat.com \
--cc=teigland@redhat.com \
--cc=torvalds@osdl.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox