From: Dave Chinner <david@fromorbit.com>
To: Roman Kononov <roman@binarylife.net>
Cc: xfs@oss.sgi.com
Subject: Re: WARNING in xfs_lwr.c, xfs_write()
Date: Wed, 26 May 2010 17:06:20 +1000 [thread overview]
Message-ID: <20100526070620.GT2150@dastard> (raw)
In-Reply-To: <20100524143428.6f3a117c@abend.internal.xtremedata.com>
On Mon, May 24, 2010 at 02:34:28PM -0500, Roman Kononov wrote:
> On Sun, 23 May 2010 23:12:24 -0500 Stan Hoeppner
> <stan@hardwarefreak.com> wrote:
> > "The whole notion of "direct IO" is totally braindamaged. Just say no.
> ...
> > From: http://lkml.org/lkml/2007/1/10/235
>
> I definitely measure dramatic overall performance benefit using
> O_DIRECT carefully.
>
> In that thread, it is doubtful that madvise+mmap+msync allow
> asynchronous zero-copy reads and writes to/from already pinned by a
> device driver memory of data produced/consumed by that device, without
> cache pollution and with intelligent handling of disk errors. Am I
> wrong?
No, you are not wrong.
Remember, just because Linus asserts something it doesn't mean he is
right. Yes, he's right an awful lot of the time, but not always. In
this case, most people with experience in writing high performance
IO engines with tell your that mmap() and advisory interfaces are no
substitute for the fine grained control of IO issue that direct IO
provides you with.
And in the case of XFS, mmap serialiseѕ write page faults to
different areas of the same file, whereas direct IO allows
concurrent reads and writes to different regions of the same file.
That makes direct IO far more scalable than than any mmap interface
will ever be....
Cheers,
Dave.
--
Dave Chinner
david@fromorbit.com
_______________________________________________
xfs mailing list
xfs@oss.sgi.com
http://oss.sgi.com/mailman/listinfo/xfs
next prev parent reply other threads:[~2010-05-26 7:04 UTC|newest]
Thread overview: 23+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-05-23 5:20 WARNING in xfs_lwr.c, xfs_write() Roman Kononov
2010-05-23 10:18 ` Dave Chinner
2010-05-23 14:23 ` Roman Kononov
2010-05-24 1:19 ` Dave Chinner
2010-06-12 5:00 ` Ilia Mirkin
2010-06-13 22:47 ` Dave Chinner
2010-06-13 23:10 ` Ilia Mirkin
2010-06-14 1:29 ` Dave Chinner
2010-06-14 3:27 ` Ilia Mirkin
2010-06-14 15:11 ` Roman Kononov
2010-05-24 4:12 ` Stan Hoeppner
2010-05-24 5:16 ` Stewart Smith
2010-05-24 19:34 ` Roman Kononov
2010-05-26 7:06 ` Dave Chinner [this message]
2010-05-26 15:07 ` NOW: o_direct -- WAS: " Stan Hoeppner
2010-05-27 11:05 ` Michael Monnerie
2010-05-27 11:47 ` Christoph Hellwig
2010-05-27 13:58 ` Stewart Smith
2010-05-27 14:57 ` Christoph Hellwig
2010-05-27 15:45 ` Stewart Smith
2010-05-28 0:25 ` Stan Hoeppner
2010-05-27 14:05 ` Stewart Smith
2010-05-28 0:42 ` Stan Hoeppner
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=20100526070620.GT2150@dastard \
--to=david@fromorbit.com \
--cc=roman@binarylife.net \
--cc=xfs@oss.sgi.com \
/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