From: Neil Brown <neilb@suse.de>
To: John Robinson <john.robinson@anonymous.org.uk>
Cc: linux-raid@vger.kernel.org
Subject: Re: Why does one get mismatches?
Date: Thu, 25 Feb 2010 20:07:10 +1100 [thread overview]
Message-ID: <20100225200710.674ae669@notabene.brown> (raw)
In-Reply-To: <4B86393F.4040707@anonymous.org.uk>
On Thu, 25 Feb 2010 08:47:59 +0000
John Robinson <john.robinson@anonymous.org.uk> wrote:
> On 24/02/2010 21:32, Neil Brown wrote:
> [...]
> > If you open /dev/md0 with O_DIRECT there is no page cache involved and so no
> > setting of Dirty flags. So you could engineer a situation with O_DIRECT
> > that writes different data to the two devices, but you would have to try
> > fairly hard.
>
> Hang on. O_DIRECT sets off all sort of alarm bells for me, not that I
> understand it properly. Of course there's O_DIRECT on files too. Linus
> Torvalds is quite outspoken about it: http://kerneltrap.org/node/7563
>
> Could we be seeing mismatches because applications are opening their
> files with O_DIRECT in a (perhaps misguided) attempt to get better
> performance?
Unlikely.
The app would need to be doing async direct-io, or it would need to be have
multiple threads, and in either case it would need to change the buffer that
was being written while the write was happening. And that would be a pretty
dumb thing to do unless it almost immediately wrote the same buffer out again.
So not exactly impossible, but probably the least-likely of the various
possible explanations.
NeilBrown
next prev parent reply other threads:[~2010-02-25 9:07 UTC|newest]
Thread overview: 104+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-01-20 11:52 Fw: Why does one get mismatches? Jon Hardcastle
2010-01-22 18:13 ` Goswin von Brederlow
2010-01-24 17:40 ` Jon Hardcastle
2010-01-24 21:52 ` Roger Heflin
2010-01-24 23:13 ` Goswin von Brederlow
2010-01-25 10:07 ` Jon Hardcastle
2010-01-25 10:37 ` Goswin von Brederlow
2010-01-25 10:52 ` Jon Hardcastle
2010-01-25 17:32 ` Goswin von Brederlow
2010-01-25 19:32 ` Iustin Pop
2010-02-01 21:18 ` Bill Davidsen
2010-02-01 22:37 ` Neil Brown
2010-02-02 15:11 ` Bill Davidsen
2010-02-03 11:17 ` Goswin von Brederlow
2010-02-11 5:14 ` Neil Brown
2010-02-11 17:51 ` Bryan Mesich
2010-02-16 21:25 ` Bill Davidsen
2010-02-16 21:38 ` Steven Haigh
2010-02-17 3:19 ` Bryan Mesich
2010-02-17 23:05 ` Neil Brown
2010-02-19 15:18 ` Piergiorgio Sartor
2010-02-19 22:02 ` Neil Brown
2010-02-19 22:37 ` Piergiorgio Sartor
2010-02-19 23:34 ` Asdo
2010-02-20 4:27 ` Goswin von Brederlow
2010-02-20 11:12 ` Asdo
2010-02-21 11:13 ` Goswin von Brederlow
[not found] ` <8754A21825504719B463AD9809E54349@m5>
[not found] ` <20100221194400.GA2570@lazy.lzy>
2010-02-22 13:01 ` Asdo
2010-02-22 13:30 ` Piergiorgio Sartor
2010-02-22 13:44 ` Piergiorgio Sartor
2010-02-24 19:42 ` Bill Davidsen
2010-02-20 4:23 ` Goswin von Brederlow
2010-02-24 14:54 ` Bill Davidsen
2010-02-24 21:37 ` Neil Brown
2010-02-26 20:48 ` Bill Davidsen
2010-02-26 21:09 ` Neil Brown
2010-02-26 22:01 ` Piergiorgio Sartor
2010-02-26 22:15 ` Bill Davidsen
2010-02-26 22:21 ` Piergiorgio Sartor
2010-02-26 22:20 ` Asdo
2010-02-27 6:01 ` Michael Evans
2010-02-28 0:01 ` Bill Davidsen
2010-02-24 14:46 ` Bill Davidsen
2010-02-24 16:12 ` Martin K. Petersen
2010-02-24 18:51 ` Piergiorgio Sartor
2010-02-24 22:21 ` Neil Brown
2010-02-25 8:41 ` Piergiorgio Sartor
2010-03-02 4:57 ` Neil Brown
2010-03-02 18:49 ` Piergiorgio Sartor
2010-02-24 21:39 ` Neil Brown
[not found] ` <4B8640A2.4060307@shiftmail.org>
2010-02-25 10:41 ` Neil Brown
2010-02-28 8:09 ` Luca Berra
2010-03-02 5:01 ` Neil Brown
2010-03-02 7:36 ` Luca Berra
2010-03-02 10:04 ` Michael Evans
2010-03-02 11:02 ` Luca Berra
2010-03-02 12:13 ` Michael Evans
2010-03-02 18:14 ` Asdo
2010-03-02 18:52 ` Piergiorgio Sartor
2010-03-02 23:27 ` Asdo
2010-03-03 9:13 ` Piergiorgio Sartor
2010-03-03 11:42 ` Asdo
2010-03-03 12:03 ` Piergiorgio Sartor
2010-03-02 20:17 ` Neil Brown
2010-02-24 21:32 ` Neil Brown
2010-02-25 7:22 ` Goswin von Brederlow
2010-02-25 7:39 ` Neil Brown
2010-02-25 8:47 ` John Robinson
2010-02-25 9:07 ` Neil Brown [this message]
2010-02-11 18:12 ` Piergiorgio Sartor
-- strict thread matches above, loose matches on Subject: below --
2010-02-01 23:14 Jon Hardcastle
2010-01-25 20:43 greg
2010-01-25 22:49 ` Steven Haigh
2010-01-27 21:54 ` Tirumala Reddy Marri
2010-01-28 9:16 ` Jon Hardcastle
2010-01-28 10:29 ` Asdo
2010-01-28 17:20 ` Tirumala Reddy Marri
2010-01-28 18:23 ` Goswin von Brederlow
2010-01-28 19:03 ` Tirumala Reddy Marri
2010-01-28 20:24 ` Goswin von Brederlow
2010-01-29 15:37 ` Jon Hardcastle
2010-01-29 23:52 ` Goswin von Brederlow
2010-01-30 10:39 ` Jon Hardcastle
2010-02-01 21:10 ` Bill Davidsen
2010-01-20 15:03 Jon Hardcastle
2010-01-20 15:34 ` Brett Russ
2010-01-20 20:44 ` Majed B.
2010-01-20 22:25 ` Brett Russ
2010-01-20 22:30 ` Majed B.
2010-01-20 22:43 ` Brett Russ
2010-01-20 23:01 ` Christopher Chen
2010-01-21 4:17 ` Steven Haigh
2010-01-21 8:08 ` Asdo
2010-01-21 10:52 ` Steven Haigh
2010-01-21 11:48 ` Farkas Levente
2010-01-21 12:15 ` Jon Hardcastle
2010-01-19 10:04 Jon Hardcastle
2010-01-20 14:19 ` Brett Russ
2010-01-20 14:34 ` Jon Hardcastle
2010-01-20 14:46 ` Brett Russ
2010-02-01 20:48 ` Bill Davidsen
2010-01-22 16:22 ` Jon Hardcastle
2010-01-22 16:34 ` Asdo
2010-01-22 17:41 ` Brett Russ
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=20100225200710.674ae669@notabene.brown \
--to=neilb@suse.de \
--cc=john.robinson@anonymous.org.uk \
--cc=linux-raid@vger.kernel.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;
as well as URLs for NNTP newsgroup(s).