qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: Laurent Vivier <Laurent.Vivier@bull.net>
To: Jamie Lokier <jamie@shareable.org>
Cc: Blue Swirl <blauwirbel@gmail.com>,
	qemu-devel@nongnu.org, Kevin Wolf <kwolf@suse.de>
Subject: Re: [Qemu-devel] Re: [PATCH][v2] Align file accesses with cache=off (O_DIRECT)
Date: Wed, 21 May 2008 01:04:47 +0200	[thread overview]
Message-ID: <1211324687.4217.8.camel@frecb07144> (raw)
In-Reply-To: <20080520223602.GE27853@shareable.org>

Le mardi 20 mai 2008 à 23:36 +0100, Jamie Lokier a écrit :
> Anthony Liguori wrote:
> > >This patch implements wrappers for raw_pread and raw_pwrite which align
> > >all file accesses and make qcow(2) work with cache=off. This method
> > >might not be the most performant one (compared to fixing qcow, qcow2 and
> > >everything else that might be using unaligned accesses), but unaligned
> > >accesses don't happen that frequently and with this patch really all
> > >image accesses should be covered."
> 
> It's a useful patch.
> 
> One little esoteric consequence you might want to document.
> 
> This occurs when a guest is running something like a database or
> journalling filesystem, and is reliant on the host disk's integrity
> properties.
> 
> One property of disks is that if you overwrite a sector and the're
> power loss, when read later that sector might be corrupt.  Even if the
> new data is the same as the old data with only some bytes changed,
> some of the _unchanged_ bytes may be corrupt by this.
> 
> When it writes to sector-aligned offset, there is a possibility that
> the guest is depending on power failure not causing corruption of
> neighouring sectors.  This is typical with some kinds of journalling.
> 
> When sector-aligned guest offsets are converted to sector-unaligned
> writes (e.g. due to qcow2 etc.), that property is no longer satisfied,
> and power failure of the host disk can cause more damage than the
> guest is designed to be resistant to.

Sector unaligned guest offset are converted to sector aligned offset.
Sector aligned guest offset are written as is.

And as we use O_DIRECT and aligned offset and data count I think we
increase disk integrity (regarding the case without O_DIRECT and without
aligned access...), so we should document the case without O_DIRECT use,
not the case with O_DIRECT use...

Regards,
Laurent
-- 
------------- Laurent.Vivier@bull.net ---------------
"The best way to predict the future is to invent it."
- Alan Kay

  parent reply	other threads:[~2008-05-20 23:04 UTC|newest]

Thread overview: 48+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2008-05-20 11:32 [Qemu-devel] [PATCH][v2] Align file accesses with cache=off (O_DIRECT) Laurent Vivier
2008-05-20 19:47 ` [Qemu-devel] " Anthony Liguori
2008-05-20 22:36   ` Jamie Lokier
2008-05-20 22:52     ` Paul Brook
2008-05-20 22:59       ` Laurent Vivier
2008-05-21  0:54         ` Paul Brook
2008-05-21  7:59           ` Laurent Vivier
2008-05-21  0:58       ` Anthony Liguori
2008-05-21  1:04         ` Jamie Lokier
2008-05-21  1:05         ` Anthony Liguori
2008-05-21  8:06           ` Kevin Wolf
2008-05-21  1:05         ` Paul Brook
2008-05-21  1:14           ` Anthony Liguori
2008-05-21  8:24             ` Kevin Wolf
2008-05-21 12:26               ` Jamie Lokier
2008-05-21 12:37                 ` Avi Kivity
2008-05-21 13:41                   ` Jamie Lokier
2008-05-21 13:55                     ` Anthony Liguori
2008-05-21 14:17                       ` Avi Kivity
2008-05-21 14:26                         ` Anthony Liguori
2008-05-21 14:57                           ` Avi Kivity
2008-05-21 15:34                             ` Jamie Lokier
2008-05-21 16:02                               ` Anthony Liguori
2008-05-21 16:24                                 ` Jamie Lokier
2008-05-21 16:48                                   ` Avi Kivity
2008-05-21 17:01                                     ` Andrea Arcangeli
2008-05-21 17:18                                       ` Avi Kivity
2008-05-21 17:47                                         ` Andrea Arcangeli
2008-05-21 17:53                                           ` Anthony Liguori
2008-05-21 18:08                                             ` Andrea Arcangeli
2008-05-21 18:25                                               ` Anthony Liguori
2008-05-21 20:13                                                 ` Andrea Arcangeli
2008-05-21 20:35                                                   ` Anthony Liguori
2008-05-21 20:42                                                     ` Andrea Arcangeli
2008-05-21 18:29                                           ` Avi Kivity
2008-05-21 16:45                                 ` Avi Kivity
2008-05-21 16:44                               ` Avi Kivity
2008-05-20 23:04     ` Laurent Vivier [this message]
2008-05-20 23:13       ` Jamie Lokier
2008-05-21  1:00     ` Anthony Liguori
2008-05-21  1:19       ` Jamie Lokier
2008-05-21  2:12         ` Anthony Liguori
2008-05-21  8:27           ` Andreas Färber
2008-05-21 14:06             ` Anthony Liguori
2008-05-21 15:31               ` Jamie Lokier
2008-05-21 11:43           ` Jamie Lokier
2008-05-23  9:12   ` Laurent Vivier
2008-05-28  7:01     ` Kevin Wolf

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=1211324687.4217.8.camel@frecb07144 \
    --to=laurent.vivier@bull.net \
    --cc=blauwirbel@gmail.com \
    --cc=jamie@shareable.org \
    --cc=kwolf@suse.de \
    --cc=qemu-devel@nongnu.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).