qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: Jamie Lokier <jamie@shareable.org>
To: Christoph Hellwig <hch@lst.de>
Cc: qemu-devel@nongnu.org
Subject: Re: [Qemu-devel] [PATCH 2/4] block: use fdatasync instead of fsync
Date: Mon, 31 Aug 2009 23:48:19 +0100	[thread overview]
Message-ID: <20090831224819.GE24318@shareable.org> (raw)
In-Reply-To: <20090831215525.GA8135@lst.de>

Christoph Hellwig wrote:
> On Mon, Aug 31, 2009 at 10:51:38PM +0100, Jamie Lokier wrote:
> > Christoph Hellwig wrote:
> > > 
> > > If we are flushing the caches for our image files we only care about the
> > > data (including the metadata required for accessing it) but not things
> > > like timestamp updates.  So use fdatasync instead of fsync to implement
> > > the flush operations.
> > 
> > > -    fsync(s->fd);
> > > +    fdatasync(s->fd);
> > 
> > I believe fsync was used because of uncertainty about whether
> > fdatasync reliably flushes the necessary metadata to access the data
> > on all hosts, after things like writing to holes and extending a file.
> > 
> > I'm still not sure if fdatasync provides that guarantee on Linux.
> 
> fdatasync is defined to provide that guarantee, and modulo the whole
> clusterfuck around volatile write caches it does the right thing
> thing on common Linux filesystems.

That's good to know.  I'm not sure about other hosts though.  It's
specified to update the metadata, but I think I've encountered people
saying it doesn't - specifically when extending a file, that it
doesn't guarantee the file size is extended on some OSes.  But that
might be an urban myth.

-- Jamie

  reply	other threads:[~2009-08-31 22:48 UTC|newest]

Thread overview: 33+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2009-08-31 20:16 [Qemu-devel] [PATCH 0/4] data integrity fixes Christoph Hellwig
2009-08-31 20:16 ` [Qemu-devel] [PATCH 1/4] block: add enable_write_cache flag Christoph Hellwig
2009-08-31 22:09   ` Jamie Lokier
2009-08-31 22:16     ` Christoph Hellwig
2009-08-31 22:46       ` Jamie Lokier
2009-08-31 23:06         ` Christoph Hellwig
2009-09-01 10:38           ` Jamie Lokier
2009-08-31 22:53       ` Anthony Liguori
2009-08-31 22:55         ` Jamie Lokier
2009-08-31 22:58         ` Christoph Hellwig
2009-08-31 22:59         ` Jamie Lokier
2009-08-31 23:06           ` Christoph Hellwig
2009-08-31 23:09             ` Christoph Hellwig
2009-09-02  3:53         ` Christoph Hellwig
2009-09-02 13:13           ` Anthony Liguori
2009-09-02 14:14             ` Christoph Hellwig
2009-09-02 19:49             ` Christoph Hellwig
2009-08-31 20:17 ` [Qemu-devel] [PATCH 2/4] block: use fdatasync instead of fsync Christoph Hellwig
2009-08-31 21:51   ` Jamie Lokier
2009-08-31 21:55     ` Christoph Hellwig
2009-08-31 22:48       ` Jamie Lokier [this message]
2009-08-31 22:57         ` Christoph Hellwig
2009-09-01 15:59   ` Blue Swirl
2009-09-01 16:04     ` Christoph Hellwig
2009-09-02  0:34       ` Jamie Lokier
2009-09-02  0:37         ` Christoph Hellwig
2009-09-02  1:18           ` Jamie Lokier
2009-09-02 14:02           ` Blue Swirl
2009-09-02 14:15             ` Christoph Hellwig
2009-08-31 20:17 ` [Qemu-devel] [PATCH 3/4] block: add bdrv_aio_flush operation Christoph Hellwig
2009-09-01 10:24   ` Avi Kivity
2009-09-01 14:25     ` Christoph Hellwig
2009-08-31 20:18 ` [Qemu-devel] [PATCH 4/4] virtio-blk: add volatile writecache feature Christoph Hellwig

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=20090831224819.GE24318@shareable.org \
    --to=jamie@shareable.org \
    --cc=hch@lst.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).