qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: "Daniel P. Berrange" <berrange@redhat.com>
To: Jamie Lokier <jamie@shareable.org>
Cc: Amit Shah <amit.shah@redhat.com>, Kevin Wolf <kwolf@redhat.com>,
	QEMU Developers <qemu-devel@nongnu.org>,
	Christoph Hellwig <hch@lst.de>
Subject: Re: [Qemu-devel] [PATCH] Add new block driver for the VDI format (use aio)
Date: Tue, 28 Jul 2009 09:56:42 +0100	[thread overview]
Message-ID: <20090728085642.GD26495@redhat.com> (raw)
In-Reply-To: <20090728083452.GA21321@shareable.org>

On Tue, Jul 28, 2009 at 09:34:52AM +0100, Jamie Lokier wrote:
> Amit Shah wrote:
> > On (Mon) Jul 27 2009 [10:23:19], Jamie Lokier wrote:
> > > Kevin Wolf wrote:
> > > > Though I guess that for static images typically not only metadata is
> > > > preallocated, but zeros are written for the whole disk content? Maybe we
> > > > could implement a three-way flag like preallocate=[no,metadata,data] and
> > > > let qemu-img handle the data part (writing zeros is the same for all
> > > > formats and would even work with raw).
> > > 
> > > Note that you can also preallocate space with posix_fallocate(), which
> > > fills the file with zeros but (sometimes) doesn't take as long as
> > > writing zeros.
> > 
> > It won't take as long as writing zeroes if the filesystem underneath has
> > support for fallocate(). ext4, btrfs, xfs have support for fallocate().
> > 
> > > Apparently it is almost essential when writing large files in small
> > > pieces on Windows, and on Linux it is supported by the ext4
> > > filesystem, but I haven't checked either claim.
> > 
> > I did some comparisons:
> > 
> > http://log.amitshah.net/2009/03/comparison-of-file-systems-and-speeding.html
> > 
> > http://log.amitshah.net/2009/04/re-comparing-file-systems.html
> 
> There was some discussion of it on the rsync list, which is where I
> learned it is important for NTFS performance on Windows.
> 
> By the way, why is fallocate() support being added to libvirt to
> improve disk image creation, instead of to qemu-img?

libvirt has to work with more than just QEMU.  Thus it has a built in
support for creating raw files, and this is where we added fallocate
support. It also has ability to call out to hypervisor specific tools
for creating non-raw formats. We support qemu-img, and qcow-create (the
latter from Xen)

Regards,
Daniel
-- 
|: Red Hat, Engineering, London   -o-   http://people.redhat.com/berrange/ :|
|: http://libvirt.org  -o-  http://virt-manager.org  -o-  http://ovirt.org :|
|: http://autobuild.org       -o-         http://search.cpan.org/~danberr/ :|
|: GnuPG: 7D3B9505  -o-  F3C9 553F A1DA 4AC2 5648 23C1 B3DF F742 7D3B 9505 :|

  reply	other threads:[~2009-07-28  8:56 UTC|newest]

Thread overview: 44+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2009-07-03 19:24 [Qemu-devel] [PATCH] RFC: Add new block driver for the VDI format Stefan Weil
2009-07-03 19:29 ` [Qemu-devel] [PATCH] Check availability of uuid header / lib Stefan Weil
2009-07-03 19:29   ` [Qemu-devel] [PATCH] Add new block driver for the VDI format Stefan Weil
2009-07-05  8:05     ` Christoph Hellwig
2009-07-05 14:02       ` Stefan Weil
2009-07-06 10:25         ` Christoph Hellwig
2009-07-06 17:19           ` Stefan Weil
2009-07-05 14:44     ` Kevin Wolf
2009-07-06 13:37 ` [Qemu-devel] [PATCH] RFC: " Anthony Liguori
2009-07-06 21:10   ` Stefan Weil
2009-07-06 21:28     ` Anthony Liguori
2009-07-07  7:55     ` Kevin Wolf
2009-07-07  9:04       ` Jamie Lokier
2009-07-07 10:30       ` Christoph Hellwig
2009-07-07 10:33         ` Kevin Wolf
2009-08-02 14:27   ` Avi Kivity
2009-08-03  2:25     ` Anthony Liguori
2009-08-03 13:02       ` Avi Kivity
2009-08-03 15:20         ` Christoph Hellwig
2009-07-23 15:58 ` [Qemu-devel] [PATCH] RFC: Add new block driver for the VDI format (aio version) Stefan Weil
2009-07-23 20:27   ` [Qemu-devel] [PATCH] Check availability of uuid header / lib Stefan Weil
2009-07-24  6:32     ` Christoph Egger
2009-10-01 18:13       ` Stefan Weil
2009-10-02  8:32         ` Christoph Egger
2009-10-01 18:10     ` [Qemu-devel] [PATCH] Check availability of uuid header / library Stefan Weil
2009-07-23 20:29   ` [Qemu-devel] [PATCH] Add new block driver for the VDI format (use aio) Stefan Weil
2009-07-24  9:18     ` Kevin Wolf
2009-07-24 16:20       ` Stefan Weil
2009-07-27  8:00         ` Kevin Wolf
2009-07-27  9:23           ` Jamie Lokier
2009-07-28  6:37             ` Amit Shah
2009-07-28  8:34               ` Jamie Lokier
2009-07-28  8:56                 ` Daniel P. Berrange [this message]
2009-07-28  9:03                   ` Jamie Lokier
2009-07-28  9:11                     ` Kevin Wolf
2009-07-31 15:04           ` Christoph Hellwig
2009-07-31 19:53             ` Stefan Weil
2009-07-31 15:25     ` Anthony Liguori
2009-07-31 18:27       ` Stefan Weil
2009-07-31 19:45         ` [Qemu-devel] [PATCH] Add new block driver for the VDI format (only aio supported) Stefan Weil
2009-07-23 20:30   ` [Qemu-devel] [PATCH] add support for new option of vdi format Stefan Weil
2009-07-23 20:34     ` [Qemu-devel] " Stefan Weil
2009-07-31 14:59     ` [Qemu-devel] " Christoph Hellwig
2009-08-13 16:53     ` 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=20090728085642.GD26495@redhat.com \
    --to=berrange@redhat.com \
    --cc=amit.shah@redhat.com \
    --cc=hch@lst.de \
    --cc=jamie@shareable.org \
    --cc=kwolf@redhat.com \
    --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).