From: "Michael S. Tsirkin" <mst@redhat.com>
To: Paul Brook <paul@codesourcery.com>
Cc: qemu-devel@nongnu.org, Jamie Lokier <jamie@shareable.org>,
Rusty Russell <rusty@rustcorp.com.au>,
virtualization@lists.linux-foundation.org, hch@lst.de,
kvm@vger.kernel.org
Subject: Re: [Qemu-devel] [PATCH] virtio-spec: document block CMD and FLUSH
Date: Wed, 21 Apr 2010 13:39:59 +0300 [thread overview]
Message-ID: <20100421103959.GA31461@redhat.com> (raw)
In-Reply-To: <201004201422.58456.paul@codesourcery.com>
On Tue, Apr 20, 2010 at 02:22:58PM +0100, Paul Brook wrote:
> > Does this mean that virtio-blk supports all three combinations?
> >
> > 1. FLUSH that isn't a barrier
> > 2. FLUSH that is also a barrier
> > 3. Barrier that is not a flush
> >
> > 1 is good for fsync-like operations;
> > 2 is good for journalling-like ordered operations.
> > 3 sounds like it doesn't mean a lot as the host cache provides no
> > guarantees and has no ordering facility that can be used.
>
> (3) allows the guest to queue overlapping transfers with well defined results.
> I have no idea how useful this is in practice, but it's certainly plausible.
>
> Paul
In theory, yes.
At the moment, qemu only implements FLUSH and lguest only
implements barrier without FLUSH.
If you think it's useful, maybe start by using FLUSH+barrier
in linux guest driver, that'd demonstrate how it's used.
--
MST
WARNING: multiple messages have this Message-ID (diff)
From: "Michael S. Tsirkin" <mst@redhat.com>
To: Paul Brook <paul@codesourcery.com>
Cc: kvm@vger.kernel.org, Rusty Russell <rusty@rustcorp.com.au>,
qemu-devel@nongnu.org, virtualization@lists.linux-foundation.org,
hch@lst.de
Subject: Re: [Qemu-devel] [PATCH] virtio-spec: document block CMD and FLUSH
Date: Wed, 21 Apr 2010 13:39:59 +0300 [thread overview]
Message-ID: <20100421103959.GA31461@redhat.com> (raw)
In-Reply-To: <201004201422.58456.paul@codesourcery.com>
On Tue, Apr 20, 2010 at 02:22:58PM +0100, Paul Brook wrote:
> > Does this mean that virtio-blk supports all three combinations?
> >
> > 1. FLUSH that isn't a barrier
> > 2. FLUSH that is also a barrier
> > 3. Barrier that is not a flush
> >
> > 1 is good for fsync-like operations;
> > 2 is good for journalling-like ordered operations.
> > 3 sounds like it doesn't mean a lot as the host cache provides no
> > guarantees and has no ordering facility that can be used.
>
> (3) allows the guest to queue overlapping transfers with well defined results.
> I have no idea how useful this is in practice, but it's certainly plausible.
>
> Paul
In theory, yes.
At the moment, qemu only implements FLUSH and lguest only
implements barrier without FLUSH.
If you think it's useful, maybe start by using FLUSH+barrier
in linux guest driver, that'd demonstrate how it's used.
--
MST
next prev parent reply other threads:[~2010-04-21 10:44 UTC|newest]
Thread overview: 68+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-02-18 22:22 [PATCH] virtio-spec: document block CMD and FLUSH Michael S. Tsirkin
2010-02-18 22:22 ` [Qemu-devel] " Michael S. Tsirkin
2010-04-19 21:26 ` Michael S. Tsirkin
2010-04-19 21:26 ` Michael S. Tsirkin
2010-04-19 21:26 ` [Qemu-devel] " Michael S. Tsirkin
2010-04-28 15:52 ` Michael S. Tsirkin
2010-04-28 15:52 ` Michael S. Tsirkin
2010-04-28 15:52 ` [Qemu-devel] " Michael S. Tsirkin
2010-04-20 1:46 ` [Qemu-devel] " Jamie Lokier
2010-04-20 1:46 ` Jamie Lokier
2010-04-20 1:46 ` Jamie Lokier
2010-04-20 13:22 ` Paul Brook
2010-04-20 13:22 ` Paul Brook
2010-04-20 13:22 ` Paul Brook
2010-04-21 10:39 ` Michael S. Tsirkin [this message]
2010-04-21 10:39 ` Michael S. Tsirkin
2010-04-21 10:39 ` Michael S. Tsirkin
2010-05-04 18:56 ` Christoph Hellwig
2010-05-04 18:56 ` Christoph Hellwig
2010-05-04 19:01 ` Michael S. Tsirkin
2010-05-04 19:01 ` Michael S. Tsirkin
2010-05-04 19:01 ` Michael S. Tsirkin
2010-05-04 4:38 ` Rusty Russell
2010-05-04 4:38 ` [Qemu-devel] " Rusty Russell
2010-05-04 6:56 ` Stefan Hajnoczi
2010-05-04 6:56 ` Stefan Hajnoczi
2010-05-04 8:34 ` Avi Kivity
2010-05-04 8:34 ` Avi Kivity
2010-05-04 8:34 ` [Qemu-devel] " Avi Kivity
2010-05-04 8:41 ` Jens Axboe
2010-05-04 8:41 ` Jens Axboe
2010-05-04 8:41 ` [Qemu-devel] " Jens Axboe
2010-05-04 20:17 ` Jamie Lokier
2010-05-04 20:17 ` Jamie Lokier
2010-05-04 20:17 ` Jamie Lokier
2010-05-05 4:58 ` Rusty Russell
2010-05-05 4:58 ` Rusty Russell
2010-05-05 4:58 ` Rusty Russell
2010-05-05 6:03 ` Neil Brown
2010-05-05 6:03 ` Neil Brown
2010-05-06 6:05 ` Rusty Russell
2010-05-06 6:05 ` Rusty Russell
2010-05-06 6:05 ` Rusty Russell
2010-05-06 14:57 ` Jamie Lokier
2010-05-06 14:57 ` Jamie Lokier
2010-05-06 14:57 ` Jamie Lokier
2010-05-05 6:03 ` Neil Brown
2010-05-06 15:25 ` Jamie Lokier
2010-05-06 15:25 ` Jamie Lokier
2010-05-06 15:25 ` Jamie Lokier
2010-05-04 10:05 ` Christoph Hellwig
2010-05-04 10:05 ` Christoph Hellwig
2010-05-04 10:05 ` [Qemu-devel] " Christoph Hellwig
2010-05-04 20:32 ` Jamie Lokier
2010-05-04 20:32 ` Jamie Lokier
2010-05-04 20:32 ` Jamie Lokier
2010-05-04 4:38 ` Rusty Russell
2010-05-04 18:54 ` Christoph Hellwig
2010-05-04 18:54 ` [Qemu-devel] " Christoph Hellwig
2010-05-04 18:56 ` Michael S. Tsirkin
2010-05-04 18:56 ` Michael S. Tsirkin
2010-05-04 18:56 ` [Qemu-devel] " Michael S. Tsirkin
2010-05-04 18:58 ` Michael S. Tsirkin
2010-05-04 18:58 ` Michael S. Tsirkin
2010-05-04 18:58 ` [Qemu-devel] " Michael S. Tsirkin
2010-05-05 5:00 ` Rusty Russell
2010-05-05 5:00 ` [Qemu-devel] " Rusty Russell
2010-05-05 5:00 ` Rusty Russell
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=20100421103959.GA31461@redhat.com \
--to=mst@redhat.com \
--cc=hch@lst.de \
--cc=jamie@shareable.org \
--cc=kvm@vger.kernel.org \
--cc=paul@codesourcery.com \
--cc=qemu-devel@nongnu.org \
--cc=rusty@rustcorp.com.au \
--cc=virtualization@lists.linux-foundation.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.