From: Avi Kivity <avi@redhat.com>
To: Anthony Liguori <anthony@codemonkey.ws>
Cc: qemu-devel <qemu-devel@nongnu.org>, Dor Laor <dlaor@redhat.com>,
Christoph Hellwig <hch@lst.de>,
Vadim Rozenfeld <vrozenfe@redhat.com>
Subject: Re: [Qemu-devel] Re: [RFC][PATCH] performance improvement for windows guests, running on top of virtio block device
Date: Mon, 11 Jan 2010 16:29:03 +0200 [thread overview]
Message-ID: <4B4B35AF.3010706@redhat.com> (raw)
In-Reply-To: <4B4B2C5F.7050403@codemonkey.ws>
On 01/11/2010 03:49 PM, Anthony Liguori wrote:
>> So instead of disabling notify while requests are active we might want
>> to only disable it while we are inside virtio_blk_handle_output.
>> Something like the following minimally tested patch:
>
>
> I'd suggest that we get even more aggressive and install an idle
> bottom half that checks the queue for newly submitted requests. If we
> keep getting requests submitted before a new one completes, we'll
> never take an I/O exit.
>
That has the downside of bouncing a cache line on unrelated exits. It
probably doesn't matter with qemu as it is now, since it will bounce
qemu_mutex, but it will hurt with large guests (especially if they have
many rings).
IMO we should get things to work well without riding on unrelated exits,
especially as we're trying to reduce those exits.
> The same approach is probably a good idea for virtio-net.
With vhost-net you don't see exits.
--
error compiling committee.c: too many arguments to function
next prev parent reply other threads:[~2010-01-11 14:29 UTC|newest]
Thread overview: 36+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-01-11 7:40 [Qemu-devel] [RFC][PATCH] performance improvement for windows guests, running on top of virtio block device Vadim Rozenfeld
2010-01-11 8:30 ` [Qemu-devel] " Avi Kivity
[not found] ` <4B4AE95D.7080305@redhat.com>
2010-01-11 9:19 ` Dor Laor
2010-01-11 13:11 ` Christoph Hellwig
2010-01-11 13:13 ` Avi Kivity
2010-01-11 13:16 ` Christoph Hellwig
2010-01-11 13:47 ` Christoph Hellwig
2010-01-11 14:00 ` Anthony Liguori
2010-02-24 2:58 ` Paul Brook
2010-02-24 14:59 ` Anthony Liguori
2010-02-25 15:06 ` Paul Brook
2010-02-25 15:23 ` Anthony Liguori
2010-02-25 16:48 ` Paul Brook
2010-02-25 17:11 ` Avi Kivity
2010-02-25 17:15 ` Anthony Liguori
2010-02-25 17:33 ` Avi Kivity
2010-02-25 18:05 ` malc
2010-02-25 19:55 ` Anthony Liguori
2010-02-26 8:47 ` Avi Kivity
2010-02-26 14:36 ` Anthony Liguori
2010-02-26 15:39 ` Avi Kivity
2010-01-11 13:42 ` Christoph Hellwig
2010-01-11 13:49 ` Anthony Liguori
2010-01-11 14:29 ` Avi Kivity [this message]
2010-01-11 14:37 ` Anthony Liguori
2010-01-11 14:46 ` Avi Kivity
2010-01-11 15:13 ` Anthony Liguori
2010-01-11 15:19 ` Avi Kivity
2010-01-11 15:22 ` Anthony Liguori
2010-01-11 15:31 ` Avi Kivity
2010-01-11 15:32 ` Anthony Liguori
2010-01-11 15:35 ` Avi Kivity
2010-01-11 15:38 ` Anthony Liguori
2010-01-11 18:22 ` [Qemu-devel] " Michael S. Tsirkin
2010-01-11 18:20 ` Michael S. Tsirkin
2010-01-11 14:25 ` [Qemu-devel] " Avi Kivity
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=4B4B35AF.3010706@redhat.com \
--to=avi@redhat.com \
--cc=anthony@codemonkey.ws \
--cc=dlaor@redhat.com \
--cc=hch@lst.de \
--cc=qemu-devel@nongnu.org \
--cc=vrozenfe@redhat.com \
/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).