From: Paul Brook <paul@codesourcery.com>
To: Samuel Thibault <samuel.thibault@ens-lyon.org>
Cc: qemu-devel@nongnu.org
Subject: Re: [Qemu-devel] [PATCH] opengl rendering in the sdl window
Date: Sun, 7 Sep 2008 16:35:54 +0100 [thread overview]
Message-ID: <200809071635.54858.paul@codesourcery.com> (raw)
In-Reply-To: <20080907151254.GP4307@implementation>
> > > Which part(s) of the framebuffer?
> >
> > Whichever parts have changed.
>
> Sure, how do you detect that?
> The previous Xen memcmp method was eating 10% cpu for a 30Hz refresh,
> just for the memcmp. Now it uses the pagetable dirty bits and after
> some idleness, trapping, but having the guest just write to actual
> video memory (when it _has_ to be shown on the screen anyway) seems the
> fastest way.
Page granularity dirtyness is trivial. In fact qemu already does this. I'd be
surprised if finer granularity gave any real benefit.
It also depends what testcase you're benchmarking. A few pixels changing every
frame is IMHO not a particularly interesting case. The only time this really
happens is mouse movement, and there are better ways of fixing that (proper
hardware mouse cursors). The interesting cases are guest completely idle, and
large screen updates.
Paul
next prev parent reply other threads:[~2008-09-07 15:36 UTC|newest]
Thread overview: 75+ messages / expand[flat|nested] mbox.gz Atom feed top
2008-08-29 15:22 [Qemu-devel] [PATCH] opengl rendering in the sdl window Stefano Stabellini
2008-09-02 16:53 ` Ian Jackson
2008-09-04 3:00 ` Anthony Liguori
2008-09-04 7:41 ` Gerd Hoffmann
2008-09-04 9:42 ` Daniel P. Berrange
2008-09-04 10:06 ` Andreas Färber
2008-09-04 10:20 ` Daniel P. Berrange
2008-09-05 16:42 ` Andreas Färber
2008-09-07 7:51 ` Avi Kivity
2008-09-07 3:07 ` Anthony Liguori
2008-09-07 16:31 ` Daniel P. Berrange
2008-09-08 0:12 ` Anthony Liguori
2008-09-04 10:06 ` Stefano Stabellini
2008-09-05 12:02 ` Jamie Lokier
2008-09-05 12:11 ` Samuel Thibault
2008-09-06 23:27 ` Jamie Lokier
2008-09-07 14:22 ` Samuel Thibault
2008-09-07 14:36 ` Paul Brook
2008-09-07 14:42 ` Samuel Thibault
2008-09-07 15:03 ` Paul Brook
2008-09-07 15:12 ` Samuel Thibault
2008-09-07 15:35 ` Paul Brook [this message]
2008-09-07 15:41 ` Samuel Thibault
2008-09-07 15:57 ` Paul Brook
2008-09-08 0:08 ` Anthony Liguori
2008-09-08 0:21 ` Samuel Thibault
2008-09-08 1:18 ` Jamie Lokier
2008-09-08 10:38 ` Stefano Stabellini
2008-09-08 13:21 ` Jamie Lokier
2008-09-05 16:44 ` Stefano Stabellini
2008-09-05 16:55 ` Daniel P. Berrange
2008-09-05 17:13 ` Stefano Stabellini
2008-09-07 3:21 ` Anthony Liguori
2008-09-08 10:48 ` Stefano Stabellini
2008-09-08 13:16 ` Jamie Lokier
2008-09-08 13:51 ` Stefano Stabellini
2008-09-08 13:41 ` Jamie Lokier
2008-09-08 13:48 ` Daniel P. Berrange
2008-09-08 14:56 ` Gerd Hoffmann
2008-09-08 15:08 ` Jamie Lokier
2008-09-08 15:35 ` Gerd Hoffmann
2008-09-08 15:39 ` Jamie Lokier
2008-09-08 16:23 ` Gerd Hoffmann
2008-09-08 16:47 ` Anthony Liguori
2008-09-08 19:15 ` Gerd Hoffmann
2008-09-08 19:43 ` Jamie Lokier
2008-09-08 15:47 ` Daniel P. Berrange
2008-09-08 16:05 ` Anthony Liguori
2008-09-08 17:08 ` Mike Kronenberg
2008-09-08 19:21 ` Gerd Hoffmann
2008-09-08 21:06 ` Mike Kronenberg
2008-09-08 19:32 ` Jamie Lokier
2008-09-08 19:48 ` Jamie Lokier
2008-09-08 19:57 ` Anthony Liguori
2008-09-08 20:11 ` Jamie Lokier
2008-09-08 23:18 ` Daniel P. Berrange
2008-09-09 0:10 ` Jamie Lokier
2008-09-09 2:45 ` Anthony Liguori
2008-09-09 4:17 ` Jamie Lokier
2008-09-08 14:22 ` Anthony Liguori
2008-09-07 7:48 ` Avi Kivity
2008-09-07 11:57 ` Daniel P. Berrange
2008-09-07 13:12 ` Avi Kivity
2008-09-08 10:30 ` Stefano Stabellini
2008-09-08 10:35 ` Daniel P. Berrange
2008-09-08 10:53 ` Stefano Stabellini
2008-09-08 11:00 ` Daniel P. Berrange
2008-09-08 12:38 ` François Revol
2008-09-08 13:05 ` Jamie Lokier
2008-09-08 13:08 ` Anthony Liguori
2008-09-08 13:44 ` François Revol
2008-09-05 18:11 ` malc
2008-09-04 10:14 ` Stefano Stabellini
2008-09-07 3:09 ` Anthony Liguori
2008-09-04 10:21 ` Andreas Färber
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=200809071635.54858.paul@codesourcery.com \
--to=paul@codesourcery.com \
--cc=qemu-devel@nongnu.org \
--cc=samuel.thibault@ens-lyon.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).