Strange speed differences on composite

[Tomasz Torcz]

On Fri, Feb 10, 2006 at 07:00:03AM -0500, Owen Taylor wrote:
> On Thu, 2006-02-09 at 18:55 +0100, Tomasz Torcz wrote:
> >   Hi,
> > 
> >   recently I've noticed something suspicious going on with compisite
> > speed. 
> >   First subject was Xephyr, CVS version dated 11th August 2005,
> > build using jhbuild. I turned it on as a 1024x768 window with GNOME
> > session inside. The I've run "xcompmgr -c" inside. Shadows appeared.
> > Now, moving windows in this Xephyr window is pretty fast and CPU isn't
> > used much (10% max), so it's pretty usable.
> >   Second test was on normal X server. I'm running Xorg 6.9.0 from
> > Slackware -current, my graphics card is Matrox G550 with mga driver
> > and Semprom 3500+ CPU. EXA is not available on mga.
> > When I run "xcompmgr -c" everything becomes very slow. Window movement
> > is painful with cpu stuck at 100%. Switching to other virtual desktop
> > takes 2-3 seconds to redraw windows.
> > 
> >   The question: how it comes that software-only Xephyr is _faster_ at
> > drawing shadows than fully hw accelerated X server with mga driver?
> 
> If you ever have to read data from the frame buffer, that's *slow* - 
> you lose far more than you gain from any hardware acceleration you
> might be getting.

  But why read data? Shouldn't it be composed by graphic card in VRAM?
Isn't that what acceleration is for?

-- 
Tomasz Torcz                "Funeral in the morning, IDE hacking
zdzichu at irc.-nie.spam-.pl    in the afternoon and evening." - Alan Cox

-------------- next part --------------
A non-text attachment was scrubbed...
Name: not available
Type: application/pgp-signature
Size: 229 bytes
Desc: not available
URL: <http://lists.x.org/archives/xorg/attachments/20060211/cd5d09e7/attachment.pgp>