Re: Performance change from X in Fedora Core 4 to Fedora Core 5

[Peter Henriksson <swany telia com>]

> As mentioned in this thread already, there was a GNOME performance BOF
> at GUADEC recently, and one of the things that came of that was a
> series of patches from Matthias Clasen to revert uses of cairo within
> GTK+ to the pre-cairo behavior.
> 
> For example, there is this one:
> 
> http://mail.gnome.org/archives/performance-list/2006-July/msg00000.html
> 
> Matthias, did the earlier patch never make it to the list? I'm not
> seeing it in the archives.
> 
> If you have good luck with any of those patches then I will be very
> interested in hearing about it, as it would definitively identify a
> performance problem in cairo, (the X server could perhaps be blamed as
> well---but conceivably, cairo could work around any X server slowness
> by using whatever X server functionality GTK+ was using prior to
> calling into cairo[*]).

I did try these patches to some extent. GtkPerf showed no difference
whatsoever.

GtkPerf 1000 iterations

Run 1:
gtk-2.10.0 (cellrenderer-cairo.patch, entry-cairo.patch and
style-cairo.patch)
cairo-1.2.0
gtk-engines-2.7.4

Total time:	235.62

Run 2:
gtk-2.10.0
cairo-1.2.0
gtk-engines-2.7.4

Total time:	235.72

What did make some difference though. Is Soren Sandmanns MMX patch [1]
from yesterday.

Run 3:
gtk-2.10.0
cairo-1.2.0 (pixman-ops.patch)
gtk-engines-2.7.4

Total time:	226.48	(~4.4% improvement)

And of course the huge difference of using an older version of
gtk-engines.

Run 4:
gtk-2.10.0
cairo-1.2.0
gtk-engines-2.6.9

Total time:	186.74

I'm afraid I don't have profiles from these runs but I believe they
would be meaningless anyways, since I'm using the propriatary nVidia
drivers.

Cheers,
Peter Henriksson

[1] http://lists.freedesktop.org/archives/cairo/2006-July/007383.html