Re: Scrolling performance

["Clemens Eisserer" <linuxhippy gmail com>]

Hi again,

Maybe GTK is using X in a way it does not like?

> of 2 other 700x1000 windows, and the window manager is doing the moving window
> in translucent mode as well, that *will* spike the processor up to about 100%
> and only 8 or 10 redraws per second.
Well but then a composition manager is installed (as far as I know
this is needed for transculesent windows), the window-content is
cached in a pixmap and just this pixmap is drawn overe and over and
the application does not receive a single expose event by X - So it
has in fact nothing to do with GTK.

Thanks for the tip with the theme, the only theme I've installed is
called "Raleigh".

> (1.6Ghz CPU, 768M of RAM, and an NVidia 440Go chipset), hardly a screamer
Well but it should be enough to handle these simple tasks very fast.
If QT can do it fast, GTK should be able too.

I just wonder why QT performs that well (and many other toolkits I've
used too like FOX or FLTK) but everytime it comes down to bad
performance of GTK the following things happen:
1.) Not even one comment from a developer. Maybe there are not enough,
maybe nobody cares, ore maybe they can't cope with critic? I don't
know.
2.) Some fans respond that on their machines its working fast enough.
Fighting against that one that brought up the topic to show him that
their favourite Gui toolkit is not as weak as it looks.
3.) The discussion dies with or without a flame.
-> no result, nothing changes.

I see/saw quite frequently complaints about GTK's performance, I saw
tables comparing GTK-1.2 vs. GTK-2 performance, authors migrating away
from GTK-2 because they were concerned loosing users when switching to
this toolkit.


> So where *does* the time go to, if not pango?  The more detail you can
> provide, the easier it is to track down.
I did some sysprof testing back when I tried to analyze why the
Eclipse/GTK port performs like crap (this was FC4 / GTK-2.6 / Default
theme). It was almost a flat profile, but X spiked quite a lot. Doing
the same test (invalidating eclispe's main window) shows about half
(!!!) of the time is spent in X. The test with gftp (moving splitters)
shows X using 67.1% of CPU whereas gftp itself only consumes 31%.
I am using Xorg 6.9 with grayscale-aa fonts (xrender is accalerated).

lg Clemens