Speedup the Sugar Shell with Psyco, Part II
Yesterday I was playing with Psyco trying to get a little bit faster Sugar shell, today I’ve done a couple of tests using Sysprof to watch the behavior of a normal sugar v/s a modified one using Psyco, so here we go:
Machine: XO-B4
Build: Joyride 227
| Library/Function | Normal Sugar | Sugar + Psyco |
| /lib/libglib-2.0.so.0.1200.13 | 86.26 % | 63.06 % |
| /usr/lib/libgtk-11-2.0.so.0.1000.14 | 86.17 % | 65.80 % |
| /usr/lib/libpython2.5.so.1.0 | 84.09 % | 85.75 % |
| /usr/bin/python | 82.21 % | 55.46 % |
| /usr/lib/python2.5/site-packages/gtk-2.0/gtk/_gtk.so | 82.11 % | 60.57 % |
| __libc_start_main | 81.62 % | 62.35 % |
| /lib/libgobject-2.0.so.0.1200.13 | 75.20 % | 63.06 % |
| /usr/lib/libhippocanvas-1.so.0.0.0 | 65.81 % | 76.48 % |
| in kernel | 3.95 % | 3.92 % |
The optimized files were:
- sugar/util.py
- shell/view/Shell.py
- shell/view/pulsingicon.py
- graphics/spreadlayout.py
- graphics/icon.py
- graphics/animation.py
- graphics/palette.py
- graphics/palettegroup.py
- graphics/toolbutton.py
the methods/functions binded by Psyco were the most heavier profiled, the resources used in this performance are just some CPU time at the beginning and 50KB of extra memory… it’s time to send patches? >:)
Categories: OLPC
