Re: Scrolling performance



On Thu, 06 Jul 2006 17:15:38 -0500, Michael Ekstrand wrote:

> You're comparing it with itself.  If the profiler reports that GTK is
> consistently spending 75% of its time in Cairo, then yeah, Cairo (or at
> least the manner in which GTK uses Cairo) is a problem.  But if it
> spends 5% of its time in Cairo, and 60% of its time grooming a cat, then
> the problem is most likely elsewhere.

Just to be clear here: I am a reasonably proficient user. I'm not an
expert. I am just a user with a working knowledge of compiling stuff up. I
have a serious performance problem to report. I'm assuming that GTK
developers actually want to know about this stuff... and as such I'm
willing to do anything within reason to collect information.

In other words: a user with a demonstrably awful performance regression
using 100% Free software stack (no binary drivers here) is sitting waiting
to be given some straightforward instructions on what to do and where to
find the tools necessary to collect the data.




[Date Prev][Date Next]   [Thread Prev][Thread Next]   [Thread Index] [Date Index] [Author Index]