Dmitri Poustovalov <pdmitri@bigfoot.com> wrote:
Just a general suggestion – this problem really sounds like one that
could be solved, or at least have a lot of light thrown on it, by
running the instrumented kernel, getting kernel traces, and looking
at exactly what was happening during that bad delay.
-David
QNX Training Services
http://www.qnx.com/support/training/
Please followup in this newsgroup if you have further questions.