[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
CPU speed problem
- Date: Fri, 27 Aug 1999 14:09:29 +0000
- From: charles.gauthier at iit.nrc.ca (Charles-Antoine Gauthier)
- Subject: CPU speed problem
Hum... where to start... So many possibilities...
I would first assume a critical race, given that the problem is related
to the speed of the CPU relative to absolute time or to network speed.
But I would look for easier sources of problems first, such as a
mis-configured driver, hardwre differences, etc. Once you have
eliminated these, then go look for a critical race problem. Critical
races probably the most difficult bugs to find, and it will probably
take you a long time to find it. Hence, don't start with that until you
have eliminated all other possible sources for the problem.
> I am studing Rtems networking .
> This study include networking, thread(Rtems POSIX),priority(POSIX priority),and CORBA(Common Object Request Broker(Meddleware))
> I use omniORB in RTEMS and Real-Time CORBA spec.
> So I develop RTMES + omniORB + Real-Time CORBA spec.
> And Rtems runs succesfully in 2-4 thread using network and with priority.
> but if thread number is 5-10, Rtems is die in Pentium 90..
> And this walk runs succesfully in Pentium 233 .
> I want to know this
> Soongsil University in Korea
> Electronic Engineering . graduated School
> Lee young ki.
> Computer is Very Good,Software is Ultra Good.
Software Engineering Group
Institute for Information Technology
National Research Council of Canada
Ottawa, ON, Canada