On Thu, Apr 12, 2012 at 10:00 PM, Jon Elson <[email protected]> wrote: > Przemek Klosowski wrote: >> The good news are here: RT integration in the mainline kernel keeps >> moving ahead, and the latest 3.x kernels need less and less patches at >> least for Thomas Gleixner's RT subsystem. >> >> http://www.h-online.com/open/features/Kernel-Log-real-time-kernel-goes-Linux-3-0-1382791.html >> > Well, what is the latency performance of this kernel? There are some > groups who > claim to have real time kernels, but when you check, they show several > MILLI-seconds of worst-case latency.
I don't know---but the project goal is to get it around 10us. The rt-linux people have a tool called cyclictest http://people.redhat.com/williams/latency-howto/rt-latency-howto.txt as well as several other interesting tools, including a way to measure SMI interrupts by reading a MSR that directly counts them. I am not a rt-linux guru but I think they have a lot of interesting tools as well as a promising kernel technology. I don't know if I will be able to work on bringing back rt-linux integration but I certainly would like to try. ------------------------------------------------------------------------------ For Developers, A Lot Can Happen In A Second. Boundary is the first to Know...and Tell You. Monitor Your Applications in Ultra-Fine Resolution. Try it FREE! http://p.sf.net/sfu/Boundary-d2dvs2 _______________________________________________ Emc-users mailing list [email protected] https://lists.sourceforge.net/lists/listinfo/emc-users
