> I'm not sure why he's trying to do this because for audio the latest >patched kernels appear to be more than adequate. That said, I don't >think you can get a guaranteed 15 microsecond interrupt response with >anyone's patches to the standard kernel. I wouldn't call what we have
true, but the problem with RTLinux is that you can get that kind of response there either if your app involves stuff that runs in the normal Linux kernel controlled space. to get that response, everything has to be done within the RT-part of RTLinux, which is *not* a POSIX-like development environment, for the simple reason that it offers normal Linux as well :) victor and i have spoken on the phone a few times about this (we used to debate a lot on rec.talk.politics back in the mid-90s, and had similar life aspirations). i just don't see it happening for anything except a dedicated flat-front-panel embedded system. and given Receptor/Plugzilla, perhaps not even then. --p
