> >if someone is interested, I just prepared a small web page about firm > >timers: http://www.cse.ogi.edu/~luca/firm.html On this page, you can > >find a small paper describing some experiments and a kernel patch > >implementing firm timers. > > fantastic work! this looks like the KURT patch done in a way that > might be more acceptable to Linus, and even if not, at least its a > patch for a relatively current kernel. where are you planning to to go > with this?
As Paul said, this is fantastic! I've tried it today and it works great. Also I noticed that the accuracy is runtime adjustable using the /proc interface. With this patch (and the low-latency/preempt patches) Linux performs just as good as BeOS, maybe even better, good enough for decent user space MIDI. Know all we need is for CLOCK_MONOTONIC to be implemented. I would love to see this patch added to 2.5. --martijn
