On Wed, 2007-01-31 at 13:46 +0200, Sampo Savolainen wrote: > That might help a bit. But keep in mind that DSP usage of 80% is really > high. It doesn't leave your computer much headroom for other tasks, or even > plugins which might periodically use more CPU cycles than normally (=which > is in fact a sign that a plugin is not "academically" real time safe). In my > opinion 80% is about the maximum of DSP usage you can expect to be stable to > work with. indeed. when stephane, jesse and i were testing jack and jackdmp last year for load limits, we found on linux and OS X that if the JACK DSP figure got close to 80% it was very hard to ensure continued RT, glitch-free performance. as sampo indicated, its partly a function of code not being truly RT safe, and partly a function of the x86 architecture compared to a real DSP chip - the DSP is totally deterministic in execution time, the x86 is not.
