[linux-audio-dev] Linux kernel HZ, audio latency and how to measure?

Mulyadi Santosa a_mulyadi at telkom.net
Fri Aug 18 19:07:47 UTC 2006


> > recording audio doesn't involve using the system timer at all. the
> > only clock involved is the sample clock that drives the audio
> > interface.

I see. I took a wrong conclusion then....

> > having HZ set too high could conceivably make the system more
> > likely to xrun, but this is not likely with a fully RT kernel.

Ehm, excuse me. "xrun" here refers to a program's name?

> High HZ will improve MIDI timing though.  MIDI is more likely to be
> polled than interrupt driven.

polled? Well, interesting. Do you mean MIDI playback? 

BTW, a friend of mine suggest to take audio synthesizing as the 
"benchmark" for this HZ experiment. So far, I guess that synthesizing 
is also timing sensitive application, thus tweaking HZ could make 
difference. Thoughts?



More information about the Linux-audio-dev mailing list