Re: real-time threaded IO with low latency (audio)

Paul Barton-Davis (pbd@Op.Net)
Sat, 24 Jul 1999 09:11:31 -0400


>I agree here. For real time audio to be useful, it must be possible to
>do while loading the rest of the system heavily.

why ? my Q20 doesn't do that! neither does the lexicon unit
that my friend has. why are you requiring the computer based solutions
to have properties not shared by their inspiration ? i'm not saying
its wrong, but i just don't understand the insistence on this ...

>Agree, but if I can chose between unreliable 20 ms latency (at the very
>least) and NO WAY to avoid crashing every now and then even if all
>plug-ins are "bug free", and rock solid 3 ms latency (or whatever I
>like) and the possibility of a crash when using a buggy plug-in, guess
>where I'll go...

and if i have to choose between RTL and running a Pulsar/Scope/Kyma
under MacOS with the massive increase in processing power it would
offer, i know what i'll do too ....

audio applications that require RTL don't interest me. its just not
the kind of system i want to use. that might change over time.

>What kind of system calls? What resources need to be hard real time in
>addition to audio and MIDI ports?

pthreads (perhaps not, if you use an event-driven model)
disk i/o
possibly shared memory stuff

--p

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/