[linux-audio-dev] another kernel patch?

[Paul Davis]

>Roger Larsson <roger.larsson at norran.net> writes:
>
>> But it is still a way to see that no client burns cycles where it should not
> -
>> jackd would not start (or stop). And you _can_ get fewer context switches,
>> but only if some client burns extra cycles.
>> 
>> Compare:
>> 
>> With jackd as highest priority:
>> Context switches: A->jd->A->B->jd
>> 
>> With jackd as lowest priority:
>> Context switches: A->jd->B->jd
>
>The actual JACK process cycle works like this:
>  jd->A->B->jd

and to be even clearer: the situation roger described where client A
is running and then we switch to jackd before running A again is
called "an xrun" :)

--p