On 15.03.23 18:18, Fons Adriaensen wrote:
On Mon, Mar 13, 2023 at 10:20:01PM +0100, Giso Grimm wrote:
I am not an expert on USB driver / kernel implementation, but measurements
show that the timing of jack callbacks using USB sound cards is not regular.
When calculating period time histograms I usually get two or three peaks,
only on rare occasions (e.g., 1ms block sizes, but not with all sound cards)
only a single peak. Often, none of the peaks is related to a 1 ms grid.
Did some test here, results at
<http://kokkinizita.linuxaudio.org/linuxaudio/timing/results.html>
Thanks, nice plots!
I can reproduce (more or less) the plots with Audient EVO16 and jack.
When I use period sizes below 1ms, I get this:
http://vegri.net/p32-n2.png
Here the clusters are at 0.5 ms and 0.75 ms. When I zoom in I see a
pattern of 0.75, 0.75, 0.5, 0.75, 0.75, 0.5, and so on. So again on the
1 ms grid (every 3 callbacks), but since the round-trip delay is smaller
than for P = 48, I guess that input and output blocks are not time-aligned.
Best,
Giso
_______________________________________________
Linux-audio-user mailing list -- linux-audio-user@xxxxxxxxxxxxxxxxxxxx
To unsubscribe send an email to linux-audio-user-leave@xxxxxxxxxxxxxxxxxxxx
