Messages in this thread | | | Subject | Re: [patch] voluntary-preempt-2.6.8.1-P0 | From | Lee Revell <> | Date | Sun, 15 Aug 2004 23:33:07 -0400 |
| |
On Sun, 2004-08-15 at 23:00, Ingo Molnar wrote: > * Ingo Molnar <mingo@elte.hu> wrote: > > > could this be some DMA starvation effect? Or is this xrun calculated > > from arrival of the audio interrupt (hence DMA completion) to the > > actual running of jackd? > > would there be a way to find out what portion of the xrun is caused by > latencies of the audio card (DMA, etc.) vs. latency from the point jackd > is woken up by the sound-driver to the point jackd preempts the mlock > process and runs? >
WHat is being measured is the length of time between jackd is woken up and when it runs - the xrun report prints the difference between the current time and the timestamp returned by snd_pcm_status_get_trigger_tstamp (updated by the interrupt handler) and the current time.
jackd prints a different error message if it detects that the interrupt handler was delayed, this is a separate issue than an xrun. I have seen this happen before, but I don't think this is going on here.
Lee
- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
| |