Re: [patch] voluntary-preempt-2.6.8.1-P0

[Lee Revell]

On Sun, 2004-08-15 at 23:00, Ingo Molnar wrote:
> * Ingo Molnar <mingo@xxxxxxx> 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@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/