Re: [patch] Real-Time Preemption, -RT-2.6.10-rc1-mm2-V0.7.7

[Michael J. Cohen]

On Thu, 2004-11-04 at 20:38 +0100, Ingo Molnar wrote:
> * Michael J. Cohen <mjc@xxxxxxx> wrote:
> 
> > threw in your tcp_window oneliner mentioned in another thread and that
> > seemed to curb the lockups I was getting.  xmms+jackd in realtime mode
> > is getting some xruns during any kind of IDE activity. network isn't
> > quite as fussy.
> 
> hm, have you chrt-ed the soundcard IRQ to a fifo priority higher than
> 50?
> 
> 	Ingo
> -
> 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/

on my x86-64, there doesn't seem to be an irq for snd-intel8x0.

optie ~ # cat /proc/interrupts 
           CPU0       
  0:    1406459    IO-APIC-edge  timer
  8:          0    IO-APIC-edge  rtc
  9:          0   IO-APIC-level  acpi
 14:      33574    IO-APIC-edge  ide0
 15:         21    IO-APIC-edge  ide1
177:     624454   IO-APIC-level  eth0
185:     286001   IO-APIC-level  libata, ehci_hcd, ohci_hcd, ohci_hcd
193:      37964   IO-APIC-level  AMD AMD8111
NMI:          0 
LOC:    1406207 
ERR:          0
MIS:          0

ps ax doesn't seem to show anything sound-related except jackd so I
tried chrt -f  75 jackd -R -d alsa -P -HMm -z s -o 6

result during an emerge metadata on V0.7.13:

**** alsa_pcm: xrun of at least 133.973 msecs
**** alsa_pcm: xrun of at least 78.544 msecs
**** alsa_pcm: xrun of at least 245.494 msecs

*much* better but we're shooting for 0 xruns, no?

------
Michael Cohen

-
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/