Messages in this thread | | | Date | Tue, 5 Dec 2006 09:25:53 +0100 | From | Ingo Molnar <> | Subject | Re: v2.6.19-rt1, yum/rpm |
| |
* Karsten Wiese <fzu@wemgehoertderstaat.de> wrote:
> I tweaked latency_trace.c to make freerunning work. Will post later.
ok, please do.
i'm trying to understand your trace:
> Below the trace shows i_usX2Y_usbpcm_urb_complete() running under an > alien context, and this is where jackd starts stalling:
by 'alien context' do you mean softirq--4? That is the following kernel thread:
4 ? S 0:00 [softirq-high/0]
handling HI_SOFTIRQ softirqs, which are the 'highprio' tasklets.
> IRQ_17-308 0D..2 3411063us : deactivate_task <IRQ_17-308> (180 2) > softirq--4 0D..2 3411064us+: __schedule <IRQ_17-308> (180 101) > softirq--4 0.... 3411072us+: i_usX2Y_usbpcm_urb_complete (8 0 dd134) > softirq--4 0.... 3411078us : try_to_wake_up (c011b4ab 0 0) > softirq--4 0D..1 3411079us : __activate_task <jackd-2667> (173 1) > softirq--4 0Dn.1 3411079us : try_to_wake_up <jackd-2667> (173 101) > softirq--4 0Dn.1 3411080us : __schedule (c032a862 0 0) > jackd-2667 0D..2 3411081us+: __schedule <softirq--4> (101 173)
it's running at SCHED_FIFO prio 80.
it's probably this use in sound/usb/usbmidi.c:
tasklet_hi_schedule(&port->ep->tasklet);
so what is your observation - if i_usX2Y_usbpcm_urb_complete() is executed in this tasklet then you are seeing xruns/delays?
Ingo - 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/
| |