Re: 2.6.13-rt12: irqs hard off for 657 usecs

[Ingo Molnar]

* Lee Revell <rlrevell@xxxxxxxxxxx> wrote:

> > The max latency is close to the period of the timer IRQ.  So either it's
> > an instrumentation bug or something really disables IRQs for up to 1/HZ
> > seconds.
> 
> I can no longer reproduce this with 2.6.14-rc4-rt1.  It seems to have 
> been a real IRQs disabled bug (not an instrumentation bug) as I was 
> also getting xruns with 2.6.13-rt12.

ok, please re-report if it occurs again. I havent fixed any preemption 
bug since -rt12, but maybe as a side-effect of other things? Some false 
positive latencies were fixed in the latency tracer, but since you also 
got xruns, they must have been real latencies. (albeit saving a long 
false-positive latency trace can cause a latency by itself!)

	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/