> With APIC at least it doesnt suprise me the least. The IRQ hack seems
> extremely racey. Remember on most systems (especially with PIII type
> APIC) IRQ delivery is asynchronous to the bus so you get
>
> IRQ arrives
> sound card
> loop
> clean up IRQ
> IRQ sent
> still more work, do it
> done
> HANDLED
>
> IRQ arrives
> sound card
> Umm duh no work for me
> NOT HANDLED
>
> Whine
>
> For anything where you get pairs of close IRQ's
Shouldn't this also be observed more easily on P4/xAPIC since you can have
a pending vector in the IRR and ISR whilst the core processes one.
Zwane
-- function.linuxpower.ca - 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/