Re: 2.5.68-mmX: Drowning in irq 7: nobody cared!

Zwane Mwaikambo (zwane@linuxpower.ca)
Tue, 6 May 2003 06:41:57 -0400 (EDT)


On Tue, 6 May 2003, Alan Cox wrote:

> 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/