Re: 2.6.17-mm6

[Eric W. Biederman]

Andrew Morton <akpm@xxxxxxxx> writes:

> On Wed, 05 Jul 2006 23:42:00 -0600
> ebiederm@xxxxxxxxxxxx (Eric W. Biederman) wrote:
>
>> So I suspect that we need to de-percpuify kernel_stat.irqs.
>
> I think so.  We do:
>
> 	struct irq_desc *desc = irq_desc + irq;
>
> 	kstat_this_cpu.irqs[irq]++;
>
> followed immediately by
>
> 	spin_lock(&desc->lock);
>
> false optimisation, or what?


As an optimization  I can't think of a reason.

It is kind of interesting to report that information by cpu.
in /proc/interrupts  (see show_interrupts).

But except for understanding system behavior I can't think of a reason
for reporting that information.

It was useful information to have when debugging the irq migration code.

Eric

-
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/