[OT] Re: IRQ Layout.
Matthew Vanecek (mev0003@unt.edu)
Tue, 30 Nov 1999 10:07:52 -0600
Ingo Molnar wrote:
>
> On Tue, 30 Nov 1999, Arjan van de Ven wrote:
>
> > > The Linux IOAPIC code just uses the IRQ layout that is present in the
> > > system, we have no influence on this.
> >
> > One day, we may want to change this. For one, on a SMP system with 2
> > NICs, one might want each of the NICs delever their interrupt to a
> > separate (but for each NIC always the same) CPU. [...]
>
> the point is that we _cannot_ change this. The IOAPIC pins are often
> directly connected to respective PCI-bus interrupt pins. If the card sends
> an INT#D then there is no way we can ever change this. This is a physical
> property. Unless every Linux distribution includes a tiny remote
> controllable robot equipped with a screwdriver and a soldering iron, i
> doubt the kernel could ever get around this.
What about all that work that's being done on so-called nano-bots? ;)
Seriously, for Intel-based systems, it would be really nice to be able
to up the number of IRQs available (in all systems), and to bind
<whatever> on IRQ <whatever> to a specific processor (in SMP systems).
--
Matthew Vanecek
Course of Study: http://www.unt.edu/bcis
Visit my Website at http://people.unt.edu/~mev0003
For answers type: perl -e 'print
$i=pack(c5,(41*2),sqrt(7056),(unpack(c,H)-2),oct(115),10);'
*****************************************************************
For 93 million miles, there is nothing between the sun and my shadow
except me. I'm always getting in the way of something...
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/