Re: 2.5.59-mm5: cpu1 not working

From: Arador (diegocg@teleline.es)
Date: Fri Jan 24 2003 - 18:41:01 EST


On Fri, 24 Jan 2003 14:44:17 -0800
"Kamble, Nitin A" <nitin.a.kamble@intel.com> wrote:

> Hi Arador,
> There is nothing wrong with the /proc/interrupts output. The kirq patch balances the interrupts load only when there is sizable load imbalance, which you don't seem to have. In such cases interrupts will not move around.
> Try generating lots of interrupts load in the system, and then the interrupts will get distributed across CPUs.

true, sorry for the noise
After ping -f i got
11: 1446896 1452624 IO-APIC-level eth0

cat /dev/hda was not enought to "distribute" the interrupts it seems.

btw, ping -f hits 24000-29000 int. per second; adding
a cat /dev/hda slows it down to 20, 22000. Shouldn't
it redistribute the interrupts in a way you get > 29000?
(note that i've not idea of this thing)

Diego Calleja
-
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/



This archive was generated by hypermail 2b29 : Fri Jan 31 2003 - 22:00:13 EST