|
Dusten Splan wrote:
I thought that this was solved with the 2.4 kernel, because it was meant to
be multithreaded. I'm running 2.4.20 with the newest LVS. Maybe I need to
run 2.5 but this is a production machine. Has anyone tried LVS on 2.5?
If 2.5.x doesn't eat your disk, it works ;). But over here a Xeon Dual with HT
(2 "virtual" processors) and LVS works like a charm under 2.4.x. I had to patch
a few things though, which, however should not relate to irq affinity problems.
I have tried the irqbalance and that doesn't seam to be helping any, Oh and
does anyone know of a web page for that patch. I guess I just might get a
3GHz box and forget the hole smp thing. Here's a sample of what mpstat has
to say about the hole thing.
I never played with irqbalance, so I don't know. Could you send me your .config,
please?
03:10:05 PM CPU %user %nice %system %idle intr/s
03:10:06 PM all 0.00 0.00 12.00 88.00 19841.00
03:10:06 PM 0 0.00 0.00 23.00 77.00 19748.00
03:10:06 PM 1 0.00 0.00 1.00 99.00 100.00
Now which interrupt is mostly imbalanced, is it the e1000 one? You could modify
the smp_affinity of this interrupt to release the processor. Let me know if it
works for you. Read up on it at ../linux/Documentation/IRQ-affinity.txt.
Best regards,
Roberto Nibali, ratz
--
echo '[q]sa[ln0=aln256%Pln256/snlbx]sb3135071790101768542287578439snlbxq' | dc
|
