two NIC on 2 core system (scheduling problem)
Bartosz Giza
gizmen at blurp.pl
Thu Oct 30 05:51:23 PDT 2008
Wednesday 29 of October 2008 14:34:05 Alexander Motin napisał(a):
> Bartosz Giza wrote:
> > So now i am lost again. If packet filtering on bge card is counted to
> > irq17: bge0 process so i think it should use more cpu.
> > From what you wrote there should be no difference for me if card use
> > tasq or irq. Those processes do exactly the same thing? If that is true
> > so why there is so much difference in cpu usage:
> >
> > 20 root 1 -68 - 0K 8K - 0 161:01 18.75% em0
> > taskq 21 root 1 -68 - 0K 8K WAIT 1 100:10 5.47%
> > irq17: bge0 23 root 1 -68 - 0K 8K WAIT 0 75:31
> > 2.98% irq16: fxp1
> >
> > If what you wrote is true that overhead of incomming packet on bge0
> > should be counted to irq17: bge0
> > So don't understand why there is so big cpu usage on em0. From what you
> > are saying irq17 and em0 taskq should have similar usage. Even more
> > bge0 passes about two times more traffic than em0. I simply don't
> > understand this.
> >
> > So don't understand why there is so big cpu usage on em0.
>
> Have no idea, there are too much possibilities to answer without
> profiling. Different incoming packet rates, different firewall match
> patterns in opposite directions, different card's hardware at least. I
> have noticed that even different types of em cards may have twice as
> different CPU usage due to using different interrupt moderation
> techniques.
THanks for all hints that you gave me. I have found what cause this high cpu
usage.... ipfw :) I have a lot of rules in ipfw and actually i have tune
them up and after that em0 taskq process sterted to use less cpu(similar to
bge0). It was bad firewall design
Could you tell me which chipset from intel would you recommend or you know
that is best from all that you tested.
Once again thanks for answers :)
More information about the freebsd-net
mailing list