LVS
lvs-users
Google
 
Web LinuxVirtualServer.org

RE: load-testing with testlvs & ipvs 1.0.4

To: Peter Mueller <pmueller@xxxxxxxxxxxx>
Subject: RE: load-testing with testlvs & ipvs 1.0.4
Cc: "'lvs-users@xxxxxxxxxxxxxxxxxxxxxx'" <lvs-users@xxxxxxxxxxxxxxxxxxxxxx>
From: Julian Anastasov <ja@xxxxxx>
Date: Thu, 18 Jul 2002 00:08:03 +0000 (GMT)
        Hello,

On Wed, 17 Jul 2002, Peter Mueller wrote:

> OK, I was just following the first example I saw.  I assume the cycles are
> wasted because REJECT sends a packet back saying "no SYN for you!" (or
> something like that), right?

        Sort of :) ipchains/iptables filtering is the most
effective way to silently account the flood.

> >     May be you have PCI 33MHz, ipchains rules, etc. The other
> > problem could be the routing cache performance. You can reduce the
> > number of clients to 10 just to see what happens.
>
> I think I have PCI 33mhz.  The director is 2.4.x kernel with essentially no
> iptables rules.

> Is this PCI bus the cause for 87% utilization at ~21000 packets/sec?

        Yes, in my tests I observe speed x 2 when on PCI 66MHz.

> Peter

Regards

--
Julian Anastasov <ja@xxxxxx>



<Prev in Thread] Current Thread [Next in Thread>