On 10/15/05, Joe Nardone <jnardone at gmail dot com> wrote:
> Basically, the Firebox left the Nokia in the dust. Using iperf, I got
> between 74-88 mbit/sec between the networks. It also left the WAN responsive
> in other runs of the test (i.e. the box wasn't crushed). The Nokia did FAR
> worse, never exceeding 28 mbit/sec in either direction (LAN->OPT1 or
What are those results without polling?
I have an IP110 but haven't ever included it in any of my performance
testing. I would presume that because it's very similar to a WRAP or
4801, though with much better NIC's (or should be much better...Intel
fxp's in general are much better than the sis NIC's on the WRAP and
Glad to see an echo of "check for duplex mismatch". :) Though those
results are almost certainly too high for that. With a mismatch on
100 Mb, you'd end up with maybe 10 Mb tops and would see the network
become almost completely unresponsive.
> 1) CPU. Even though it has the faster clock speed, is the Geode that much of
> a dog? This is definitely part of the problem -- the CPU load spiked during
> the transfers on the Nokia. The Firebox II's P200 is just a standard socket7
The WRAP and 4801 have the same CPU and can exceed 40-45 Mb without
polling. And with lesser NIC's. CPU load spike suggests polling
wasn't enabled or at least not functioning properly.
> 2) Ethernet. The Nokia has "Intel 82559ER Embedded 10/100 Ethernet" (fxp)
> ports, the Firebox has "Intel 21143 10/100BaseTX" (dc) ports. Is there
> anything in the driver implementation that would make it so lousy?
nope, fxp's are the best performing NIC's on FreeBSD. The ones in the
IPxxx's are slightly abnormal, but I wouldn't expect that kind of a
> I guess there's a 3rd possibility -- the Nokia I have has some kind of
> problem, but I don't think that's the case.
kinda doubt that.