Has anyone had problems with using current Intel quad ethernet cards for packet capture? As a proof-of-concept test we bought an Intel PWLA8494GT and hooked it up to some Network Critical taps. There was a very strange issue with corruption of the captured packets. The *only* issue (but it's a big one) is that the source IP on some captured packets is munged. As far as I can tell that's the *only* issue with the packet captures - no other data is corrupted.
Oh, and to rule out other issues:
1. Corruption seen both when using network taps and when using a port
span/mirror (so it's not the taps).
2. Corruption *not* seen using the on-board broadcom nics of the test
host (so it's not the box).
So I'm pretty sure we narrowed it down to the card. We tried the card in
an indentical host and saw the same problems.
I thought it might be a driver issue - I tried both gentoo and FreeBSD (not sure how different the drivers are) just to see if it mattered at all and it didn't. Much googling didn't show this to be a known issue - just wondering if anyone else has seen it? Other recommendations welcome - the next step is, I suppose, a broadcom-based PCI-X card. (I've got some old pizza boxes I'm trying to repurpose as network probes.)
Thanks,
John
Hello John ,
Has anyone had problems with using current Intel quad ethernet cards for packet capture? As a proof-of-concept test we bought an Intel PWLA8494GT and hooked it up to some Network Critical taps. There was a very strange issue with corruption of the captured packets. The *only* issue (but it's a big one) is that the source IP on some captured packets is munged. As far as I can tell that's the *only* issue with the packet captures - no other data is corrupted.
Oh, and to rule out other issues:
1. Corruption seen both when using network taps and when using a port
span/mirror (so it's not the taps).
2. Corruption *not* seen using the on-board broadcom nics of the test
host (so it's not the box).
So I'm pretty sure we narrowed it down to the card. We tried the card in
an indentical host and saw the same problems.
I thought it might be a driver issue - I tried both gentoo and FreeBSD (not sure how different the drivers are) just to see if it mattered at all and it didn't. Much googling didn't show this to be a known issue - just wondering if anyone else has seen it? Other recommendations welcome - the next step is, I suppose, a broadcom-based PCI-X card. (I've got some old pizza boxes I'm trying to repurpose as network probes.)
Thanks,
John
Does this device provide 4 unique mac-addresses ? Reason for the question is some old(I mean old) multiport cards presented a single mac-address because the were driven by a single 'Switch chip' . Just a thought . I've been looking a the Intel site gandering over the overview & have not seen anything to relieve my concern . But one Hopes they have learned not to create themselves such a problem .
Hth , JimL
Yea cards are default for separate physicals MACs, since they are
supported by individual net chips. The only time one would see a
"logical" Mac, is when the ports are trunked, and this is driven by
software.
Jay Murphy
IP Network Specialist
NM Department of Health
ITSD - IP Network Operations
Santa Fe, New Mexico 87502
Bus. Ph.: 505.827.2851
"We move the information that moves your world."
One more note.... it is a bridging chip, not switching, that is resident
on the board that is the communicator to the other NIC chipsets.
Jay Murphy
IP Network Specialist
NM Department of Health
ITSD - IP Network Operations
Santa Fe, New Mexico 87502
Bus. Ph.: 505.827.2851
"We move the information that moves your world."
Dumb question... It sounds like you've only used the card in packet
capture mode (i.e. promiscuous mode). Have you tried testing the card
just for normal host-to-host network flows? Maybe you have a bad
card?
If you still see problems on host-host flows, it's more likely to be a
bad card rather then a bad driver. (Given that a driver that can't
handle host-host flows is going to be obvious pretty quickly.)
Good Luck,
Bill Bogstad
Hello,
Has anyone had problems with using current Intel quad ethernet cards for
packet capture? As a proof-of-concept test we bought an Intel PWLA8494GT
and hooked it up to some Network Critical taps. There was a very strange
issue with corruption of the captured packets. The *only* issue (but it's
a big one) is that the source IP on some captured packets is munged. As
far as I can tell that's the *only* issue with the packet captures - no
other data is corrupted.
...
So I'm pretty sure we narrowed it down to the card. We tried the card in
an indentical host and saw the same problems.
About three years back we had an issue with a dual-port E1000 NIC
in Intel 7230NH based 1U servers. Together with the knowledgeable
folks at iXsystems we tracked that down to a PCI riser card issue. The
'default' riser was the standard PCB 1U with perpendicular female PCI
connector. Using these we saw checksum mismatches on many packets using
FreeBSD. After replacing this riser with another one that has a flat
ribbon cable to draw more power from an adjacent PCI slot all works well.
We did similar elimination troubleshooting: the board worked fine, the
card worked fine, the card worked fine when sticking it into the slot
while the case was open. Just when using the riser we had trouble.
-andreas