I'm at my wits end with this, Citrix is stumped, Dell is stumped, and with
the supply chain issues the way they are we can't just yank these out in
favor of X550s. The problem is we have a group of Dell R740s with X710
dual-port NICs and the performance is, in a word, awful. Like 5-6 megabit
On 3/14/2022 8:28 AM, Kevin Bowling wrote:
Fortville (700) has always been a bit of a disaster
(https://cdrdv2.intel.com/v1/dl/getContent/331430?explicitVersion=true),
I'd see if you can press your Intel reps into getting you the 550s or
the 800-series NICs for the unnecessary troubles it's a
I'll give that a try after my day ends, just in case it drops the link. I
had a problem before where I changed some offload settings using ethtool
and the links went hard down and the only way I could bring them back up
was a reboot. I'll let you the results after I make the change.
My kernel
That's interesting! We had issues in the past with LLDP and LACP but it
"only" caused bundles to flap, not some funky speed. I'm trying to re-read
the spec, but I don't see any specific requirements for LLDP to be enabled
for LACP to actually work. I do believe it LACP has its own
That's really weird.
- How are you measuring performance? iperf?
- Are you able to put a Ubuntu/other OS directly on the R740 and
validate the performance?
We have a lot of X710 with various firmware and I have never seen something
like this.
On Mon, Mar 14, 2022 at 2:49 PM Matthew
The issue was with the integrated LLDP daemon. Disabling it according to
Jesse Brandeburg's excellent recommendation solved the issue that both
Citrix and Dell couldn't figure out. Running the following on all NICs in
the LACP bond brought my performance from 5 megabit to full ten gigabit
line
Wow! That is good to know. We had issues in the past with hardware lldp
agent eating our OS lldp packets.
But never eating the actual data packets!
On Mon, Mar 14, 2022, 7:43 PM Matthew Weiner
wrote:
> The issue was with the integrated LLDP daemon. Disabling it according to
> Jesse
The LLDP FW Agent only “eats” LLDP packets but it can confuse LACP, OVS or
other sw bridges since they expect LLDP info from the TOR. With LACP the bond
sw does not receive anything from the TOR so it might think the port is down.
The FW agent also response back with the same MAC on both ports
Fortville (700) has always been a bit of a disaster
(https://cdrdv2.intel.com/v1/dl/getContent/331430?explicitVersion=true),
I'd see if you can press your Intel reps into getting you the 550s or
the 800-series NICs for the unnecessary troubles it's a much nicer
design.
It's surprising they are
