[Openstack-operators] Intel 10 GbE / bonding issue with hash policy layer3+4

Sascha Vogt sascha.vogt at gmail.com
Tue Mar 29 10:57:40 UTC 2016


Hi Kevin,

Am 24.03.2016 um 16:44 schrieb Fox, Kevin M:
> We saw a problem recently with layer3+4. We're still working on it,
> but a possible datapoint:
> We had them connected through a cisco switch and saw iperf only use
> 50% of capacity about 50% of the runs, and most of the rest of the time
> full. Seemingly randomly.
> 
> We connected the two nodes directly together with layer3+4 balancing
> and it hit full performance every time. so in our case, it has something
> to do with the switch in the middle.
> 

For now I would rule out the switch (Dell, Force10 S4810 with Dell
Operating System Version:  2.0 and Dell Application Software Version:
9.7(0.0))

We have full performance under Kernel 3.16 and also when on Kernel 4.2.0
and the Server on 4.2.0 is on the receiving side. So the links are
definetly up and LACP working as expected (from a switch point of view).

Thanks for the feedback anyway,
Greetings
-Sascha-



More information about the OpenStack-operators mailing list