On Wed, Feb 1, 2012 at 5:18 PM, Juan Tellez <j...@embrane.com> wrote: > We also suspect vswitchd as responsible for dropping packets. > > > > 39: RX packets:494125 errors:0 dropped:0 overruns:0 frame:0 > > 40: TX packets:519707 errors:0 dropped:8357 overruns:0 > carrier:0 > > 46: RX packets:455837 errors:0 dropped:0 overruns:0 frame:0 > > 47: TX packets:485736 errors:0 dropped:10118 overruns:0 > carrier:0 > > 53: RX packets:455547 errors:0 dropped:0 overruns:0 frame:0 > > 54: TX packets:484577 errors:0 dropped:5718 overruns:0 > carrier:0 > > 60: RX packets:455611 errors:0 dropped:0 overruns:0 frame:0 > > 61: TX packets:481385 errors:0 dropped:10404 overruns:0 > carrier:0 > > 67: RX packets:455162 errors:0 dropped:0 overruns:0 frame:0
These stats are coming from your NIC? Assuming yes, it's unlikely that they are caused by OVS directly because those are hardware counters. Since OVS runs before hardware transmit, in order for the packet to be dropped in hardware it would have to already have passed through OVS. What are the outputs of dmesg and ovs-dpctl show? _______________________________________________ discuss mailing list discuss@openvswitch.org http://openvswitch.org/mailman/listinfo/discuss
