[c-nsp] WRR Confusion on 6748 blades

[Phil Mayers]

On 27/06/12 16:58, John Neiberger wrote:

> I'm still researching this and trying to get to the bottom of it. I
> think we're missing something important that would make this all make
> more sense. I appreciate everyone's help!

Queueing on this platform is complex.

Google "qos srnd" and read the sections on 6500 carefully, if you 
haven't already.

In particular, note that queues don't have bandwidth, they have size and 
weight. The actual rate at which packets leave a queue is a weighted 
function of arrival rate at ALL queues. A queue can absorb a burst in 
excess of the empty rate up to the queue size, with a drop threshold (if 
RED is enabled) controlled by queue size & CoS.

If you are seeing a queue dropping packets, and the offered load into 
that queue is less than egress link speed, then some OTHER queue must 
have a weight AND OFFERED LOAD that is causing the dropped queue to be 
under-serviced.

The 6748 does have DWRR, so you shouldn't be suffering from starvation.

At this point, a "sh queueing int ..." on the egress port would help.

Are you running a "default" QoS config? Are you trusting CoS/DSCP or not?