Melinda,

I would need a bit more clarity on what is "per circuit".  The mechanism
works by looking at the utilization on individual component links within a
LAG/ECMP.  The port-level queues and packet/byte counters are always
visible to an implementation.

It is possible that some implementations may not be able to control the
flow of traffic in the way that is proposed in the draft (i.e. mapping
specific large flows to an individual component link), but I'm not aware of
any in recent memory (5+ years).

Anoop


On Tue, Sep 10, 2013 at 10:46 AM, Melinda Shore <[email protected]>wrote:

> One issue that's been raised off-list is that there may not be
> sufficient visibility into the per-circuit queues for this to
> be implementable.  Does one of the authors have any feedback
> on this?
>
> Melinda
> _______________________________________________
> OPSAWG mailing list
> [email protected]
> https://www.ietf.org/mailman/listinfo/opsawg
>
_______________________________________________
OPSAWG mailing list
[email protected]
https://www.ietf.org/mailman/listinfo/opsawg

Reply via email to