In message <52D5568F.2070600@xxxxxxxxxxxxxxx> "Joel M. Halpern" writes: > Isn't that basically the problem of the inner traffic sender, not the > problem of the tunnel that is carrying the traffic? > Asking tunnel's to solve the problem of applications with undesirable > behavior seems backwards. > > Yours, > Joel Or perhaps the job of some form of very fair AQM like SFQ. Any tunneling complicates the AQM notion of what a flow is and therefore may affect its assessment of what is fair in bad ways. This too is out of scope for a draft-ietf-mpls-in-udp discussion. Curtis > On 1/14/14 10:20 AM, Eggert, Lars wrote: > > On 2014-1-14, at 15:20, Stewart Bryant <stbryant@xxxxxxxxx> wrote: > >> Yes, the inner (real) transport header is the only meaningful place > >> to apply congestion avoidance. > > > > But what if the inner traffic isn't congestion controlled? > > > > Lars