Re: [LOOPS] BOF co-chairs thinking on LOOPS next steps

[Carsten Bormann <[e-mail]>]

On Jul 31, 2019, at 14:56, Wesley Eddy <[e-mail]> wrote:
> 
> In LOOPS tunneling, do different traffic classes wind up in different tunnels, or are they all lumped into the same tunnel?

That depends entirely on the tunnel setup, which is out of scope of LOOPS itself.

A network operator typically will select the traffic that will receive the (relatively speaking, more expensive) LOOPS treatment.  In a host-to-node scenario (that was stressed to be important at the BOF), there may be sufficient explicit configuration to do this as well, or it may be a catch-all.

So LOOPS is meant to operate on an aggregate, not just a finely sliced piece of traffic (or a single flow).

I’m not aware of proposals to have the LOOPS protocol itself handle different classes differently.  However, the actual retransmission decision has some room for adding (unilateral) secret sauce, and that may include looking at the class.

Grüße, Carsten