Hi, Lucas,

On Mon, Oct 19, 2020 at 4:31 PM Lucas Pardue <[email protected]>
wrote:

>
>
> On Mon, 19 Oct 2020, 22:25 Florin Baboescu, <[email protected]>
> wrote:
>
>> Hi Lucas,
>>
>> Based on how the ATSSS-LL sender is implemented, in-order delivery of the
>> packets may not be guaranteed at the receiver side once multiple paths are
>> used.
>>
>
> What packets are you talking about here? Why does in-order delivery
> matter? TCP and QUIC are designed to accommodate reordering. But QUIC
> specifically offers no ordering guarantees across different streams.
>

This is in Mirja's slides (not uploaded yet), but Release 16/Phase 1
ATSSS uses MPTCP to provide multipath support for TCP traffic, and a
different protocol called ATSSS-LL at a lower level of the protocol stack.

We talked about this in
https://tools.ietf.org/html/draft-bonaventure-quic-atsss-overview-00#section-5.3,
which says

   Techniques to provide ATSSS are classified by the 3GPP into two
   flavors: (1) higher-layer techniques which operate above the IP layer
   (e.g., MPTCP), and (2) lower-layer techniques which operate below the
   IP layer.

Most of the Release 17/ Phase 2 conversations I've been involved with have
centered on QUIC-based techniques, analogous to MPTCP, with ATSSS-LL just
carried over from Release 16/Phase 1.

Does that help?

Best,

Spencer




> Cheers
> Lucas
>
>
>
>>

Reply via email to