[Bloat] quic's spin bit proposal

Jesper Louis Andersen jesper.louis.andersen at gmail.com
Fri Dec 15 12:06:34 EST 2017


On Tue, Dec 12, 2017 at 9:47 PM Dave Taht <dave.taht at gmail.com> wrote:

>
> In a world where quic is 7% of all traffic presently (wow, I didn't
> know)...
>
>
BitTorrent's MicroTP (uTP) had about 15% at some point as well. This was
especially scary as:

* it used the then not-fully-understood LEDBAT congestion algorithm.
* the de-facto implementation wasn't too well understood and there no
competing implementations in order to understand interoperability.
* there were no formal process when it was created.
* for simplicty it dropped half-open connections. But implemented that in a
slightly faulty way.

I know, because I had an experiment where I did an Erlang-implementation of
the protocol.

At least QUIC seems to be getting some process now, which is good.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://lists.bufferbloat.net/pipermail/bloat/attachments/20171215/b6dff227/attachment.html>


More information about the Bloat mailing list