[e2e] Is a non-TCP solution dead?

[Stefan Savage]

> > case.  As Savage, et.al. showed in their 1999 CCR paper a receiver
> > can split ACKs and induce the sender into increasing cwnd faster
> > than it should.
> 
> In preventing this, ABC is obviously sane - and sanity in the face of
> a savage attack is a good thing. This is why ABC should go
> standards-track.

Not a pun I hope :-)

FWIW, the ack division attack is also well handled by the Linux behavior
of only increasing the congestion window when the entire segment sent is
acknowledged (i.e. partial packet acks have no impact on cwnd).  I like
ABC, but I'm not sure this should be its raison d'etre.

- Stefan