On 6/14/12 10:54 AM, Eric Dumazet wrote:
On Thu, 2012-06-14 at 09:22 +0200, Michael Welzl wrote:
One ECN-specific concern that was addressed is that it's often in the
interest of the receiver, but not the sender, to lie about ECN and
simply cheat (reflect "nonono, no congestion at all" back to the
sender). This is addressed by RFC3540, which is experimental and not
really used.
Yes, apparently :(
I tried to restrain myself from self-promoting, but you asked for it :-)
http://heim.ifi.uio.no/~michawe/research/projects/spurious/index.html
There is code! - and there are possible additional benefits from the nonce.
I didn't push for that in the IETF because there is a conflict with
conex (I think? I lost track of all their plans for bits) for using the
bit-combination required by the nonce. And conex is a bigger, better
plan than my "Nonce++" suggestion.
Cheers,
Michael
_______________________________________________
Bloat mailing list
[email protected]
https://lists.bufferbloat.net/listinfo/bloat
