Hi Abhijan, Carsten,

(Good point, and great measurement paper!)

Yes, this is indeed bad 'news', and a problem.

I agree with Abhijan that a detailed analysis on using TCP Fast Open in
this context, versus long connections aided by (realistic) keep-alive
mechanisms, is definitely needed.

Thanks!

Carles


> On 22 June 2016 at 14:39:52, Abhijan Bhattacharyya
> ([email protected]) wrote:
> That is understood. The point is that, there is an element of doubt
> regarding whether the implementations in reality abide by the given time
> interval or silently times out without the knowledge of the end-points.
> There is no doubt at all :-/
>
> http://conferences.sigcomm.org/imc/2010/papers/p260.pdf
>
> Figure 7, Section 4.2:
>
> "More than half the devices fail to meet the IETF recommended timeout of
> 124 min” 
>
> This study is a few years old, but I would be surprised if the situation
> has become much better.
>
> (Are there newer studies of this type?)
>
> Grüße, Carsten
>
>


_______________________________________________
Lwip mailing list
[email protected]
https://www.ietf.org/mailman/listinfo/lwip

Reply via email to