[e2e] Re: Mixed ECN and Non-ECN traffic flows.

Chong Poh Kit thesoothsayer at pd.jaring.my
Fri Oct 11 19:03:52 PDT 2002

comments inline:

On Fri, 11 Oct 2002 13:44:56 -0400, Mutlu Arpaci wrote:

>In addition, for a given max_p, the performance improvement of ECN flows
>increases as the number of NonECN flows increases. 

I found the same thing in my simulations and I think that this is due to the fact that the ECN flows are contending for bandwidth with 
flows that react slower to congestion and suffer multiple RTOs thus giving ECN flows opportunity to dominate the AQMs packet 
marking/dropping probability to favour themselves. Because of the fact that ECN traffic rarely seem to suffer from RTOs, for a flow to be 
controlled at throughput, T bps, ECN traffic needs a higher marking probability as opposed to non-ECN traffic.

>This second point implies
>that as the traffic load increases, the NonECN connections are punished more
>severely than ECN flows."

My opinion on this is because non-ECN traffic will suffer many more RTOs severely affecting their throughput and even worse performance in 
their goodput.

>The question of "fairness" regarding ECN vs non-ECN flows is not
>straightforward in my opinion, because one can argue that ECN-flows should
>outperform non-ECN anyway (otherwise what's the point?). This may also
>promote the usage of ECN in the network. Both ECN and non-ECN based AQM
>implementations aim to avoid congestion in the network, but ECN achieves a
>much higher resource efficiency, and provides better performance to the

Yes, ECN flows should outperform non-ECN flows but I'm wondering if this should involve non-ECN flows having to suffer a performance 
degradation during the transition period from non-ECN to ECN traffic.
I totally agree with the implementation of ECN because of its inherent advantages but I was wondering if there is a need to protect non-ECN 
traffic during this transition period.



P.K. Chong
Post-graduate Student
Multimedia University, Malaysia
Tel:6016-3174831 (M) / 603-83125373 (Lab) / 603-90768272 (H)
6:45:29 AM 12/10/2002

More information about the end2end-interest mailing list