[Bloat] different speeds on different ports? (benchmarking fun)

Stefan Alfredsson stefan.alfredsson at kau.se
Thu Sep 21 06:58:39 EDT 2017


On 2017-08-30 07:15, Aaron Wood wrote:

>
> The current hypothesis that we have is that this is due to either 
> traffic class, or the ports that traffic are running on.  I've ruled 
> out the ping streams, as a parallel set of netperf tcp_maerts 
> downloads has the same 120Mbps roof.

Also think of server differentiation (maybe full capacity to known 
measurement servers, shaped for other destinations). Does dslreports 
have flent/netperf responders on their servers as well?

>
> It would be interesting if we could run some netperf tests using port 
> 80/443 for the listening socket for the data connection (although if 
> doing deep-packet inspection, we might need to use an actual HTTP 
> transfer).

UDP 443 (QUIC) would also be interesting for comparison.

/Stefan



More information about the Bloat mailing list