[Web10g-user] web10G/web100 result verification

[rapier]

Mojgan,

We do not, at this time, have any published results absolutely verifying 
the metrics. However, internal testing (verified against numerous 
tcptrace runs) have assured us that the results are accurate. That being 
said, there have been instances in which some metrics had been 
overcounted. These errors are picked up quickly and resolved (case in 
point, a recent set of changes included to address some efficiency 
issues results in double counting slow starts in BIC and HTCP. This was 
discovered last Friday and resolved yesterday). Fortunately the code 
lends itself pretty well to independent analysis and you can clearly see 
where the counters are being incremented. We've had outside partners 
working with the code (quite extensively) and they've verified to their 
satisfaction that the results are correct.

I'm sorry that we cannot provide you to any published sources but we 
simply haven't had the time to formalize our previous results.

On 8/23/13 9:36 AM, Mojgan Ghasemi wrote:
> Hi,
> I was wondering how the web10G project and web100 project verified the correctness of their measurements in the first place.
> I'd really appreciate it if you could give me a link or something…
>
> Regards,
> Mojgan Ghasemi
> _______________________________________________
> Web10g-user mailing list
> Web10g-user at web10g.org
> https://lists.psc.edu/mailman/listinfo/web10g-user
>
> To UNSUBSCRIBE visit https://lists.psc.edu/mailman/unsubscribe/web10g-user
>