I've never performed a verification of netperf as a task - I started using
it to solve a problem and results at the time seemed to map within a couple
of percent or so of the two analysers I was using. Subsequent tests where an
analyser was in parallel have never caused me to react negatively to
netperf's results. I suppose that I only really use netperf to prove I'm
right/wrong or do comparative tests. The only time where errors are large
are when networks are being deliberately congested/corrupted in which case
netperf gives strange answers.
Andy Leigh
Senior Planning Engineer, BBC Strategic Network Developments
> -----Original Message-----
> From: Rick Jones [SMTP:raj@cup.hp.com]
> Sent: Thursday, August 20, 1998 6:06 PM
> To: netperf-talk@hpisrdq.cup.hp.com
> Subject: [Fwd: Verification of netperfs results.]
>
> All my verifications of netperf have been less sophisticated than what
> is mentioned below.("Yep, that seems reasonable." - though ages ago I
> may have checked with an HP 4972 on a thinlan network) Anyone else done
> anything more sophisticated?
>
> rick
> --
> these opinions are mine, all mine; HP might not want them anyway... :)
> feel free to email, or post, but please do not do both...
> my email address is raj in the cup.hp.com domain... << Message:
> Verification of netperfs results. >>