🚀 go-pugleaf

Neither Dejanews nor Rogers news server has the post Vic sent (to me
perhaps?)
and that Michael is responding to here. If anyone could email that
post to
mreid@rogers.wave.ca it would be appreciated...

Thanks for the URLs, I had just asked for such references in another
post.

In article <slrn5vpu82.5n.mcr@amaterasu.sandelman.ottawa.on.ca>,
  mcr@sandelman.ottawa.on.ca wrote:

>Vik Wrote:
> >You cannot expect to provide real-world performance figures from
> >one host.  Accordingly, the best you can do is give a time-averaged
> >estimate by RTT method of the effective throughput for
unidirectional
> >communcation to an ISP along the link from ISP to network provider.
> >Of course, this is of only limited value for obvious reasons.
>
>   Mike, please listen to Vik, he knows what he is talking about.

I'm happy to hear anyone's views on the subject. I hope I made it
agonizingly
clear that I have posted multiple disclaimers to that effect and that
I have
intentions of implementing distributed performance measurement. I
don't
relish the alternative of removing my web pages just because some
people may
not read the disclaimers and misinterpret the very limited data I have
at
this time.

> >And I don't mean to seem antagonistic to the idea, because
> >I am not.  I just maintain that the problem is far more complicated
> >than has been suggested, and there is very little information
> >that can be gained from a single host, regardless of method.

Here's a quote from my performance testing page at
http://home.on.rogers.wave.ca/mreid/ottisp/perftest.html :

 .Comprehensive testing of ISP performance levels is a daunting task.
There are
 .many aspects to performance and no single test tells a complete
story.
 .Furthermore,
 .there are many uncontrollable aspects of the test environment. Test
results
 .will often be different depending on when and from where they are
done. More
 .complete
 .and comprehensive testing would require the use of multiple test
locations and
 .continuous testing over a period of time to ensure the statistical
validity of
 .the tests.


If I've suggested anywhere on my pages, the newsgroups or elsewhere
that
performance testing is not fraught with difficulty, please let me know
and
I'll be more than happy to retract the statement. If my original
posting
suggested this to you or anybody because of it's brevity or lack of
disclaimers
in the original posting itself, then I humbly apologize.

Regards,
Mike Reid.

-------------------==== Posted via Deja News ====-----------------------
      http://www.dejanews.com/     Search, Read, Post to Usenet