Hey all,
I went to Justin's link and followed a few more and found this:
http://lsr.internet2.edu/
That link not only has the original text that the news article quoted, but
it explains that this is a contest and gives the rules for the contest. I
will leave it to the greater minds in the group to interpret the rules...
:-)
Geoff Mossburg
-----Original Message-----
From: Justin Kinney [mailto:[EMAIL PROTECTED]
Sent: Friday, March 07, 2003 8:09 PM
To: [EMAIL PROTECTED]
Subject: RE: Intenet Speed Record: What am I missing? [7:64767]
Actually, the application they used was straight tcp. You can get it at
http://www.cnd.gatech.edu/rapid/.
Again, I think the message is that this was done over a switched network,
and they did this over a 196msec, 6 hop path.
Justin
-----Original Message-----
From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED]
Sent: Friday, March 07, 2003 5:31 PM
To: [EMAIL PROTECTED]
Subject: RE: Intenet Speed Record: What am I missing? [7:64767]
s vermill wrote:
>
> John Neiberger wrote:
What you're missing is the cluelessness of news reporters and the public
maybe...
> >
> > Here's a quote from something I just saw in the news:
> >
> > "Scientists at the Stanford Linear Accelerator Center used
> > fiber-optic
> > cables to transfer 6.7 gigabytes of data -- the equivalent of
> > two DVD
> > movies -- across 6,800 miles in less than a minute.
Well, nobody actually watched the movies! Now a real feat would be to send
it over in that time and have someone watching it.
> >
> > Pushing the tech envelope
> > The team was able to transfer uncompressed data at 923
> megabits
> > per
> > second for 58 seconds from Sunnyvale, California, to
> Amsterdam,
> > Netherlands. That's about 3,500 times faster than a typical
> > Internet
> > broadband connection. "
Whoopee!
> >
> > Okay, 923 Mbps is a speed record? An OC-48 is roughly 2.6
> > times faster
> > and they're fairly common. What's the big deal about 923
> > Mbps? I
> > realize that I must be missing something very obvious here but
> > I don't
> > understand the milestone they're claiming to have passed.
> >
> > Admittedly, I'm about to fall asleep in my chair but that's
> par
> > for the
> > course with me. :-)
> >
> > So, what's the big deal? In a world of OC-192 and up, why is
> > > earth shattering?
> >
> > John
> >
>
> John,
>
> It clearly isn't a bandwidth record in terms of bps. I'm aware
> of as many as a few hundred OC-192s being "DWDMed" onto a
> single fiber. I suspect this has to do with the
> control/reliability mechanisms associated with the file
> transfer.
I suspect that they ignored the control issues. :-) If they used FTP/TCP/IP,
they probably started measuring after the control and data 3-way handshakes
and set the TCP window as huge as possible??
They probably rolled their own transfer mechanism, I would guess, but maybe
not. TCP could be pretty good for this....
Priscilla
> I read the same article. Nothing was said about the
> protocols involved (it was packaged for mass consuption
> evidentally). It was likely FTP/TCP/IP or something along
> those lines (although a negative ack approach would likely be
> the most effective). I noticed that there were several
> intermediate hops. Don't know if that was a ploy to reduce the
> delay portion of the bandwidth*delay product between any two
> points or if there were other reasons.
>
> Scott
Message Posted at:
http://www.groupstudy.com/form/read.php?f=7&i=64807&t=64767
--------------------------------------------------
FAQ, list archives, and subscription info: http://www.groupstudy.com/list/cisco.html
Report misconduct and Nondisclosure violations to [EMAIL PROTECTED]
