[32841] in North American Network Operators' Group
RE: Packet Loss
daemon@ATHENA.MIT.EDU (Roeland Meyer)
Thu Dec 14 17:35:48 2000
Message-ID: <9DC8BBAD4FF100408FC7D18D1F0922869B35@condor.mhsc.com>
From: Roeland Meyer <rmeyer@mhsc.com>
To: "'Steven M. Bellovin'" <smb@research.att.com>,
Valdis.Kletnieks@vt.edu
Cc: Roeland Meyer <rmeyer@mhsc.com>,
'Scott Bradner' <sob@harvard.edu>, nanog@merit.edu
Date: Thu, 14 Dec 2000 14:30:21 -0800
MIME-Version: 1.0
Content-Type: text/plain;
charset="iso-8859-1"
Errors-To: owner-nanog-outgoing@merit.edu
> From: Steven M. Bellovin [mailto:smb@research.att.com]
> Sent: Thursday, December 14, 2000 1:14 PM
> >> Never under-estimate the bandwidth of a mini-van filled
> with DLT tapes, on
> >> the freeway at 65 mph.
> >> - updated to current - rmeyer - original author unknown
> >
> >Andy Tanenbaum, "Computer Networks", if I remember correctly.
>
> *Much* older -- I first heard it in 1969, and I don't think it was
> orginal then...
I know for certain that it dates back to the pain-frame daze and originally
refered to 9600 baud open-reel tape. It was a true anacdote involving a
chevy impala stationwagon and they needed to get a massive amount of IBM 360
data, from somewhere in Los Angeles to Sacramento. One of the alternatives
was unreliable 300 baud links (1200 baud wouldn't work for some reason).
They chose to use the chevy, they beat the time by days.
I was an MTS-III, at /HAC/C&DP/LB (pre-GM), when I heard it the first time.
I am amazed that, that far back (20 years), I remember that much detail. The
context I heard it in was that we had a similar problem getting some data
from behind the "cactus curtain", in Tuscon, AZ.
If you want to transfer a multi-TB database, a short distance, it still
holds true.
