ATM Wide-Area Networks (was: sell shell accounts?)

From: Dave Siegel <dave@rtd.net>
Subject: Re: ATM Wide-Area Networks (was: sell shell accounts?)
To: salo@msc.edu (Tim Salo)
Date: Tue, 23 Jul 1996 10:22:23 -0700 (MST)
Cc: dave@rtd.net, agislist@interstice.com, nanog@merit.edu
  [...]
Even
with the improved buffering, if you fill your pipe into the ATM switch,
your ATM switch still becomes a packet shredder, compared to the more
graceful packet drops seen on a clear channel line.
  [...]

"Good" ATM switches are doing Early Packet Discard and Partial Packet
Discard. You can ask your favorite switch vendor for details, or look
at the following for a nice summary:

  http://www.fore.com/html/atm-edu/whitep/FTBMWP.html

-tjs

I am not quite sure how an ATM switch becomes a "packet shredder," or
even what a "packet shredder" is...

An ATM switch shreds a 1500 byte IP packet into 29 ATM cells of 53 bytes
each. If an ATM has a 5% loss, i.e. 1 in every 20 cells is lost, then 0%
of the IP traffic will get through. This is a worst case kind of scenario
but I'm sure you can see other scenarios where the 53 byte ATM transport
could cause problems. For instance, if the first ATM cell containing a new
IP packet gets lost, the switch may continue to transmit the other 28
cells in the packet even though these are now useless garbage data that
don't need to be forwarded.

The 7 layer model can be useful as an intellectual tool to separate the
different mechanisms required to implement networks but it is wrong to
assume that arbitrary combinations of layers can operate efficiently and
effectively in the real world.

Of course, ATM switch vendors are learning how to make their equipment
handle IP packets better, and then there is Ipsilon http://www.ipsilon.com
RFC 1953 and RFC 1954

Michael Dillon - ISP & Internet Consulting
Memra Software Inc. - Fax: +1-604-546-3049
http://www.memra.com - E-mail: michael@memra.com