sorry ... not cut through

Josip Loncaric josip at
Wed May 15 10:54:39 PDT 2002

Greg Lindahl wrote:
> You said this backwards: cutthrough switches ought to be better on
> latency. 
> Cut-through vs. store-and-forward ought not affect bandwidth at all.

I'd second that -- and add that an important reason why people build
store-and-forward switches despite (slightly) worse latencies is to
filter out malformed packets.  Isolating such failures can save the
whole network from an expensive problem (e.g., lost business).


Dr. Josip Loncaric, Research Fellow               mailto:josip at
ICASE, Mail Stop 132C           PGP key at
NASA Langley Research Center             mailto:j.loncaric at
Hampton, VA 23681-2199, USA    Tel. +1 757 864-2192  Fax +1 757 864-6134

More information about the Beowulf mailing list