> > It's worse than that
> Than what? Surely you just sumarised what I said :)
The point was that the 2 camps had each for good reasons, a maximum (in
Telco case) and a mimimum (in Data case) which should not be breached, and
they were mutually incompatible.
Neither side was technically satisfied, it wasn't just bruised ego's.
> However that can easily be changed - I am currently playing with an MTU
> of around 100 in order to get reasonable throughput on UoN's student
> network with the stupid levels of packet loss being experienced by
> myself and my neighbours... :)
Huh, something very wrong here, if you need to do that...
Shouldn't your Adaption Layer be hiding this from you? (The AAL3/4 saga is
another example, of why you shouldn't try and design by commitee). AAL5
ought to allow sending of variable (sane) length packets, which are
fragmented into cells transparently.
If you're seeing an MTU of 100 at the OS level, it's way way tooo low! I
would have though something like 100x or 200x cell size (or the FDDI MTU)
would be standard.
ATM does have a place in high performance WANs, but really for a LAN
Ethernet (Fast or Giga) will offer best price/performance.
Rob
--------------------------------------------------------------------
http://www.lug.org.uk http://www.linuxportal.co.uk
http://www.linuxjob.co.uk http://www.linuxshop.co.uk
--------------------------------------------------------------------
This archive was generated by hypermail 2.1.3 : Thu 22 Nov 2001 - 13:12:16 GMT