The Routing Over Large Clouds Mailing List Archive by date

[Dilip Kandlur <kandlur@watson.ibm.com>]

Andrew,

 > The implication is that QoS requirements would be considered as a
 > guide to setup SVCs.  Yes, there is also a belief that an SVC would
 > provide better QoS (e.g. delay) since it avoids IP level handling
 > costs at intermediate nodes.

 I don't think we should be making assumptions like that in an architectural
 document: that is an implementation issue. I certainly know of some ATM switches
 with higher latency (under some traffic conditions) than routers .... :-)

We can, however, make the assertion that the QoS characteristics of
the ATM SVC would be based on the QoS requirements of the higher
layers.  The belief that ATM SVCs are more desirable than multiple IP
hops is one that is in line with the objectives of ROLC.

-- Dilip.