Alex Rubenstein <alex@nac.net> wrote:
It can also be argued that at some point, the speed capabilities of the core router scheme will not be able to keep up with currently technology.
Yawn. What do you think the speed capabilities of "core router scheme" are? You know, some very fast routers are rumored to ship this year.
It's my opinion that at some point a 'routed' core will no longer be feasible, and it will be switched -- using what mechanism, I don't know (ATM? MPLS?).
ATM, MPLS (or whatever idiotic virtual circuit scheme there is) can not increase switching or routing capacity of boxes, period. These only serve to screw up dynamic adaptive routing, forcing carriers to rely on wasteful dual-ring SONET redundancy instead (and it still doesn't protect from a switch crashing every few minutes). --vadim
On Thu, Feb 10, 2000 at 05:45:33PM -0800, Randy Bush wrote:
What do you think the speed capabilities of "core router scheme" are? You know, some very fast routers are rumored to ship this year.
damed hard to move packets on rumors
haven't you heard -- it's RFC 3133t -- A Standard for the Transmission of IP Datagrams on Vaporware. ;->
Alex Rubenstein <alex@nac.net> wrote:
It can also be argued that at some point, the speed capabilities of the core router scheme will not be able to keep up with currently technology.
Yawn. What do you think the speed capabilities of "core router scheme" are? You know, some very fast routers are rumored to ship this year.
As rumoured much faster traffic levels. Probably the need will eclipse the ability, soon enough.
It's my opinion that at some point a 'routed' core will no longer be feasible, and it will be switched -- using what mechanism, I don't know (ATM? MPLS?).
ATM, MPLS (or whatever idiotic virtual circuit scheme there is) can not increase switching or routing capacity of boxes, period. These only serve to screw up dynamic adaptive routing, forcing carriers to rely on wasteful dual-ring SONET redundancy instead (and it still doesn't protect from a switch crashing every few minutes).
No comment on this, as I have none.
participants (4)
-
Alex Rubenstein -
Eric Kozowski -
Randy Bush -
Vadim Antonov