Re: yesterday

[Masataka Ohta <mohta@necom830.hpcl.titech.ac.jp>]

Cedric;

As I have been documenting that:

  One may still be allowed, though discouraged, to have local
  configuration with dumb end systems and an intelligent proxy. But,
  such configuration should be implemented with a protocol for purely
  local use without damaging the global protocol.

having proxies for really dumb hosts is discouraged but not prohibitted.

But, do it locally.

> Agreed. I think that putting all the informations in the end-hosts would 
> imply an unacceptable
> waste of resources. Moreover, to best take advantage from the BGP 
> routing system, we should
> get access not to only one BGP table but to _all_ the BGP tables of the 
> providers. This is
> clearly unacceptable to put in all the end hosts.

That is clearly unacceptable, though it has nothing to do with my
proposal.

So?

> Of course. NAROS is not limited to just looking at BGP. It can monitor 
> the exit links, check their
> correct utilization, and change accordingly the way it proposes the best 
> addresses.

That's a job already done by the routing system.

We know very well that having a central server for routing
job is a bad idea. Let the job done by routers.

> in a short period. Without lifetimes, the NAROS load would be rapidly 
> unacceptable.

That is one reason against proxies, but there are a lot more.

> Of course this does not mean that this timeout is always the best one. 
> This is always a
> trade-off between the server load and the traffic engineering quality.

No. Proper timeout is determined by applications.

							Masataka Ohta