Is anyone actually USING IP QoS?

Danny McPherson danny at qwest.net
Tue Jun 15 18:27:34 UTC 1999



> Do i miss something 

perhaps :-)

> Please.  Caching is _at least_ as efficient as multicasting (multicasting
> _is_ caching, with zero retention time) - w/o associated security and
> scalability problems.

Great, please do clue me in.  I wasn't aware that you'd corrected all the 
issues with caching, and somehow defied physics wrt the process of "duplicate 
bits" on a wire not actually utilizing b/w.

> Presenting L2/L3 multicasting as the best or the only
> or even a meaningful way to reduce transmission duplication is quite wrong.

I don't recall anyone doing that.  They're both good ideas, they both need 
work.

> A primary concern is the absense (and most likely, impossibility) of any L2/L3
> multicast routing scheme capable of supporting any significant number of 
> mcast trees.

Oh, and caching has no problems?  I believe they're addressing two _slightly_ 
different problems.

> Scalability on the Internet pretty much means that algorithms should run in
> O(log(N)**M) where N is the total number of end-points and M is constant.
> (Note that non-CIDR unicast routing doesn't fit this criterion, but CIDR does).

Perhaps O(log(N)**M) does apply to unicast, but the multicast model should 
differ.  I'd agree that in an ideal state, sure, looks good, but...

> The benefits of mining cheap cheese on the Moon are quite obvious.  If you're
> willing to overlook the small fact that the Moon isn't made from cheese.

I'm with Brett, never been to the moon..

> _No_ technological advances can help the fact that L2/L3 multicasts cannot
> be routed in a scalable fashion.  Think what happens when there is 1mil
> multicast trees in the network.

and 10 billion caching servers won't give you even one extra bit to the 
end-user.

-danny






More information about the NANOG mailing list