Pete Kruckenberg <pete@kruckenberg.com> wrote:

The presentations I've seen about QoS implementations have all seemed to contain major sections about how the networks had to work around problems or scale back the implementation because of resource limitations (CPU, memory, etc). Haven't seen anyone implement RSVP on a wide scale, due to similar types of problems.

It is painfully obvious that RSVP cannot be implemented on a large scale for years now for reasons having to do more with fundamental properties of algorithms (i.e. complexity) than with particulars of protocols or implementations. RSVP - perpetuum mobile of 90s? :)

Sounds like QoS is marketing material, not the stuff networks are built on. Is that still the case?

Yep. Altough not _all_ QoS schemes are broken-as-designed. The most trivial per-packet priority combined with ingress priority mix shaping works. Ths idea of end-to-end whatever reservations or guarantees is usually propounded by people who either neglected their CS courses or those who are trying to sell it.

How the heck are people able to deploy native-IP networks with these kinds of limitations/problems with QoS? Or did I miss something about QoS recently?

Yep. The biggest QoS secret is that nobody actually needs it. Bandwidth is cheap and is growing cheaper. The manpower needed to deploy and maintain QoS is getting more and more expensive. --vadim