QoS Not Needed Ben Teitelbaum Internet2 VoIP SIG September, 2006.

QoS Not Needed

Ben TeitelbaumInternet2 VoIP SIG

September, 2006

Outline

QoS dreams Mechanisms Problems

Theoretic Practical Economic

Alternatives Non-History Non-Future

The Holy Grail of computer networking is to design a network that has the flexibility and low cost of the Internet, yet offers the end-to-end quality-of-service guarantees of the telephone network.

- S. Keshav

What QoS Is Not

It is not a synonym for “good performance”It is not about local rationing

E.g. Packeteer, Vonage ATA

And, in this talk, is not taken to include non-elevated services E.g. ABE, QBone Scavenger

What QoS Is

Differentiated network service to provide better-than-default (BE) service

WLOG, assume hereafter a Van Jacobson, virtual leased line, Premium Service

Note that QoS is about removing only one factor that can cause a networked transaction to fail

Mechanisms: Classification

Policing Queuing / AQMClassification

?

Mechanisms: Policing

Queuing / AQMClassification Policing

Mechanisms: Queuing / AQM

Policing Queuing / AQMClassification

Some Problems with QoS

TheoreticPracticalEconomic

GigaPoPA

CampusA

CampusC

CampusD

Backbone

CampusB

GigaPoPB

Theoretic Problems How do edge-to-edge

“virtual trunks” concatenate to form an e2e service?

What exactly are the policers and shapers at inter-domain boundaries?

Practical Problems

Requires all-or-nothing network upgrades (e.g. all access interfaces must police)

Dramatic changes to network operations, peering arrangements, and business models

Practical Problems (cont.)

In a well-provisioned network Premium is indistinguishable from BE

How can a user (or even a provider) verify service?

What happens to Premium service in the face of a determined adversary?

Economic Problems

Router costsOperational costsBilling costsSupport costs

Some Alternatives to QoS

Overprovisioning Cheapest way to provide fabulous service to important

apps, is to provide it to all apps Pricing

Congestion pricing Nice theoretic properties But not practical

Usage-based pricing Would help a lot Business access is increasingly metered Could provide differentiated services (e.g. Paris Metro

Pricing)

A History of Non-Deployment

QoS Wasn’t Needed (1997-2001)QoS Isn’t Needed (2002-2006)QoS Shouldn’t Be Needed (2007-)

QoS Wasn’t Needed (1997-2001)

Ambitious QoS program (QBone) Many hard-won lessons Negative outcome not at all a foregone

conclusion

Naïve codecs ported from ISDN world wouldn’t tolerate packet loss

Few users of real-time applications anyway

QoS Isn’t Needed (2002-2006)

Adaptive, loss-tolerant codecsMany users of real-time applications

(Vonage, Skype, Internet2 videoconf)Generous provisioning ensures that real-

time apps just work

Hang On a Second!

●~104 hosts with nothing slower than switched 100Mbps Ethernet between them●~25 of these could congest the 2.4 Gbps Abilene backbone (or 100 the 10 Gbps)●90% of traffic is TCP●TCP is designed to congest●Yet, the backbone is lightly loaded●What’s going on?!

http://netflow.internet2.edu/weekly/20060501/

The Terrible Truth(overprovisioning works, because TCP doesn’t)

QoS Shouldn’t Be Needed (2007-)

Either TCP will stay broken or be replacedNew transport protocols (e.g. XCP,

MaxNet, PCP) don’t build huge queuesEven better packet loss concealment

through improved codecs

Summary

QoS is interestingQoS is expensiveScarcity should become scarcerQoS has not been needed thus farQoS should not be needed for the

foreseeable future