computer networks ii - unina stidueunina.stidue.net/computer networks 2/materiale/slides/02.1 -...

43
1 Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II Computer Networks II a.a. 2009/2010 Computer Networks II QoS: Techniques and Architectures Giorgio Ventre COMICS LAB Dipartimento di Informatica e Sistemistica Università di Napoli Federico II Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II Computer Networks II a.a. 2009/2010 Nota di Copyright Quest‟insieme di trasparenze è stato ideato e realizzato dai ricercatori del Gruppo di Ricerca sull‟Informatica Distribuita del Dipartimento di Informatica e Sistemistica dell‟Università di Napoli e del Laboratorio Nazionale per la Informatica e la Telematica Multimediali. Esse possono essere impiegate liberamente per fini didattici esclusivamente senza fini di lucro, a meno di un esplicito consenso scritto degli Autori. Nell‟uso dovrà essere esplicitamente riportata la fonte e gli Autori. Gli Autori non sono responsabili per eventuali imprecisioni contenute in tali trasparenze né per eventuali problemi, danni o malfunzionamenti derivanti dal loro uso o applicazione.

Upload: others

Post on 26-Mar-2020

3 views

Category:

Documents


0 download

TRANSCRIPT

Page 1: Computer Networks II - UniNa STiDuEunina.stidue.net/Computer Networks 2/Materiale/Slides/02.1 - CN-II QoS in IP.pdf4 Computer Networks II –a.a. 2009/2010 Dipartimento di Informatica

1

Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II Computer Networks II – a.a. 2009/2010

Computer Networks II

QoS: Techniques and

Architectures

Giorgio Ventre

COMICS LAB

Dipartimento di Informatica e Sistemistica

Università di Napoli Federico II

Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II Computer Networks II – a.a. 2009/2010

Nota di Copyright

Quest‟insieme di trasparenze è stato ideato e realizzato dai

ricercatori del Gruppo di Ricerca sull‟Informatica Distribuita del

Dipartimento di Informatica e Sistemistica dell‟Università di

Napoli e del Laboratorio Nazionale per la Informatica e la

Telematica Multimediali. Esse possono essere impiegate

liberamente per fini didattici esclusivamente senza fini di lucro,

a meno di un esplicito consenso scritto degli Autori. Nell‟uso

dovrà essere esplicitamente riportata la fonte e gli Autori. Gli

Autori non sono responsabili per eventuali imprecisioni

contenute in tali trasparenze né per eventuali problemi, danni o

malfunzionamenti derivanti dal loro uso o applicazione.

Page 2: Computer Networks II - UniNa STiDuEunina.stidue.net/Computer Networks 2/Materiale/Slides/02.1 - CN-II QoS in IP.pdf4 Computer Networks II –a.a. 2009/2010 Dipartimento di Informatica

2

Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II Computer Networks II – a.a. 2009/2010

Why better-than-best-effort (QoS-enabled) Internet ?

Quality of Service (QoS) building blocks

End-to-end protocols: RTP, H.323

Network protocols:» Integrated Services(IntServ), RSVP.

» Scalable differentiated services: DiffServ

Control plane: QoS routing, traffic engineering, policy management, pricing models

Overview

Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II Computer Networks II – a.a. 2009/2010

Why Better-than-Best-Effort (QoS)?

To support a wider range of applications

» Real-time, Multimedia, etc

To develop sustainable economic models

and new private networking services

» Current flat priced models, and best-effort

services do not cut it for businesses

Page 3: Computer Networks II - UniNa STiDuEunina.stidue.net/Computer Networks 2/Materiale/Slides/02.1 - CN-II QoS in IP.pdf4 Computer Networks II –a.a. 2009/2010 Dipartimento di Informatica

3

Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II Computer Networks II – a.a. 2009/2010

Quality of Service: What is it?

Multimedia applications: network audio and video

network provides application with level of performance needed for application to function.

QoS

Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II Computer Networks II – a.a. 2009/2010

What is QoS?

“Better performance” as described by a set of parameters or measured by a set of metrics.

Generic parameters:

» Bandwidth

» Delay, Delay-jitter

» Packet loss rate (or loss probability)

Transport/Application-specific parameters:

» Timeouts

» Percentage of “important” packets lost

Page 4: Computer Networks II - UniNa STiDuEunina.stidue.net/Computer Networks 2/Materiale/Slides/02.1 - CN-II QoS in IP.pdf4 Computer Networks II –a.a. 2009/2010 Dipartimento di Informatica

4

Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II Computer Networks II – a.a. 2009/2010

What is QoS (contd) ?

These parameters can be measured at

several granularities:

» “micro” flow, aggregate flow, population.

QoS considered “better” if

» a) more parameters can be specified

» b) QoS can be specified at a fine-granularity.

QoS spectrum:Best Effort Leased Line

Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II Computer Networks II – a.a. 2009/2010

Fundamental Problems

In a FIFO service discipline, the performance

assigned to one flow is convoluted with the

arrivals of packets from all other flows!

» Can‟t get QoS with a “free-for-all”

» Need to use new scheduling disciplines which

provide “isolation” of performance from arrival rates

of background traffic

B

Scheduling DisciplineFIFO

B

Page 5: Computer Networks II - UniNa STiDuEunina.stidue.net/Computer Networks 2/Materiale/Slides/02.1 - CN-II QoS in IP.pdf4 Computer Networks II –a.a. 2009/2010 Dipartimento di Informatica

5

Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II Computer Networks II – a.a. 2009/2010

Fundamental Problems

Conservation Law

(Kleinrock): (i)Wq(i) = K

Irrespective of scheduling

discipline chosen:

» Average backlog (delay) is

constant

» Average bandwidth is

constant

Zero-sum game => need

to “set-aside” resources

for premium services

Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II Computer Networks II – a.a. 2009/2010

QoS Big Picture: Control/Data Planes

Internetwork or WANWorkstation

Router

Router

RouterWorkstation

Control Plane: Signaling + Admission Control or

SLA (Contracting) + Provisioning/Traffic Engineering

Data Plane: Traffic conditioning (shaping, policing, marking

etc) + Traffic Classification + Scheduling, Buffer management

Page 6: Computer Networks II - UniNa STiDuEunina.stidue.net/Computer Networks 2/Materiale/Slides/02.1 - CN-II QoS in IP.pdf4 Computer Networks II –a.a. 2009/2010 Dipartimento di Informatica

6

Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II Computer Networks II – a.a. 2009/2010

QoS Components

QoS => set aside resources for premium

services

QoS components:

» a) Specification of premium services:

(service/service level agreement design)

» b) How much resources to set aside?

(admission control/provisioning)

» c) How to ensure network resource utilization,

do load balancing, flexibly manage traffic

aggregates and paths ?

(QoS routing, traffic engineering)

Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II Computer Networks II – a.a. 2009/2010

QoS Components (Continued)

» d) How to actually set aside these resources in

a distributed manner ?

(signaling, provisioning, policy)

» e) How to deliver the service when the traffic

actually comes in (claim/police resources)?

(traffic shaping, classification, scheduling)

» f) How to monitor quality, account and price

these services?

(network mgmt, accounting, billing, pricing)

Page 7: Computer Networks II - UniNa STiDuEunina.stidue.net/Computer Networks 2/Materiale/Slides/02.1 - CN-II QoS in IP.pdf4 Computer Networks II –a.a. 2009/2010 Dipartimento di Informatica

7

Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II Computer Networks II – a.a. 2009/2010

How to upgrade the Internet for QoS?

Approach: de-couple end-system evolution from network evolution

End-to-end protocols: RTP, H.323 etc to spur the growth of adaptive multimedia applications

» Assume best-effort or better-than-best-effort clouds

Network protocols: IntServ, DiffServ, RSVP, MPLS, COPS …

» To support better-than-best-effort capabilities at the network (IP) level

Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II Computer Networks II – a.a. 2009/2010

QOS SPECIFICATION, TRAFFIC, SERVICE CHARACTERIZATION, BASIC MECHANISMS

Page 8: Computer Networks II - UniNa STiDuEunina.stidue.net/Computer Networks 2/Materiale/Slides/02.1 - CN-II QoS in IP.pdf4 Computer Networks II –a.a. 2009/2010 Dipartimento di Informatica

8

Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II Computer Networks II – a.a. 2009/2010

Service Specification

Loss: probability that a flow‟s packet is lost

Delay: time it takes a packet‟s flow to get

from source to destination

Delay jitter: maximum difference between

the delays experienced by two packets of

the flow

Bandwidth: maximum rate at which the

soource can send traffic

QoS spectrum:

Best Effort Leased Line

Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II Computer Networks II – a.a. 2009/2010

Hard Real Time: Guaranteed Services

Service contract

» Network to client: guarantee a deterministic

upper bound on delay for each packet in a

session

» Client to network: the session does not send

more than it specifies

Algorithm support

» Admission control based on worst-case analysis

» Per flow classification/scheduling at routers

Page 9: Computer Networks II - UniNa STiDuEunina.stidue.net/Computer Networks 2/Materiale/Slides/02.1 - CN-II QoS in IP.pdf4 Computer Networks II –a.a. 2009/2010 Dipartimento di Informatica

9

Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II Computer Networks II – a.a. 2009/2010

Soft Real Time: Controlled Load Service

Service contract:

» Network to client: similar performance as an

unloaded best-effort network

» Client to network: the session does not send

more than it specifies

Algorithm Support

» Admission control based on measurement of

aggregates

» Scheduling for aggregate possible

Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II Computer Networks II – a.a. 2009/2010

Traffic and Service Characterization

To quantify a service one has two know

» Flow‟s traffic arrival

» Service provided by the router, i.e., resources reserved at each router

Examples:

» Traffic characterization: token bucket

» Service provided by router: fix rate and fix buffer space

– Characterized by a service model (service curve framework)

Page 10: Computer Networks II - UniNa STiDuEunina.stidue.net/Computer Networks 2/Materiale/Slides/02.1 - CN-II QoS in IP.pdf4 Computer Networks II –a.a. 2009/2010 Dipartimento di Informatica

10

Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II Computer Networks II – a.a. 2009/2010

Token Bucket

Characterized by three parameters (b, r, R)» b – token depth

» r – average arrival rate

» R – maximum arrival rate (e.g., R link capacity)

A bit is transmitted only when there is an available token

» When a bit is transmitted exactly one token is consumed

r tokens per second

b tokens

<= R bps

regulatortime

bits

b*R/(R-r)

slope R

slope r

Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II Computer Networks II – a.a. 2009/2010

Characterizing a Source by Token Bucket

Arrival curve – maximum amount of bits transmitted by time t

Use token bucket to bound the arrival curve

time

bits

Arrival curve

time

bps

Page 11: Computer Networks II - UniNa STiDuEunina.stidue.net/Computer Networks 2/Materiale/Slides/02.1 - CN-II QoS in IP.pdf4 Computer Networks II –a.a. 2009/2010 Dipartimento di Informatica

11

Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II Computer Networks II – a.a. 2009/2010

Example

Arrival curve – maximum amount of bits transmitted by time t

Use token bucket to bound the arrival curve

size of time

interval

bitsArrival curve

time

bps

0 1 2 3 4 5

1

2

1 2 3 4 5

1

2

3

4

(b=1,r=1,R=2)

Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II Computer Networks II – a.a. 2009/2010

Per-hop Reservation

Given b,r,R and per-hop delay d

Allocate bandwidth ra and buffer space Ba such that to guarantee d

bits

b

slope rArrival curve

d

Ba

slope ra

Page 12: Computer Networks II - UniNa STiDuEunina.stidue.net/Computer Networks 2/Materiale/Slides/02.1 - CN-II QoS in IP.pdf4 Computer Networks II –a.a. 2009/2010 Dipartimento di Informatica

12

Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II Computer Networks II – a.a. 2009/2010

What is a Service Model?

The QoS measures (delay,throughput,

loss, cost) depend on offered traffic, and

possibly other external processes.

A service model attempts to characterize

the relationship between offered traffic,

delivered traffic, and possibly other

external processes.

“external process”

Network elementoffered traffic

delivered traffic

(connection oriented)

Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II Computer Networks II – a.a. 2009/2010

Arrival and Departure Process

Network ElementRin Rout

Rin(t) = arrival process

= amount of data arriving up to time t

Rout(t) = departure process

= amount of data departing up to time t

bits

t

delay

buffer

Page 13: Computer Networks II - UniNa STiDuEunina.stidue.net/Computer Networks 2/Materiale/Slides/02.1 - CN-II QoS in IP.pdf4 Computer Networks II –a.a. 2009/2010 Dipartimento di Informatica

13

Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II Computer Networks II – a.a. 2009/2010

Traffic Envelope (Arrival Curve)

Maximum amount of service that a flow

can send during an interval of time t

slope = max average rate

b(t) = Envelope

slope = peak rate

t

“Burstiness Constraint”

Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II Computer Networks II – a.a. 2009/2010

Service Curve

Assume a flow that is idle at time s and it is

backlogged during the interval (s, t)

Service curve: the minimum service

received by the flow during the interval (s, t)

Page 14: Computer Networks II - UniNa STiDuEunina.stidue.net/Computer Networks 2/Materiale/Slides/02.1 - CN-II QoS in IP.pdf4 Computer Networks II –a.a. 2009/2010 Dipartimento di Informatica

14

Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II Computer Networks II – a.a. 2009/2010

Big Picture

t t

slope = C

t

Rin(t)

Service curvebits bits

bits

Rout(t)

Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II Computer Networks II – a.a. 2009/2010

Delay and Buffer Bounds

t

S (t) = service curve

E(t) = Envelope

Maximum delay

Maximum buffer

bits

Page 15: Computer Networks II - UniNa STiDuEunina.stidue.net/Computer Networks 2/Materiale/Slides/02.1 - CN-II QoS in IP.pdf4 Computer Networks II –a.a. 2009/2010 Dipartimento di Informatica

15

Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II Computer Networks II – a.a. 2009/2010

Mechanisms: Traffic Shaping/Policing

Token bucket: limits input to specified Burst Size (b) and Average Rate (r).» Traffic sent over any time T <= r*T + b

» a.k.a Linear bounded arrival process (LBAP)

Excess traffic may be queued, marked BLUE, or simply dropped

Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II Computer Networks II – a.a. 2009/2010

Mechanisms: Queuing/Scheduling

Use a few bits in header to indicate which queue (class) a packet goes into (also branded as CoS)

High $$ users classified into high priority queues, which also may be less populated

=> lower delay and low likelihood of packet drop

Ideas: priority, round-robin, classification, aggregation, ...

Class C

Class B

Class A

Traffic

Classes

Traffic

Sources

$$$$$$

$$$

$

Page 16: Computer Networks II - UniNa STiDuEunina.stidue.net/Computer Networks 2/Materiale/Slides/02.1 - CN-II QoS in IP.pdf4 Computer Networks II –a.a. 2009/2010 Dipartimento di Informatica

16

Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II Computer Networks II – a.a. 2009/2010

Mechanisms: Buffer Mgmt/Priority Drop

Ideas: packet marking, queue thresholds,

differential dropping, buffer assignments

Drop RED and BLUE packets

Drop only BLUE packets

Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II Computer Networks II – a.a. 2009/2010

SCHEDULING

Page 17: Computer Networks II - UniNa STiDuEunina.stidue.net/Computer Networks 2/Materiale/Slides/02.1 - CN-II QoS in IP.pdf4 Computer Networks II –a.a. 2009/2010 Dipartimento di Informatica

17

Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II Computer Networks II – a.a. 2009/2010

Packet Scheduling

Decide when and what packet to send on

output link

» Usually implemented at output interface

1

2

Scheduler

flow 1

flow 2

flow n

Classifier

Buffer

management

Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II Computer Networks II – a.a. 2009/2010

Focus: Scheduling Policies

Priority Queuing: classes have different priorities; class may depend on explicit marking or other header info, eg IP source or destination, TCP Port numbers, etc.

Transmit a packet from the highest priority class with a non-empty queue

Preemptive and non-preemptive versions

Page 18: Computer Networks II - UniNa STiDuEunina.stidue.net/Computer Networks 2/Materiale/Slides/02.1 - CN-II QoS in IP.pdf4 Computer Networks II –a.a. 2009/2010 Dipartimento di Informatica

18

Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II Computer Networks II – a.a. 2009/2010

Scheduling Policies (more)

Round Robin: scan class queues serving one from

each class that has a non-empty queue

Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II Computer Networks II – a.a. 2009/2010

Round-Robin Discussion

Advantages: protection among flows» Misbehaving flows will not affect the performance

of well-behaving flows– Misbehaving flow – a flow that does not implement any

congestion control

» FIFO does not have such a property

Disadvantages:» More complex than FIFO: per flow queue/state

» Biased toward large packets – each flow receives service proportional to the number of packets it sends (multiplied by the bytes carried by packets).

Page 19: Computer Networks II - UniNa STiDuEunina.stidue.net/Computer Networks 2/Materiale/Slides/02.1 - CN-II QoS in IP.pdf4 Computer Networks II –a.a. 2009/2010 Dipartimento di Informatica

19

Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II Computer Networks II – a.a. 2009/2010

Generalized Processor Sharing(GPS)

Assume a fluid model of traffic

» Visit each non-empty queue in turn (RR)

» Serve infinitesimal from each

» Leads to “max-min” fairness

GPS is un-implementable!

» We cannot serve infinitesimals, only packets

Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II Computer Networks II – a.a. 2009/2010

Weighted Fair Rate in GPS

A work conserving GPS is defined as

where» wi – weight of flow i

» Wi(t1, t2) – total service received by flow i during [t1, t2)

» W(t1, t2) – total service allocated to all flows during [t1, t2)

» B(t) – number of flows backlogged

)(),(),(

)(

tBiw

dtttW

w

dtttW

tBj ji

i

Page 20: Computer Networks II - UniNa STiDuEunina.stidue.net/Computer Networks 2/Materiale/Slides/02.1 - CN-II QoS in IP.pdf4 Computer Networks II –a.a. 2009/2010 Dipartimento di Informatica

20

Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II Computer Networks II – a.a. 2009/2010

Weighted Fair Rate Computation in GPS

Associate a weight wi with each flow i

If link congested, compute f such that

Cwfr i

i

i ),min(

8

6

2

26

2

f = 2: min(8, 2*3) = 6

min(6, 2*1) = 2

min(2, 2*1) = 2

10(w1 = 3)

(w2 = 1)

(w3 = 1)

Bit x bit Round Robin

Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II Computer Networks II – a.a. 2009/2010

Bit-by-bit Round Robin when dealing with Packets

Single flow: clock ticks when a bit is transmitted. For packet i:

» Pi = length, Ai = arrival time, Si = begin transmittime, Fi = finish transmit time

» Fi = Si+Pi = max (Fi-1, Ai) + Pi

Multiple flows: clock ticks when a bit from all active flows is transmitted round number

» Can calculate Fi for each packet if number of flows is known at all times

– This can be complicated

Page 21: Computer Networks II - UniNa STiDuEunina.stidue.net/Computer Networks 2/Materiale/Slides/02.1 - CN-II QoS in IP.pdf4 Computer Networks II –a.a. 2009/2010 Dipartimento di Informatica

21

Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II Computer Networks II – a.a. 2009/2010

Standard techniques of approximating fluid GPS» Select packet that finishes first in GPS assuming

that there are no future arrivals

Important properties of GPS» Finishing order of packets currently in system

independent of future arrivals

Implementation based on virtual time» Assign virtual finish time to each packet upon

arrival

» Packets served in increasing order of virtual times

Packet Approximation of Fluid System

Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II Computer Networks II – a.a. 2009/2010

Fair Queuing (FQ)

Idea: serve packets in the order in which they would have

finished transmission in the fluid flow system

Mapping bit-by-bit schedule onto packet transmission

schedule

Transmit packet with the lowest Fi at any given time

Variation: Weighted Fair Queuing (WFQ)

Page 22: Computer Networks II - UniNa STiDuEunina.stidue.net/Computer Networks 2/Materiale/Slides/02.1 - CN-II QoS in IP.pdf4 Computer Networks II –a.a. 2009/2010 Dipartimento di Informatica

22

Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II Computer Networks II – a.a. 2009/2010

Approximating GPS with WFQ

Fluid GPS system service order

0 2 104 6 8

Weighted Fair Queueing

» select the first packet that finishes in GPS

Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II Computer Networks II – a.a. 2009/2010

FQ Example

F=10

Flow 1

(arriving)

Flow 2

transmittingOutput

F=2

F=5

F=8

Flow 1 Flow 2 Output

F=10

Cannot preempt packet

currently being transmitted

Page 23: Computer Networks II - UniNa STiDuEunina.stidue.net/Computer Networks 2/Materiale/Slides/02.1 - CN-II QoS in IP.pdf4 Computer Networks II –a.a. 2009/2010 Dipartimento di Informatica

23

Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II Computer Networks II – a.a. 2009/2010

FQ Advantages

FQ protect well-behaved flows from ill-behaved flows

Example: 1 UDP (10 Mbps) and 31 TCP‟s sharing a 10 Mbps link

FQ

0

0.2

0.4

0.6

0.8

1

1.2

1.4

1.6

1.8

2

1 4 7 10 13 16 19 22 25 28 31

Flow NumberT

hro

ug

hp

ut(

Mb

ps

)RED

0

1

2

3

4

5

6

7

8

9

10

1 4 7 10 13 16 19 22 25 28 31

Flow Number

Th

ro

ug

hp

ut(

Mb

ps

)

Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II Computer Networks II – a.a. 2009/2010

Big Picture

FQ does not eliminate congestion it just

manages the congestion

You need both end-host congestion control

and router support for congestion control

» end-host congestion control to adapt

» router congestion control to protect/isolate

Don‟t forget buffer management: you still

need to drop in case of congestion. Which

packet‟s would you drop in FQ?

» one possibility: packet from the longest queue

Page 24: Computer Networks II - UniNa STiDuEunina.stidue.net/Computer Networks 2/Materiale/Slides/02.1 - CN-II QoS in IP.pdf4 Computer Networks II –a.a. 2009/2010 Dipartimento di Informatica

24

Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II Computer Networks II – a.a. 2009/2010

Parekh-Gallager theorem

Let a connection be allocated weights at each

WFQ scheduler along its path, so that the least

bandwidth it is allocated is g

Let it be leaky-bucket regulated such that # bits

sent in time [t1, t2] <= g(t2 - t1) +

Let the connection pass through K schedulers,

where the kth scheduler has a rate r(k)

Let the largest packet size in the network be P

1

1 1

)(///___K

k

K

k

krPgPgdelayendtoend

Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II Computer Networks II – a.a. 2009/2010

Significance

P-G Theorem shows that WFQ scheduling can provide end-to-end delay bounds in a network of multiplexed bottlenecks

» WFQ provides both bandwidth and delayguarantees

» Bound holds regardless of cross traffic behavior (isolation)

» Needs shapers at the entrance of the network

Can be generalized for networks where schedulers are variants of WFQ, and the link service rate changes over time

Page 25: Computer Networks II - UniNa STiDuEunina.stidue.net/Computer Networks 2/Materiale/Slides/02.1 - CN-II QoS in IP.pdf4 Computer Networks II –a.a. 2009/2010 Dipartimento di Informatica

25

Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II Computer Networks II – a.a. 2009/2010

QoS ARCHITECTURES

Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II Computer Networks II – a.a. 2009/2010

Stateless vs. Stateful QoS Solutions

Stateless solutions – routers maintain no fine

grained state about traffic

scalable, robust

weak services

Stateful solutions – routers maintain per-flow state

powerful services

– guaranteed services + high resource utilization

– fine grained differentiation

– protection

much less scalable and robust

Page 26: Computer Networks II - UniNa STiDuEunina.stidue.net/Computer Networks 2/Materiale/Slides/02.1 - CN-II QoS in IP.pdf4 Computer Networks II –a.a. 2009/2010 Dipartimento di Informatica

26

Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II Computer Networks II – a.a. 2009/2010

Existing Solutions

Stateful Stateless

QoS

Tenet [Ferrari &

Verma ‟89]

IntServ [Clark et al

‟91]

ATM [late ‟80s]

DiffServ

- [Clark &

Wroclawski „97]

- [Nichols et al ‟97]

Network

support for

congestion

control

Round Robin [Nagle

‟85]

Fair Queueing

[Demers et al ‟89]

Flow Random Early

Drop (FRED) [Lin &

Morris ‟97]

DecBit [Ramkrishnan &

Jain ‟88]

Random Early Detection

(RED) [Floyd & Jacobson

‟93]

BLUE [Feng et al ‟99]

REM [Low at al ‟00]

Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II Computer Networks II – a.a. 2009/2010

Integrated Services (IntServ)

An architecture for providing QOS guarantees in IP

networks for individual application sessions

Relies on resource reservation, and routers need to

maintain state information of allocated resources (eg:

g) and respond to new Call setup requests

Page 27: Computer Networks II - UniNa STiDuEunina.stidue.net/Computer Networks 2/Materiale/Slides/02.1 - CN-II QoS in IP.pdf4 Computer Networks II –a.a. 2009/2010 Dipartimento di Informatica

27

Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II Computer Networks II – a.a. 2009/2010

Signaling semantics

Classic scheme: sender initiated

SETUP, SETUP_ACK, SETUP_RESPONSE

Admission control

Tentative resource reservation and confirmation

Simplex and duplex setup; no multicast support

Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II Computer Networks II – a.a. 2009/2010

RSVP: Internet Signaling

Creates and maintains distributed reservation

state

De-coupled from routing:

» Multicast trees setup by routing protocols, not RSVP

(unlike ATM or telephony signaling)

Receiver-initiated: scales for multicast

Soft-state: reservation times out unless refreshed

Latest paths discovered through “PATH”

messages (forward direction) and used by RESV

mesgs (reverse direction).

Page 28: Computer Networks II - UniNa STiDuEunina.stidue.net/Computer Networks 2/Materiale/Slides/02.1 - CN-II QoS in IP.pdf4 Computer Networks II –a.a. 2009/2010 Dipartimento di Informatica

28

Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II Computer Networks II – a.a. 2009/2010

Call Admission

Session must first declare its QoS

requirement and characterize the traffic it

will send through the network

R-spec: defines the QoS class assigned

T-spec: defines the traffic characteristics

A signaling protocol is needed to carry the

R-spec and T-spec to the routers where

reservation is required; RSVP is a leading

candidate for such signaling protocol

Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II Computer Networks II – a.a. 2009/2010

Call Admission

Call Admission: routers will admit calls based on

their R-spec and T-spec and based on the current

resource allocated at the routers to other calls.

Page 29: Computer Networks II - UniNa STiDuEunina.stidue.net/Computer Networks 2/Materiale/Slides/02.1 - CN-II QoS in IP.pdf4 Computer Networks II –a.a. 2009/2010 Dipartimento di Informatica

29

Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II Computer Networks II – a.a. 2009/2010

Stateful Solution: Guaranteed Services

SenderReceiver

Achieve per-flow bandwidth and delay guarantees

» Example: guarantee 1MBps and < 100 ms delay to a flow

Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II Computer Networks II – a.a. 2009/2010

Stateful Solution: Guaranteed Services

SenderReceiver

Allocate resources - perform per-flow

admission control

Page 30: Computer Networks II - UniNa STiDuEunina.stidue.net/Computer Networks 2/Materiale/Slides/02.1 - CN-II QoS in IP.pdf4 Computer Networks II –a.a. 2009/2010 Dipartimento di Informatica

30

Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II Computer Networks II – a.a. 2009/2010

Stateful Solution: Guaranteed Services

SenderReceiver

Install per-flow state

Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II Computer Networks II – a.a. 2009/2010

SenderReceiver

Challenge: maintain per-flow state

consistent

Stateful Solution: Guaranteed Services

Page 31: Computer Networks II - UniNa STiDuEunina.stidue.net/Computer Networks 2/Materiale/Slides/02.1 - CN-II QoS in IP.pdf4 Computer Networks II –a.a. 2009/2010 Dipartimento di Informatica

31

Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II Computer Networks II – a.a. 2009/2010

Stateful Solution: Guaranteed Services

SenderReceiver

Per-flow classification

Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II Computer Networks II – a.a. 2009/2010

Stateful Solution: Guaranteed Services

SenderReceiver

Per-flow buffer management

Page 32: Computer Networks II - UniNa STiDuEunina.stidue.net/Computer Networks 2/Materiale/Slides/02.1 - CN-II QoS in IP.pdf4 Computer Networks II –a.a. 2009/2010 Dipartimento di Informatica

32

Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II Computer Networks II – a.a. 2009/2010

Stateful Solution: Guaranteed Services

SenderReceiver

• Per-flow scheduling

Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II Computer Networks II – a.a. 2009/2010

Stateful Solution Complexity

Data path

» Per-flow classification

» Per-flow buffer

management

» Per-flow scheduling

Control path

» install and maintain

per-flow state for

data and control paths

Classifier

Buffer

management

Scheduler

flow 1

flow 2

flow n

output interface

Per-flow State

Page 33: Computer Networks II - UniNa STiDuEunina.stidue.net/Computer Networks 2/Materiale/Slides/02.1 - CN-II QoS in IP.pdf4 Computer Networks II –a.a. 2009/2010 Dipartimento di Informatica

33

Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II Computer Networks II – a.a. 2009/2010

Stateless vs. Stateful

Stateless solutions are more

» scalable

» robust

Stateful solutions provide more powerful

and flexible services

» guaranteed services + high resource utilization

» fine grained differentiation

» protection

Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II Computer Networks II – a.a. 2009/2010

Question

Can we achieve the best of two worlds, i.e., provide services implemented by stateful networks while maintaining advantages of stateless architectures?

» Yes, in some interesting cases. DPS, CSFQ.

Can we provide reduced state services, I.e., maintain state only for larger granular flows rather than end-to-end flows?

» Yes: Diff-serv

Page 34: Computer Networks II - UniNa STiDuEunina.stidue.net/Computer Networks 2/Materiale/Slides/02.1 - CN-II QoS in IP.pdf4 Computer Networks II –a.a. 2009/2010 Dipartimento di Informatica

34

Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II Computer Networks II – a.a. 2009/2010

Differentiated Services (DiffServ)

Intended to address the following difficulties with Intserv and RSVP;

Scalability: maintaining states by routers in high speed networks is difficult due to the very large number of flows

Flexible Service Models: Intserv has only two classes, want to provide more qualitative service classes; want to provide „relative‟ service distinction (Platinum, Gold, Silver, …)

Simpler signaling: (than RSVP) many applications and users may only want to specify a more qualitative notion of service

Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II Computer Networks II – a.a. 2009/2010

Differentiated Services Model

Edge routers: traffic conditioning (policing, marking,

dropping), SLA negotiation

» Set values in DS-byte in IP header based upon negotiated

service and observed traffic.

Interior routers: traffic classification and forwarding

(near stateless core!)

» Use DS-byte as index into forwarding table

Ingress

Edge Router

Egress

Edge Router

Interior Router

Page 35: Computer Networks II - UniNa STiDuEunina.stidue.net/Computer Networks 2/Materiale/Slides/02.1 - CN-II QoS in IP.pdf4 Computer Networks II –a.a. 2009/2010 Dipartimento di Informatica

35

Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II Computer Networks II – a.a. 2009/2010

Diffserv Architecture

Edge router:

- per-flow traffic management

- marks packets as in-profile and out-profile

Core router:

- per class TM

- buffering and scheduling

based on marking at edge

- preference given to in-profile packets- Assured Forwarding

scheduling

...

r

b

marking

Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II Computer Networks II – a.a. 2009/2010

Packet format support

Packet is marked in the Type of Service

(TOS) in IPv4, and Traffic Class in IPv6:

renamed as “DS”

6 bits used for Differentiated Service Code

Point (DSCP) and determine PHB that the

packet will receive

2 bits are currently unused

Page 36: Computer Networks II - UniNa STiDuEunina.stidue.net/Computer Networks 2/Materiale/Slides/02.1 - CN-II QoS in IP.pdf4 Computer Networks II –a.a. 2009/2010 Dipartimento di Informatica

36

Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II Computer Networks II – a.a. 2009/2010

Traffic Conditioning

It may be desirable to limit traffic injection

rate of some class; user declares traffic

profile (eg, rate and burst size); traffic is

metered and shaped if non-conforming

Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II Computer Networks II – a.a. 2009/2010

Per-hop Behavior (PHB)

PHB: name for interior router data-plane functions

» Includes scheduling, buff. mgmt, shaping etc

Logical spec: PHB does not specify mechanisms

to use to ensure performance behavior

Examples:

» Class A gets x% of outgoing link bandwidth over time

intervals of a specified length

» Class A packets leave first before packets from class B

Page 37: Computer Networks II - UniNa STiDuEunina.stidue.net/Computer Networks 2/Materiale/Slides/02.1 - CN-II QoS in IP.pdf4 Computer Networks II –a.a. 2009/2010 Dipartimento di Informatica

37

Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II Computer Networks II – a.a. 2009/2010

PHB (contd)

PHBs defined:

» Expedited Forwarding: departure rate of packets from a class equals or exceeds a specified rate (logical link with a minimum guaranteed rate)

– Emulates leased-line behavior

» Assured Forwarding: 4 classes, each guaranteed a minimum amount of bandwidth and buffering; each with three drop precedence partitions

– Emulates frame-relay behavior

Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II Computer Networks II – a.a. 2009/2010

Scalable Core (SCORE)

A trusted and contiguous region of network in

which

» edge nodes – perform per flow management

» core nodes – do not perform per flow management

core nodes edge nodes

edge nodes

Page 38: Computer Networks II - UniNa STiDuEunina.stidue.net/Computer Networks 2/Materiale/Slides/02.1 - CN-II QoS in IP.pdf4 Computer Networks II –a.a. 2009/2010 Dipartimento di Informatica

38

Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II Computer Networks II – a.a. 2009/2010

SLA Definitions Today

SLA statistical definitions do matter» min/avg/max versus percentile

» Measured time interval

» interval between probes

» Point-to-point vs. point-to-multipoint vs. multipoint-to-multipoint

SLAs definitions today tend to be loose» averaged over a month

» averaged over many POP-to-POP pairs (temptation to add short pairs to reduce average…)

» Round-trip

Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II Computer Networks II – a.a. 2009/2010

Deploying Tight-SLA services on an IP Backbone

Number of tools are available to enable tight SLA services to be offered

» Physical network design and topology

» Diffserv: per-hop congestion management– Applying differential queuing and scheduling

mechanism to implement a differentiated SLA scheme

» Capacity planning and active monitoring

» Tuning IGP Convergence– slow convergence upon link/node failure directly

impacts SLAs

Page 39: Computer Networks II - UniNa STiDuEunina.stidue.net/Computer Networks 2/Materiale/Slides/02.1 - CN-II QoS in IP.pdf4 Computer Networks II –a.a. 2009/2010 Dipartimento di Informatica

39

Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II Computer Networks II – a.a. 2009/2010

Deploying Tight-SLA services on an IP Backbone

Number of tools are available to enable tight SLA

services to be offered (contd …)

» Traffic engineering: avoid aggregation on

shortest path

– IP aggregation on the shortest path can cause sub

optimal use of resources, and can impact SLAs

» Fast ReRoute (FRR) Protection

– FRR can be used to protect key resources and

provide rapid restoration for tight SLAs

Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II Computer Networks II – a.a. 2009/2010

The key for controlling Loss, Latency and Jitter: Provisioning!

The service that traffic receives is dependent

upon the ratio of traffic load to available capacity

More Bandwidth (offer) than traffic (demand)

means

» Low loss

» Low Latency

» Low Jitter

Page 40: Computer Networks II - UniNa STiDuEunina.stidue.net/Computer Networks 2/Materiale/Slides/02.1 - CN-II QoS in IP.pdf4 Computer Networks II –a.a. 2009/2010 Dipartimento di Informatica

40

Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II Computer Networks II – a.a. 2009/2010

Over-Provisioned Backbone

Over provision by ~2x the max. aggregate

traffic load

» Refs: {BONALD, CASNER, CHARNY}

Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II Computer Networks II – a.a. 2009/2010

Over-provisioning (Source: Stephen Casner, Packet Design, NANOG 22)

Jitter Measurement Summary

for the Week

69 million packets transmitted

Zero packets lost

100% jitter < 700s

Page 41: Computer Networks II - UniNa STiDuEunina.stidue.net/Computer Networks 2/Materiale/Slides/02.1 - CN-II QoS in IP.pdf4 Computer Networks II –a.a. 2009/2010 Dipartimento di Informatica

41

Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II Computer Networks II – a.a. 2009/2010

Over-provisioned Backbone

Effective

Simple» Available bandwidth > aggregate traffic

demand

» QoS mechanisms kept at to edge

» Network is simple to design, deploy and operate

Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II Computer Networks II – a.a. 2009/2010

Overprovisioned Backbone - Drawback

Risk related to provisioning failure

No service isolation» VPN, VoIP, Internet: same fate!

Expensive» design for the aggregate!!!

» Internet receives the same quality as VoIP

Page 42: Computer Networks II - UniNa STiDuEunina.stidue.net/Computer Networks 2/Materiale/Slides/02.1 - CN-II QoS in IP.pdf4 Computer Networks II –a.a. 2009/2010 Dipartimento di Informatica

42

Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II Computer Networks II – a.a. 2009/2010

99.99%

“Not every week is like this”(Source: Stephen Casner, Packet Design, NANOG 22)

Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II Computer Networks II – a.a. 2009/2010

Over-provisioning – Expensive

Aggregate bandwidth overprovision comes at a cost, however:» e.g. 150Mbps of VoIP and 1.5Gbps of data

between two POPs

» 1.65Gbps of aggregate load

» requires 3.3Gbps of bandwidth for 2x over-provisioning

» typically provisioned using 2x STM16/OC48

» hence 5Gbps of bandwidth used tosupport 1.65Gbps aggregate load with 150Mbps of low delay, low jitter, low loss traffic

Page 43: Computer Networks II - UniNa STiDuEunina.stidue.net/Computer Networks 2/Materiale/Slides/02.1 - CN-II QoS in IP.pdf4 Computer Networks II –a.a. 2009/2010 Dipartimento di Informatica

43

Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II Computer Networks II – a.a. 2009/2010

Over-provisioning – Expensive

Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II Computer Networks II – a.a. 2009/2010

Over-provisioning – Expensive