modeling the interactions of congestion control and switch scheduling

32
Modeling the Interactions of Congestion Control and Switch Scheduling Alex Shpiner Joint work with Isaac Keslassy Faculty of Electrical Engineering, Technion IIT, Haifa, Israel

Upload: hewitt

Post on 24-Feb-2016

45 views

Category:

Documents


0 download

DESCRIPTION

Modeling the Interactions of Congestion Control and Switch Scheduling. Alex Shpiner Joint work with Isaac Keslassy. Faculty of Electrical Engineering , Technion IIT, Haifa, Israel. Users Vs. Routers. Users. Users. Congestion Control. Switch Scheduling. Congestion Control. - PowerPoint PPT Presentation

TRANSCRIPT

Page 1: Modeling the Interactions of Congestion Control and  Switch Scheduling

Modeling the Interactions of Congestion Control and

Switch Scheduling

Alex ShpinerJoint work with Isaac Keslassy

Faculty of Electrical Engineering,

Technion IIT, Haifa, Israel

Page 2: Modeling the Interactions of Congestion Control and  Switch Scheduling

2

Users Vs. Routers

Users Users

Congestion Control Congestion

Control

Switch Scheduling

Page 3: Modeling the Interactions of Congestion Control and  Switch Scheduling

User-Centric View

3

End-to-end congestion control algorithms (TCP) regulate the Internet

Routers are just passive elements.

Users

Users

Page 4: Modeling the Interactions of Congestion Control and  Switch Scheduling

4

Related Work: User-Centric View

Flow rate equilibrium F. Kelly, “Mathematical modeling of the Internet”, 2001.

Router Buffer Sizing G. Appenzeller, I. Keslassy, and N. McKeown, “Sizing router

buffers”, 2004. TCP Dynamics

M. Wang, “Mean-field analysis of buffer sizing”, 2007. Weighted Fair Queuing (WFQ)

H. Hassan, O. Brun, J. M. Garcia, and D. Gauchard, “Integration of streaming and elastic traffic: a fixed point approach”, 2008.

Active Queue Managemnet (AQM) T. Bu and D. F. Towsley, “A fixed point approximation of TCP

behavior in a network”, 2001.

Page 5: Modeling the Interactions of Congestion Control and  Switch Scheduling

5

Router-Centric View Switch scheduling

algorithms regulate the Internet.

Users are just passive elements.

Page 6: Modeling the Interactions of Congestion Control and  Switch Scheduling

6

Related Work: Router-Centric View

Maximum Weight Matching (MWM) N. McKeown, V. Anantharan, and J. Walrand, “Achieving 100%

throughput in an input-queued switch”, 1996. Birkhoff von-Neumann (BvN)

C. S. Chang, W. J. Chen, and H. Y. Huang, “On service guarantees for input buffered crossbar switches”, 1999.

iSLIP N. McKeown, “The iSLIP scheduling algorithm for input-queued

switches”, 1999.

Page 7: Modeling the Interactions of Congestion Control and  Switch Scheduling

7

Single Port Model (Nx1)

C in

C outQueue 1

C in

No switch scheduling:FIFO (OQ)

Page 8: Modeling the Interactions of Congestion Control and  Switch Scheduling

8

Single Port Model (Nx1)

With switch scheduling:iSLIP RRMaximum Weight Match (MWM) LQF

Scheduler

C in

C out

Q1

C in

QN

Page 9: Modeling the Interactions of Congestion Control and  Switch Scheduling

Simple Example – The Two Views

9

TCP cong. control + Ideal switch (FIFO)

TCP rate equilibrium

No starvation

UDP + MWM switch sched.

C1 = λ1

C2 = λ2

As long as λ1+λ2< Cout

No starvation

t

W1, W2

Source 1

DestinationSource 2

TCPUDP

FIFOMWM

(UDP is non-responsive traffic)

[Shah and Wischik ’06]

[Kelly ’01]

Page 10: Modeling the Interactions of Congestion Control and  Switch Scheduling

Simple Example – The Interaction

10Q2 t

Q1

TCP Source 1

TCP Destination

1

TCP Source 2

TCP Destination

2

TCP congestion control+ MWM switch scheduling

Q1

Q2

Starvation!

Page 11: Modeling the Interactions of Congestion Control and  Switch Scheduling

Routers UsersOK - +

Routers UsersOK - +OK + -

11

Two Conflicting Views of Regulation

Routers UsersOK - +OK + -X + +

Page 12: Modeling the Interactions of Congestion Control and  Switch Scheduling

12

Related Work

Interaction of responsive flows with MWM switch scheduling P. Giaccone, E. Leonardi, F. Neri, “On the behavior of optimal

scheduling algorithms under TCP sources”, 2006. Prove fair system equilibrium. But: rely on RED AQM and doesn’t reflect the possible extreme

unfairness which occur without AQM. Interaction of responsive flows in wireless networks

A. Eryilmaz and R. Srikant, “Fair resource allocation in wireless networks using queue-length-based scheduling and congestion control”, 2005.

Assume congestion control fundamentally different from TCP.

Page 13: Modeling the Interactions of Congestion Control and  Switch Scheduling

13

Our Contributions

Study interactions between congestion control and switch scheduling

Discover different modes of interaction Starvation, oscillation, equalization.

Describe system dynamics using differential equations

Page 14: Modeling the Interactions of Congestion Control and  Switch Scheduling

14

Outline

IntroductionFairnessNetwork DynamicsNxN SwitchSimulations

Page 15: Modeling the Interactions of Congestion Control and  Switch Scheduling

15

Example:

Throughput of flow k:

In general:

Intuition: symmetry

Fair for flows

Fairness in Ideal (FIFO / OQ) Switch

.k outCCnum of flows

11outk CC

Page 16: Modeling the Interactions of Congestion Control and  Switch Scheduling

16

Fairness of IQ Switch with iSLIP Scheduling

Example:

Throughput of flow k in port i:

In general:

Intuition: round-robin between ports

Fair for ports, but not for flows!

2010*21outoutk CCC

21*22outoutk CCC

iportinflowsofnumNCC outk

i .*

RR

Page 17: Modeling the Interactions of Congestion Control and  Switch Scheduling

17

MWM Scheduling

Three modes: Starvation Oscillation Equalization

LQF

Page 18: Modeling the Interactions of Congestion Control and  Switch Scheduling

18

MWM – Starvation Mode

ΔtC – time before window starts growing againΔtE – time to equalize the queue

ΔtE >ΔtCAlways Q1 > Q2 : Starvation mode

Congestion transitinpacketsW ~

Page 19: Modeling the Interactions of Congestion Control and  Switch Scheduling

19

MWM – Oscillation Mode

ΔtC – time before window starts growing againΔtE – time to equalize the queues

ΔtE <ΔtCAny of the queues might start

growing after congestion:Oscillation mode

transitinpacketsW ~

Time

Con

gest

ion

Win

dow

W1, W1

Q1

λ1

Q2

W1

W1,max

W1,max /2

ΔtC

ΔtE

C1

W1

Que

ue L

engt

h B

Arr

ival

s an

d D

epar

ture

s

Time

Time

λ1

W1, W1

λ1,2, C2

~ ~

~W2

λ2, C2

C1

Q2

Q1

λ2

C2

C1,2

W2

Congestion

Page 20: Modeling the Interactions of Congestion Control and  Switch Scheduling

20

MWM – Equalization Mode Until now we talked about TCP only. How does UDP (non-responsive traffic) affect the model? In equalization mode - roughly Q1(t)=Q2(t) If whenever Q1(t)>Q2(t) , then no prevailing queue

)()( 21 tdtdQt

dtdQ

For UDP arrivals rate large enough, the model looks likeUDP + MWM

UDP + MWMC1 = λ1

C2 = λ2

As long as λ1+λ2< Cout

Fair

Page 21: Modeling the Interactions of Congestion Control and  Switch Scheduling

21

Simulations - MWM Modes

Simulation parameters:Fig. 1 –2 TCP flows, no UDP, Cout=1Mbps, B=41KB , avg. tp

= 100/150 ms

Fig. 2 – 10 TCP flows, no UDP, Cout = 5Mbps, B=150KB , avg. tp = 100/150 ms

Fig. 3 – 2 TCP flows, Cout = 2Mbps, B=31KB, UDP = 20%*C , avg. tp

= 100/150 ms

2x1 MWM Starvation Mode

2x1 MWM Oscillation Mode

2x1 MWM Equalization Mode

Page 22: Modeling the Interactions of Congestion Control and  Switch Scheduling

22

Outline

IntroductionFairnessNetwork DynamicsNxN SwitchSimulations

Page 23: Modeling the Interactions of Congestion Control and  Switch Scheduling

23

Network Dynamics Set of equations describing the dynamics of Internet

traffic through Nx1 IQ switch.1. Congestion control equations (users)

TCP Stable phase TCP Congestion phase UDP flow

2. Switch scheduling equations (routers) iSLIP MWM

TCP Source 1,1

Scheduler

Destination 1

TCP Source 1,m1 C in

C out

Queue 1

TCP Source N,1

TCP Source N,mN C in

Queue N

UDP Source N

UDP Source 1

Page 24: Modeling the Interactions of Congestion Control and  Switch Scheduling

24

Network Dynamics - iSLIP Set of equations describing the dynamics of Internet

traffic through Nx1 IQ switch.1. Congestion control equations

TCP Stable phase TCP Congestion phase UDP flow

2. Switch scheduling equations iSLIP

2 equations per flow:- Congestion control- Switch scheduling

2 variables per flow:NiSktCtQ i

kk ,1,),(),(

Page 25: Modeling the Interactions of Congestion Control and  Switch Scheduling

25

Network Dynamics - MWM Set of equations describing the dynamics of Internet

traffic through Nx1 IQ switch.1. Congestion control equations

TCP Stable phase TCP Congestion phase UDP flow

2. Switch scheduling equations

MWM

2 equations per flow- Congestion control- Switch scheduling

2 variables per flowNiSktCtQ i

kk ,1,),(),(

Page 26: Modeling the Interactions of Congestion Control and  Switch Scheduling

26

Simulations – iSLIP Network Dynamics

Simulation parameters:2x1, 100 TCP flows, 5%*Cout UDP rate, Cout= 100Mbps, B=180KB, avg. tp = 100/150 ms

Matlab Model Ns2 Simulation

Time (sec)Time (sec)

Page 27: Modeling the Interactions of Congestion Control and  Switch Scheduling

27

Simulations – MWM Network Dynamics

Matlab Model Ns2 Simulation

Simulation parameters:2x1, 100 TCP flows, UDP rate 5%*Cout, Cout= 5Mbps, B=70KB, avg. tp = 100/150 ms

Time (sec)Time (sec)

(equalization mode)

Page 28: Modeling the Interactions of Congestion Control and  Switch Scheduling

28

Outline

IntroductionFairnessNetwork DynamicsNxN switchSimulations

Page 29: Modeling the Interactions of Congestion Control and  Switch Scheduling

29

NxN switch

Nx1 → NxN

MWM: We expect equalization/starvation of the number of packets in permutations, not in individual queues.

3,32,31,3

3,22,21,2

3,12,11,1

QQQQQQQQQ

1,3

1,2

1,1

QQQ

Page 30: Modeling the Interactions of Congestion Control and  Switch Scheduling

30

Simulations –3x3 MWM

Equalization mode(for permutations)

Starvation mode(for permutations)

Simulation Parameters:100 TCP flows per input/output pair and UDP rate 5%*Cout

Cout = 100Mbps, B=2.5MB, avg. tp=100ms Cout = 1Mbps, B=10MB, avg. tp=100ms

Page 31: Modeling the Interactions of Congestion Control and  Switch Scheduling

31

Summary

Interactions of congestion control and switch scheduling can lead to extreme unfairness and flow starvation.

iSLIP switch model can be fair for ports, not for flows. Three modes of MWM behavior: starvation, oscillation

and equalization. Dynamics of Internet traffic in real iSLIP and MWM

switches. iSLIP less unfair than MWM.

Page 32: Modeling the Interactions of Congestion Control and  Switch Scheduling

Thank you.