combining multipath routing and congestion control for robustness peter key

21
Combining Multipath Routing and Combining Multipath Routing and Congestion Control for Congestion Control for Robustness Robustness Peter Key Peter Key

Post on 21-Dec-2015

221 views

Category:

Documents


1 download

TRANSCRIPT

Combining Multipath Routing and Combining Multipath Routing and Congestion Control for RobustnessCongestion Control for Robustness

Peter KeyPeter Key

Motivation

• Performance of Internet /overlays unpredictable – and hard to manage

• Multiple ownership / policies (eg BGP) can exacerbate performance problems

• … but diversity increasing– Multihoming– Mesh

• So why not harness the diversity?

Outline

• Motivation• Framework• Resource Pooling

– 2 resources– the function– Cutset dimensioning

• Multipath – Coordinated control– Fluid dynamics

• Route choices & architectures• Concluding remarks

Framework

• Network: capacited graph – G=[X,J]

• Edges have capacity Cj

• Routes s S , sets of edges

• Demands type r, associated source –destination, can use a set of routes

• Link-route incidence matrix A,

route flow incidence matrix B

Framework

• File Transfers– Arrival rate – Mean file size

– Nr in progress

• Streaming – Arrival rate

– Mean holding time

– Mr in progress

• Rate allocation : – xr to both types (fair share): exact rate depends on utility

function

rload r

rr

1r rF

r1

r

lrlr

rrr CxMN :

)(

Resource sharing

Fixed Routing

Dynamic Routing

Fixed Proportions

FMean transf er time

C-

Capacity C

2

F

2p

1-p

1 FTransf er time

2 C-

p 1-pTransf er time F

C-2 C-2 (1 )p p

2 max( ,1 )Stable C p p

F

– Assume performance measure

– non-decreasing in 1st arg., non-increasing in second

– Dimensioning means

– Eg

Performance : the function

( , )C

( , ) some measurable C D D

( , ) =(- ,0)C C , D1( , ) ( )C C

( , )C

Take a cutset C of the Graph G

Under resource pooling, necessary performance conditions are

Becomes interesting when related to sufficiency

Cutset Dimensioning

,j r

j

r jjC

C

D

C

C

Node cutsets:

(Keslassy et al)

• Symmetric case; – Valiant load balancing, – Dynamic routing

Mesh Network Example

6

1

5 4

2

3

and ij j ij j

r r

2 per link suffi cient traffi c matrices

rN

1r

N 2r

N

Multipath Routing: Utility functions

• Utility function associated with type r flow

• increasing, strictly concave etc– Eg TCP,

– Putting w=k/(RTT)2 implies familiar

( )rU x

( )U x w x

1 1 TCP f air:

( )r

r

xT p r

Cost functions

• Now require “cost” convex, and

• True for packet marking etc • with “prices” pj,:

• is prob of drop/marking at j when load is yj,

• Eg small buffer model

( , )j C

0

( , ) /jy

j j j j jy C p z C dz

( ; ) ( ; )L z C Lz LC

j j jp y C

min 1,j j

j j

by yC Cjp

Multipath

Maximise

;r r sr sr j r j s sr sr jr s j r s

N U B x N A B x C

over

• Coordinated

• Single utility function across possible routes flow can choose– Single dependence on RTT

0srx

Fluid Dynamics

• Scale arrival rates and capacities by large number L and take limits

• Gives limiting ODE (FLLN)

1

, 1

rrrr ML

mNL

n

( ) ( ) ( ) ( );

( ) ' ( )r r r r r

r r r r

n t n t x n t mt C

m t m t

Limit Theorems

• Theorem:– Under multipath routing, there is a unique

invariant point– System in Lyapunov stable (under mild

conditions on )– Allocation is only non-zero to routes s for

which “prices” on route are equal– When no streaming, offered load is split

optimally, independent of utility functions

ˆ ˆˆ,r r r r r rm n x

j

Remarks

• Prices on route s are

• Unless “prices” are equal on different routes, only one route is used

• Coordinated multipath chooses load fractions to minimise total “cost”– if no streaming traffic present, fractions

independent of utility functions

ˆ' ( ; )j s j j jj

A y C

rs

Remarks

• Coordinated multipath chooses load fractions to minimise total “cost”rs

,

ˆ ;rrj j s sr sr sr j

j s r

A B x C

Route Choices

• How to search for low cost paths?– Use 2 per nominal route, (eg “direct” +1)– Periodically add new route at random– Probe to chose which route to drop

• Cf “Sticky Random” DAR– “Power of 2”, Mitzenmacher

• Theorem: Under random path resampling, mulitpath routing will find an optimal feasible load split, if one exists

Architecture

• Need path diversity– Dual homing– Multiple addresses (eg IPv6)

• For overlays, wireless, or the Internet?

• Need coordinated congestion control, uncoordinated, parallel, inefficient (see Laurent’s talk …)– at transport or application layer

Summary: Multipath routing/multi-access

• Source /edge routing

• Halve delay (processor sharing)

• Resilience • Simpler dimensioning (cutsets)

C

C

C

C

22 vs 2p p

1 1

vs 2 2 ) ( )C C

• Robust routing provides robustness to– Traffic variations /uncertainty– Routing / BGP / Network operators

• Need to combine multipath routing with congestion control

• Challenges: – Time-scales for route adaptation– Removing RTT bias of TCP?

Summary

References

• Fluid models of integrated traffic and multipath routing, Peter Key & Laurent Massoulié, QUESTA, June 2006

• Network Programming methods for loss networks, Gibbens and Kelly, JSAC 1995

• Stability of end-to-end algorithms for joint routing and rate control, Kelly and Voice, CCR, 2005

• Dynamic Alternative Routing, Gibbens, Kelly and Key, ITC, 1989.