pathchirp efficient available bandwidth estimation

24
pathChirp Efficient Available Bandwidth Estimation Vinay Ribeiro Rice University Rolf Riedi Jiri Navratil Rich Baraniuk Les Cottrell (Rice) (SLAC)

Upload: patty

Post on 25-Feb-2016

31 views

Category:

Documents


2 download

DESCRIPTION

pathChirp Efficient Available Bandwidth Estimation. Vinay Ribeiro Rice University Rolf Riedi Jiri Navratil Rich Baraniuk Les Cottrell (Rice) (SLAC). Network Model. Packet delay = constant term (propagation, service time) - PowerPoint PPT Presentation

TRANSCRIPT

Page 1: pathChirp Efficient Available Bandwidth Estimation

pathChirp

Efficient Available Bandwidth Estimation

Vinay RibeiroRice University

Rolf Riedi Jiri NavratilRich Baraniuk Les Cottrell

(Rice) (SLAC)

Page 2: pathChirp Efficient Available Bandwidth Estimation

Network Model

Packet delay = constant term (propagation,

service time) + variable term (queuing delay)

• End-to-end paths– Multi-hop– No packet reordering

• Router queues– FIFO– Constant service rate

Page 3: pathChirp Efficient Available Bandwidth Estimation

Available Bandwidth• Unused capacity along

path

)],0[(min],0[number queue T

TACTB iii

Available bandwidth:

• Goal: use end-to-end probing to estimate available bandwidth

Page 4: pathChirp Efficient Available Bandwidth Estimation

Applications

• Network monitoring

• Server selection• Route selection (e.g. BGP)

• SLA verification• Congestion control

Page 5: pathChirp Efficient Available Bandwidth Estimation

Available Bandwidth Probing Tool

Requirements• Fast estimate within few RTTs

• Unobtrusive introduce light probing load

• Accurate

• No topology information (e.g. link speeds)

• Robust to multiple congested links

• No topology information (e.g. link speeds)

• Robust to multiple congested links

Page 6: pathChirp Efficient Available Bandwidth Estimation

Principle of Self-Induced Congestion

• Advantages– No topology information required– Robust to multiple bottlenecks

• TCP-Vegas uses self-induced congestion principle

Probing rate < available bw no delay increase

Probing rate > available bw delay increases

Page 7: pathChirp Efficient Available Bandwidth Estimation

Trains of Packet-Pairs (TOPP) [Melander et al]

)( st)( rt

• Vary sender packet-pair spacing• Compute avg. receiver packet-pair spacing• Constrained regression based estimate

• Shortcoming: packet-pairs do not capture temporal queuing behavior useful for available bandwidth estimation Packet-pairsPacket train

Page 8: pathChirp Efficient Available Bandwidth Estimation

Pathload [Jain & Dovrolis]

• CBR packet trains • Vary rate of successive trains • Converge to available bandwidth

• Shortcoming Efficiency: only one data rate per train

Page 9: pathChirp Efficient Available Bandwidth Estimation

Chirp Packet Trains

• Exponentially decrease packet spacing within packet train

• Wide range of probing rates• Efficient: few packets

100Mbps-1 packets, 134.1

Page 10: pathChirp Efficient Available Bandwidth Estimation

Chirps vs. Packet-Pairs• Each chirp train of N packets contains N-1 packet pairs at

different spacings

• Reduces load by 50% – Chirps: N-1 packet spacings, N packets– Packet-pairs: N-1 packet spacings, 2N-2 packets

• Captures temporal queuing behavior

Page 11: pathChirp Efficient Available Bandwidth Estimation

Chirps vs. CBR Trains• Multiple rates in each chirping train

– Allows one estimate per-chirp

– Potentially more efficient estimation

Page 12: pathChirp Efficient Available Bandwidth Estimation

CBR Cross-Traffic Scenario

• Point of onset of increase in queuing delay gives available bandwidth

Page 13: pathChirp Efficient Available Bandwidth Estimation

Bursty Cross-Traffic Scenario

• Goal: exploit information in queuing delay signature

Page 14: pathChirp Efficient Available Bandwidth Estimation

PathChirp MethodologyI. Per-packet pair

available bandwidth, (k=packet number)

II. Per-chirp available bandwidth

III. Smooth per-chirp estimate over sliding time window of size

kk

kkk

t

tED

kE

Page 15: pathChirp Efficient Available Bandwidth Estimation

Self-Induced Congestion Heuristic

• Definitions: delay of packet k inst rate at packet k

kkkk

kkkk

REqqREqq

1

1

kqkk tR size/packet

Page 16: pathChirp Efficient Available Bandwidth Estimation

Excursions

• Must take care while using self-induced congestion principle• Segment signature into excursions from x-axis• Valid excursions are those consisting of at least “L” packets• Apply only to valid excursions

kk RE

Page 17: pathChirp Efficient Available Bandwidth Estimation

Setting Per-Packet Pair Available Bandwidth

• Valid excursion increasing queuing delaykk

kk

RE

RE

nk

kk

RE

RE

• Valid excursion decreasing queuing delay

nk

kk

RE

RE

•Last excursion• Invalid excursions

nk RE

Page 18: pathChirp Efficient Available Bandwidth Estimation

pathChirp Tool• UDP probe packets• No clock synchronization required, only uses

relative queuing delay within a chirp duration • Computation at receiver• Context switching detection• User specified average probing rate

• open source distribution at spin.rice.edu

Page 19: pathChirp Efficient Available Bandwidth Estimation

Performance with Varying Parameters

• Vary probe size, spread factor

• Probing load const.• Mean squared error

(MSE) of estimates Result: MSE decreases with increasing probe size, decreasing spread factor

Page 20: pathChirp Efficient Available Bandwidth Estimation

Multi-hop Experiments

• First queue is bottleneck

• Compare– No cross-traffic at

queue 2– With cross-traffic

at queue 2• Result: MSE close in

both scenarios

Page 21: pathChirp Efficient Available Bandwidth Estimation

Internet Experiments

• 3 common hops between SLACRice and ChicagoRice paths

• Estimates fall in proportion to introduced Poisson traffic

Page 22: pathChirp Efficient Available Bandwidth Estimation

Comparison with TOPP

30% utilization

• Equal avg. probing rates for pathChirp and TOPP

• Result: pathChirp outperforms TOPP

70% utilization

Page 23: pathChirp Efficient Available Bandwidth Estimation

Comparison with Pathload • 100Mbps links• pathChirp uses 10

times fewer bytes for comparable accuracy

Available bandwidth

Efficiency Accuracypathchirp pathload pathChirp

10-90%pathloadAvg.min-max

30Mbps 0.35MB 3.9MB 19-29Mbps 16-31Mbps50Mbps 0.75MB 5.6MB 39-48Mbps 39-52Mbps70Mbps 0.6MB 8.6MB 54-63Mbps 63-74Mbps

Page 24: pathChirp Efficient Available Bandwidth Estimation

Conclusions• Chirp trains

– Probe at multiple rates simultaneously– Efficient estimates

• pathChirp– Self-induced congestion– Excursion detection

• Experiments– Internet experiments promising– Large probe packet size, small spread factor better– Outperforms existing tools

• open-source code is available at spin.rice.edu

• Demo during 10:30a.m. break