LCN06MW - Computer Science and Engineering

advertisement

Experimental and Analytical Evaluation of Available Bandwidth Estimation Tools

Cesar D. Guerrero and Miguel A. Labrador

Department of Computer Science & Engineering

University of South Florida

• Motivation

• Problem

• Testbed Description

• Analytical Model

• Target Tools

• Performance Evaluation

• Conclusions

Outline

Motivation

Why to evaluate available bandwidth tools?

• Available bandwidth  to improve network applications performance.

• Applications  different time, accuracy, and overhead from estimators.

• Evaluation  determine whether a tool is suitable for an application.

Problem

What issues do we want to solve?

Topology

Link capacities

Packet loss rate

Delay

• Evaluate tools over the same variable network conditions

• Analytical model to have a theoretical value to compare with

Testbed Description

Architecture

Low cost

Link A

192.168.3.0/24

Link B

192.168.2.0/24

Link C

192.168.1.1/24

Link D

192.168.0.0/24

192.168.4.0/24

Client

Probing packets Cross Traffic Server

• Client and server hosting bandwidth estimation tools

• Intermediate nodes hosting a packet shaper and a traffic generator

• Phython applications running in all the machines to automatically perform experiments.

• Internet connected

Analytical Model

Jackson Network

Probing packets Cross Traffic

λ

8

8

λ

1

1

λ

2

2

λ

3

3

λ

4

4

λ

5

5

λ

6

6 λ

7

7

Client

λ

0

γ

1

γ

3

γ

5

γ

7

• Eight M/M/1 queues model input and output packet flows.

• The Jackson model gives the average arrival rate to a node

λ j

= γ j

+

Σ λ i

θ ij

• The available bandwidth is the minimum non utilized capacity of the queues associated to the links:

A = min i= 1,3,5,7

( A i

) = min i= 1,3,5,7

(1-ρ i

)

Server

Target Tools

Estimation Approaches

Probe Rate Model

• • Pathload.

• TOPP

• Pathchirp

• PTR

Probe Gap Model

• Delphy

Target Tools

Pathload grey region

Figure copied from the paper “

Pathload: A Measurement Tool for

End-to-end Available Bandwidth

” by M. Jain and C. Dovrolis

• Fleet of probing streams are sent to fill the available bandwidth.

• The one-way delay increases when the rate of the probing traffic is higher that the available bandwidth.

• In the gray region , the tool reports the available bandwidth

Target Tools

IGI turning point

• Estimates the cross traffic as a function of the amount of traffic inserted between a packet pair.

• Available bandwidth is given by the average rate of the packet train when the initial packet gap is equal to the output gap.

Figure copied from the paper “ Evaluation and

Characterization of Available Bandwidth Probing

Techniques

” by N. Hu and P. Steenkiste

Target Tools

Spruce

• Probing packets are sent with an intra-pair gap ( Δ in

) equal to the narrow link transmission time of a 1500B packet (to guarantee that the pair will be in the queue at the same time)

• Cross traffic is measured using the dispersion of the probing packets

( Δ out

) calculated at the receiver.

• It requires a previous calculation of the tight link capacity (

C )

A

C

 1

 out

 in

 in



Performance Evaluation

Experiments

• Metrics: accuracy, time, overhead

• 28 network scenarios : link capacities from 1 to 10 Mbps and from 10 to

100 Mbps

• Each scenario with four cross traffic loads : 0%, 25%, 50%, and 75% of the capacity

• Every estimation was performed 35 times

• Accuracy plots have a 95% confidence interval

11760 experiments

Performance Evaluation

Accuracy with 75% of the capacity as cross traffic

Estimated available bandwidth / total bandwidth (capacity)

Pathload IGI Spruce

Performance Evaluation

Relative Error

β  experiment al

A

 analytical analytical

A

A

Pathload IGI Spruce

Performance Evaluation

Convergence Time

Pathload IGI Spruce

Performance Evaluation

Overhead

Probing traffic / total bandwidth (capacity) in the tight link

Pathload IGI Spruce

Conclusions

• Main contributions:

 Low cost and flexible testbed to evaluate estimation tools in a controlled network.

Analytical model to fairly compare the tools accuracy with a theoretical value.

• Regarding to the tools evaluation:

Pathload is the most accurate tool but the slowest to converge

IGI is the fastest tool but the least accurate

Spruce is the least intrusive tool with intermediate accuracy and convergence time.

Experimental and Analytical Evaluation of Available Bandwidth Estimation Tools

Cesar D. Guerrero cguerrer@cse.usf.edu

Miguel A. Labrador labrador@cse.usf.edu

Department of Computer Science & Engineering

University of South Florida

Download