[e2e] packet-pair probe implementation

[Constantine Dovrolis]

Jon Crowcroft wrote:

> joking aside:
> Van's original release notes with pathchar explain how you derive the
> capacity from a series of measurements...
>
> the biggest problem i have had with all the pathchar variants
> is level 2 trickery interfering with the queue service rate
> (on wireless (MAC and GPRS scheduling), on MPLS (ATM or frame relay
> CIF window effects etc), on paths with multilink, isdn channel
> bonding, or multipath routing in operation, etc etc etc)

The effect of hidden layer 2 devices is something that has been
studied in detail. Unfortunately there is no general way to fix
the pathchar estimation methodology in the presence of store-and-forward
layer 2 boxes.
The related references are:

@INPROCEEDINGS{pasztor:imw02,
     AUTHOR = "A. Pasztor and D. Veitch",
     TITLE = "{Active Probing using Packet Quartets}",
     BOOKTITLE = "Proceedings Internet Measurement Workshop (IMW)",
     YEAR = "2002"
}

@INPROCEEDINGS{prasad:infocom03,
     AUTHOR = "R. S. Prasad and C. Dovrolis and B. A. Mah",
     TITLE = "{The Effect of Layer-2 Store-and-Forward Devices on Per-Hop
               Capacity Estimation}",
     BOOKTITLE = "Proceedings of IEEE INFOCOM",
     YEAR = "2003"
}

I want to emphasize though that pathchar does not use packet pairs,
but a different methodology that we call "Variable Packet Size"
probing. Capacity estimation techniques based on packet dispersion
(i.e., packet pairs and trains) are not affected by layer 2 devices.


Constantinos

--------------------------------------------------------------
Constantinos Dovrolis | 218 GCATT | 404-385-4205
Assistant Professor | Networking and Telecommunications Group
College of Computing | Georgia Institute of Technology
dovrolis at cc.gatech.edu
http://www.cc.gatech.edu/fac/Constantinos.Dovrolis/