The available bandwidth of a path directly impacts the per- formance of throughput sensitive applications, e.g., p2p con- tent replication or podcasting. Several tools have been de- vised to estimate the available bandwidth. The vast major- ity of these tools follow either the Probe Rate Model (PRM) or the Probe Gap Model (PGM). Lao et al.  and Liu et al.  have identified biases in the PGM approach that lead to consistent underestimations of the available bandwidth. Those results were obtained under the ideal assumption of stationary cross traffic. In this note, we confirm the existence of these biases ex- perimentally, i.e., for the case of non stationary cross traffic. To do so, we compare one representative of the PRM family, namely Pathload, and one representative of the PGM fam- ily, namely Spruce, using long term (several day long) traces collected on an example path. We first propose a methodology to compare operational results of two available bandwidth measurement tools. Based on the sanitized data obtained using the previous method- ology, we next show that the biases identified by previous works are clearly observable on the long term, even with non stationary cross traffic. We further uncover the formal link that exists between the work by Liu et al. and the one by Lao et al.
Operational comparison of available bandwidth estimation tools
ACM SIGCOMM Computer Communications Review, Volume 38 N°1, January 2008
© ACM, 2008. This is the author's version of the work. It is posted here by permission of ACM for your personal use. Not for redistribution. The definitive version was published in ACM SIGCOMM Computer Communications Review, Volume 38 N°1, January 2008 http://doi.acm.org/10.1145/1341431.1341438
PERMALINK : https://www.eurecom.fr/publication/2413