pathChirp : A Light-Weight Available Bandwidth Estimation Tool for Network-Aware Applications

Many grid computing applications require massive data transfers for distributed analysis. Knowledge of network properties like the available bandwidth along the communication paths between grid nodes can reduce data transfer times and improve scheduling of grid computing tasks thereby enhancing performance. This paper presents pathChirp, a light-weight active probing tool for estimating the available bandwidth on a communication network path. Based on the concept of “self-induced congestion,” pathChirp features an exponential flight pattern of probes we call a chirp. By rapidly increasing the probing rate within each chirp, pathChirp obtains a rich set of information from which to dynamically estimate the available bandwidth. PathChirp does not require synchronous nor highly stable clocks at the sender and receiver. Simulations and Internet experiments show that pathChirp provides good estimates of the available bandwidth while using only a fraction of the number of probe bytes that current state-of-the-art techniques use.

[1]  Kihong Park,et al.  Multiple Time Scale Congestion Control for Self-Similar Network Traffic , 1999, Perform. Evaluation.

[2]  Zhi-Li Zhang,et al.  Small-time scaling behaviors of Internet backbone traffic: an empirical study , 2003, IEEE INFOCOM 2003. Twenty-second Annual Joint Conference of the IEEE Computer and Communications Societies (IEEE Cat. No.03CH37428).

[3]  Richard G. Baraniuk,et al.  Multifractal Cross-Traffic Estimation , 2000 .

[4]  Philip A. Chou,et al.  Rate-distortion optimized streaming of packetized media , 2006, IEEE Transactions on Multimedia.

[5]  Jennifer C. Hou,et al.  On exploiting long range dependence of network traffic in measuring cross traffic on an end-to-end basis , 2003, IEEE INFOCOM 2003. Twenty-second Annual Joint Conference of the IEEE Computer and Communications Societies (IEEE Cat. No.03CH37428).

[6]  Fouad A. Tobagi,et al.  Analysis of measured single-hop delay from an operational backbone network , 2002, Proceedings.Twenty-First Annual Joint Conference of the IEEE Computer and Communications Societies.

[7]  Hari Balakrishnan,et al.  Resilient overlay networks , 2001, SOSP.

[8]  Mats Björkman,et al.  Regression-Based Available Bandwidth Measurements , 2002 .

[9]  Brian Neil Levine,et al.  Evaluation of a novel two-step server selection metric , 2001, Proceedings Ninth International Conference on Network Protocols. ICNP 2001.

[10]  Scott Shenker,et al.  Endpoint admission control: architectural issues and performance , 2000, SIGCOMM.

[11]  Mats Björkman,et al.  A new end-to-end probing and analysis method for estimating bandwidth bottlenecks , 2000, Globecom '00 - IEEE. Global Telecommunications Conference. Conference Record (Cat. No.00CH37137).

[12]  C. Dovrolis,et al.  End-to-end available bandwidth: measurement methodology, dynamics, and relation with TCP throughput , 2002, SIGCOMM '02.