Abstract
This paper investigates the practical issues in applying network tomography to monitor failures. We outline an approach for selecting paths to monitor, detecting and confirming the existence of a failure, correlating multiple independent observations into a single failure event, and applying existing binary networking tomography algorithms to identify failures. We evaluate the ability of network tomography algorithms to correctly detect and identify failures in a controlled environment on the VINI testbed.
- A. Bavier, N. Feamster, M. Huang, J. Rexford, and L. Peterson. In VINI Veritas: Realistic and Controlled Network Experimentation. In Proc. ACM SIGCOMM, 2006. Google ScholarDigital Library
- R. Caceres, N. Duffield, S. Moon, and D. Towsley. Inference of Internal Loss Rates in the MBone. In Proc. IEEE Global Internet, 1999.Google ScholarCross Ref
- R. Caceres, N.G. Duffield, J. Horowitz, D.F. Towsley, and T. Bu. Multicast-Based Inference of Network-Internal Characteristics: Accuracy of Packet Loss Estimation. In Proc. IEEE INFOCOM, 1999.Google ScholarCross Ref
- R. Castro, M. Coates, G. Liang, R. Nowak, and B. Yu. Network Tomography: Recent Developments. Statistical Science, 19(3):499--517, 2004.Google ScholarCross Ref
- A. Dhamdhere, R. Teixeira, C. Dovrolis, and C. Diot. NetDiagnoser:Troubleshooting network unreachabilities using end-to-end probes and routing data. In Proc. CoNEXT, 2007. Google ScholarDigital Library
- N. Duffield. Network tomography of binary network performance characteristics. IEEE Trans. Information Theory, 52, 2006. Google ScholarDigital Library
- N.G. Duffield, F.L. Presti, V. Paxson,and D.F. Towsley. Inferring Link Loss Using Striped Unicast Probes. In Proc. IEEE INFOCOM, 2001.Google ScholarCross Ref
- S. Kandula, D. Katabi, and J.-P. Vasseur. Shrink: A Tool for Failure Diagnosis in IP Networks. In ACM SIGCOMM Workshop on mining network data (MineNet), August 2005. Google ScholarDigital Library
- E. Katz-Bassett, H.V. Madhyastha, J.P. John, A. Krishnamurthy, D. Wetherall, and T. Anderson. Studying Black Holes in the Internet with Hubble. In Proc. USENIX Symposium on Networked Systems Design and Implementation, 2008. Google ScholarDigital Library
- I. Katzela and M. Schwartz. Schemes for Fault Identification in Communication Networks. IEEE/ACM Trans. Networking, 3(6), 1995. Google ScholarDigital Library
- Keynote Systems -- The mobile and Internet performance authority. http://www.keynote.com/.Google Scholar
- R.R. Kompella, J. Yates, A. Greenberg, and A.C. Snoeren. Detection and Localization of Network Blackholes. In Proc. IEEE INFOCOM, May 2007.Google Scholar
- H. Nguyen and P. Thiran. Active measurement for multiple link failures diagnosis in ip networks. In Proc. of Passive and Active Measurement Workshop, 2004.Google ScholarCross Ref
- H. Nguyen and P. Thiran. Network Loss Inference with Second Order Statistics of End-to-End Flows. In Proc. Internet Measurement Conference, 2007. Google ScholarDigital Library
- Quagga Routing Suite. http://www.quagga.net/.Google Scholar
- RIPE. Test Traffic Measurements Service. http://www.ripe.net/ttm/.Google Scholar
- M. Steinder and A.S. Sethi. Probabilistic Fault Localization in Communication Systems Using Belief Networks. IEEE/ACM Trans. Networking, 12(5), 2004. Google ScholarDigital Library
- M. Zhang, C. Zhang, V. Pai, L.Peterson, and R. Wang. PlanetSeer: Internet Path Failure Monitoring and Characterization in Wide-Area Services. In Proc. USENIX OSDI, Dec 2004. Google ScholarDigital Library
Index Terms
- Practical issues with using network tomography for fault diagnosis
Recommendations
Distributed Link Anomaly Detection via Partial Network Tomography
We consider the problem of detecting link loss anomalies from end-to-end measurements using network tomography. Network tomography provides an alternative to traditional means of network monitoring by inferring link-level performance characteristics ...
SDN enhanced tomography for performance profiling in cloud network
For cloud network performance profiling, network tomography is useful for deducing the network performance based on end‐to‐end measurement. However, most tomography problems are under‐constrained, thus requires additional assumptions in order to be ...
Measurement methods for fast and accurate blackhole identification with binary tomography
IMC '09: Proceedings of the 9th ACM SIGCOMM conference on Internet measurementBinary tomography - the process of identifying faulty network links through coordinated end-to-end probes - is a promising method for detecting failures that the network does not automatically mask (e.g., network "blackholes"). Because tomography is ...
Comments