Answering what-if deployment and configuration questions with wise

ABSTRACT

Designers of content distribution networks often need to determine how changes to infrastructure deployment and configuration affect service response times when they deploy a new data center, change ISP peering, or change the mapping of clients to servers. Today, the designers use coarse, back-of-the-envelope calculations, or costly field deployments; they need better ways to evaluate the effects of such hypothetical "what-if" questions before the actual deployments. This paper presents What-If Scenario Evaluator (WISE), a tool that predicts the effects of possible configuration and deployment changes in content distribution networks. WISE makes three contributions: (1) an algorithm that uses traces from existing deployments to learn causality among factors that affect service response-time distributions; (2) an algorithm that uses the learned causal structure to estimate a dataset that is representative of the hypothetical scenario that a designer may wish to evaluate, and uses these datasets to predict future response-time distributions; (3) a scenario specification language that allows a network designer to easily express hypothetical deployment scenarios without being cognizant of the dependencies between variables that affect service response times. Our evaluation, both in a controlled setting and in a real-world field deployment at a large, global CDN, shows that WISE can quickly and accurately predict service response-time distributions for many practical What-If scenarios.

REFERENCES

• 1: Akamai Technologies. www.akamai.com
• 2: Martin Arlitt , Balachander Krishnamurthy , Jeffrey C. Mogul, Predicting short-transfer latency from TCP arcana: a trace-based validation, Proceedings of the 5th ACM SIGCOMM conference on Internet Measurement, p.19-19, October 19-21, 2005, Berkeley, CA
• 3: Luiz André Barroso , Jeffrey Dean , Urs Hölzle, Web Search for a Planet: The Google Cluster Architecture, IEEE Micro, v.23 n.2, p.22-28, March 2003 [doi>10.1109/MM.2003.1196112]
• 4: Paramvir Bahl , Ranveer Chandra , Albert Greenberg , Srikanth Kandula , David A. Maltz , Ming Zhang, Towards highly reliable enterprise network services via inference of multi-level dependencies, Proceedings of the 2007 conference on Applications, technologies, architectures, and protocols for computer communications, August 27-31, 2007, Kyoto, Japan
• 5: N. Cardwell, S. Savage, T. Anderson. Modeling TCP Latency. IEEE Infocomm 2000.
• 6: Gregory F. Cooper, A Simple Constraint-Based Algorithm for Efficiently Mining Observational Databases for Causal Relationships, Data Mining and Knowledge Discovery, v.1 n.2, p.203-224, 1997 [doi>10.1023/A:1009787925236]
• 7: Emulab Network Testbed. http://www.emulab.net
• 8: Nick Feamster , Jennifer Rexford, Network-wide prediction of BGP routes, IEEE/ACM Transactions on Networking (TON), v.15 n.2, p.253-266, April 2007 [doi>10.1109/TNET.2007.892876]
• 9: Michael J. Freedman , Eric Freudenthal , David Mazières, Democratizing content publication with coral, Proceedings of the 1st conference on Symposium on Networked Systems Design and Implementation, p.18-18, March 29-31, 2004, San Francisco, California
• 10: A. Gray, A. Moore, 'N-Body' Problems in Statistical Learning. Advances in Neural Information Processing Systems 13. 2000.
• 11: Lucene Hadoop. http://lucene.apache.org/hadoop/
• 12: Q. He, C. Dovrolis, M. Ammar. On the Predictability of Large Transfer TCP Throughput. ACM SIGCOMM 2006.
• 13: A. Barbir , B. Cain , R. Nair , O. Spatscheck, Known Content Network (CN) Request-Routing Mechanisms, RFC Editor, 2003
• 14: Srikanth Kandula , Dina Katabi , Jean-Philippe Vasseur, Shrink: a tool for failure diagnosis in IP networks, Proceedings of the 2005 ACM SIGCOMM workshop on Mining network data, August 26-26, 2005, Philadelphia, Pennsylvania, USA [doi>10.1145/1080173.1080178]
• 15: Ramana Rao Kompella , Jennifer Yates , Albert Greenberg , Alex C. Snoeren, IP fault localization via risk modeling, Proceedings of the 2nd conference on Symposium on Networked Systems Design & Implementation, p.57-70, May 02-04, 2005
• 16: Jeffrey Dean , Sanjay Ghemawat, MapReduce: simplified data processing on large clusters, Proceedings of the 6th conference on Symposium on Opearting Systems Design & Implementation, p.10-10, December 06-08, 2004, San Francisco, CA
• 17: Mariyam Mirza , Joel Sommers , Paul Barford , Xiaojin Zhu, A machine learning approach to TCP throughput prediction, Proceedings of the 2007 ACM SIGMETRICS international conference on Measurement and modeling of computer systems, June 12-16, 2007, San Diego, California, USA
• 18: Netezza http://www.netezza.com/
• 19: Jitendra Padhye , Victor Firoiu , Donald F. Towsley , James F. Kurose, Modeling TCP Reno performance: a simple model and its empirical validation, IEEE/ACM Transactions on Networking (TON), v.8 n.2, p.133-145, April 2000 [doi>10.1109/90.842137]
• 20: Judea Pearl, Causality: models, reasoning, and inference, Cambridge University Press, New York, NY, 2000
• 21: I. Rish, M. Brodie, S. Ma. Efficient Fault Diagnosis Using Probing. AAAI Spring Symposium on DMDP. 2002.
• 22: Rob Pike , Sean Dorward , Robert Griesemer , Sean Quinlan, Interpreting the data: Parallel analysis with Sawzall, Scientific Programming, v.13 n.4, p.277-298, October 2005
• 23: P. Sprites, C. Glymour. An Algorithm for fast recovery of sparse causal graphs. Social Science Computer Review 9. USENIX Symposium on Internet Technologies and Systems. 1997.
• 24: M. Tariq, A. Zeitoun, V. Valancius, N. Feamster, M. Ammar. Answering "What-if" Deployment and Configuration Questions with WISE. Georgia Tech Technical Report GT-CS-08-02. February 2008.
• 25: L. Wasserman. All of Statistics: A Concise Course in Statistical Inference. Springer Texts in Statistics. 2003.
• 26: J. Wolberg. Data Analysis Using the Method of Least Squares. Springer. Feb 2006.

INDEX TERMS

Primary Classification:
  C. Computer Systems Organization
  C.2 COMPUTER-COMMUNICATION NETWORKS
      C.2.3 Network Operations
          Subjects: Network management

General Terms:
Algorithms, Design, Management, Performance

Keywords:
content distribution networks, performance modeling, what-if scenario evaluation