Neil Gunther
Skip Abstract Section
Abstract
We often see more than 100 percent speedup efficiency! came the rejoinder to the innocent reminder that you can’t have more than 100 percent of anything. But this was just the first volley from software engineers during a presentation on how to quantify computer system scalability in terms of the speedup metric. In different venues, on subsequent occasions, that retort seemed to grow into a veritable chorus that not only was superlinear speedup commonly observed, but also the model used to quantify scalability for the past 20 years failed when applied to superlinear speedup data.
- Apache Whirr; https://whirr.apache.org.Google Scholar
- Calvert, C., Kulkarni, D. 2009. Essential LINQ. Boston, MA: Pearson Education Inc. Google ScholarDigital Library
- Cloudera Hadoop; http://www.cloudera.com/content/cloudera/en/downloads/cdh/cdh-4-7-0.html.Google Scholar
- Eijkhout, V. 2014. Introduction to high-performance scientific computing. Lulu.com. Google ScholarDigital Library
- Feynman, R. P. The Papp perpetual motion engine; http://hoaxes.org/comments/papparticle2.html.Google Scholar
- Gunther, N. J. 1993. A simple capacity model of massively parallel transaction systems. In Proceedings of International Computer Measurement Group Conference; http://www.perfdynamics.com/Papers/njgCMG93.pdf.Google Scholar
- Gunther, N. J. 2001. Performance and scalability models for a hypergrowth e-commerce Web site. In Performance Engineering, State of the Art and Current Trends. (Eds.) Dumke, R. R., Rautenstrauch, C., Schmietendorf, A., Scholz, A. Lecture Notes in Computer Science 2047: 267-282. Springer-Verlag. Google ScholarDigital Library
- Gunther, N. J. 2007. Guerrilla Capacity Planning: A Tactical Approach to Planning for Highly Scalable Applications and Services. Springer;
http://www.springer.com/computer/communication+networks/book/978-3-540-26138-4. Google ScholarDigital Library
- Gunther, N. J. 2008. A general theory of computational scalability based on rational functions; http://arxiv.org/abs/0808.1431.Google ScholarDigital Library
- Gunther, N. J. 2012. PostgreSQL scalability analysis deconstructed;
http://perfdynamics.blogspot.com/2012/04/postgresql-scalability-analysis.html.Google Scholar
- Gunther, N. J., Subramanyam, S., Parvu, S. 2010. Hidden scalability gotchas in Memcached and friends. VELOCITY Web Performance and Operations Conference;
http://velocityconf.com/velocity2010/public/schedule/detail/13046.Google Scholar
- Haas, R. 2011. Scalability, in graphical form, analyzed;
http://rhaas.blogspot.com/2011/09/scalability-in-graphical-form-analyzed.html.Google Scholar
- Hadoop Log Tools; https://github.com/melrief/Hadoop-Log-Tools.Google Scholar
- Hennessy, J. L., Patterson, D. A. 1996. Computer Architecture: A Quantitative Approach. Second edition. Waltham, MA: Morgan Kaufmann. Google ScholarDigital Library
- Hunt, P., Konar, M., Junqueira, F. P., Reed, B. 2010. ZooKeeper: Wait-free coordination for Internet-scale systems. In Proceedings of the Usenix Annual Technical Conference;
https://www.usenix.org/legacy/event/usenix10/tech/full_papers/Hunt.pdf. Google ScholarDigital Library
- O'Malley, O. 2008. TeraByte Sort on Apache Hadoop;
http://sortbenchmark.org/YahooHadoop.pdf.Google Scholar
- O'Malley, O., Murthy, A. C. 2009. Winning a 60 second dash with a yellow elephant; http://sortbenchmark.org/Yahoo2009.pdf.Google Scholar
- Parvu, S. 2012. Private communication.Google Scholar
- Performance Dynamics Company. 2014. How to quantify scalability (including calculator tools);
http://www.perfdynamics.com/Manifesto/USLscalability.html.Google Scholar
- Schwartz, B. 2011. Is VoltDB really as scalable as they claim? Percona MySQL Performance Blog;
http://www.percona.com/blog/2011/02/28/is-voltdb-really-as-scalable-as-they-claim/.Google Scholar
- sFlow. 2010. SDN analytics and control using sFlow standard Superlinear;
http://blog.sflow.com/2010/09/superlinear.html.Google Scholar
- Stackoverflow. Where does superlinear speedup come from?;
http://stackoverflow.com/questions/4332967/where-does-super-linear-speedup-come-from.Google Scholar
- Sun Fire X2270 M2 super-linear scaling of Hadoop TeraSort and CloudBurst benchmarks. 2010;
https://blogs.oracle.com/BestPerf/entry/20090920_x2270m2_hadoop.Google Scholar
- Sutter, H. 2008. Going superlinear. Dr. Dobb's Journal 33(3);
http://www.drdobbs.com/cpp/going-superlinear/206100542.Google Scholar
- Sutter, H. 2008. Super linearity and the bigger machine. Dr. Dobb's Journal 33(4);
http://www.drdobbs.com/parallel/super-linearity-and-the-bigger-machine/206903306.Google Scholar
- TechCrunch. 2015. AuroraTek tried to pitch us a gadget that breaks the laws of physics at CES;
http://techcrunch.com/2015/01/08/auroratek-tried-to-pitch-us-a-gadget-that-breaks-the-laws-of-physics-at-ces/.Google Scholar
- White, T. 2012. Hadoop: The Definitive Guide. Storage and Analysis at Internet Scale, 3rd edition. O'Reilly Media, Inc. Google ScholarDigital Library
- Yahoo! Hadoop Tutorial; https://developer.yahoo.com/hadoop/tutorial/module1.html#scalability.Google Scholar
Index Terms
- Hadoop Superlinear Scalability: The perpetual motion of parallel performance
Recommendations
Non-asymptotic superlinear convergence of standard quasi-Newton methods
AbstractIn this paper, we study and prove the non-asymptotic superlinear convergence rate of the Broyden class of quasi-Newton algorithms which includes the Davidon–Fletcher–Powell (DFP) method and the Broyden–Fletcher–Goldfarb–Shanno (BFGS) method. The ...
Comments