Performance Ponderings

of

Dr. Neil Gunther

1. A General Theory of Computational Scalability Based on Rational Functions (2008)
   The main theorem in this paper:

   The universal scalability law is equivalent to the synchronous queueing bound on throughput in a linear, load-dependent, machine repairman model,

   is the generalization of paper 24.
   
   
2. Getting in the Zone for Successful Scalability (2008)
   Jointly with J. Holtman. Accepted for CMG 2008, Las Vegas, Nevada.

   Abstract: The Universal Scalability Law (USL) is an analytic function used to quantify application scaling. It is universal because it subsumes Amdahl's law (AL) and linear scaling (LS) as special cases. Using simulation, we show (1) that USL is equivalent to synchronous queueing in a load-dependent machine repairman model, and (2) how LS, AL and USL can be regarded as boundaries defining three performance zones. Typical throughput measurements lie in all three zones. Simulation scenarios provide insight into which application features should be tuned to get into the optimal performance zone.

   
   
   
3. Multidimensional Visualization of Oracle Performance Using Barry007 (2008)
   Jointly with T. Põder. Accepted for CMG 2008, Las Vegas, Nevada.

   Abstract: Most generic performance tools display only system-level performance data using 2-dimensional plot or diagram, and this limits the informational detail that can be displayed. A modern relational database system like Oracle, however, can concurrently serve thousands of client processes with different workload characteristics and generic data displays inevitably hide important information. Drawing on our previous work, this paper demonstrates the application of Barry007 (See paper 6) multidimensional visualization for analyzing Oracle end-user session-level performance showing both collective trends and individual performance anomalies.

   
   
   
4. Eine Chance für Linux (2008)
   Appears in the May 18 volume of Linux Technical Review. (in German)

   Abstract (Translation): Linux could be in a position to expand its presence in the server market by looking to mainframe computer performance management as a role model and adapting its instrumentation accordingly.

   
   
   
5. Better Performance Management Through Better Visualization Tools (2008)
   Invited presentation at the Hotsos Symposium in Dallas, Texas, March 2-6 2008.
   
   
6. Seeing It All at Once with Barry (2007)
   Jointly with M. F. Jauvin. Presented at CMG 2007, San Diego, California.
   Paper (PDF), Slides (PDF), Animations (HTML), Tools (HTML).
   
   
7. Leistungsdiagnostik (Load Averages and Stretch Factors) (2007)
   To appear in the July 2007 issue of Linux Magazin. (in German)
   
   
8. Moore's Law: More or Less? (2007)
   Published in the May issue of the CMG MeasureIT e-zine.
   
   
9. Visualizing Virtualization (2007)
   Guest editorial for the March issue of the CMG e-zine called MeasureIT.
   
   
10. Berechenbare Performance (Predicting Performance) (2007)
    Invited paper published in the Linux Technical Review 02 Ð Monitoring. (in German)
    
    
11. Guerrilla Scalability: How to Do Virtual Load Testing (2007)
    Invited presentation at the Hotsos Symposium 2007, March, Dallas, Texas.
    
    
12. The Virtualization Spectrum from Hyperthreads to GRIDs (2006)
    This paper, presented at CMG 2006, Reno, Nevada, is based on the following observations:
    • Disparate types of virtual machines lie on a discrete spectrum bounded by hyperthreading at one extreme and hyperservices at the other,
      
      
    • Poll-based scheduling is the common architectural element in most virtual machine implementations.
      
      
    The associated polling frequency (from GHz to μHz) positions each virtual machine implementation into a region of the VM-spectrum. Several case studies are analyzed to illustrate how this insight can make virtual machines more visible to performance management techniques.
    
    
13. Reconstructing the Future: Capacity Planning with Data That's Gone Troppo (2006)
    Jointly with S. Jenkin. Paper presented at CMG-A 2006, Sydney, Australia.
    
    
14. Benchmarking Blunders and Things That Go Bump in the Night (2006)
    Published as Part I and Part II in the CMG MeasureIT online magazine.
    
    
15. Unification of Amdahl's Law, LogP and Other Performance Models for Message-Passing Architectures (2005)
    This paper generalizes the theorem in paper 24 below and was presented at PDCS 2005 VII International Conference on Parallel and Distributed Computing Systems
    
    
16. (Numerical) Investigations into Physical Power-law Models of Internet Traffic Using the Renormalization Group (2005)
    Paper presented at the Triennial Conference of the International Federation of Operations Research Societies, Honolulu, Hawaii, July 11-15, 2005.
    Uses the real-space variant of the renormalization group to exclude certain models that have appeared in the literature to account for so-called self-similar Internet traffic and further suggests that the claimed ramifications for Internet capacity planning may have been over-emphasized.
    Chapter 10 of Guerrilla Capacity Planning presents these conclusions in a less mathematical form.
    
    
17. Millennium Performance Problem 1: Performance Visualization (2005)
    Published in the CMG MeasureIT online magazine.
    
    
18. Benchmarking Blunders and Things That Go Bump in the Night (2004)
    Presented at WORP2 Workshop 2004
    Available from arXiv server.
    
    
19. How to Get Unbelievable Load Test Results (2004)
    Featured at TeamQuest Corporation as an online capacity planning column.
    
    
20. Performance Evaluation of Packet-to-Cell Segmentation Schemes in Input Buffered Packet Switches (2003)
    Jointly with K. J. Christensen, K. Yoshigoe and A. Roginsky
    Presented at High-Speed Networks Symposium of the IEEE International Conference on Communications (ICC 2004).
    Available from arXiv server.
    
    
21. Series on the UNIX Load Average Metric (2003-2004)
    TeamQuest online performance column.
    • LA Triplets Quiz
      
      
    • Part 1 How It Works
      
      
    • Part 2 Not Your Average Average
      
      
    • Addendum Hz vs. HZ
      
      
    NOTE: The hyperlinked version of the Linux kernel is release 2.6.xx
    This information, like everything else, can be found in the online files along with the source code (as cited in my writings).
    It also appears as Chapter 4 in my book Analyzing Computer System Performance with Perl::PDQ.
    An updated paper on this topic was presented at CMG 2004.
    
    
22. Series on Guerrilla Capacity Planning (2003)
    These two articles:
    • PART 1: Hit-and-Run Tactics for Website Scalability
      
      
    • PART II: Weapons of Mass Instruction
      
      
    were published in the CMG MeasureIT online magazine.
    
    
23. Characterization of the Burst Stabilization Protocol for the RR/CICQ Switch (2003)
    Jointly with K. J. Christensen and K. Yoshigoe
    Accepted by IEEE Conference on Local Computer Networks
    Download as a PDF from arXiv server.
    
    
24. A New Interpretation of Amdahl's Law and Geometric Scalability (2002)
    Amongst other things, this paper presents the theorem:

    Amdahl's law for parallel speedup is equivalent to the synchronous queueing bound on throughput in the repairman model of a symmetric multiprocessor.

    
    
    
25. Hit-and-Run Tactics Enable Guerrilla Capacity Planning (2002)
    Published in IEEE IT Professional journal, pp. 40-46, July-August issue, 2002.
    
    
26. Capacity Calculations: Handle with Care (2002)
    TeamQuest online column.
    
    
27. Hypernets: Good (G)news for Gnutella! (2002)
    Online article responding to an earlier analysis of Gnutella written by Jordan Ritter in 2001.
    Measurements of both Napster and Gnutella are also disussed in this 2003 paper.
    I point out that hypernets like a 20-degree virtual hypertorus or hypercube are much more efficient than a tree.
    I looks as though BitTorrent if fact does something like this.
    This online article was slashdotted in Feb, 2002.
    
    
28. Of Buses and Bunching: Strangeness in the Queue (2001)
    TeamQuest online column.
    
    
29. Quantifying Application and Server Scalability (2001)
    The following series of three articles:
    • Commercial Clusters and Scalability
      
      
    • How to Measure an Elephant
      
      
    • Evaluating Scalability Parameters: A Fitting End
      
      
    were published as TeamQuest online columns.
    
    
30. How to Write Application Probes (Updated 2001)
    TeamQuest performance column online.
    
    
31. Scalability Models for a Hypergrowth e-Commerce Website (2000)
    Published in the Springer Lecture Notes in Computer Science series.
    
    
32. BIRDS-I: A Benchmark for Image Retrieval on the Internet (2000)
    Tech Report published by HP Labs.
    
    
33. Windows NT Scalability (1997-1998)
    The following series of three papers:
    • NT to the Max (NoT!)
      
      
    • The ABC's of TPC's
      
      
    • How to Stack Cyberbrix
      
      
    were published in the USENIX journal.
    
    
34. The MP Effect: Parallel Processing in Pictures (1996)
    Received CMG 1996 Best Paper award.
    
    
35. A Simple Capacity Model of Massively Parallel Transaction Systems (1993)
    This is the original paper that forms the basis of the Universal Law of Computational Scaling, and was presented at CMG 1993, San Diego, California.
    
    
36. The Collapse of Internet Performance (1988)
    Online article.