Abstract
Software systems obey the 80/20 rule: aggressively optimizing a vital few execution paths yields large speedups. However, finding the vital few paths can be difficult, especially for large systems like web applications. This paper describes a novel approach to finding bottlenecks in such systems, given (possibly very large) profiles of system executions. In the approach, for each kind of profile (for example, call-tree profiles), a tool developer implements a simple profile interface that exposes a small set of primitives for selecting summaries of profile measurements and querying how summaries overlap. Next, an analyst uses a search tool, which is written to the profile interface and thus independent of the kind of profile, to find bottlenecks. Our search tool (Bottlenecks) manages the bookkeeping of the search for bottlenecks and provides heuristics that automatically suggest likely bottlenecks. In one case study, after using Bottlenecks for half an hour, one of the authors found 14 bottlenecks in IBM’s WebSphere Application Server. By optimizing some of these bottlenecks, we obtained a throughput improvement of 23% on the Trade3 benchmark. The optimizations include novel optimizations of J2EE and Java security, which exploit the high temporal and spatial redundancy of security checks.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Aguilera, M.K., Mogul, J.C., Wiener, J.L., Reynolds, P., Muthitacharoen, A.: Performance debugging for distributed systems of black boxes. In: Proceedings of the Nineteenth ACM Symposium on Operating Systems Principles, pp. 74–89. ACM Press, New York (2003)
Ammons, G., Ball, T., Larus, J.R.: Exploiting hardware performance counters with flow and context sensitive profiling. In: Proceedings of the ACM SIGPLAN 1997 Conference on Programming Language Design and Implementation, pp. 85–96. ACM Press, New York (1997)
Real-time ArcFlow, http://www.ibm.com/developerworks/oss/pi
Ball, T., Larus, J.R.: Efficient path profiling. In: Proceedings of the 29th Annual ACM/IEEE International Symposium on Microarchitecture, pp. 46–57. IEEE Computer Society, Los Alamitos (1996)
Ball, T., Larus, J.R., Rosay, G.: Analyzing path profiles with the Hot Path Browser. In: Workshop on Profile and Feedback-Directed Compilation (1998)
Ball, T., Mataga, P., Sagiv, S.: Edge profiling versus path profiling: The showdown. In: Symposium on Principles of Programming Languages, pp. 134–148 (1998)
Ball, T., Larus, J.R.: Optimally profiling and tracing programs. ACM Transactions on Programming Languages and Systems 16(3), 1319–1360 (1994)
Corwin, J., Bacon, D.F., Grove, D., Murthy, C.: MJ: A rational module system for Java and its applications. In: Proceedings of the 18th ACM SIGPLAN Conference on Object-oriented Programming, Systems, Languages, and Applications, pp. 241–254. ACM Press, New York (2003)
IBM DB2 Universal Database, http://www.ibm.com/db2
De Rose, L., Reed, D.A.: SvPablo: A multi-language architectureindependent performance analysis system. In: Proceedings of the International Conference on Parallel Processing (ICPP 1999) (September 1999)
Fields, B.A., Bodík, R., Hill, M.D., Newburn, C.J.: Using interaction costs for microarchitectural bottleneck analysis. In: Proceedings of the 36th Annual IEEE/ACM International Symposium on Microarchitecture (MICRO-36), December 2003, pp. 228–242 (2003)
Hall, R.J.: Call path refinement profiles. IEEE Transactions on Software Engineering 21(6), 481–496 (1995)
Hall, R.J.: CPPROFJ: Aspect-capable call path profiling of multi-threaded Java applications. In: Proceedings of the 17th IEEE International Conference on Automated Software Engineering (ASE 2002), September 2002, pp. 107–116 (2002)
Java 2 Platform, Enterprise Edition (J2EE), http://java.sun.com/j2ee
Java 2 Platform, Standard Edition (J2SE), http://java.sun.com/j2se
Juran, J.M., Godfrey, A.B. (eds.): Juran’s Quality Handbook, 5th edn. McGraw-Hill, New York (1999)
Larus, J.R.: Whole program paths. In: Proceedings of the ACM SIGPLAN 1999 Conference on Programming Language Design and Implementation, pp. 259–269. ACM Press, New York (1999)
IBM Tivoli Directory Server, http://www.ibm.com/tivoli
McCabe, T.J., Schulmeyer, G.G.: The Pareto Principle Applied to Software Quality Assurance. In: Handbook of Software Quality Assurance, pp. 178–210. Van Nostrand Reinhold Company (1987)
Mellor-Crummey, J., Fowler, R., Marin, G., Tallent, N.: HPCView: A tool for top-down analysis of node performance. The Journal of SuperComputing 23, 81–101 (2002)
Melski, D., Reps, T.W.: Interprocedural path profiling. In: Computational Complexity, pp. 47–62 (1999)
Miller, B.P., Callaghan, M.D., Cargille, J.M., Hollingsworth, J.K., Irvin, R.B., Karavanic, K.L., Kunchithapadam, K., Newhall, T.: The Paradyn parallel performance measurement tool. IEEE Computer 28(11), 37–46 (1995)
Objective Caml, http://www.ocaml.org
O’Callahan, R., Marinov, D.: Object equality profiling. In: Proceedings of the 18th ACM SIGPLAN Conference on Object-oriented Programming, Systems, Languages, and Applications (OOPSLA 2003), October 2003, pp. 313–325 (2003)
Red Hat Linux, http://www.redhat.com
Roth, P.C., Miller, B.P.: Deep start: A hybrid strategy for automated performance searches. In: Monien, B., Feldmann, R.L. (eds.) Euro-Par 2002. LNCS, vol. 2400, p. 86. Springer, Heidelberg (2002)
Sevitsky, G., De Pauw, W., Konuru, R.: An information exploration tool for performance analysis of Java programs. In: Proceedings of TOOLS Europe (2001)
SPECjAppServer2002, http://www.specbench.org/jAppServer2002
IBM Trade3 J2EE Benchmark Application, http://www.ibm.com
WebSphere Application Server, http://www.ibm.com/websphere
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ammons, G., Choi, JD., Gupta, M., Swamy, N. (2004). Finding and Removing Performance Bottlenecks in Large Systems. In: Odersky, M. (eds) ECOOP 2004 – Object-Oriented Programming. ECOOP 2004. Lecture Notes in Computer Science, vol 3086. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-24851-4_8
Download citation
DOI: https://doi.org/10.1007/978-3-540-24851-4_8
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-22159-3
Online ISBN: 978-3-540-24851-4
eBook Packages: Springer Book Archive