Abstract
Many studies have shown that the best performer among a set of garbage collectors tends to be different for different applications. Researchers have proposed applicationspecific selection of garbage collectors. In this work, we concentrate on a second dimension of the problem: the influence of program inputs on the selection of garbage collectors. We collect tens to hundreds of inputs for a set of Java benchmarks, and measure their performance on Jikes RVM with different heap sizes and garbage collectors. A rigorous statistical analysis produces four-fold insights. First, inputs influence the relative performance of garbage collectors significantly, causing large variations to the top set of garbage collectors across inputs. Profiling one or few runs is thus inadequate for selecting the garbage collector that works well for most inputs. Second, when the heap size ratio is fixed, one or two types of garbage collectors are enough to stimulate the top performance of the program on all inputs. Third, for some programs, the heap size ratio significantly affects the relative performance of different types of garbage collectors. For the selection of garbage collectors on those programs, it is necessary to have a cross-input predictive model that predicts the minimum possible heap size of the execution on an arbitrary input. Finally, by adoptingstatistical learning techniques, we investigate the cross-input predictability of the influence. Experimental results demonstrate that with regression and classification techniques, it is possible to predict the best garbage collector (along with the minimum possible heap size) with reasonable accuracy given an arbitrary input to an application. The exploration opens the opportunities for tailoring the selection of garbage collectors to not only applications but also their inputs.
- Java Grande benchmark. http://www2.epcc.ed.ac.uk/javagrande/.Google Scholar
- Spec jvm98. http://www.spec.org/jvm98/.Google Scholar
- M. Arnold, S. Fink, D. Grove, M. Hind, and P.F. Sweeney. Adaptive optimization in the Jalapeno JVM. In Proceedings of ACM SIGPLAN Conference on Object-Oriented Programming Systems, Languages and Applications, Minneapolis, MN, October 2000. Google ScholarDigital Library
- M. Arnold, A. Welc, and V.T. Rajan. Improving virtual machine performance using a cross-run profile repository. In the Conference on Object-Oriented Systems, Languages, and Applications, 2005. Google ScholarDigital Library
- P. Berube and J.N. Amaral. Benchmark design for robust profile-directed optimization. In Standard Performance Evaluation Corporation (SPEC) Workshop, 2007.Google Scholar
- S.M. Blackburn, P. Cheng, and K. McKinley. Oil and water: High performance garbage collection in Java with MMTk. In Proceedings of the 26th International Conference on Software Engineering, 2004. Google ScholarDigital Library
- S.M. Blackburn, P. Cheng, and K.S. McKinley. Myths and realities: the performance impact of garbage collection. SIGMETRICS Perform. Eval. Rev., 32(1), 2004. Google ScholarDigital Library
- S.M. Blackburn et al. The DaCapo benchmarks: Java benchmarking development and analysis. In Proceedings of ACM SIGPLAN Conference on Object-Oriented Programming Systems, Languages and Applications, October 2006. Google ScholarDigital Library
- C. Ding and Y. Zhong. Predicting whole-program locality with reuse distance analysis. In Proceedings of ACM SIGPLAN Conference on Programming Language Design and Implementation, pages 245--257, San Diego, CA, June 2003. Google ScholarDigital Library
- L. Eeckhout, H. Vandierendonck, and K.D. Bosschere. Quantifying the impact of input data sets on program behavior and its applications. Journal of Instruction-Level Parallelism, pages 1--33, 2003.Google Scholar
- R. Fitzgerald and D. Tarditi. The case for profile-directed selection of garbage collection. In Proceedings of the International Symposium on Memory Management, 2000. Google ScholarDigital Library
- A. Georges, D. Buytaert, and L. Eeckhout. Statistically rigorous Java performance evaluation. In Proceedings of ACM SIGPLAN Conference on Object-Oriented Programming Systems, Languages and Applications, 2007. Google ScholarDigital Library
- T. Hastie, R. Tibshirani, and J. Friedman. The elements of statistical learning. Springer, 2001.Google ScholarCross Ref
- F. Mao and X. Shen. Cross-input learning and discriminative prediction in evolvable virtual machine. In Proceedings of the International Symposium on Code Generation and Optimization (CGO), 2009. Google ScholarDigital Library
- T. Printezis. Hot-swapping between a mark&sweep and a mark&compact garbage collector in a generational environment. In Proceedings of the 1st Java Virtual Machine Research and Technology Symposium, 2001. Google ScholarDigital Library
- X. Shen and F. Mao. Modeling relations between inputs and dynamic behavior for general programs. In Proceedings of the Workshop on Languages and Compilers for Parallel Computing, 2007.Google Scholar
- X. Shen, Y. Zhong, and C. Ding. Predicting locality phases for dynamic memory optimization. Journal of Parallel and Distributed Computing, 67(7), 2007. Google ScholarDigital Library
- J. Singer, G. Brown, I. Watson, and J. Cavazos. Intelligent selection of application-specific garbage collectors. In Proceedings of the International Symposium on Memory Management, 2007. Google ScholarDigital Library
- F. Smith and G. Morrisett. Comparing mostly-copying and mark-sweep conservative collection. In Proceedings of the International Symposium on Memory Management, 1998. Google ScholarDigital Library
- S. Soman, C. Krintz, and D.F. Bacon. Dynamic selection of application-specific garbage collectors. In Proceedings of the International Symposium on Memory Management, 2004. Google ScholarDigital Library
- D. Wall. Predicting program behavior using real or estimated profiles. In Proceedings of PLDI, Toronto,Canada, June 1991. Google ScholarDigital Library
- B. Zorn. Comparing mark-and-sweep and stop-and-copy garbage collection. In Proceedings of ACM Conference on Lisp and Functional Programming, 1990. Google ScholarDigital Library
Index Terms
- The study and handling of program inputs in the selection of garbage collectors
Recommendations
Influence of program inputs on the selection of garbage collectors
VEE '09: Proceedings of the 2009 ACM SIGPLAN/SIGOPS international conference on Virtual execution environmentsMany studies have shown that the best performer among a set of garbage collectors tends to be different for different applications. Researchers have proposed application-specific selection of garbage collectors. In this work, we concentrate on a second ...
The case for profile-directed selection of garbage collectors
Many garbage-collected systems use a single garbage collection algorithm across all applications. It has long been known that this can produce poor performance on applications for which that collector is not well suited. In some systems, such as those ...
Dynamic selection of application-specific garbage collectors
ISMM '04: Proceedings of the 4th international symposium on Memory managementMuch prior work has shown that the performance enabled by garbage collection (GC) systems is highly dependent upon the behavior of the application as well as on the available resources. That is, no single GC enables the best performance for all programs ...
Comments