Analyzing the Characteristic of JAVA Objects

Abstract:

Java is a very popular Object-oriented programming (OOP) language because of its platform independent and automatic memory release mechanism (or garbage collection). However, garbage collection also speeds CPU time and should be done after careful consideration. In the paper, memory usage behavior and run-time object characteristics, including heap and object size, object age and access frequency, are studied using several commercial benchmarks. The profiler design method and experiment detail are represented in the paper. The runtime object characteristics are very important to guide the employment of different memory management algorithm.

• Periodical: Applied Mechanics and Materials (Volumes 303-306)
• Pages: 2329-2332
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.303-306.2329
• Online since: February 2013
• Authors: Jun Yi Li, Jing Yu Chen, Anthony S. Fong
• Keywords: Benchmark, Heap, Java, Locality, Object, Object-Oriented Programming

References

[1] Gosling, J., Joy, B., and Steele, G.: The Java Language Specification. Addison-Wesley, Boston, MA, (1996).

[2] Lindholm, T., and Yellin, F.: The Java Virtual Machine Specification. Addison-Wesley, Boston, MA, (1997).

[3] El-Kharashi, M.W., and Elguibaly, F.: Java microprocessors: Computer architecture implications. IEEE Pacific Rim Conference on Communications, Computers and Signal Processing, Aug. 1997, Vol. 1, p.277–280.

DOI: 10.1109/pacrim.1997.619954

[4] Levanoni, Y. and Petrank, E.: An On-The-Fly Reference-Counting Garbage Collector for Java. ACM TOPLAS, Vol. 28, Issue 1, Jan. 2006, pp.1-69.

DOI: 10.1145/1111596.1111597

[5] Muthukumar, R.M. and Janakiram, D.: Yama: a scalable generational garbage collector for Java in multiprocessor systems, IEEE Transactions on Parallel and Distributed Systems, Feb. (2006).

DOI: 10.1109/tpds.2006.28

[6] Kim, J.S., and Hsu, Y.: Memory System Behavior of Java Programs: Methodology and Analysis. In Proceedings of the 2000 ACM SIGMETRICS International Conference on Measurement and Modeling of Computer Systems, Jun. 2000, pp.264-274.

DOI: 10.1145/339331.339422

[7] Shuf, Y., Serrano M.J., Gupta, M., and Singh, J.P.: Characterizing the memory behavior of Java workloads: a structured view and opportunities for optimizations. 2001 ACM SIGMETRICS international conference on Measurement and modeling of computer systems, June (2001).

DOI: 10.1145/378420.378783

[8] Venners, B.: Inside the Java Virtual Machine. ISBN 0-07-913248-0, McGraw-Hill, (1997).

[9] SPEC: SPEC release SPEC JVM98, first industry-standard benchmark for measuring Java virtual machine performanc'. Press Release, August (1998).

[10] Liang, S., and Viswanathan, D.: Comprehensive Profiling Support in the Java Virtual Machine,. USENIX Conference on Object-Oriented Technologies (COOTS), May 1999, pp.229-240.

[11] Dieckmann, S., and Holzle, U.: A study of the allocation behavior of the SPECJvm98 Java benchmarks. European Conference on Object-oriented Programming, June 1999, p.92–115.

DOI: 10.1007/3-540-48743-3_5