Experimental Evaluation of Compound System Calls in the Linux Kernel
Resumo
The overhead caused by system calls in many applications has motivated research works focusing on reducing their execution costs. In this work we implement three types of compound system calls, which are evaluated experimentally by taking into account their execution time in systems with one up to eight cores. We also investigate the system calls running in both physical and virtual machines. All proposed compound system calls present performance gains when compared to their conventional counterparts. The results indicate reduction in the execution time up to 58 percent. The dataset obtained through controlled experiments is analyzed using ANOVA and Tukey tests. We also verify that the highest improvements occur in the non-virtualized environment.
Referências
D. P. Bovet and M. Cesati Understanding The Linux Kernel 3rd Edition. O'Reilly 2005.
R. R. Appleton "File system call accounting measuring different workloads " in CATA'09 2009 pp. 278-283.
J. Pasquale E. Anderson and P. K. Muller "Container shipping operating system support for io intensive applications " Computer vol. 27 pp. 84-93 March 1994.
M. Burnside and A. D. Keromytis "High-speed I/O: the operating system as a signalling mechanism " in Proceedings of the ACM SIGCOMM workshop on Network-I/O convergence: experience lessons implications ser. NICELI '03. New York NY USA: ACM 2003 pp. 220-227. [Online]. Available: http://doi.acm.org/10.1145/944747.944756
A. Purohit J. Spadavecchia C. Wright and E. Zadok "Improving application performance through system call composition " Stony Brook University Tech. Rep. FSL-02-01 2003.
L. Schaelicke and A. L. Davis "Design Trade-Offs for User-Level I/O Architectures " IEEE Trans. Comput. vol. 55 pp. 962-973 2006. [Online]. Available: http://portal.acm.org/citation.cfm?id=1159194 (Pubitemid 44193984)
K. Minghao K. Y. Chyang and E. Karuppiah "Performance analysis and optimization of user space versus kernel space network application " in Research and Development 2007. SCOReD 2007. 5th Student Conference on 2007 pp. 1-6.
S. K. Palaniappan and P. B. Nagaraja "Efficient data transfer through zero copy " in IBM developerworks 2008.
P. Joubert R. B. King R. Neves M. Russinovich and J. M. Tracey "High-performance memory-based web servers: Kernel and userspace performance " in Proceedings of the General Track: 2002 USENIX Annual Technical Conference. Berkeley CA USA: USENIX Association 2001 pp. 175-187. [Online]. Available: http://portal.acm.org/citation.cfm?id=647055.715778
R. Love Linux Kernel Development Second Edition. Sams Publishing 2005.
