응답시간 향상을 위한 커넥션 스케줄링 기법

Connection Scheduling for Improving the Response Time

  • 방지호 (홍익대학교 컴퓨터공학과) ;
  • 하란 (홍익대학교 컴퓨터공학과)
  • 발행 : 2006.02.01

초록

웹서버가 클라이언트들의 요청을 처리하는 방법은 요청된 문서의 크기를 고려한 스케줄링 기법과 요청된 문서의 크기를 고려하지 않는 스케줄링 기법으로 구분할 수 있다. 웹 문서의 크기를 고려한 스케줄링 기법은 크기를 고려하지 않은 스케줄링 기법 보다 평균 응답시간이 우수하다. 크기기반의 스케줄링 기법인 SRPT(Shortest Remaining Processing Time first)는 웹 문서의 크기를 고려한 대표적인 스케줄링 기법으로 대부분의 연구들이 SRPT 스케줄링 기법을 기반으로 하고 있다. 그러나, 기존 연구들 대부분은 HTTP/1.0 기반으로 클라이언트들이 각각의 커넥션을 통해 HTML 문서에 포함된 다수의 문서들을 동시에 요청할 수 있는 HTTP/1.1 프로토콜의 특성을 고려하지 않았다. 본 논문은 HTTP/1.1 프로토콜을 기반에서 스케줄링 윈도우를 사용하여 커넥션의 전체 응답시간을 향상시키는 커넥션 스케줄링 기법을 제시하고, 성능분석을 통해 제안한 커넥션 스케줄링 기법의 커넥션 응답시간이 SRPT를 이용한 커넥션스케줄링보다 $10\%$ 정도 향상됨을 보인다.

The client request scheduling techniques for web server can classified into the scheduling techniques considering a document size to be requested and not. The scheduling techniques considering a document site to be requested provides a better average response time than another As the size-based SRPT(Shortest Remaining Processing Time first) is typical, and the most of scheduling techniques considering a web document size are based on SRPT. Most of existing researches, however, have not considered the feature of HTTP/1.1 which enable the clients to request concurrent multiple inlined-contents in a HTML document via each connection. In this paper we propose a connection scheduling technique with the scheduling window which provides a better response time in HTTP/1.1. The experimental results show that the performance with the proposed approach is improved about $10\%$ more than the connection scheduling with SRPT.

키워드

참고문헌

  1. R. Fielding, J. Gettys, J. Mogul, H. Frystyk, L. Masinter, P. Leach, and T. Berners-Lee. 'HyperText Transfer Protocol-HTTP/1.1,' IETF RFC 2616, June 1999
  2. M. E. Crovella, R. Frangioso, and M. HarcholBalter, 'Connection Scheduling in Web Servers,' Proceedings of the 1999 USENIX Symposium on Internet Technologies and Systems, pp.243-254, October 1999
  3. M. Harchol-Balter, B. Schroeder, N. Bansal, and M. Agrawal, 'Size-Based Scheduling to Improve Web Performance,' ACM Transactions on Computer Systems, Vol.21, No.2, pp.207-233, May 2003 https://doi.org/10.1145/762483.762486
  4. E. J. Friedman and S. G. Henderson, 'Fairness and Efficiency in Web Server Protocols,' Proceedings of ACM SIGMETRICS'03, pp.229-237, June 2003 https://doi.org/10.1145/781027.781056
  5. D. Lu, P. Dinda, Y. Qiao, and H. Sheng, 'Effects and Implications of File Size/Service Time Correlation on Web Server Scheduling Policies,' Technical Report NWU-CS-04-33, April 19, 2004
  6. D. Lu, H. Sheng, and P. Dinda, 'Size-based Scheduling Policies with Inaccurate Scheduling Information,' Proceedings of the IEEE Computer Society's 12th Annual International Symposium on MASCOTS '04, pp.31-38, Oct. 2004 https://doi.org/10.1109/MASCOT.2004.1348179
  7. N. Bhatti and Rich Friedrich, 'Web Server Support for Tiered Services', HPL-1999-160, 1999
  8. J. Almeida, M. Dabu, A. Manikutty, and P.Cao, 'Providing Different Levels of Service in Web Content Hosting,' Proceedings of the Internet Server Performance Workshop, March 1998
  9. P. Bhoj, S. Ramanathan, and S. Singhal, 'Web2K: Bringing QoS to Web Servers,' HPL-2000-61, 2000
  10. M. Bender, S. Chakravarti, and S. Muthukrishnan, 'Flow and Stretch Metrics For Scheduling Continuous Job Streams,' Proceedings of the 9th Annual ACM-SIAM Symposium on Discrete Algorithms, pp.270-279, 1998
  11. C. Lu, T. Abdelzaher, T. Stankovic, and S. Son, 'A Feedback Control Approach for Guaranteeing Relative Delays in Web Servers,' IEEE Real-Time Technology and Applications Symposium, TaiPei, Taiwan, June 2001 https://doi.org/10.1109/RTTAS.2001.929865
  12. The Apache Group. http://www.apache.org
  13. V. N. Padmanabhan and J. Mogul, 'Improving HTTP Latency,' Computer Networks and ISDN Systems, vol. 28, pp.25-35, December 1995 https://doi.org/10.1016/0169-7552(95)00106-1
  14. V. S. Pai, P. Druschel, and W. Zwaenepoel, 'Flash: An Efficient and Portable Web Server,' Proceedings of the USENIX 1999 Annual Technical Conference, pp.199-212, June 1999
  15. P. Barford and M. Crovella, 'Generating Representative Web Workloads for Network and Server Performance Evaluation,' Proceedings of Performance '98/ACM SIGMETRICS '98, pp.151-160, Madison WI. Slightly expanded version appears as BUCS-TR-1997-006, November 4, 1997 https://doi.org/10.1145/277851.277897
  16. P. Barford, A. Bestavros, A. Bradley, and M. Crovella, 'Changes in Web Client Access Patterns: Characteristics and Caching Implications,' World Wide Web, Special Issue on Characterization and Performance Evaluation, Vol. 2, pp.15-28, 1999