The KIPS Transactions:PartC (정보처리학회논문지C)

Korea Information Processing Society (한국정보처리학회)
권호 표지
DOI QR코드

DOI QR Code

Modeling and Performance Evaluation of the Web server supporting Persistent Connection

Persistent Connection을 지원하는 웹서버 모델링 및 성능분석

  • Min, Byeong-Seok (Dept.of Electric Electronics Engineering, Yonsei University) ;
  • Nam, Ui-Seok (Dept.of Electric Electronics Engineering, Yonsei University) ;
  • Lee, Sang-Mun (Dept.of Electric Electronics Engineering, Yonsei University) ;
  • Sim, Yeong-Seok (Dept.of Electric Electronics Engineering, Yonsei University) ;
  • Kim, Hak-Bae (Dept.of Electric Electronics Engineering, Yonsei University)
  • 민병석 (연세대학교 대학원 전기전자공학과) ;
  • 남의석 (연세대학교 전기전자공학과 BK21) ;
  • 이상문 (연세대학교 대학원 전기전자공학과) ;
  • 심영석 (연세대학교 대학원 전기전자공학과) ;
  • 김학배 (연세대학교 전기전자공학과)
  • Published : 2002.08.01
Download PDF
⟨ Previous Next ⟩

Abstract

Amount of the web traffic web server handles are explosively increasing, which requires that the performance of the web server should be improved for the various web services. Although the analysis for the HTTP traffic with the proper tuning for the web server is essential, the research relevant to the subject are insignificant. In particular, although most of applications are implemented over HTTP 1.1 protocol, the researches mostly deal with the performance evaluation of the HTTP 1.0 protocol. Consequently, the modeling approach and the performance evaluation over HTTP 1.1 protocol have not been well formed. Therefore, basing on the HTTP 1.1 protocol supporting persistent connection, we present an analytical end-to-end tandem queueing model for web server to consider the specific hardware configuration inside web server beginning at accepting the user request until completing the service. we compare various performances between HTTP 1.0 and HTTP 1.1 under the overloading condition, and then analyze the characteristics of the HTTP traffic that include file size requested to web server, the OFF time between file transfers, the frequency of requests, and the temporal locality of requests. Presented model is verified through the comparing the server throughput according to varying requests rate with the real web server. Thereafter, we analyze the performance evaluation of the web server, according to the interrelation between TCP Listen queue size, the number of HTTP threads and the size of the network buffers.

웹서버가 처리하는 웹 트래픽 양이 폭발적으로 증가하고, 다양한 형태의 웹 서비스에 대한 웹서버의 성능 개선이 요구되고 있다. 이를 위해, HTTP 트래픽의 특성에 대한 분석과 웹서버의 적절한 튜닝이 요구되고 있지만 이에 대한 연구는 아직 미진한 상태이다. 특히, 현재 대부분의 어플리케이션이 HTTP 1.0에 기반하여 구현되고 있음에도 불구하고, 대부분의 연구들이 HTP 1.0에 기반하여 성능 분석이 이루어진 반면 HTTP 1.1에 대한 모델링과 성능분석은 거의 이루어지지 못하였다. 따라서, 본 논문에서는 Persistent connection을 지원하는 HTTP 1.1 프로토콜을 기반으로 하여 서버내의 세부 하드웨어 특성 등을 고려하여, 웹서버가 사용자의 요청을 받아들이면서부터 서비스를 마칠 때까지의 과정을 Tandem 네트워크 큐잉 모델을 사용하여 해석적인 웹서버 모델을 제안한다. 그리고, HTTP 1.0에 대한 HTTP 1.1의 개선된 점과 과부하 하에서의 문제점 등을 분석하고, 웹 서버에 요청하는 파일크기, 파일전송 사이의 OFF 시간, 요청빈도, 요청시간에 대한 지역성과 같은 HTTP 트래픽에 대한 특성을 분석한다. 제안된 모델은 실제 웹서버에서 웹 서비스 요청율의 변화에 따른 서버의 처리량에 대한 비교를 통해 검증하였다. 또, HTTP 1.1 기반의 웹서버에 있어서, TCP 요청 대기큐 크기와 HTTP 쓰레드의 개수 및 네트워크 버퍼 크기와의 상관 관계에 따른 웹서버의 성능분석을 하였다.

Keywords

References

  1. Zhen Liu, N. Niclause, C. Jalpa-Villaneva, 'Traffic model and Performance Evaluation of web servers,' Performance Evaluation 46, pp.77-100, 2000 https://doi.org/10.1016/S0166-5316(01)00046-3
  2. P. Barford, M.E. Crovella, 'A Performance Evaluation of Hyper Text Transfer protocols,' proceedings of the ACM Sigmetrics'99, 1999 https://doi.org/10.1145/301453.301560
  3. B. A. Mah, 'An empirical model of HTTP network traffic,' Proceedings of the IEEE INFOCOM'97, 1997 https://doi.org/10.1109/INFCOM.1997.644510
  4. P. Barford, M. E. Crovella, 'Generating repr besentative web workloads for network and server performance evaluation,' Proceedings of the ACM Sigmetrics '98, 1998
  5. E. Casilari, F. J. Gonzalez, F. Sandoval, 'Modeling of HTTP traffic,' IEEE Communications Letters, Vol.5, No.6, June, 2001 https://doi.org/10.1109/4234.929610
  6. R. D. Van der Mei, R. Hariharan, P. K. Reeser, 'Web Server Performance Modeling,' Proceedings of 4th Informs Telecom Conference, Special Issue of Telecommunication
  7. P. K. Reeser, R. Hariharan, 'Analytical Model of Web Servers in distributed Environment,' Proceedings of the second international workshop on software and performance, September, 2000 https://doi.org/10.1145/350391.350427
  8. J. Dilley, R. Friedrich, T. Jin, J. Rolia, 'Web server performance measurement and modeling techniques,' Performance Evaluation 33, pp.5-26, 1998 https://doi.org/10.1016/S0166-5316(98)00008-X
  9. J. Heidenmann, K. Obraczka, J. Touch, 'Modeling the Performance of HTTP Over Several Transport Protocols,' IEEE transactions on networking, Vol.5, No.5, October, 1997 https://doi.org/10.1109/90.649564
  10. J. Mogul, 'The Case for Persistent-Connection HTTP,' Proceedings of ACM SIGCOMM '95, Cambridge, MA, pp. 299-313, 1995 https://doi.org/10.1145/217382.217465
  11. M. Arlitt, 'Characterizing Web User Sessions,' Hewlett-Packard Laboratories Technical Report HPL-2000-43, May, 2000
  12. Padmanabhan, Mogul, 'improving HTTP latency,' proceedings of the second WWW conference, 1994 https://doi.org/10.1016/0169-7552(95)00106-1
  13. M. Crovella, R. Frangioso, M.Harchol-Balte, 'Connection scheduling in web servers,' proceedings of the 1999 USENIX Symposium on internet Technologies and Systems(USITS '99), October, 1999
  14. V. Almeida, A. Bestavros, M. Crovella, A. de Oliveira, 'Characterizing reference locality in the WWW,' proceedings of 1996 International Conference on Parallel and Distributed Information Systems, pp.92-103, December, 1996 https://doi.org/10.1109/PDIS.1996.568672
  15. Douglas E. Comer, 'Internetworking with TCP/IP vol I : Principle, and Architecture 3rd edition,' 1995, Prentice-Hall, Inc.
  16. Alberto Leon-Garcia, 'Probability and Random Processes for Electrical Engineering,' second edition, Addison Wesley
  17. Patreick Killelea, 'Web Performance Tuning,' O'Reilly, 1998
  18. http://httpd.apache.org/docs
  19. Allen B. Downey, 'The Structual cause of file size distributions,' MASCOTS'01 https://doi.org/10.1145/378420.378824
  20. M. F. Arlitt, C. L. Williamson, 'Web Server Workload Characterization : The Search for Invariants,' ACM SIGMETRICS '96, pp.126-137, May, 1996 https://doi.org/10.1145/233013.233034
  21. http://www.etestinglabs.com.