Feedback Control with Prediction for Thread Allocation in Pipeline Architecture Web Server

With the sharply development of high-speed backbone network and phenomenal growth of Web applications, many kinds of Web server structures have been advanced and implemented to increase the serving ability of Web server. In this paper, we propose a pipeline architecture multi-thread web server open KETA which divides the requests processing into several independent phases. This architecture reduces parallelism granularity and achieves inner-request parallelism to enhance its processing capability. Furthermore, a combined feed-forward/feedback model is designed to manage thread allocation in this special architecture. The feed-forward predictor relates instantaneous measurements of queue length and processing rate of each pipeline phase to the thread allocation over a finite prediction horizon. The feedback controller deals with the uncertainty the predictor brings and improves open KETA's performance farther. Experimental results show the capability of open KETA and the effectiveness of the thread allocation model.

[1]  T. Abdelzaher,et al.  Improved prediction for Web server delay control , 2004, Proceedings. 16th Euromicro Conference on Real-Time Systems, 2004. ECRTS 2004..

[2]  Balachander Krishnamurthy,et al.  Web Protocols and Practice - HTTP/1.1, Networking Protocols, Caching, and Traffic Measurement , 2001 .

[3]  Sang Hyuk Son,et al.  Feedback Control Real-Time Scheduling in Distributed Real-Time Systems , 2001, RTSS 2001.

[4]  Eric A. Brewer,et al.  USENIX Association Proceedings of HotOS IX : The 9 th Workshop on Hot Topics in Operating Systems , 2003 .

[5]  Willy Zwaenepoel,et al.  Flash: An efficient and portable Web server , 1999, USENIX Annual Technical Conference, General Track.

[6]  Sang Hyuk Son,et al.  A feedback control approach for guaranteeing relative delays in Web servers , 2001, Proceedings Seventh IEEE Real-Time Technology and Applications Symposium.

[7]  T.F. Abdelzaher,et al.  Web server QoS management by adaptive content delivery , 1999, 1999 Seventh International Workshop on Quality of Service. IWQoS'99. (Cat. No.98EX354).

[8]  Mark Russinovich,et al.  High-Performance Memory-Based Web Servers: Kernel and User-Space Performance , 2001, USENIX ATC, General Track.

[9]  Tim Brecht,et al.  accept()able Strategies for Improving Web Server Performance , 2004, USENIX ATC, General Track.

[10]  Shan Zhi.  Web Quality of Service:A Survey , 2004 .

[11]  Prashant J. Shenoy,et al.  Rules of thumb in data engineering , 2000, Proceedings of 16th International Conference on Data Engineering (Cat. No.00CB37073).

[12]  Shanshan Li,et al.  Dynamic Thread Management in Kernel Pipeline Web Server , 2005, NPC.

[13]  Philip S. Yu,et al.  The state of the art in locally distributed Web-server systems , 2002, CSUR.

[14]  K. Shin,et al.  Performance Guarantees for Web Server End-Systems: A Control-Theoretical Approach , 2002, IEEE Trans. Parallel Distributed Syst..