Fine-Grained Parallelism in Dynamic Web Content Generation: The Parse and Dispatch Approach

Dynamic Web content is gaining in popularity over traditional static HTML as the means of providing Web users with personalized and dynamic information. To enable dynamic content, various technologies have been developed for embedding of script code blocks into static HTML files in order to perform various forms of tasks such as session tracking, bank transactions, financial calculations, products catalog generation, dynamic image generation, or even fetching information from remote servers. In this way, static HTML pages are transformed into dynamic web pages. Typically, dynamic Web pages include a number of tasks that are executed in a serial manner by current Web servers. In this paper, we propose a back-end, finer-grained parallel approach for dynamic content generation, and elaborate on how it affects the design and performance of Web servers. We have developed a prototype Web server that supports the parallel processing of tasks involved in the dynamic content generation with improved throughput as compared to the serial approach.

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

[2]  David E. Culler,et al.  SEDA: an architecture for well-conditioned, scalable internet services , 2001, SOSP.

[3]  Michelle Butler,et al.  A Scalable HTTP Server: The NCSA Prototype , 1994, Comput. Networks ISDN Syst..

[4]  Gerti Kappel,et al.  Connecting Databases to the Web: A Taxonomy of Gateways , 1997, DEXA.

[5]  Suresha,et al.  Proxy-based acceleration of dynamically generated content on the world wide web: an approach and implementation , 2002, SIGMOD '02.

[6]  Byrav Ramamurthy,et al.  LSMAC and LSNAT: two approaches for cluster-based scalable Web servers , 2000, 2000 IEEE International Conference on Communications. ICC 2000. Global Convergence Through Communications. Conference Record.

[7]  Franco Frattolillo,et al.  Efficient Content-aware Connections Despatching in Clustered Web Servers , 2002, PDPTA.

[8]  Prasant Mohapatra,et al.  Workshop on performance and architecture of web servers , 2000, SGMD.

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

[10]  Tim Berners-Lee,et al.  The World-Wide Web , 1994, CACM.

[11]  Krithi Ramamritham,et al.  Dynamic content acceleration: a caching solution to enable scalable dynamic Web page generation , 2001, SIGMOD '01.

[12]  Steve Goddard,et al.  The SASHA architecture for network-clustered web servers , 2001, Proceedings Sixth IEEE International Symposium on High Assurance Systems Engineering. Special Topic: Impact of Networking.

[13]  Tim Berners-Lee,et al.  The world-wide web : Internet technology , 1994 .

[14]  Alexandros Labrinidis,et al.  WebView materialization , 2000, SIGMOD 2000.

[15]  Ken Arnold,et al.  The Java Programming Language , 1996 .

[16]  Gary Hutchinson,et al.  Implementation of a dynamic Web database: interface using cold fusion , 1998, SIGUCCS '98.

[17]  James Aweya,et al.  An adaptive load balancing scheme for web servers , 2002, Int. J. Netw. Manag..

[18]  Roy T. Fielding,et al.  The Apache HTTP Server Project , 1997, IEEE Internet Comput..

[19]  Wenfei Fan,et al.  Keys with Upward Wildcards for XML , 2001, DEXA.

[20]  Alexandros Labrinidis,et al.  Balancing Performance and Data Freshness in Web Database Servers , 2003, VLDB.

[21]  James R. Larus,et al.  Using Cohort-Scheduling to Enhance Server Performance , 2002, USENIX Annual Technical Conference, General Track.