Replicated Web Services: A Comparative Analysis of Client-Based Content Delivery Policies

The increase of the Internet users and web applications leads to the need for more reliable and faster Web services. Different techniques were developed to address this issue and to provide a better QoS for the Internet users. Among them, an important role is played by the replication of Web services. Replication of Web services is obtained by implementing a Web service with several Web servers. This replication can be deployed either locally (e.g. by a cluster of computers) or geographically (e.g. servers distributed sparsely in the Internet). In this paper we deal with geographical replication. Two main approaches are currently used for geographical replication: client-side and server-side approach. We focused our analysis on thc client-side approach. We classified and contrasted, qualitatively and quantitatively (via simulation), different client side techniques to find the pro and cons of each approach with the aim to identify the best solutions for content-delivery systems.

[1]  Mark Crovella,et al.  Dynamic Server Selection using Bandwidth Probing in Wide-Area Networks , 1996 .

[2]  Peter A. Dinda,et al.  Performance characteristics of mirror servers on the Internet , 1999, IEEE INFOCOM '99. Conference on Computer Communications. Proceedings. Eighteenth Annual Joint Conference of the IEEE Computer and Communications Societies. The Future is Now (Cat. No.99CH36320).

[3]  Marco Conti,et al.  QoS-based Architectures for Geographically Replicated Web Servers , 2001, Cluster Computing.

[4]  Enrico Gregori,et al.  Load distribution among replicated Web servers: a QoS-based approach , 2000, PERV.

[5]  Ludmila Cherkasova,et al.  Peak load management for commercial Web servers using adaptive session-based admission control , 2001, Proceedings of the 34th Annual Hawaii International Conference on System Sciences.

[6]  Maurizio Molina,et al.  Web traffic modeling exploiting TCP connections' temporal clustering through HTML-REDUCE , 2000, IEEE Netw..

[7]  Peter Scheuermann,et al.  Web++: A System for Fast and Reliable Web Service , 1999, USENIX Annual Technical Conference, General Track.

[8]  Ludmila Cherkasova,et al.  Performance analysis of "content-aware" load balancing strategy FLEX: two case studies , 2001, Proceedings of the 34th Annual Hawaii International Conference on System Sciences.

[9]  Mark Crovella,et al.  Server selection using dynamic path characterization in wide-area networks , 1997, Proceedings of INFOCOM '97.

[10]  Ellen W. Zegura,et al.  Application-layer anycasting: a server selection architecture and use in a replicated Web service , 2000, TNET.

[11]  Michael Mitzenmacher,et al.  Accessing multiple mirror sites in parallel: using Tornado codes to speed up downloads , 1999, IEEE INFOCOM '99. Conference on Computer Communications. Proceedings. Eighteenth Annual Joint Conference of the IEEE Computer and Communications Societies. The Future is Now (Cat. No.99CH36320).

[12]  Pablo Rodriguez,et al.  Parallel-access for mirror sites in the Internet , 2000, Proceedings IEEE INFOCOM 2000. Conference on Computer Communications. Nineteenth Annual Joint Conference of the IEEE Computer and Communications Societies (Cat. No.00CH37064).

[13]  Peter Scheuermann,et al.  Selection algorithms for replicated Web servers , 1998, PERV.

[14]  Kay A. Robbins,et al.  An empirical evaluation of client-side server selection algorithms , 2000, Proceedings IEEE INFOCOM 2000. Conference on Computer Communications. Nineteenth Annual Joint Conference of the IEEE Computer and Communications Societies (Cat. No.00CH37064).

[15]  Bruce S. Davie,et al.  Computer Networks: A System Approach , 1998, IEEE Communications Magazine.

[16]  Jussi Kangasharju,et al.  Performance evaluation of redirection schemes in content distribution networks , 2001, Comput. Commun..

[17]  Marco Roccetti,et al.  Client-centered load distribution: a mechanism for constructing responsive Web services , 2001, Proceedings of the 34th Annual Hawaii International Conference on System Sciences.