Consideration of Service Time in Placing Clients of Web-Based Services

Web-based services involving dynamic computation of the content are increasingly used on the Web. This computation may not only involve processing, but often involves access to other back-end services typically for database access. These multi-tiered Web-based services have different characteristics than traditional Web content and new models need to be considered not only how to manage them, but also how the DNS mechanism should map clients to the appropriate front-end server. In this work we study the potential of considering back-end service times in the decision of mapping clients to servers. We do so by gathering data from deployed platforms in the Internet today from client locations both scattered around the globe and around the United States. We use these data for the simulation of straightforward policies that account for back-end service time. Our results show that in the best case our simple policies have better performance than using current DNS decisions, while in the worst case they provide comparable performance for a range of performance metrics.

[1]  Zhe Chen,et al.  Resource Allocation Based On Workflow For Enhancing the Performance of Composite Service , 2007, IEEE International Conference on Services Computing (SCC 2007).

[2]  Anees Shaikh,et al.  On the responsiveness of DNS-based network control , 2004, IMC '04.

[3]  Asser N. Tantawi,et al.  An analytical model for multi-tier internet services and its applications , 2005, SIGMETRICS '05.

[4]  Balachander Krishnamurthy,et al.  ATMEN: a triggered network measurement infrastructure , 2005, WWW '05.

[5]  Larry L. Peterson,et al.  Using PlanetLab for network research: myths, realities, and best practices , 2005, OPSR.

[6]  Balachander Krishnamurthy,et al.  On the use and performance of content distribution networks , 2001, IMW '01.

[7]  Prashant J. Shenoy,et al.  Agile dynamic provisioning of multi-tier Internet applications , 2008, TAAS.

[8]  Guillaume Pierre,et al.  Autonomous resource provisioning for multi-service web applications , 2010, WWW '10.

[9]  Balachander Krishnamurthy,et al.  WWW 2009 MADRID! Track: Security and Privacy / Session: Web Privacy Privacy Diffusion on the Web: A Longitudinal Perspective , 2022 .

[10]  Jie Gao,et al.  Moving beyond end-to-end path information to optimize CDN performance , 2009, IMC '09.

[11]  Anees Shaikh,et al.  On the effectiveness of DNS-based server selection , 2001, Proceedings IEEE INFOCOM 2001. Conference on Computer Communications. Twentieth Annual Joint Conference of the IEEE Computer and Communications Society (Cat. No.01CH37213).