A paracasting model for concurrent access to replicated content

We propose a framework to study how to download effectively a copy of the same document from a set of replicated servers. A generalized application-layer anycasting, known as paracasting, has been proposed to advocate concurrent access of a subset of replicated servers to satisfy cooperatively a client's request. Each participating server satisfies the request in part by transmitting a subset of the requested file to the client. The client can recover the complete file when different parts of the file sent from the participating servers are received. This framework allows us to estimate the average time to download a file from the set of homogeneous replicated servers, and the request blocking probability when each server can accept and serve a finite number of concurrent. requests. Our results show that the file download time drops when a request is served concurrently by a larger number of homogeneous replicated servers, although the performance improvement quickly saturates when the number of servers used increases. If the total number of requests that a server can handle simultaneously is finite, the request blocking probability increases with the number of replicated servers used to serve a request concurrently. Therefore, paracasting is effective in using a small number of servers, say, up to four, to serve a request concurrently.

[1]  Victor O. K. Li,et al.  DIVERSITY TRANSMISSIONS IN A COMMUNICATION NETWORK WITH UNRELIABLE COMPONENTS. , 1987 .

[2]  Hui Zhang,et al.  Measurement-based optimization techniques for bandwidth-demanding peer-to-peer systems , 2003, IEEE INFOCOM 2003. Twenty-second Annual Joint Conference of the IEEE Computer and Communications Societies (IEEE Cat. No.03CH37428).

[3]  Wanjiun Liao,et al.  Distributed multimedia systems , 1997, Proc. IEEE.

[4]  William H. Press,et al.  The Art of Scientific Computing Second Edition , 1998 .

[5]  William H. Press,et al.  The Art of Scientific Computing Second Edition , 1998 .

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

[7]  Thomas Bonald,et al.  Statistical bandwidth sharing: a study of congestion at flow level , 2001, SIGCOMM.

[8]  Catherine Rosenberg,et al.  Analysis of parallel downloading for large file distribution , 2003, The Ninth IEEE Workshop on Future Trends of Distributed Computing Systems, 2003. FTDCS 2003. Proceedings..

[9]  William H. Press,et al.  Numerical Recipes in FORTRAN - The Art of Scientific Computing, 2nd Edition , 1987 .

[10]  Leonard Kleinrock,et al.  Queueing Systems: Volume I-Theory , 1975 .

[11]  Pablo Rodriguez,et al.  Dynamic parallel access to replicated content in the internet , 2002, TNET.

[12]  William H. Press,et al.  Numerical recipes in C. The art of scientific computing , 1987 .

[13]  Peter B. Danzig,et al.  Evaluating the performance of flood-d: a tool for efficiently replicating Internet information services , 1998, IEEE J. Sel. Areas Commun..

[14]  Victor O. K. Li,et al.  Generalized load sharing for packet-switching networks , 2000, Proceedings 2000 International Conference on Network Protocols.

[15]  Nicholas F. Maxemchuk,et al.  Dispersity Routing in High-Speed Networks , 1993, Comput. Networks ISDN Syst..

[16]  Ka-Cheong Leung,et al.  A resequencing model for high speed networks , 1999, 1999 IEEE International Conference on Communications (Cat. No. 99CH36311).

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