Performance Analysis of a Dynamic Parallel Downloading Scheme from Mirror Sites Throughout the Internet

In this paper, we describe paraloading, a novel approach to retrieving files from the Internet by establishing parallel connections with multiple mirror sites. This method contrasts with the conventional download method where the client retrieves data from a single source. The advantages of paraloading over single-connection downloading include improved performance gained from aggregating the bandwidths of the parallel connections, increased efficiency gained from load balancing download requests among the parallel connections. and increased resilience against congestion or failures on any one path, In order for paraloading to work, servers must be mirrored throughout the Internet. However, as mirror sites become more widespread and as end users upgrade to higher connection speeds, we believe that paraloading—if implemented properly— will offer significant performance gain over the traditional singlesource file accesses. Paraloading is a subject that has not been extensively studied by the research community. This paper examines the performance and the design of a paraloading scheme proposed in [21]. We have developed a paraloader application in Java that uses HTTP 1.1 for its range-request and persistent connection features. We have conducted a series of experiments using our paraloader at MIT and at UC Berkeley, and we have found that the performance gains of paraloading are not as good as those claimed in [21]. This suggests that paraloading may not fair well in different network environments. Nevertheless, we believe that there are a number of enhancements that can be made to the paraloader to improve its performance in different network environments. We will outline some of these enhancement techniques and discuss some open research issues on

[1]  Michael O. Rabin,et al.  Efficient dispersal of information for security, load balancing, and fault tolerance , 1989, JACM.

[2]  Jeffrey C. Mogul,et al.  Improving HTTP Latency , 1995, Comput. Networks ISDN Syst..

[3]  Srinivasan Seshan,et al.  SPAND: Shared Passive Network Performance Discovery , 1997, USENIX Symposium on Internet Technologies and Systems.

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

[5]  Ellen W. Zegura,et al.  A novel server selection technique for improving the response time of a replicated service , 1998, Proceedings. IEEE INFOCOM '98, the Conference on Computer Communications. Seventeenth Annual Joint Conference of the IEEE Computer and Communications Societies. Gateway to the 21st Century (Cat. No.98.

[6]  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).

[7]  David D. Clark,et al.  Architectural considerations for a new generation of protocols , 1990, SIGCOMM '90.

[8]  Jussi Kangasharju.  Locating copies of objects using the Domain Name System , 1999 .

[9]  Roy T. Fielding,et al.  Hypertext Transfer Protocol - HTTP/1.0 , 1996, RFC.

[10]  Sally Floyd,et al.  Promoting the use of end-to-end congestion control in the Internet , 1999, TNET.

[11]  Srinivasan Seshan,et al.  TCP behavior of a busy Internet server: analysis and improvements , 1997, Proceedings. IEEE INFOCOM '98, the Conference on Computer Communications. Seventeenth Annual Joint Conference of the IEEE Computer and Communications Societies. Gateway to the 21st Century (Cat. No.98.

[12]  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).

[13]  Srinivasan Seshan,et al.  An integrated congestion management architecture for Internet hosts , 1999, SIGCOMM '99.

[14]  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).