The success of the World Wide Web has brought an exponential growth of the user population the to tal host count and the amount of total tra c vol ume on the Internet As the Internet connectivity is reaching the global community the World Wide Web is becoming a global scale data dissemination sys tem Inevitably this over night exponential growth has also caused tra c overload at various places in the network Until recently advances in delivery fabrics gave the impression that scaling the Inter net was simply an issue of adding more resources Bandwidth and processing power could be brought to where they were needed The Internet s exponen tial growth however exposed this impression as a myth Information access has not been nor will it likely be evenly distributed As have been repeated observed popular Web pages create hot spots of network load with the same data transmitted over the same network links again and again to thousands of di erent users Hot spots also move around The photographs of Venus congested Los Nettos for one week the Midnight Madness release of Microsoft s Internet Explorer congested NorthWestNet for hours threatening Internet connectivity to Univer sity of Washington These are but a couple of well publicized examples Recent studies by Margo Seltzer of Harvard University also con rms that ash crowds are very common and that the cool site of the day moves around Bottleneck hot spots develop and break up more quickly than the network or the Web servers can be re provisioned A brute force approach to provisioning is not only infeasible but also ine ec tive
[1]
Jun Li,et al.
MASH: the multicasting Archie server hierarchy
,
1997,
CCRV.
[2]
Edward A. Fox,et al.
Removal policies in network caches for World-Wide Web documents
,
1996,
SIGCOMM '96.
[3]
QUTdN QeO,et al.
Random early detection gateways for congestion avoidance
,
1993,
TNET.
[4]
ZHANGLi-xia,et al.
A reliable multicast framework for light-weight sessions and application level framing
,
1995
.
[5]
D. Estrin,et al.
RSVP: a new resource reservation protocol
,
1993,
IEEE Communications Magazine.
[6]
Rajive L. Bagrodia,et al.
Maisie: A Language for the Design of Efficient Discrete-Event Simulations
,
1994,
IEEE Trans. Software Eng..
[7]
V. Jacobson,et al.
Random early detection gateways for congestion avoidance
,
1993,
TNET.
[8]
Margo I. Seltzer,et al.
World Wide Web Cache Consistency
,
1996,
USENIX Annual Technical Conference.
[9]
kc claffy,et al.
Evolution of the NLANR cache hierarchy: Global configuration challenges
,
1996
.