|
|
| The
viability of future Internet applications will depend on their
scalability. The Patia project aims to carry out studies into data
placement and request scheduling to prototype an adaptive webserver
management system. |

|
| Today,
web sites have moved beyond static HTML pages on single webservers
and are required to host many media and types of documents whilst
generating dynamic content or processing transactions. That is,
websites now include multiple resources -- webserver, files,
applications, databases, and other software processes on multiple
servers in many locations. For example a single ‘web site’ may
consist of a selection of traditional hypertext documents,
which may be relatively immutable but are required to be indexed for
searching purposes. It also may host dynamic pages, which are
generated typically from a combination of relational database
systems and other sources. At the same time, it may host chat-room
areas or community arenas as well as perhaps ('live') video and
other multi-media. Further, with the introduction of technology for
mobile phones and PDAs these sites must also maintain a lightweight
version of their pages and must also store the mechanisms to
generate this. There are many current examples. As well as web-TV
fitting this description it has been found that 79 percent of audio
webcast listeners buy products online while listening to their
favourite web-station [13]. Such a statistic encourages what we call
a multi-faceted web site. We believe the success of such
'portals' in terms of performance lies in the architecture of the
underlying servers and their ability to adapt to changes in demand
and resource availability, as well as their ability to scale.
The name Patia
is a shortened form of Hypatia,
the only recorded woman scholar in the ancient
world. |
Personnel
|
Last
modified: 22 Jan 2002 12:47 |
|
(c)
J.A.McCann, Imperial College. This information can only be
used for review and criticism, no other use is permitted without
prior permission by the author. |
|