|
The MAGIC project begain in the early 1990s under the principle that
an increasing number of applications utilize powerful computing
resources that are distributed over local- and wide-area networks (LANs
and WANs). In such an environment, the full potential of these
resources can be realized only if the network speeds are sufficient to
support the processing demands. WANs at that time operated at
megabit-per-second (Mbps) speeds and therefore could limit the overall
performance of these distributed systems. Gigabit-per-second WANs
promised the next major advance in computing and communications:
powerful, geographically distributed computing resources with
high-speed access to remote and time-critical data sources. Such
networks would allow researchers to develop distributed, interactive
applications with massive and real-time data
requirements. Furthermore, they would allow data from multiple sources
to be integrated for use by these applications, with neither the data
sources nor the users colocated with the computing resources. Many
challenges needed to be addressed before the benefits of gigabit WANs could
be achieved. Someof these include:
- Ensuring that heterogeneous computing and networking devices can interoperate
- Coordinating multiple data streams destined for a single location
- Accommodating bursty as well as steady traffic
- Compensating for the effects of network delays and errors on high-throughput data transmissions
The MAGIC (Multidimensional Applications and Gigabit Internetwork
Consortium) project was established to develop a very high-speed,
wide-area networking testbed that would address these challenges and
demonstrate real-time, interactive exchange of data at
gigabit-per-second (Gbps) rates among multiple distributed servers and
clients. Participants in the project included organizations from
government, industry, and academia.
It was one of the six "information superhighway" projects funded by the Information Technology Office (ITO)
of the Defense Advanced Research Projects Agency (DARPA) and the National Science Foundation (NSF). MAGIC
participants included:
The MAGIC testbed consisted of
the following three components:
- An interactive, real-time, terrain visualization application
- A distributed image server system with performance sufficient to
support the terrainvisualization application
- A high-speed internetwork to link the computing resources required
for real-time rendering of the terrain
The terrain visualization
application, known as TerraVision, was designed to allow a user to view
andnavigate through a representation of a landscape. The
initial landscape was created from aerial images of the U.S. Army
National Training Center (NTC) in Fort Irwin,
California. As exercises were conducted, the locations of vehicles
were superimposed on the view of the terrain and updated in real
time. TerraVision is of direct interest to the U.S. Army since the
ability of acommander to see the battlefield, and to share a common
view of the battlefield with his command, is critical to effective
command and control. TerraVision requires very large amounts of data
in real time, transferred at both very bursty and high steady rates,
and has network throughput as its major limiting factor. Steady
traffic occurs when a user moves smoothly through the terrain,
whereas bursty traffic occurs when the user jumps ("teleports") to a
new position.
The following documentation is available on the MAGIC project.
Follow-on funding was secured from DARPA to continue
the work of the MAGIC Consortium. This
produced the MAGIC II
effort, which SRI also contributed towards. | |
