|
Grid computing has emerged as an important new field, distinguished from
conventional distributed computing by its focus on large-scale resource
sharing, innovative applications, and, in some cases, high-performance orientation.
The Globus project
is developing basic software infrastructure needed to build
computational Grids across geographically distributed computational and
information resources. Grids are persistent environments that enable software applications
to integrate instruments, displays, computational and information resources
that are managed by diverse organizations in widespread locations. The
development of the World Wide Web has revolutionized the way we think about
information. We take for granted our ability to access information from
all over the world via the Web. The goal of the Globus project is to bring
about a similar revolution with respect to computation. We can hardly imagine
the types of applications we might construct if access to supercomputers,
live satellite imagery, and mass storage were as straightforward as access
to the Web. The Globus Project is developing the technology that can make
this vision a reality. The Globus software toolkit facilitates the creation
of usable Grids, enabling high-speed coupleing of people, computers, databases
and instruments.
The Globus Project was first developed jointly by Argonne and USC's
Information Sciences Institute). Currently,
this project is leading the definition of standard Grid protocols and APIs,
in such areas as security, resource management, data management, and information
discovery. The open source Globus Toolkit, which provides a reference implementation
of these Grid protocols and APIs, has been adopted my most of the
major Grid projects world-wide, to provide a common, robust
infrastructure for building applications that exploit distributed,
heterogeneous, Grid-enabled resources.
With Globus one can run gigabyte-per-time-step dataset
jpb on two or more high-performance machines at the same time, even though
the machines might be located far apart and owned by different organisations.
Globus concepts are continuously tested on a global scale by
participants in the Globus Ubiquitous Supercomputing Testbed Organization (GUSTO).
Globus software is used for large distributed computational
jobs, remote instrumentation, remote data transfer and shared immersive
space. In particular it helps scientists deal with very large datasets
and complex remote collaborations. See for example:
Globus is designed to offer features such as uniform
access to distributed resources with diverse scheduling mechanisms; information
service for resource publication, discovery and selection; API and command-line
tools for remote file management, staging of executables and data; and
enhanced performance through multiple communication protocols.
Globus is developing two interesting services: (1) GASS:
Global Access to Secondary Storage for wide area computing systems; and
(2) GARA:
Globus Architecture for Resource Allocation, which does distributed resource
allocation.
More introduction material about Globus can be found here:
|
|
