GEMS Project Page

GEMS: Grid Enabled Molecular Simulation

The Scientific Storage Problem:	The GEMS Solution:
Scientific applications often demand more intermediate storage space than is available on small servers. In a typical University or business network, a great deal of storage space is available for harvesting, because modern workstations ship with much more space than is usually immediately consumed. How can users safely and easily cooperate to use this space, with security, high fault-tolerance, and disk management?	GEMS offers users a convenient way to group free disk space into an dynamic storage pool. The GEMS system builds atop the Chirp system to provide fault-tolerant access to a distributed system of servers. We provide: client tools to insert sets of files with searchable metadata tags as well as search and retrieve file sets a Java-based server to perform simple replication, auditing, garbage collection, and metadata services

Scientific applications often demand more intermediate storage space than is available on small servers. In a typical University or business network, a great deal of storage space is available for harvesting, because modern workstations ship with much more space than is usually immediately consumed. How can users safely and easily cooperate to use this space, with security, high fault-tolerance, and disk management?

GEMS offers users a convenient way to group free disk space into an dynamic storage pool. The GEMS system builds atop the Chirp system to provide fault-tolerant access to a distributed system of servers. We provide:

client tools to insert sets of files with searchable metadata tags as well as search and retrieve file sets
a Java-based server to perform simple replication, auditing, garbage collection, and metadata services

GEMS introductory slide show: [PDF] [ODP]

Focus Areas

Our immediate focus areas include:

GUI development: We continue to develop the GUI tool to search the system.

Application - protein conformation analysis: Our target application, transition path sampling, will flex the architecture as it provides enough reliable intermediate storage on a multi-use university network to benefit researchers performing real-world biocomplexity research

Fault-tolerance in distributed storage: As GEMS finds a place among the great tradition of distributed storage systems, we continue to produce published work in the field of distributed storage systems.

Faculty	Students
Doug Thain Aaron Striegel Jesus A. Izaguirre	Justin Wozniak - Ph.D. Paul Brenner - Ph.D.

Research Sponsors

NSF DBI-0450067