EPSRC Reference: |
GR/S03058/01 |
Title: |
Performance-based Middleware for Grid Computing |
Principal Investigator: |
Nudd, Professor G |
Other Investigators: |
|
Researcher Co-Investigators: |
|
Project Partners: |
|
Department: |
Computer Science |
Organisation: |
University of Warwick |
Scheme: |
Standard Research (Pre-FEC) |
Starts: |
01 October 2002 |
Ends: |
30 September 2005 |
Value (£): |
608,342
|
EPSRC Research Topic Classifications: |
Networks & Distributed Systems |
Parallel Computing |
System on Chip |
|
|
EPSRC Industrial Sector Classifications: |
|
Related Grants: |
|
Panel History: |
|
Summary on Grant Application Form |
Despite the current interest in Grid-based computing, if it is to to be accepted, effective'middleware' must be developed to allow users to automatically use the resources within the Grid with minimum user intervention. This is a difficult issue and at best involves techniques to automatically and in real-time: discover what resources currently exist on the Grid together with their current activity, determine the state of the network in terms of all user traffic; estimate the resource requirement of incoming applications in terms of processing, storage and communication needs; evaluate the system costs in terms of overall execution time, network traffic and resource use for all feasible distributions, and from the above determine the optimum scheduling of incoming jobs to satisfy predefined service policies and quality of service requirements. Due to the complexity of the Grid, the need for rapid response time and the required faulttolerance, it is important that these facilities are not centralised. This project uses our existing work, which has been under development since 1992, to provide a distributed system for these tasks. This project will: provide enhancements to an existing performance prediction system (PACE) which evaluates the performance of incoming applications; enable the development of an agent system (A4) for resource advertisement and discovery; allow the extension of an existing scheduler (Titan) to include network traffic analysis, service policy and QoS metrics; integrate these facilities with existing Grid middleware tools such as Globus. This integrated system will be demonstrated on application(s) of interest to our collaborators including IBM's Thomas Watson Laboratories.
|
Key Findings |
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
|
Potential use in non-academic contexts |
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
|
Impacts |
Description |
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk |
Summary |
|
Date Materialised |
|
|
Sectors submitted by the Researcher |
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
|
Project URL: |
|
Further Information: |
|
Organisation Website: |
http://www.warwick.ac.uk |