FG-24
Resource discovery in an asynchronous grid and cloud
PonD : Dynamic Creation of HTC Pool on Demand Using a Decentralized Resource Discovery System
[fg-1909] Lee, K., D. I. Wolinsky, and R. Figueiredo,
"PonD : Dynamic Creation of HTC Pool on Demand Using a Decentralized Resource Discovery System",
Proceedings of the 21st international symposium on High Performance Distributed Computing (HPDC), Delft, the Netherlands, ACM, 06/2012.
High Throughput Computing (HTC) platforms aggregate heterogeneous resources to provide vast amounts of computing power over a long period of time. Typical HTC systems, such as Condor and BOINC, rely on central managers for resource discovery and scheduling. While this approach simplifies deployment, it requires careful system configuration and management to ensure high availability and scalability.
Resource discovery in an asynchronous grid and cloud
Project Details
- Project Lead
- Kyungyong Lee
- Project Manager
- Kyungyong Lee
- Supporting Experts
- Javier Diaz Montes, Tao Huang
- Institution
- University of Florida, ACIS Lab.
- Discipline
- Computer Science (401)
Abstract
This project will be focusing on an appropriate resource discovery in a grid and cloud computing. The first step will be testing a decentralized resource discovery system, and the next step will be providing a resource discovery service in an asynchronous grid and cloud middleware.
Intellectual Merit
Providing a decentralized resource discovery system.
Broader Impacts
This project will provide a way to communicate among different grid and cloud computing middleware.
Scale of Use
At this time, I want to access a machine which can overview the entire status of future grid pool with a cloud computing middleware (e.g., Nimbus or Eucalyptus) installed.