Title :
Creating personal adaptive clusters for managing scientific jobs in a distributed computing environment
Author :
Walker, Edward ; Gardner, Jeffrey P. ; Litvin, Vladimir ; Turner, Evan L.
Author_Institution :
Texas Adv. Comput. Center, Texas Univ., Austin, TX
Abstract :
We describe a system for creating personal clusters in user-space to support the submission and management of thousands of compute-intensive serial jobs to the network-connected compute resources on the NSF TeraGrid. The system implements a robust infrastructure that submits and manages job proxies across a distributed computing environment. These job proxies contribute resources to personal clusters created dynamically for a user on-demand. The system adapts to the prevailing job load conditions at the distributed sites by migrating job proxies to sites expected to provide resources more quickly. The version of the system described in this paper allows users to build large personal Condor and Sun Grid Engine clusters on the TeraGrid. Users can then submit, monitor and control their scientific jobs with a single uniform interface, using the feature-rich functionality found in these job management environments. Up to 100,000 user jobs have been submitted through the system to date, enabling approximately 900 teraflops of scientific computation
Keywords :
grid computing; resource allocation; workstation clusters; Condor; NSF TeraGrid; Sun Grid Engine cluster; cooperative system; distributed computing environment; personal adaptive cluster; resource management; scientific job management; Aggregates; Collision mitigation; Computer aided instruction; Computer network management; Computer networks; Distributed computing; Environmental management; Intelligent networks; Middleware; Resource management;
Conference_Titel :
Challenges of Large Applications in Distributed Environments, 2006 IEEE
Conference_Location :
Paris
Print_ISBN :
1-4244-0420-7
DOI :
10.1109/CLADE.2006.1652061
