Storage Weather Service: Grid Storage Performance Forecaster
 
DongWoo Lee and R.S.Ramakrishna
 
Department of Information and Communication
Kwangju Institute of Science and Technology
1, Oryong-dong, Buk-gu
Gwangju 500-712, Republic of Korea
{leepro, rsr}@kjist@ac.kr
 
 
Abstract
 
 
To maximize the efficiency of using Grid resources, resource discovery and resource scheduling have been emphasized. It is desirable to provide meaningful resource performance information to Grid middleware, especially to a resource scheduler. We have developed an on-line Disk I/O performance monitoring and forecast system for storage resources. This includes a low-level performance monitoring system in real time and an on-line performance forecast system for delivering processed forecast information to an information consumer. This abstract briefly describes the Grid storage performance forecaster, called Storage Weather Service(SWS).