On-line feedback-based automatic resource configuration for distributed applications |
| |
Authors: | Hao Liu Søren-Aksel Sørensen |
| |
Institution: | (1) School of Natural Resources, University of Nebraska, 135 Hardin Hall, 3310 Holdrege Street, Lincoln, NE 68583-0982, USA;(2) USDA/APHIS/WS/National Wildlife Research Center, 4101 Laporte Avenue, Fort Collins, CO 80521, USA;(3) School of Natural Resources, University of Nebraska, 415 Hardin Hall, 3310 Holdrege Street, Lincoln, NE 68583-0982, USA;(4) School of Natural Resources, University of Nebraska, 414 Hardin Hall, 3310 Holdrege Street, Lincoln, NE 68583-0982, USA;(5) Department of Fisheries and Wildlife Sciences, University of Missouri, 302 Natural Resources Building, Columbia, MO 65211, USA;(6) School of Natural Resources, University of Nebraska, 306 Hardin Hall, 3310 Holdrege Street, Lincoln, NE 68583-0982, USA;(7) West Central Research and Extension Center, University of Nebraska, 402 West State Farm Road, North Platte, NE 69101, USA |
| |
Abstract: | A key problem in executing performance critical applications on distributed computing environments (e.g. the Grid) is the
selection of resources. Research related to “automatic resource selection” aims to allocate resources on behalf of users to
optimize the execution performance. However, most of current approaches are based on the static principle (i.e. resource selection
is performed prior to execution) and need detailed application-specific information. In the paper, we introduce a novel on-line
automatic resource selection approach. This approach is based on a simple control theory: the application continuously reports
the Execution Satisfaction Degree (ESD) to the middleware Application Agent (AA), which relies on the reported ESD values
to learn the execution behavior and tune the computing environment by adding/replacing/deleting resources during the execution
in order to satisfy users’ performance requirements. We introduce two different policies applied to this approach to enable
the AA to learn and tune the computing environment: the Utility Classification policy and the Desired Processing Power Estimation
(DPPE) policy. Each policy is validated by an iterative application and a non-iterative application to demonstrate that both
policies are effective to support most kinds of applications. |
| |
Keywords: | |
本文献已被 SpringerLink 等数据库收录! |
|