On-line automatic resource selection in distributed computing

Abstract

A key problem in executing performance critical applications on distributed computing environments (e.g. the Grid) is the resource selection. Research related to "automatic resource selection" aims to select suitable 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 execution environment by adding/replacing/deleting resources at runtime in order to satisfy users' performance requirements. We use a utility-based learning and tuning algorithm to enable the automatic resource tuning/selection. A typical 2-D heat equation application is used to validate the approach. Results show that without resource or application knowledge being provided in advance, the approach is able to find the best-effort resources to satisfy users' execution requirements, and classify resources according to their contribution made to the application.

On the replacement of objects from round-based applications over heterogeneous environments

“…Their decisions for rescheduling consider only process‐level characteristics and are not suitable for multiphase scientific applications. Liu et al introduced a novel algorithm for resource selection in which the application reports the Execution Satisfaction Degree (ESD) to the scheduling middleware. The main weakness of this proposal is the fact that developers must define the ESD function for each new application.…”

Process Rescheduling in High Performance Computing Environments

“…Furthermore, this work does not consider the communication issue on selection decisions. Liu et al (Liu et al, 2009) introduced a novel algorithm for resource selection whose the application reports the Execution Satisfaction Degree (ESD) to the scheduling middleware. Then, this last entity tune the environment by adding/replacing/deleting resources in order to satisfy the user's performance requirements.…”