| Hi-index | 0.00 |
Highly variable parallel application execution time is a persistent issue in cluster computing environments, and can be particularly acute in systems composed of Networks of Workstations (NOWs). Performance modeling and management in these computing environments has focused on performance optimization of a single subsystem or application, often on a single system. This work focuses on network performance and uses techniques from fault management to define systemic performance consistency. The goal of this research is to characterize parallel application sensitivity- to network performance and develop a strategy for its use. The method developed, called "Parallel Application Run time Sensitivity Evaluation" (PARSE), uses the "Parallel Application Communication Emulation" (PACE) framework to identify application run time sensitivity to network performance degradation. When used together, PARSE and PACE can characterize and evaluate a, parallel application without the need to instrument it. Results demonstrate how PARSE and PACE expose and quantify run time sensitivity to network performance degradation. This work also defines a continuous variable sensitivity factor and demonstrates how application run time statistics influenced by PACE can be used to quantify it. The sensitivity factor is independent of application and considers changes in the coefficients of mean and variation. The characterization of application sensitivity can be used to set network performance goals, thereby defining soft faults. Network performance also depends on the virtual topology imposed by the scheduler's allocation of nodes and the communication patterns of the set of all running applications. The sensitivity factor can be used strategically by other subsystems to maintain consistent systemic performance. It can also be used to aid in program design and tuning.