To achieve improved performance, application schedulers are typically designed to satisfy the resource requirements of specific applications. Consequently, application characteristics and models are often embedded in the scheduler itself. Results have shown that this strategy is effective for achieving improved application performance. However, application-specific schedulers may not be easily retargeted for other applications. In this thesis, we propose a modular application scheduler design that employs detailed application performance models and mapping strategies that promote application performance, but does not embed such components within the scheduler itself. Our scheduler is both environment-sensitive and configurable. To ensure that schedules are properly targeted for conditions of the target execution environment at run-time, the scheduler can incorporate dynamic resource availability in scheduling decisions. The scheduler also supports a set of configurable scheduling policies that are easily tuned to control scheduler behavior. We implement a prototype scheduler and use the class of iterative, mesh-based applications to test the prototype. We implement two test applications, Jacobi and the Game of Life, and develop performance models and mapping strategies for each application. We present experimental results we obtained by applying our scheduling methodology to Jacobi and the Game of Life in Computational Grid environments. Our testbeds included up to 20 machines organized in 4 clusters at 3 geographically distributed sites. In these experiments, our approach consistently outperforms conventional scheduling approaches.

Pre-2018 CSE ID: CS2002-0698

In this paper we propose an adaptive scheduling approach designed to improve the performance of parallel applications in Computational Grid environments. A primary contribution of our work is that our design is modular and provides a separation of the scheduler itself from the application-specific components needed for the scheduling process. As part of the scheduler, we have also developed a search procedure which effectively and efficiently identifies desirable schedules. As test cases for our approach, we selected two applications from the class of iterative, mesh-based applications. For each of the test applications, we developed data mappers and performance models. We used a prototype of our approach in conjunction with these application-specific components to perform validation experiments in production Grid environments. Our results show that our scheduler provides significantly better application performance than conventional scheduling strategies. We also show that our scheduler gracefully handles degraded levels of availability of application and Grid resource information. Finally, we demonstrate that the overheads introduced by our methodology are reasonable. This work evolved in the context of the Grid Application Development Software Project (GrADS). Our scheduling approach is designed to be easily integrated with other GrADS program development tools.

Pre-2018 CSE ID: CS2002-0708

Like all computing platforms, grids are in need of a suite of benchmarks by which they can be evaluated and characterized. As a first step towards this goal, we have developed a set of probes that exercise basic grid operations by simulating simple grid applications. We run these probes on a testbed, collecting performance data such as compute times, network transfer times, and Globus middleware overhead. The results of our experiments help provide insight into the stability, robustness, and performance of this grid testbed, as well as some recommendations for future grid development.

Pre-2018 CSE ID: CS2003-0760