Abstract not found

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

Computational mechanics, an approach to structural complexity, defines a process’s causal states and gives a procedure for finding them. We show that the causal-state representation—an E-machine—is the minimal one consistent with

Program development environments are instrumental in providing users with easy and efficient access to parallel computing platforms. While a number of such environments have been widely accepted and used for traditional HPC systems, there are currently no widely used environments for Grid programming. The goal of the Grid Application Development Software (GrADS) project is to develop a coordinated set of tools, libraries and run-time execution facilities for Grid program development. In this paper, we describe a Grid scheduler component that is integrated as part of the GrADS software system. Traditionally, application-level schedulers (e.g. AppLeS) have been tightly integrated with the application itself and were not easily applied to other applications. Our design is generic: we decouple the scheduler core (the search procedure) from the application-specific (e.g. application performance models) and platformspecific (e.g. collection of resource information) components used by the search procedure. We provide experimental validation of our approach for two representative regular, iterative parallel programs in a variety of real-world Grid testbeds. Our scheduler consistently outperforms static and user-driven scheduling methods. This material is based upon work supported by the National Science Foundation under Grant #9975020.

Abstract not found

Developing grid applications is a challenging endeavor, which at the moment requires both extensive labor and expertise. The Grid Application Development Software Project (GRADS) provides a system to simplify grid application development. This system incorporates tools at all stages of the application development and execution cycle. In this chapter we focus on application scheduling, and present the three scheduling approaches developed in GRADS: development of an initial application schedule (launch-time scheduling), modification of the execution platform during execution (rescheduling), and negotiation between multiple applications in the system (metascheduling). These approaches have been developed and evaluated for platforms that consist of distributed networks of shared workstations, and applied to real-world parallel applications.

In this chapter, I review the main methods and techniques of complex systems science. As a

In recent years the labels “gossip ” and “gossip-based ” have been applied to an increasingly general class of algorithms, including approaches to information aggregation, overlay network management and clock synchronization. These algorithms are intuitively similar, irrespective of their purpose. Their distinctive features include relying on local information, being round-based and relatively simple, and having a bounded information transmission and processing complexity in each round. Our position is that this class can and should be significantly extended to involve algorithms from other disciplines that share the same orsimilar distinctive features, like certain parallel numerical algorithms, routing protocols, bio-inspired algorithms and cellular automata, to name but a few. Such a broader perspective would allow us to import knowledge and tools to design and understand gossip-based distributed systems, and we could also export accumulated knowledge to re-interpret some of the problems in other disciplines, such as vehicular traffic control. In this position paper we describe a number of areas that show parallels with gossip protocols. These example areas will hopefully serve as inspiration for future research. In addition, we believe that comparisons with other fields also helps clarify the definition of gossip protocols and represents a necessary first step towards an eventual formal definition. 1.

Improvements in networking and middleware technology are enabling large-scale grids that aggregate resources over wide-area networks to support applications at unprecedented levels of scale and performance. Unfortunately, existing middleware and tools can not in general inform a user as to the suitability of a given grid topology for a specific grid application. Instead, users generally develop ad hoc performance models for mapping their applications to resource and network topologies. Because application behavior alone is complex, and resource and network behavior further complicate the picture, users are typically reduced to nearly blind experimentation to discover how to deploy their application in the new grid environment. Only after the fact can a user discovers if the match was a good one. Further, even after finding a desirable configuration, there is no basis on which to determine if a much better configuration exists. We present a richer methodology for evaluating grid software and diverse grid environments based on the MicroGrid grid emulator. With the MicroGrid, users, grid researchers, or grid operators can define and emulate arbitrary collections of resources and networks. This allows study of an existing grid testbed under controlled conditions or even to study the efficacy of higher performance environments than are available today. Further, the MicroGrid supports direct execution of grid applications unchanged. These application can be written with MPI, C, C++, Perl, and/or Python and use the Globus middleware. This enables detailed and accurate study of application behavior.

Improvements in networking and middleware technology are enabling large-scale grids that aggregate resources over wide-area networks to support applications at unprecedented levels of scale and performance. Unfortunately, existing middleware and tools provide little information to users as to the suitability of a given grid topology for a specific grid application. Instead, users generally use ad-hoc performance models to evaluate mappings of their applications to resource and network topologies. Grid application behavior alone is complex, and adding resource and network behavior makes the situation even worse. As a result, users typically employ nearly blind experimentation to find good deployments of their applications in each new grid environment. Only through actual deployment and execution can a user discovers if the mapping was a good one. Further, even after finding a good configuration, there is no basis to determine if a much better configuration has been missed. This approach slows effective grid application development and deployment.