Learn More
SUMMARY We present a scheme for reserving job resources with imprecise requests. Typical parameters such as the estimated runtime, the start time or the type or number of required CPUs need not be fixed at submission time but can be kept fuzzy in some aspects. Users may specify a list of preferences which guide the system in determining the best matching(More)
We present Stellaris, the information service of the community project AstroGrid-D. Stellaris is the core component of the AstroGrid-D mid-dleware that enables scientists to share their resources, provides access to large datasets and integrates instruments such as robotic telescopes. Besides the many diverse types of resources, the information service also(More)
In this paper, we present an experimental study of deterministic non-preemptive multiple workflow scheduling strategies on a Grid. We distinguish twenty five strategies depending on the type and amount of information they require. We analyze scheduling strategies that consist of two and four stages: labeling, adaptive allocation, prioritization, and(More)
We present an architectural framework for specifying and processing co-reservations in grid environments. Compared to other approaches, our co-reservation framework is more general. It can be applied to the reservation of applications running concurrently on multiple resources (multi-site applications) and to the planning of job flows, where the components(More)
Workflow scheduling in Grids becomes an important area as it allows users to process large scale problems in an atomic way. However, validating the performance of workflow scheduling strategies in real production environment cannot be feasibly carried out. The complexity of production systems, dynamicity of Grid execution environments, and the difficulty to(More)
We present an algorithm for reserving compute resources in a Grid, that allows users to define an optimization strategy , if multiple candidates match the specified requirements. Reservations need not to be exact, but can be elastic in some properties like start-, end-time, duration or the number of requested CPUs. Our algorithm takes the speedup of(More)
We present a framework for the co-ordinated, autonomic management of multiple clusters in a compute center and their integration into a Grid environment. Site autonomy and the automation of administrative tasks are prime aspects in this framework. The system behavior is continuously monitored in a steering cycle and appropriate actions are taken to resolve(More)
Clusters provide an outstanding cost/performance ratio , but their efficient orchestration, i.e. their cooperative management, maintenance, and use, still poses difficulties. Moreover, many sites operate multiple clusters, each possibly running under a different cluster management system. In this paper, we present an architectural scheme for the coordinated(More)
This paper discusses the problem of planning resource outsourcing and local configurations for infrastructure services that are subject to Service Level Agreements (SLA). The objective of our approach is to minimize implementation and outsourcing costs for reasons of competitiveness, while respecting business policies for profit and risk. We implement a(More)