Large-scale distributed applications are subject to frequent disruptions due to resource contention and failure. Such disruptions are inherently unpredictable and, therefore, robustness is a desirable property for the distributed operating environment. In this work, we describe and evaluate a robust topology for applications that operate on a spanning tree overlay network. Unlike previous work that is adaptive or reactive in nature, we take a proactive approach to robustness. The topology itself is able to simultaneously withstand disturbances and exhibit good performance. We present both centralized and distributed algorithms to construct the topology, and then demonstrate its effectiveness through analysis and simulation of two classes of distributed applications: Data collection in sensor networks and data dissemination in divisible load scheduling. The results show that our robust spanning trees achieve a desirable trade-off for two opposing metrics where traditional forms of spanning trees do not. In particular, the trees generated by our algorithms exhibit both resilience to data loss and low power consumption for sensor networks. When used as the overlay network for divisible load scheduling, they display both robustness to link congestion and low values for the makespan of the schedule

This paper presents an architecture and implementation for a dynamic OGSA-based grid service architecture that extends GT3 to support dynamic service hosting - where to host and re-host a service within the grid in response to service demand and resource fluctuation. Our model goes beyond current OGSI implementations in which the service is presumed to be pre-installed at all sites (and only service instantiation is dynamic). In dynamic virtual organizations (VOs), we believe dynamic service hosting provides an important flexibility. Our model also defines several new adaptive grid service classes that support adaptation at multiple levels. Dynamic service deployment allows new services to be added or replaced without taking down a site for reconfiguration and allows a VO to respond effectively to dynamic resource availability and demand. The preliminary results suggest that the cost of dynamic installation, deployment, and invocation, is tolerable.

Scheduling strategies for parallel and distributed computing have mostly been oriented toward performance, while striving to achieve some notion of fairness. With the increase in size, complexity, and heterogeneity of today's computing environments, we argue that, in addition to performance metrics, scheduling algorithms should be designed for robustness. That is, they should have the ability to maintain performance under a wide variety of operating conditions. Although robustness is easy to define, there are no widely used metrics for this property. To this end, we present a methodology for characterizing and measuring the robustness of a system to a specific disturbance. The methodology is easily applied to many types of computing systems and it does not require sophisticated mathematical models. To illustrate its use, we show three applications of our technique to job scheduling; one supporting a previous result with respect to backfilling, one examining overload control in a streaming video server, and one comparing two different scheduling strategies for a distributed network service. The last example also demonstrates how consideration of robustness leads to better system design as we were able to devise a new and effective scheduling heuristic.