Gossip-based algorithms were first introduced for reliably disseminating data in large-scale distributed systems. However, their simplicity, robustness, and flexibility make them attractive for more than just pure data dissemination alone. In particular, gossiping has been applied to data aggregation, overlay maintenance, and resource allocation. Gossiping applications more or less fit the same framework, with often subtle differences in algorithmic details determining divergent emergent behavior. This divergence is often difficult to understand, as formal models have yet to be developed that can capture the full design space of gossiping solutions. In this paper, we present a brief introduction to the field of gossiping in distributed systems, by providing a simple framework and using that framework to describe solutions for various application domains.

Scientific and Engineering domain Applications like high energy physics applications have huge computational and storage needs. Such applications rely mainly on geographically dispersed productions farms for their computing needs. Production farms typically consist of commercial off-the-shelf (COTS) clusters, Network of Workstations (NOW) and intranets. In a grid environment, these clusters are interfaced to the grid middleware via cluster management software like a batch system. In this paper we focus on a detrimental effect that one or more faulty nodes in a cluster have on the efficiency and throughput of the cluster and the application in general. This effect is what we call as the ‘Black hole effect’. A ‘Black Hole ’ is a faulty node in the cluster that causes the application to fail on it due to incompatibilities between application requirements and the execution environment. 1.