Optimizing Data Management in Grid Environments

Abstract

AbstractGrids currently serve as platforms for numerous scientific as well as business applications that generate and access vast amounts of data. In this paper, we address the need for efficient, scalable and robust data management in Grid environments. We propose a fully decentralized and adaptive mechanism comprising of two components: A Distributed Replica Location Service (DRLS) and a data transfer mechanism called GridTorrent. They both adopt Peer-to-Peer techniques in order to overcome performance bottlenecks and single points of failure. On one hand, DRLS ensures resilience by relying on a Byzantine-tolerant protocol and is able to handle massive concurrent requests even during node churn. On the other hand, GridTorrent allows for maximum bandwidth utilization through collaborative sharing among the various data providers and consumers. The proposed integrated architecture is completely backwards-compatible with already deployed Grids. To demonstrate these points, experiments have been conducted in LAN as well as WAN environments under various workloads. The evaluation shows that our scheme vastly outperforms the conventional mechanisms in both efficiency (up to 10 times faster) and robustness in case of failures and flash crowd instances.KeywordsLarge Hadron ColliderGrid EnvironmentDistribute Hash TableGlobus ToolkitReplica LocationThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.