外文翻譯----文件系統(tǒng)虛擬化和服務網(wǎng)格數(shù)據(jù)管理-預覽頁
【正文】 cause an optimization tailored for one application (., aggressive prefetching of file contents) may result in performance degradation for several others (., sparse files, databases), applicationtailored features are typically not implemented in generalpurpose O/S kernels. In addition, kernellevel modifications are difcult to port and deploy, notably in shared environments. Toolkitbased solutions typically give users powerful APIs to program remote data access with desired behaviors, but few programmers are skilled to make efective use of such APIs. To solve this problem, userlevel DFS customizations are proposed to support applicationtailored GVFS data sessions. In particular, enhancements designed for gridstyle environments are provided upon the virtualization layer in GVFS, which include customizable disk caching and multithreading for highperformance data access, efcient consistency protocols for applicationdesired data coherence, strong and gridpatible security for secure gridwide data access, and reliability protocols supporting applicationtransparent failure detection and recovery. Based on GVFS, data sessions can be created on demand on a perapplication basis, where each session can apply and configure these enhancements independently to address its application39。s point of view, it is expected that the resource use is healthy and profitable. Therefore, this dissertation presents a novel servicebased autonomic data management approach to automatically manage and optimize the data provisioning according to such highlevel objectives. This dissertation proposes a set of data management services to manage the perapplication GVFS sessions, enforce the isolation among the independent sessions, and apply the desired customization for each session. They support ?exible control over the lifecycles and configurations of data sessions, and can explore the knowledge of applications (., data access patterns, data sharing scenarios, and service quality requirements) to customize their data sessions on the use of performance, consistency, security, and reliability enhancements. These services also provide interoperable interfaces which allow for direct interactions with other grid middleware services and automated executions of data provisioning tasks. To further reduce human intervention in managing data sessions and enable them to promptly adapt to the changing environments, autonomic functions are built into the data management services to make them capable of automatically monitoring, analyzing, and optimizing the distributed entities of gridwide data sessions, and cooperatively working together to achieve the desired data provisioning and resource usage goals. Such autonomic management is applied to several important aspects of data sessions including cache configuration, data replication, and session redirection. In summary, the GVFSbased data management system addresses the last question by employing autonomic services to provide automatic management and optimization of data sessions according to the application needs and changing environments.
畢業(yè)設計相關(guān)推薦
鄂ICP備17016276號-1