Optimized dependent file fetch middleware in transparent computing platform |
| |
| Affiliation: | 1. School of Information Science and Engineering, Central South University, Changsha, China;2. Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education (Nanjing University of Science and Technology), Nanjing, China;3. Faculty of Computer and Information Sciences, Hosei University, Tokyo, Japan;1. Computer Science Department, Wellesley College, Wellesley, MA 02481, United States;2. Computer Science Department, Boston University, Boston, MA 02215, United States;1. Department of Computer Science and Information Technology, RMIT University, Melbourne, VIC 3001, Australia;2. Swinburne University of Technology, Melbourne, VIC 3122, Australia;1. Department of Computer Science, Virginia Tech, USA;2. Department of Computer Engineering, King Mongkut’s University of Technology Thonburi, Thailand;3. Department of Physics, European Organization for Nuclear Research (CERN), Switzerland |
| |
| Abstract: | A middleware is proposed to optimize file fetch process in transparent computing (TC) platform. A single TC server will receive file requests of large scale distributed operating systems, applications or user data from multiple clients. In consideration of limited size of server’s memory and the dependency among files, this work proposes a middleware to provide a file fetch sequence satisfying: (1) each client, upon receiving any file, is able to directly load it without waiting for pre-required files (i.e. “receive and load”); and (2) the server is able to achieve optimization in reducing overall file fetch time cost. The paper firstly addresses the features of valid file fetch sequence generating problem in the middleware. The method solves the concurrency control problem when the file fetch is required for the multiple clients. Then it explores the methods to determine time cost for file fetch sequence. Based on the established model, we propose a heuristic and greedy (HG) algorithm. According to the simulation results, we conclude that HG algorithm is able to reduce overall file fetch time roughly by 50% in the best cases compared with the time cost of traditional approaches. |
| |
| Keywords: | Middleware File dependency File fetch Heterogeneous network Transparent computing |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
