Font Size: a A A

Research On Fault-Tolerant Policy In Grid Computing

Posted on:2011-01-10Degree:MasterType:Thesis
Country:ChinaCandidate:Z H ZhangFull Text:PDF
GTID:2178330332971048Subject:Communication and Information System
Abstract/Summary:PDF Full Text Request
With the development of computer and Internet, the grid has evolved from pure high-performance computing systems into infrastructure of the heterogeneous, dynamic, distributed environment for resource sharing and collaborative computing. Grid computing has the capability of breakthrough current computational barriers, integrating large scale distributed and free resources, resolving complex scientific and engineering problems collaboratively, flourishing the development of scientific research and engineering practice extremely. Nevertheless, accomplished by the highly dynamic and heterogeneous characteristics, grid systems are more prone to failures. The frequently occurrence of failures is becoming a main problem that obsesses many scientists, engineers and users. How to improve reliability and robustness of grids, by means of introducing an appropriate fault-tolerance mechanism, is one of the most difficult issues in literature.For the question of grid computation in error processing, this article has analyzed the theory of grid fault-tolerant, discussed the redundancy, which is the foundation of grid fault-tolerant. Base on deep research existing grid fault-tolerant technology contrasts the respective good and bad points and after calculate the best parameters of fault-tolerant system, we gave the double node type adaptive fault-tolerant strategy. This fault-tolerant strategy's merit lies under the different network environment, does not need to replace the fault-tolerant strategy, does not need the artificial establishment node quantity, the auto-adapted fault-tolerant strategy can automatic basis grid situation try again to choose the appropriate node quantity ,increases the redundancies to carry on the job level fault-tolerant, completes until the complete work success. Through mathematical modeling to the commonly used fault-tolerant strategy and new auto-adapted fault tolerant in the average execution time and the system resources consumption. In the last of this paper, we contrast the existing each kind of grid emulation tools and chosen the GridSim tool to confirmation the algorithm we gave, through the data production by the tool, we generate the line chart, and obtains the auto-adapted fault-tolerant strategy has more superiority in the average execution time and the system resources consumption.
Keywords/Search Tags:Grid Computing, Fault-Tolerant, Self-adapting
PDF Full Text Request
Related items