A Fault-Tolerant Scheduling Algorithm using Hybrid Overloading Technology for Dynamic Grouping based Multiprocessor Systems
Author(s) -
Xing-biao Yu,
Junsuo Zhao,
Changwen Zheng,
Xiaohui Hu
Publication year - 2014
Publication title -
international journal of computers communications and control
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.422
H-Index - 33
eISSN - 1841-9844
pISSN - 1841-9836
DOI - 10.15837/ijccc.2012.5.1358
Subject(s) - computer science , backup , multiprocessing , fault tolerance , parallel computing , scheduling (production processes) , distributed computing , algorithm , operating system , mathematics , mathematical optimization
In order to extend the application area of fault-tolerant scheduling algorithm based on hybrid overloading for multiprocessor and increase the fault-tolerant number of processors, we propose a new fault-tolerant scheduling algorithm, which is based on hybrid overloading and dynamic grouping for multiprocessor by combining logic grouping strategy for processors in primary backup overloading and backup backup overloading.This algorithm presents the formalization of the dynamic grouping for processors in fault-tolerant scheduling based on hybrid overloading and enlarges the task number included in overloading task link. In the process of fault-tolerant scheduling the processors are dynamically divided into some groups based on overloading task link, so as to keep good scheduling success ratio and enhance the fault-tolerant performance of processors. Both theoretical analysis and simulation experiment prove this algorithm’s effectiveness respectively.
Accelerating Research
Robert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom
Address
John Eccles HouseRobert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom