作者: K.H. Kim , H.O. Welch
DOI: 10.1109/12.24266
关键词:
摘要: The concept of distributed execution recovery blocks is examined as an approach for uniform treatment hardware and software faults. A useful characteristic the relatively small time cost it requires. thus suitable incorporation into real-time computer systems. specific formulation that aimed at minimizing presented, called scheme. DRB scheme capable effecting forward while handling both faults in a manner. An to incorporating capability load-sharing multiprocessing also discussed. Two experiments testing efficiency applications have been conducted on two different multimicrocomputer networks. results clearly indicate feasibility achieving tolerance >