Papers by Author: Xiao Zong Yang

Abstract: Availability is one of the key features for transaction processing systems. Fault injection is one of the important techniques to hasten availability tests. A fault injection platform is designed in this paper for IA64 system which is being widely used in transaction processing business. The fault injection platform is implemented using client/server mode and a series of fault injection tools are accomplished which covers CPU faults, memory faults, disk faults, IO faults, file system faults and system call boundary errors. A group of experiments on a typical IA64 server are described and performed, and the experiment results validate the effectiveness of the fault injection platform.

Abstract: Importance measures are widely used to characterize the contribution of components to the system performance such as reliability, availability, risk, etc, and thus give great help in identifying system weaknesses and prioritizing system improvement activities. Although much work has been carried out on component importance analysis, most studies only concern the consistent states of components within which components exhibit consistent performance until state changes happen. Unfortunately, field data shows that many transient faults in components may result in severe consequences without causing any state changes, and, this can lead to a misunderstanding of component importance. This paper focuses on the reliability importance analysis in presence of transient faults, and proposes a composite measure for evaluation. A sample series parallel system is analyzed to illustrate the use of this measure.