Adaptive Quality of Security Control in Storage Systems BY

and to my fiance Hisham Albataineh, who made all of this possible, for their endless encouragement and patience. ii Since security is of critical importance for modern storage systems, it is imperative to protect stored data from being tampered or disclosed. Although an increasing number of secure storage systems have been developed, there is no way to adaptively choose security services to meet disk requests flexible security requirements. Furthermore, existing security techniques for disk systems are not suitable to guarantee desired response times of disk requests. In this dissertation research, we proposed a series of adaptive quality of security control strategies, which can judiciously select the most appropriate security service for disk requests while endeavoring to guarantee desired response times of all disk requests. Specifically , we proposed in this dissertation a quality of security framework or StReD for storage resources. The StReD framework integrates a quality of security adaptor with an array of security services. Next, an adaptive strategy or AWARDS was developed for local storage systems to improve dynamically improve quality of security without adversely affecting the response times of write requests. To prove the efficiency of AWARDS, we built an analytical model to measure the probability that a disk request is completed before its desired response time. Furthermore , we designed and implemented an adaptive quality of security control strategy or ASPAD for parallel disk systems. ASPAD makes it possible for parallel disk systems to adapt to changing security requirements and workload conditions. Last but not least, we devised a security-aware cache management mechanism or CaPaS for cluster storage systems. CaPaS aims at achieving high security and desired performance for data-intensive applications running on clusters. CaPaS is used in combination with the ASPAD strategy, thereby providing high quality of security for cluster storage systems. Extensive trace-driven simulations, which are based on a set of real applications as well as synthetic workloads with various disk I/O characteristics, show that the adaptive quality of security control schemes sig-iii nificantly improve security of local disk systems, parallel disk systems, and cluster storage systems without adversely affecting the performance of storage systems. iv Acknowledgments First of all, I would like to express my heartfelt thanks to my advisor, Dr. Xiao Qin, for his guidance, support, and encouragement during the course of my graduate study at the University of New Mexico Tech. I am especially indebted to him for teaching me both …