Principles of Optimally Placing Data in Tertiary Storage Libraries

摘要

Recently, technological advances have resulted in the wide availability of commercial products offering near-line, robot-based, tertiary storage libraries. Thus, such libraries have become a crucial component of modern large-scale storage servers, given the very large storage requirements of modern applications. Although the subject of optimal data placement (ODP) strategies has received considerable attention for other storage devices (such as magnetic and optical disks and disk arrays), the issue of optimal data placement in tertiary libraries has been neglected. The latter issue is more critical since tertiary storage remains three orders of magnitude slower than secondary storage. In this paper, we address this issue by deriving such optimal placement algorithms. First, we study the ODP problem in disk libraries (jukeboxes) and subsequently, in tape libraries. In our studies, we consider different scheduling algorithms, different configurations of disk libraries and different tape library technologies (reflecting different existing commercial products) and show how these impact on the ODP strategy.