Principles of Optimally Placing Data in Tertiary Storage Libraries

Abstract

Recently, technological advances have resulted in the wide availability of commercial prod-ucts 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 stor-age requirements of modern applications. Al-though the subject of optimal data placement (ODP) strategies has received considerable at-tention for other storage devices (such as mag-netic and optical disks and disk arrays), the issue of optimal data placement in tertiary libraries has been neglected. The latter is-sue is more critical since tertiary storage re-mains 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 con-figurations of disk libraries and different tape library technologies (reflecting different exist-ing commercial products) and show how these impact on the ODP strategy. *Support for this work was provided by the European Com-munity through the ESPRIT Long Term Research Project HER-MES no. 9141.