ITR: Self-* Storage Systems

Carnegie Mellon University, Pittsburgh PA

Investigators

Abstract

Human administration of storage systems (including capacity planning, back-up, load balancing, etc.) is a large and growing issue in modern IT infrastructures; reported ratios of 1 sysadmin per 1-10TB of storage are scary with multi-petabyte data centers on the horizon. This research program defines and explores a new storage architecture that integrates automated management functions and simplifies the human administrative task. We refer to conforming systems as self-* storage systems in an attempt to capture many recent buzzwords in a single meta-buzzword; self-* systems should be self-configuring, self-organizing, self-tuning, self-healing, self-managing, etc. Human administrators provide only muscle for component addition and guidance on acceptable risk levels and current levels of satisfaction. Borrowing organizational ideas from corporate structure and technologies from AI and control systems, self-* storage should simplify storage administration, increase system robustness, and simplify system construction.