Operating Systems Research Group
Operating Systems Research on Energy, Reliability and Autonomy

Intelligent Storage Systems

Technology trends indicate that today's computing is becoming more and more data-centric. The widespread use of data devices and services has created unprecedented demand to store and retrieve information. Data is the primary asset of most companies in the current information age. As a result, the amount of data storage managed by data centers is growing rapidly, around 60\% per year. By 2008, the average data center will manage 10 times as much data as it does today.

Consequently, storage systems have become ever so complex in order to satisfy the increasing demand. To deliver satisfactory performance, many modern storage systems have exploited new hardware technologies such as multi-processors, clusters, memory caching, and storage area networks. For example, an EMC Symmetric server contains up to eighty 333 MHz microprocessors with up to 256 GB of memory as the storage cache.

The goal of our project is to exploit the intelligence in such storage systems to improve performance, manageability and reliability.