Randolph Wang - US grants

The role played by magnetic storage systems is becoming increasingly important as computing systems accelerate their transformation from "number-crunching" devices to "information appliances". However, the technology has advanced so far that the inadequacies of the state-of-art are becoming apparent. The first of these is the lack of understanding of the science behind the architecture of a device that delivers optimal performance/cost ratio. The second inadequacy is the lack of coordination of the various levels of hardware and software in a storage system. The third is that the file system designers have not yet recognized the emergence of the ubiquitous consumer devices as one of the network storage research issues. This research explores two critical questions: how to provide very low latency I/O and how to manage ubiquitous network storage. Low latency is achieved by a combination of innovations in architecture of the devices themselves and exploiting the interactions between these devices, file systems, and applications. Ubiquitous storage management is achieved by leveraging the emergence of ubiquitous connectivity and a peer-to-peer architecture. By addressing the issues of performance and functionality of magnetic storage systems, the proposed research contributes to the science underlying a crucial backbone of the information infrastructure.

One consequence of the phenomenal storage density improvement is the
emergence of highly compact disk storage that can be integrated into
various computing and networking devices of various shapes and forms.
Our conjecture is that mobile storage will become a dominant form of
storage in the near future, especially for personal user data,
subsuming conventional disks enshrined in server rooms. This proposal
describes a project that studies how to build, manage, and use
discrete storage devices to form ad hoc, distributed storage systems.

In this project, we propose to build system software to intelligently
coordinate the discrete storage elements. The system has four core
mechanisms: (1) a multicast-like data location mechanism, (2) an
invalidation mechanism for purging obsolete data from the system, (3)
a snapshot mechanism for supporting sharing and backup, and (4) a
storage level solution that can support existing file systems. In
this proposal, we describe how combinations of these four core
mechanisms allow us to achieve our consistency, transparency,
reliability, security, and performance goals.

Furthermore, the data management needs addressed by this project are
by no means limited to traditional desktop applications. As the data
management functionalities are separated from cumbersome generic
computing devices, and as these functionalities are cleanly
encapsulated in modular small form factor devices that can readily
interact with other consumer electronic devices (such as cameras, MP3
players, phones, and email devices), these application-specific
devices would be freed from the burden of having to solve and re-solve
a difficult mobile storage problem, and we may multiply the utility of
these devices and potentially foster new applications.