PERSPECTIVE: A Home Storage Solution
Contact: Greg Ganger, Brandon Salmon
The home provides a new and challenging environment for data management, with both the number of storage-enhanced devices and the amount/variety of content growing rapidly. Moreover, devices in the home are extremely heterogeneous in computational power, storage capacity, and usage model. We need much simpler and more automated data management approaches to allow users to manage data in this new environment, sharing information across devices, finding information when needed, handling reliability issues, and so on. Perspective is a distributed data management system for home/consumer storage architected around the concept of a view. A view is a description of data about which a device is interested, published to other Perspective devices. Views provide a solid building block for efficient consistency management, inter-device search, device departure and arrival handling, and data protection. Within Perspective, we are also exploring automated data distribution approaches, effective search mechanisms, and security management for home/consumer storage.
This diagram shows how views facilitate object update or addition. In this case, Steve’s laptop
has received a new movie (perhaps from the Internet). Because it holds all the views in the system, it knows that both the desktop
and DVR need to see update messages for this new object. Note that the cell phone’s view does not include the object and, therefore,
does not need to see the update. |
People
FACULTY
Lujo Bauer
Lorrie Cranor
Greg Ganger
STAFF
GRAD STUDENTS
Hardik Doshi
Jared Goerner
Yuan Liang
Michelle Mazurek
Prerak Mehta
Brandon Salmon
Zoheb Shivani
INDUSTRY COLLABORATORS
Lily Mummert (Intel)
Publications
- Perspective: Semantic Data Management for the Home. Brandon Salmon, Steven W. Schlosser, Lorrie Faith Cranor, Gregory R. Ganger. 7th USENIX Conference on File and Storage Technologies (FAST '09). Feb. 24-27, 2009. San Francisco, CA. Supercedes Carnegie
Mellon University Parallel Data Lab Technical Report CMU-PDL-08-105, May
2008.
Abstract / PDF [275KM]
- Learning to Share: A Study of Sharing Among Home Storage Devices. Brandon Salmon, Frank Hady, Jay Melican. Carnegie Mellon University Parallel Data Lab Technical Report CMU-PDL-07-107, October, 2007.
Abstract / PDF [726K]
- Putting Home Storage Management into Perspective. Brandon Salmon, Steven W. Schlosser, Lily B. Mummert, Gregory R. Ganger.
Carnegie Mellon University Parallel Data Lab Technical Report CMU-PDL-06-110, September 2006.
Abstract / PDF [382K]
- Towards Efficient Semantic Object Storage for the Home. Brandon Salmon, Steven W. Schlosser, Gregory R. Ganger. Carnegie Mellon University Parallel Data Lab Technical Report CMU-PDL-06-103, May 2006.
Abstract / PDF [ 297K]
Acknowledgements
We thank the members and companies of the PDL Consortium: American Power Conversion, Data Domain, Inc., EMC Corporation, Facebook, Google, Hewlett-Packard Labs, Hitachi, IBM, Intel Corporation, LSI, Microsoft Research, NetApp, Inc., Oracle Corporation, Seagate Technology, Sun Microsystems, Symantec Corporation and VMware, Inc. for their interest, insights, feedback, and support.