Loading...
Please wait, while we are loading the content...
Similar Documents
Preference driven server selection in peer-2-peer data sharing systems
| Content Provider | ACM Digital Library |
|---|---|
| Author | Elwaer, Abdelhamid Rana, Omer Taylor, Ian |
| Abstract | In scientific applications utilizing a distributed computing infrastructure, data may not be co-located with computation, and may need to be retrieved from one or more remote servers. Where such computation is being supported through volunteered resources, often the data storage server is centralized, but the processing nodes (peers) are distributed. For instance, the BOINC project has been widely used to develop "volunteer computing" projects, utilizing a centralized server to distribute data to users. This can be limiting in terms of performance, scalability and reliability. We describe a framework which utilizes an alternative data distribution and access approach, making use of a BitTorrent-like protocol and integrated with BOINC, for supported automated server selection. In this framework, a node within the system can be a client requesting data, a data hosting service (data center) or a lookup server responsible for providing data to its clients to calculate the "trust value" of data centers. These trust values are used to select data centers to download from based on preferences identified by clients. We demonstrate how such a framework could be used to improve data access time and reliability in Peer-2-Peer based volunteer computing projects. |
| Starting Page | 9 |
| Ending Page | 16 |
| Page Count | 8 |
| File Format | |
| ISBN | 9781450307048 |
| DOI | 10.1145/1996014.1996017 |
| Language | English |
| Publisher | Association for Computing Machinery (ACM) |
| Publisher Date | 2011-06-08 |
| Publisher Place | New York |
| Access Restriction | Subscribed |
| Subject Keyword | Volunteer computing Data distribution Trust P2p |
| Content Type | Text |
| Resource Type | Article |
