Scale and performance in a distributed file system
ACM Transactions on Computer Systems (TOCS)
Exploiting weak connectivity for mobile file access
SOSP '95 Proceedings of the fifteenth ACM symposium on Operating systems principles
Feasibility of a serverless distributed file system deployed on an existing set of desktop PCs
Proceedings of the 2000 ACM SIGMETRICS international conference on Measurement and modeling of computer systems
OceanStore: an architecture for global-scale persistent storage
ASPLOS IX Proceedings of the ninth international conference on Architectural support for programming languages and operating systems
Progress in Linear Programming-Based Algorithms for Integer Programming: An Exposition
INFORMS Journal on Computing
Taming aggressive replication in the Pangaea wide-area file system
ACM SIGOPS Operating Systems Review - OSDI '02: Proceedings of the 5th symposium on Operating systems design and implementation
Performance of the IBM General Parallel File System
IPDPS '00 Proceedings of the 14th International Symposium on Parallel and Distributed Processing
SOSP '03 Proceedings of the nineteenth ACM symposium on Operating systems principles
Erasure Code Replication Revisited
P2P '04 Proceedings of the Fourth International Conference on Peer-to-Peer Computing
Deploying Digital Media Libraries in Multi-Service Access Networks
ISM '06 Proceedings of the Eighth IEEE International Symposium on Multimedia
Replica placement in ring based content delivery networks
Computer Communications
Hi-index | 0.00 |
Anytime, anywhere and anyhow access to personalized services requires the complete decoupling of devices for accessing the service and the supporting personal data storage. When deploying such transparent personalized services, an important question that needs answering is where to install the storage servers. In this respect, this paper considers the deployment of a personal content storage service in multi-service access networks. The storage server placement problem is formulated as a binary integer linear programming (BILP) problem and a heuristic storage server placement algorithm (SSPA) is presented and evaluated. First it is assumed that servers do not fail. Consequently, the problem formulation is extended to include replication and striping and both BILP and heuristic methods are modified to cope with the additional constraints. The extended SSPA heuristic is used to analyze several resilience and striping scenarios. It is shown that the SSPA produces close to optimal results and is very efficient for optimizing server placement in personal content storage deployments.