Andrew: a distributed personal computing environment
Communications of the ACM - The MIT Press scientific computation series
Scale and performance in a distributed file system
ACM Transactions on Computer Systems (TOCS)
ISCA '88 Proceedings of the 15th Annual International Symposium on Computer architecture
Coda: A Highly Available File System for a Distributed Workstation Environment
IEEE Transactions on Computers
Caching in large-scale distributed file systems
Caching in large-scale distributed file systems
A caching relay for the World Wide Web
Selected papers of the first conference on World-Wide Web
Performance engineering of the World Wide Web: application to dimensioning and cache design
Proceedings of the fifth international World Wide Web conference on Computer networks and ISDN systems
ICDE '96 Proceedings of the Twelfth International Conference on Data Engineering
The case for geographical push-caching
HOTOS '95 Proceedings of the Fifth Workshop on Hot Topics in Operating Systems (HotOS-V)
Application-level document caching in the Internet
SDNE '95 Proceedings of the 2nd International Workshop on Services in Distributed and Networked Environments
Characteristics of WWW Client-based Traces
Characteristics of WWW Client-based Traces
An Efficient Scheme for Dynamic Data Replication
An Efficient Scheme for Dynamic Data Replication
World-wide web cache consistency
ATEC '96 Proceedings of the 1996 annual conference on USENIX Annual Technical Conference
Supporting quality of service in HTTP servers
PODC '98 Proceedings of the seventeenth annual ACM symposium on Principles of distributed computing
Analysis of Task Assignment Policies in Scalable Distributed Web-Server Systems
IEEE Transactions on Parallel and Distributed Systems
IEEE Transactions on Parallel and Distributed Systems
IEEE Transactions on Knowledge and Data Engineering
HCW '98 Proceedings of the Seventh Heterogeneous Computing Workshop
Placement of Read-Write Web Proxies in the Internet
ICDCS '01 Proceedings of the The 21st International Conference on Distributed Computing Systems
GEMA: An Object Replacement Algorithm for Cooperative Web Proxy Systems
Multimedia Tools and Applications
Optimizing Download Time of Embedded Multimedia Objects for Web Browsing
IEEE Transactions on Parallel and Distributed Systems
Static and adaptive distributed data replication using genetic algorithms
Journal of Parallel and Distributed Computing
Policies for Caching OLAP Queries in Internet Proxies
IEEE Transactions on Parallel and Distributed Systems
Providing dynamic and customizable caching policies
USITS'99 Proceedings of the 2nd conference on USENIX Symposium on Internet Technologies and Systems - Volume 2
USITS'97 Proceedings of the USENIX Symposium on Internet Technologies and Systems on USENIX Symposium on Internet Technologies and Systems
Combining replica placement and caching techniques in content distribution networks
Computer Communications
Small cache, big effect: provable load balancing for randomly partitioned cluster services
Proceedings of the 2nd ACM Symposium on Cloud Computing
Dynamically selecting distribution strategies for web documents according to access pattern
EUC'05 Proceedings of the 2005 international conference on Embedded and Ubiquitous Computing
Hi-index | 0.00 |
Research on replication techniques to reduce traffic and minimize the latency of information retrieval in a distributed system has concentrated on client-based caching. In this technique, recently and frequently accessed information is cached at a client (or at a proxy thereof) in anticipation of future accesses. Such myopic solutions-focusing exclusively on a particular client or set of clients-will likely have a limited impact. Instead, the author offers a solution that replicates information on a global supply-and-demand basis. The author proposes a data-dissemination mechanism that allows information to propagate from its producers to servers that are closer to its consumers. This dissemination reduces network traffic and balances load among servers by exploiting the geographic and temporal locality of reference exhibited in client-access patterns. The level of dissemination depends on the relative popularity of documents, and on the expected reduction in traffic that results from such dissemination. Using extensive HTTP logs, the author and his colleagues devised an analytical model of server popularity and file-access profiles. With that model, he shows that disseminating the most popular documents on servers closer to clients could reduce network traffic considerably, while balancing server loads. Trace-driven simulations quantify the performance gains achievable through such a protocol.