Optimal static load balancing in distributed computer systems
Journal of the ACM (JACM)
A relational approach to monitoring complex systems
ACM Transactions on Computer Systems (TOCS)
Non-intrusive and interactive profiling in parasight
PPEALS '88 Proceedings of the ACM/SIGPLAN conference on Parallel programming: experience with applications, languages and systems
On robust transaction routing and load sharing
ACM Transactions on Database Systems (TODS)
An annotated bibliography of interactive program steering
ACM SIGPLAN Notices
Dienst: an architecture for distributed document libraries
Communications of the ACM
Satisfying response time goals in transaction processing systems
PDIS '93 Proceedings of the second international conference on Parallel and distributed information systems
On-Line Monitoring: A Tutorial
Computer
JEWEL: Design and Implementation of a Distributed Measurement System
IEEE Transactions on Parallel and Distributed Systems
Dienst: Implementation Reference Manual
Dienst: Implementation Reference Manual
Issues in the Development and Operation of a Digital Library
ECDL '99 Proceedings of the Third European Conference on Research and Advanced Technology for Digital Libraries
QoS Based Ranking for Web Search
WI-IAT '08 Proceedings of the 2008 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology - Volume 01
| Hi-index | 0.00 |
In this paper, we investigate issues of performance management in Digital Libraries. We defined a management architecture for measuring and monitoring the behavior of digital libraries as they operate, so that we can make performance conclusions using real life digital library load. Our architecture can be easily applied on any digital library system, introducing minimal overhead to digital library performance, and requiring minimal changes to the digital library code. We implemented this architecture over a testbed of Dienst servers using real data and workload. We defined the relevant parameters for investigating the performance of the servers and we made visualization tools to study the performance results. We also demonstrated how the performance results can be used by the digital library itself, to produce advanced unattended operations, like load balancing and dynamic timeout adaptation.