An approach to detecting relevant updates to cached data using XML and active databases

Client/server information systems use caching techniques to reduce the volume of transmitted data as well as response time and, especially in the case of systems with mobile clients, to reduce energy consumptions. Updating the server database might cause inconsistencies between server data and cached data. Guaranteeing consistency at least demands to invalidate outdated caches. To avoid invalidation of caches that are not affected by a particular update one must check the relevancy of each update for each cache. It has been proven, that this can only be done on a stateful server.

This paper presents the purely database system (DBS) based DRUpE method for checking the relevance of server side updates to cached data by analyzing the intersection between modified data and cached data. A non-empty intersection means that the update operations are relevant to the cached data. The necessary cache descriptions are stored in form of XML-documents inside the DBS. The paper introduces the used XML-model XReal as well as the relevancy proof-of-concept system Uptime. The main contribution of our work is that the system utilizes the DBS utilities to detect update relevance, notify clients and manage the required repository of the queries issued by the clients. Hence, no additional middleware is required in order to realize consistency aware client/server information systems, even if clients are small footprinted mobile devices.