Optimized Regional Caching for On-Demand Data Delivery

Systems for on-demand delivery of large, widely-shared data can use several techniques to improve cost/performance, including: multicast data delivery, segmented data delivery, and regional (or proxy) servers that cache some of the data close to the clients. This paper makes three contributions to the state-of-the-art design of such systems. First, we show how segmented multicast delivery techniques, in particular the recently proposed high-performance dynamic skyscraper scheme, can be modiied to allow each object to be partially or fully cached at regional servers. The new partitioned delivery architecture supports shared delivery between the regional and remote servers and improves performance even if one server delivers the entire object. The second contribution is an analytic model that can be solved to determine the full/partial object caching strategy that minimizes delivery cost in the context of a system that has homogeneous regional servers. Finally, results in the paper illustrate the use of the model and provide insight into how the optimal caching strategy is innuenced by key system and workload parameters, including client request rate, the relative severity of the disk bandwidth and storage capacity constraints at the regional servers, and the relative costs of regional and remote delivery. Two important conclusions from the results are: (1) it is often cost-eeective to cache the initial segments of many data objects rather than the complete data for fewer objects, and (2) the partitioned delivery architecture and caching partial objects can each greatly reduce delivery cost.