Shared data management needs adaptive methods

Object-based client caching allows clients to keep more frequently accessed objects while discarding colder objects that reside on the same page. However, when these objects are modified and sent to the server, it may need to read the corresponding page from disk to install the update. These `installation reads´ are not required with a page-based cache because whole pages are sent to the server. The relative effectiveness of the two cache techniques depends crucially on the application workload and on the object layout on pages. In a large system, when many applications share data objects, customizing cache management to either an object-based or a page-based configuration may not be optimal to any of the applications. We describe a hybrid system that permits clients to cache objects and pages. The system uses a simple cache design that combines the best of object caching and page caching. The client increases its cache hit ratio as in object-based caching. The client avoids some installation reads by sending pages to the server when possible. Using simulated workloads, we explore the performance of our design and show that it can offer a significant performance improvement over both pure object caching and pure page caching on a range of workloads