摘要 |
Admission of new objects into a memory such as a web cache is selectively controlled. If an object is not in the cache, but has been requested a specified number of prior occasions (e.g., if the object has been requested at least once before), it is admitted into the cache regardless of size. If the object has not previously been requested the specified number of times, the object is admitted into the cache if the object satisfies a specified size criterion (e.g., if it is smaller than the average size of objects currently stored in the cache). To make room for new objects, other objects are evicted from the cache on, e.g., a Least Recently Used (LRU) basis. The invention could be implemented on existing web caches, on distributed web caches, in client-side web caching, and in contexts unrelated to web object caching.
|