System and method for indexing and retriving cached objects

Abstract

A system and method for indexing and retrieving objects stored in a cache on a persistent medium (e.g., a disk) introduces the concepts of probable hits and asynchronous retrieval of cached objects during a search. Each index entry is a “bucket” for holding corresponding cached objects whose keys are convertible by means of a lossy compression mechanism to an identification (“ID”) of the index entry. When a request for a data object is received, the cached objects in the bucket of the index entry corresponding to the requested object key are checked to see if any of them is the requested object. For a cached object likely to be the requested object, an asynchronous retrieval operation is performed to retrieve that cached object from the persistent medium, and its key is compared with the requested object key. To further reduce the memory space required for implementing the index, a lightweight synchronization scheme is used instead of conventional semaphore objects. This synchronization scheme uses a short access status field (e.g., 2 bytes) that is settable to indicate a locking status of the index entry due to its involvement in read/write operations.

Dependencies are inferred from the claim text.