Maintaining multiple cache areas in a storage device having multiple processors includes loading data into a first local cache in response to a first processor of a first subset of the processors performing a read operation to the specific portion of non-volatile storage, where the first local cache is accessible to the first subset of the processors and is inaccessible to other processors, loading data into a second local cache in response to a second processor of the second subset of the processors performing a read operation to the specific portion of non-volatile storage, where the second local cache is accessible to the second subset of the processors and is inaccessible to other processors, and loading data into a global cache in response to one of the processors performing a write operation to the specific portion of non-volatile storage, where the global cache is accessible to all the processors.