DATA DEDUPLICATION IN A BLOCK-BASED STORAGE SYSTEM

摘要

A method and system are disclosed for storing client data objects in a deduplicated storage system. Deduplicated data may be stored in a plurality of physical data blocks. A content map layer can provide a mapping between the physical data blocks to logical map objects associated with the client data objects. The deduplicated data may be mapped to logical data blocks that comprise the client data objects.

主权项

1. A method for storing client data objects in a storage system, the method comprising:
storing, by a computer system, deduplicated data that comprise a plurality of client data objects among a plurality of physical data blocks that comprise the storage system; associating, by the computer system, each physical data block with a first mapping object comprising a computed value computed using data stored in said each physical data block, an address of said each physical data block, and a reference count; and associating, by the computer system, each logical data block that comprises a client data object with a respective second mapping object comprising an address of a physical data block that stores the same data that comprises said each logical data block and a pointer to a first mapping object associated with the physical data block, the reference count in each first mapping object indicative of how many other second mapping objects point to said each first mapping object.