Managing deduplication in a data storage system using a bloomier filter data dictionary
View Patent ↗A method including maintaining a library having a plurality of storage tablets, each storage tablet storing a plurality of hash-to-storage mappings, each mapping a hash value to a storage location at which a block of data is stored, the block of data translating to the hash value pursuant to a hashing algorithm. The method also including upon receipt and/or determination of a new hash for incoming data pursuant to the hashing algorithm: a) querying a tablet cache for a hash-to-storage mapping having the new hash, the tablet cache comprising a subset of storage tablets copied from the library; and/or b) querying a secondary index for a hash-to-storage tablet mapping having the new hash, the secondary index including a plurality of filters, each filter mapping each of a plurality of key hashes to a storage tablet of the library storing that particular key hash in a hash-to-storage mapping.
1. A method for facilitating data deduplication in a data storage system, the method comprising:
maintaining an electronic data library comprising a plurality of storage tablets, each storage tablet electronically storing a plurality of hash-to-storage mappings, each mapping a hash value to a storage address location in a data storage subsystem at which a block of data is stored, the block of data translating to the hash value pursuant to a hashing algorithm; and
maintaining a secondary index comprising a plurality of filters, each filter electronically mapping each of a plurality of hashes to a storage tablet of the data library storing that particular hash in a hash-to-storage mapping.
2. The method of claim 1 , further comprising maintaining the data library in non-volatile memory.
3. The method of claim 2 , further comprising maintaining the plurality of filters of the secondary index in random access memory (RAM).
4. The method of claim 2 , further comprising maintaining the plurality of storage tablets in the data library as read-only.
5. The method of claim 1 , wherein each of the plurality of filters is a Bloomier filter.
6. An information handling system comprising:
a processor; and
a memory accessible to the processor and storing instructions that, when executed by the processor, cause the processor to:
maintain an electronic data library comprising a plurality of storage tablets, each storage tablet electronically storing a plurality of hash-to-storage mappings, each mapping a hash value to a storage address location in the information handling system at which a block of data is stored, the block of data translating to the hash value pursuant to a hashing algorithm; and
maintain a secondary index comprising a plurality of filters, each filter electronically mapping each of a plurality of hashes to a storage tablet of the data library storing that particular hash in a hash-to-storage mapping.
7. The information handling system of claim 6 , wherein the data library is stored in non-volatile memory.
8. The information handling system of claim 7 , wherein the plurality of filters of the secondary index are stored in random access memory (RAM).
9. The information handling system of claim 8 , wherein the hash-to-storage mappings for each storage tablet are sorted by hash value.
10. The information handling system of claim 8 , wherein the hashing algorithm is a collision-resistant hash function.
11. The information handling system of claim 8 , wherein each of the plurality of filters is a Bloomier filter.
12. The information handling system of claim 11 , wherein the plurality of filters are categorized into layers, with a plurality of filters in each layer.
13. The information handling system of claim 6 , wherein the plurality of filters are categorized into layers, with a plurality of filters in each layer.
14. The information handling system of claim 12 , wherein the layers form a cascade of filter layers with, for each layer above a bottom layer, a filter from that layer is formed from a combination of the filters from a lower layer.
15. The information handling system of claim 7 , wherein the data library is a fixed size, circular log of storage tablets, such that when it is at capacity, the oldest storage tablet is overwritten.
16. The information handling system of claim 6 , wherein one or more of the storage tablets of the data library are write stream specific, storing only hash-to-storage mappings corresponding to blocks of data from the same write stream.
17. The information handling system of claim 8 , further comprising a tablet cache stored in RAM, the tablet cache comprising a subset of storage tablets copied from the data library.
18. The information handling system of claim 17 , wherein the tablet cache comprises a storage tablet copied from the data library that has been most recently accessed for a hash-to-storage mapping.
19. The information handling system of claim 11 , wherein the plurality of hashes mapped by the filters of the secondary index are a pre-defined subset of hashes stored in the storage tablets of the data library.
20. A method for data deduplication in a data storage system, the method comprising:
maintaining an electronic data library comprising a plurality of storage tablets, each storage tablet electronically storing a plurality of hash-to-storage mappings, each mapping a hash value to a storage address location in the data storage system at which a block of data is stored, the block of data translating to the hash value pursuant to a hashing algorithm;
upon at least one of receipt and determination of a new hash for incoming data pursuant to the hashing algorithm, at least one of:
querying a tablet cache for a hash-to-storage mapping comprising the new hash, the tablet cache comprising a subset of storage tablets copied from the data library; and
querying a secondary index for a hash-to-storage tablet mapping comprising the new hash, the secondary index comprising a plurality of filters, each filter electronically mapping each of a plurality of key hashes to a storage tablet of the data library storing that particular key hash in a hash-to-storage mapping.