Granted Patent B2

US 9,858,300 · App. 14/312,724 · Granted Jan 2, 2018

Inventor: Yechiel Yochai (Moshav Aviel, IL)

Assignee: INFINIDAT LTD.

G06F17/30303G06F17/3033

Abstract

Claims (49)

1. A method for de-duplication, the method comprises:

receiving a request to store in a storage system a received data entity;

obtaining a received data entity signature that is responsive to the received data entity;

selecting a selected data structure out of a set of data structures that comprises multiple (K) data structures; wherein for each value of a variable k that ranges between 1 and K, each k'th data structure of the set is associated with a k'th hash function for producing indices for the k'th data structure; wherein for each value of the variable k that ranges between 2 and K, the k'th data structure includes stored data entity signatures that collided with stored data entity signatures that are stored in each one of a first till (k−1)'th data structures of the set when applying any of a first to (k−1)'th hash functions; wherein each data structure of the set comprises multiple entries for storing multiple data entity signatures, and wherein different data structures comprise different number of entries;

calculating an index by applying, on the received data entity signature, a hash function that is associated with the selected data structure; wherein the hash function is different from a hash function that produced the received data entity signature;

determining whether an entry that is associated with the index and belongs to the selected data structure is empty;

if the entry is empty: writing the received data entity signature to the entry; calculating a target address within an address space of the storage system, based at least on a location of the entry in the set, wherein the location of the entry in the set comprises the index and a value of the variable k that represents the selected data structure; and storing the received data entity at the target address; wherein each entry of the set does not store the target address, thereby reducing the size of the set; and

selecting, if (a) the entry is not empty and (b) the received data entity signature differs from a stored data entity signature that is stored in the entry, a new data structure of the set, and repeating at least the stages of calculating and determining.

2. The method according to claim 1 comprising preventing from storing the data entity in the storage system if (a) the entry is not empty and (b) the received data entity signature equals the stored data entity signature that is stored in the entry.

3. The method according to claim 1 wherein K repetition of the selecting of the selected data structure results in scanning the set, starting from a first data structure.

4. The method according to claim 1 wherein each entry of the set only stores a stored data entity signature of a received data entity that is associated with the entry.

5. The method according to claim 1 wherein the target address is a physical address and wherein the method comprising storing the received data entity at the physical address.

6. The method according to claim 1 wherein the target address is a virtual address and wherein the method comprising storing the received data entity at the virtual address.

7. The method according to claim 1 further comprising receiving a request to read a requested data entity that has a requested data entity signature;

selecting a selected data structure out of the set;

calculating an index by applying, on the requested data entity signature, a hash function that is associated with the selected data structure;

determining whether there is a match between (a) a stored data entity signature that is stored in an entry that is associated with the index and belongs to the selected data structure and (b) the requested data entity signature;

providing, if there is a match, a data entity that is associated with the entry;

selecting, if there is no match, a new data structure of the set and repeating at least the stages of calculating and determining.

8. A non-transitory computer readable medium that stores instructions that once executed by a computer causes the computer to perform the stages of:

receiving a request to store in a storage system a received data entity;

applying a certain hash function on the received data entity to provide a data entity signature;

selecting a selected data structure out of a set of data structures that comprises multiple (K) data structures; wherein for each value of a variable k that ranges between 1 and K, each k'th data structure of the set is associated with a k'th hash function for producing indices for the k'th data structure; wherein for each value of the variable k that ranges between 2 and K, the k'th data structure includes stored data entity signatures that collided with stored data entity signatures that are stored in each one of a first till (k−1)'th data structures of the set when applying any of a first to (k−1)'th hash functions; wherein each data structure of the set comprises multiple entries for storing multiple data entity signatures, and wherein different data structures comprise different number of entries;

calculating an index by applying, on the data entity signature, a hash function that is associated with the selected data structure; wherein the hash function is different from a hash function that produced the received data entity signature;

determining whether an entry that is associated with the index and belongs to the selected data structure is empty;

if the entry is empty: writing the received data entity signature to the entry; calculating a target address within an address space of the storage system, based at least on a location of the entry in the set, wherein the location of the entry in the set comprises the index and a value of the variable k that represents the selected data structure; and storing the received data entity in the storage system at the target address; wherein each entry of the set does not store the target address, thereby reducing the size of the set; and

selecting, if (a) the entry is not empty and (b) the received data entity signature differs from a stored data entity signature that is stored in the entry, a new data structure of the set, and repeating at least the stages of calculating and determining.

9. The non-transitory computer readable medium according to claim 8 that stores instructions for preventing from storing the data entity in the storage system if (a) the entry is not empty and (b) the received data entity signature equals the stored data entity signature that is stored in the entry.

10. The non-transitory computer readable medium according to claim 8 wherein K repetition of the selecting of the selected data structure results in scanning the set, starting from a first data structure.

11. The non-transitory computer readable medium according to claim 8 wherein each entry of the set only stores a stored data entity signature of a received data entity that is associated with the entry.

12. The non-transitory computer readable medium according to claim 8 that stores instructions for storing the received data entity at a physical address, wherein the target address is the physical address.

13. The non-transitory computer readable medium according to claim 8 that stores instructions for storing the received data entity at a virtual address, wherein the target address is the virtual address.

14. The non-transitory computer readable medium according to claim 8 that stores instructions for receiving a request to read a requested data entity that has a requested data entity signature;

selecting a selected data structure out of the set;

calculating an index by applying, on the requested data entity signature, a hash function that is associated with the selected data structure;

determining whether there is a match between (a) a stored data entity signature that is stored in an entry that is associated with the index and belongs to the selected data structure and (b) the requested data entity signature;

providing, if there is a match, a data entity that is associated with the entry;

selecting, if there is no match, a new data structure of the set and repeating at least the stages of calculating and determining.

15. A storage system, comprising:

a processor that is arranged to receive a request to store, in the storage system, a received data entity; obtain a received data entity signature that is responsive to the received data entity;

select a selected data structure out of a set of data structures; calculate an index by applying, on the received data entity signature, a hash function that is associated with the selected data structure, wherein the hash function is different from a hash function that produced the received data entity signature; determine whether an entry that is associated with the index and belongs to the selected data structure is empty; if the entry is empty: write, the received data entity signature to the entry, calculate a target address within an address space of the storage system, based at least on a location of the entry in the set, and assist in storing the received data entity at the target address; select, if (a) the entry is not empty and (b) the received data entity signature differs from a stored data entity signature that is stored in the entry, a new data structure of the set, and repeating at least the stages of calculating and determining; and

a memory for storing the set of data structures; wherein the set of data structures comprises multiple (K) data structures; wherein for each value of a variable k that ranges between 1 and K, each k'th data structure of the set is associated with a k'th hash function for producing indices for the k'th data structure; wherein for each value of the variable k that ranges between 2 and K, the k'th data structure includes stored data entity signatures that collided with stored data entity signatures that are stored in each one of a first till (k−1)'th data structures of the set when applying any of a first to (k−1)'th hash functions; wherein each data structure of the set comprises multiple entries for storing multiple data entity signatures, and wherein different data structures comprise different number of entries; wherein each entry of the set does not store the target address, thereby reducing the size of the set;

wherein the location of the entry in the set comprises the index and a value of the variable k that represents the selected data structure.

16. The storage system according to claim 15 wherein the processor is arranged to prevent a storing of the data entity in the storage system if (a) the entry is not empty and (b) the received data entity signature equals the stored data entity signature that is stored in the entry.

17. The storage system according to claim 15 wherein K repetition of the selecting of the selected data structure results in scanning the set, starting from a first data structure.

18. The storage system according to claim 15 wherein each entry of the set only stores a stored data entity signature of a received data entity that is associated with the entry.

19. The storage system according to claim 15 wherein the target address is a physical address and wherein the processor is arranged to store the received data entity at the physical address.

20. The storage system according to claim 15 wherein the target address is a virtual address and wherein the processor is arranged to store the received data entity at the virtual address.

21. The storage system according to claim 15 wherein the processor is further arranged to receive a request to read a requested data entity that has a requested data entity signature; selecting a selected data structure out of the set; calculate an index by applying, on the requested data entity signature, a hash function that is associated with the selected data structure; determine whether there is a match between (a) a stored data entity signature that is stored in an entry that is associated with the index and belongs to the selected data structure and (b) the requested data entity signature; provide, if there is a match, a data entity that is associated with the entry; select, if there is no match, a new data structure of the set and repeating at least the stages of calculating and determining.

Assignments (8)

Continuity (1)