Storage system and method for deduplicating data
AssigneeHitachi, Ltd.
InventorsMisato YOSHIDA, Mitsuo HAYASAKA
Life of this patent
Estimating the term…
Abstract
The present invention provides a storage system capable of performing deduplication among nodes in a cluster configuration with a low overhead. The respective nodes mutually monitor whether there is update of deduplication information in other nodes. When it is determined in its own node that there is update in another node, it reflects the update information in another node to the deduplication information of its own node. Then, each node uses the deduplication information having reflected the deduplication information of other nodes to perform deduplication of the storage data of its own node.
Claims15
A storage system of a cluster configuration for deduplicating and storing a content from a superior device, wherein
- the storage system has two or more nodes with a storage device for storing a content by dividing the same into one or more chunks having a fixed length or a variable length;
- wherein each node includes:
- a deduplication information including a storage information for storing the content in a given area within the storage device and managing the same, for managing a result of execution of the deduplication;
- and
- a deduplication information update log for reflecting the result of deduplication in its own node to a deduplication information in another node;
- when a deduplication information update log not yet reflected to the deduplication information of its own node exists in anther node, updates the not-yet-reflected deduplication information update log to the deduplication information of its own node;
- and
- based on the reflected deduplication information of its own node, performs deduplication by determining whether a duplicated chunk exists in a content to be stored in its own node.
A method for eliminating duplicated data of a storage system having a cluster configuration for deduplicating and storing a content from a superior device, wherein
- the storage system has two or more nodes with a storage device for storing a content by dividing the same into one or more chunks having a fixed length or a variable length;
- wherein each node includes:
- a deduplication information including a storage information for storing the content in a given area within the storage device and managing the same, for managing a result of execution of the deduplication;
- and
- a deduplication information update log for reflecting the result of deduplication in its own node to a deduplication information in another node;
- when a deduplication information update log not yet reflected to the deduplication information of its own node exists in anther node, updates the not-yet-reflected deduplication information update log to the deduplication information of its own node;
- and
- based on the reflected deduplication information of its own node, performs deduplication by determining whether a duplicated chunk exists in a content to be stored in its own node.
Dependencies are inferred from the claim text.