Remote Copy Storage Control Using Summary Information Matching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing remote copy operations in storage systems face inefficiencies due to unnecessary data transfer, as they often copy all allocated blocks, including those not needed for backup, and deal with undeduplicated data, leading to increased data transfer and storage space consumption.
Innovation Solution
A storage control apparatus that transfers summary information, such as hash values, to determine if data units need to be copied, only transferring data units that do not match existing data at the copy-destination storage apparatus, thereby reducing unnecessary data transfer.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If all allocated blocks in the storage pool are subject to copy operation, then the remote copy operation can ensure complete data backup, but the amount of data transfer increases significantly
Solution Approach 1:
The system performs preliminary actions by transferring only summary information (hash values, metadata) of data units to the copy-destination storage apparatus before actual data transfer. This preliminary comparison enables the system to identify which data units need to be copied and which can be skipped, thereby reducing unnecessary data transfer while maintaining backup completeness.
Solution Approach 2:
The invention extracts only the necessary information (summary information, hash values) for comparison purposes from the full data units. By separating the comparison function from the data transfer function, the system can efficiently determine what needs to be copied without transferring unnecessary data, thus resolving the contradiction between backup completeness and data transfer volume.
2Quantity of substance
If deduplicated data is transferred as transfer target, then the amount of data transfer is reduced, but virtual volumes not needed for backup are included in the transfer
Solution Approach 1:
The system applies local quality by allowing selective definition of transfer targets at the virtual volume level. Users can specify which virtual volumes need to be backed up, and the system will only transfer data units belonging to those selected virtual volumes. This enables precise control over the scope of remote copy operations while maintaining the benefits of deduplicated data transfer.
3Ease of operation
If virtual volume is defined as transfer target, then control over data transfer is achieved, but undeduplicated data is handled resulting in large data transfer
Solution Approach 1:
Before actual data transfer, the system performs a preliminary comparison by transferring and comparing summary information (hash values) of data units between the copy-source and copy-destination storage apparatuses. This preliminary action identifies duplicate data units that can be skipped, ensuring that only unique data units are transferred, thereby reducing the amount of data transfer while maintaining user control over transfer targets.
4Reliability
If all allocated blocks are copied, then complete data redundancy is achieved, but storage space in copy-destination storage apparatus is consumed unnecessarily
Solution Approach 1:
The system extracts only the essential comparison information (summary information, hash values) from data units for the purpose of identifying duplicates. By separating the comparison function from full data handling, the system can determine which data units actually need to be copied to the destination, preventing unnecessary consumption of storage space while maintaining adequate data redundancy.
Data Source
AI summary
A storage system is able to perform an operation of remote copy from a first storage apparatus to a second storage apparatus. A first control unit transfers summary information of copy target data stored in the first storage apparatus from the first storage apparatus to the second storage apparatus. A second control unit checks the summary information against information stored in the second storage apparatus. The second control unit transfers the checked result from the second storage apparatus to the first storage apparatus. If the checked result indicates matching discrepancy, the first control unit transfers the copy target data to the second storage apparatus and completes the remote copy operation.


