Remote Data Replication Metadata Extraction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing remote data replication systems face high bandwidth overheads due to the need to replicate data blocks and their corresponding metadata between production and disaster recovery arrays, which increases the load on redundancy links.
Innovation Solution
A remote data replication method where the production array sends a data replication request with an identifier and data block to the disaster recovery array, allowing the array to create a target object with a different physical address, reducing the need to replicate metadata and thus saving bandwidth by allowing flexible storage and layout of data blocks without requiring identical identifiers or metadata.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If data blocks and their corresponding metadata are replicated between production and disaster recovery arrays, then data redundancy is achieved, but bandwidth overhead increases and load on redundancy links increases
Solution Approach 1:
The patent extracts metadata from the replication process and handles it locally at the disaster recovery array. Instead of replicating both data blocks and metadata over the redundancy link, only data blocks are transmitted. The disaster recovery array independently creates the metadata (including physical address mappings) locally, thereby removing the metadata replication burden from the bandwidth-constrained link while maintaining complete data redundancy.
2Reliability
If data blocks and their corresponding metadata are replicated between production and disaster recovery arrays, then data redundancy is achieved, but load on redundancy links increases
Solution Approach 1:
The patent extracts metadata from the replication process and handles it locally at the disaster recovery array. Instead of replicating both data blocks and metadata over the redundancy link, only data blocks are transmitted. The disaster recovery array independently creates the metadata (including physical address mappings) locally, thereby removing the metadata replication burden from the bandwidth-constrained link while maintaining complete data redundancy.
3Loss of information
If physical addresses of data blocks are replicated from production array to disaster recovery array, then data location information is preserved, but flexibility in storage layout is reduced
Solution Approach 1:
The patent inverts the traditional approach: instead of the production array telling the disaster recovery array where to store data blocks (by replicating physical addresses), the disaster recovery array independently determines its own storage layout and creates its own physical address mappings. This inversion grants the disaster recovery array full flexibility to optimize storage locally while still achieving complete data redundancy, as the inverted control mechanism preserves all necessary data location information locally at the disaster recovery array.
Data Source
AI summary
A remote data replication method and a storage system, where a production array sends a data replication request to a disaster recovery array. The data replication request includes an identifier of a source object and a data block corresponding to the source object. The data block is stored in physical space of a hard disk of the production array. The disaster recovery array receives the data replication request. The disaster recovery array creates a target object when the disaster recovery array does not include an object having a same identifier as the source object. An identifier of the target object is the same as the identifier of the source object, the disaster recovery array writes the data block into the physical space.