Unified Data Path Architecture for Active-Active Storage Access
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current data storage systems face challenges in managing block-based and file-based access efficiently, leading to stranded storage and increased complexity in design and maintenance, as they lack a unified approach to handle both types of data access protocols effectively.
Innovation Solution
A unified data path architecture that combines block-based and file-based functionality, enabling a common set of functions to be applied to both types of objects, and allows for the reallocation of storage units between block-based and file-based objects, thereby reducing stranded storage and enhancing storage utilization.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If separate programming and hardware structures are used for block-based and file-based access, then each access type can be handled independently, but the system design complexity increases and maintenance becomes more difficult
Solution Approach 1:
The patent combines separate block-based and file-based access structures into a unified data path architecture. The common data path allows both access types to share the same hardware and software resources, eliminating the need for separate programming and hardware structures while maintaining independent handling capabilities for each access type.
Solution Approach 2:
The unified data path architecture creates a universal structure that can handle both block-based and file-based access through a single common pathway. This multi-functional design allows the same hardware and software components to serve multiple access protocols, reducing overall system complexity while preserving adaptability.
2Reliability
If storage units are allocated to specific access types, then dedicated resources improve performance, but stranded storage occurs when reallocation is needed
Solution Approach 1:
The patent implements dynamic storage allocation through the unified data path architecture. Storage units can be dynamically reassigned between block-based and file-based access types as needs change, eliminating stranded storage while maintaining dedicated resource allocation for optimal performance. The common data path enables flexible resource sharing without compromising access performance.
3Reliability
If data storage systems operate in active-standby mode, then data safety is maintained, but access latency increases and productivity decreases
Solution Approach 1:
The patent uses the unified data path as an intermediary structure that enables active-active operation between geographically dispersed data storage systems. The common data path architecture allows both systems to simultaneously serve as active units while maintaining data safety through coordinated access, eliminating the need for active-standby mode and thereby improving productivity without compromising reliability.
Data Source
AI summary
There is disclosed a method for use in managing data storage. In one embodiment, the method comprises operating storage processors of respective data storage systems at different location. The storage processors comprising a distributed data manager and an IO stack arranged within the storage processor such that the distributed data manager can receive a LUN outputted by the IO stack. The method further comprises distributed data managers receiving LUNs outputted by their corresponding IO stacks, controlling LUN output and providing LUN output that enables active-active access to the storage systems at the respective different locations.