Storage System Routing Circuits Parallel Data Write
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional storage systems experience processing delays when updating data during backup operations, as new data cannot be written to the main storage region until updated data are overwritten, leading to inefficiencies in data management.
Innovation Solution
A storage system with multiple routing circuits and node modules that allow simultaneous writing of data to both a first and second storage region, enabling parallel data processing and reducing processing delays by writing new data into both regions concurrently.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If updated data are written to a separate storage region and overwritten into the main storage region after backup completion, then data consistency during backup is improved, but processing speed deteriorates due to sequential operations
Solution Approach 1:
The storage system divides the storage region into multiple independent segments (first storage region and second storage region). During backup operations, data can be written to one region while simultaneously being read from another region, enabling parallel operations that maintain data consistency while improving processing speed.
Solution Approach 2:
The patent introduces a temporal dimension to the storage architecture by implementing multiple storage regions that can operate independently in parallel. This allows the system to perform backup and update operations simultaneously in different regions, transforming sequential operations into parallel ones and resolving the contradiction between consistency and speed.
2Reliability
If new data writing is blocked during main storage region updates, then data integrity is maintained, but system responsiveness deteriorates
Solution Approach 1:
By segmenting the storage system into multiple independent regions, the patent allows new data to be written to regions that are not currently undergoing update operations. This maintains data integrity in active regions while preserving system responsiveness through parallel writing capabilities.
Solution Approach 2:
The patent introduces intermediate storage regions that act as buffers between the main storage region and the external system. These intermediary regions allow new data to be written without interfering with ongoing update operations in the main region, thus maintaining both integrity and responsiveness.
3Device complexity
If a single storage region is used for both backup and updates, then device complexity is reduced, but processing parallelism deteriorates
Solution Approach 1:
The patent divides the storage system into multiple segments (first and second storage regions) that can operate independently. This segmentation enables parallel processing of backup and update operations simultaneously, improving productivity while maintaining manageable complexity through a systematic multi-region architecture.
Solution Approach 2:
The patent transitions from a single-dimension storage architecture to a multi-dimensional architecture with multiple independent storage regions. This dimensional expansion allows parallel operations to occur simultaneously in different regions, achieving processing parallelism without excessive complexity.
Data Source
AI summary
A storage system includes a storage unit having a plurality of routing circuits electrically networked with each other, each of the routing circuits being locally connected to a plurality of node modules, each of which includes nonvolatile memory, the plurality of node modules forming at least first and second storage regions, and a plurality of connection units, each connected to one or more of the routing circuits, and access the first and second storage regions through one or more of the routing circuits in accordance with a command. When one of the connection units receives a command to write second data into the first storage region while first data are being read out from the first storage region, said one of the connection units writes the second data into both the first and second storage regions.