Data Buffering Storage Device Read Threshold Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Non-volatile memory experiences read disturbance and reduced service life due to frequent data reading, which affects data storage integrity and longevity.
Innovation Solution
A data management method that directs frequently read data into a second storage space within a data buffering storage device, while less frequently read data is stored in a first storage space, optimizing data storage and reducing the number of reads on the non-volatile memory.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If data is frequently read from non-volatile memory, then data reading efficiency is improved, but the service life of non-volatile memory deteriorates due to read disturbance
Solution Approach 1:
The patent segments the data buffering storage device into two distinct storage spaces: a first storage space for storing pages with read count ≤ threshold, and a second storage space for storing pages with read count > threshold. This segmentation allows frequently accessed pages to be isolated and retained in the second storage space, preventing them from being evicted back to non-volatile memory, thereby reducing read disturbance while maintaining reading efficiency.
Solution Approach 2:
The patent performs preliminary action by pre-storing frequently accessed pages (those exceeding the read threshold) in the second storage space of the data buffering storage device before they would otherwise be written back to non-volatile memory. This proactive retention strategy ensures that subsequent read operations can be served from the buffer, preventing additional read disturbance to the non-volatile memory.
2Device complexity
If data is stored in a single storage space, then device complexity is reduced, but data reading efficiency deteriorates due to frequent replacements
Solution Approach 1:
The patent divides the data buffering storage device into two storage spaces with different functions: the first storage space handles pages with lower read frequency, while the second storage space is dedicated to frequently accessed pages. This segmentation prevents frequent replacement of hot data and improves reading efficiency, while the overall structure remains relatively simple and manageable.
Solution Approach 2:
The patent applies local quality by giving different storage spaces different characteristics and purposes. The second storage space is specifically optimized for retaining frequently accessed data, while the first storage space handles less frequently accessed data. This localized optimization improves overall system performance without requiring complete redesign of the storage architecture.
Data Source
AI summary
A data management method includes steps of: receiving a read command; reading a page containing target data from a non-volatile memory when the target data corresponding to the read command is stored in the non-volatile memory; determining whether a count of reading of the page is greater than a read threshold; and if false, storing at least one record of subsequent data into a first storage space of a data buffering storage device; or if true, storing the at least one record of subsequent data into a second storage space of the data buffering storage device. Both of the target data and the at least one record of subsequent data are stored in the page, and the target data and the at least one record of subsequent data have a sequential relationship in terms of data reading. Another data management method and a corresponding data storage device are also provided.