Storage Controller Data Distribution for SSD Life Balance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing storage devices with SSDs face inefficiencies in data distribution when adding new memory devices, leading to prolonged data redistribution times and increased consumption of remaining life due to write amplification and storage ratio imbalances.
Innovation Solution
A storage device with a control unit that configures parity groups to distribute user data across multiple SSDs, allowing for initial data movement to a new SSD during first-order distribution and subsequent redistribution to balance data volume and reduce redundant data, thereby shortening data distribution times and leveling SSD life consumption.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If data restructuring is performed when a new memory device is added, then data is distributed among existing and new memory devices, but data distribution takes a long time which delays the decrease in consumption rate for remaining life
Solution Approach 1:
The data distribution process is segmented into two distinct phases: first-order distribution that moves existing user data to the new memory device without restructuring, and second-order distribution that performs restructuring to optimize data layout. This segmentation allows the system to achieve rapid initial data distribution while deferring time-consuming restructuring operations, thereby resolving the contradiction between data distribution completeness and distribution time.
Solution Approach 2:
The patent performs preliminary data movement (first-order distribution) before performing data restructuring (second-order distribution). By moving data to the new memory device first and restructuring later, the system achieves rapid data distribution to decrease the consumption rate for remaining life, while still ensuring eventual data optimization through deferred restructuring operations.
2Quantity of substance
If storage ratio for data increases, then more data can be stored, but efficiency of garbage collection decreases and write amplification occurs increasing consumption rate for remaining life
Solution Approach 1:
The patent implements dynamic data distribution that adapts to changing storage conditions. When new memory devices are added, the system dynamically redistributes data to maintain optimal storage ratios across all devices. This dynamic adjustment prevents storage ratio imbalances that would otherwise degrade garbage collection efficiency and increase write amplification, allowing the system to maintain high productivity even as storage capacity increases.
Solution Approach 2:
The system changes the distribution parameters of data across memory devices based on the addition of new devices. By adjusting how data is distributed and maintaining optimal storage ratios, the system prevents write amplification and maintains efficient garbage collection while utilizing increased storage capacity.
3Reliability
If data is redistributed among existing and new memory devices, then storage ratio balance is improved, but data distribution time increases delaying the decrease in consumption rate
Solution Approach 1:
The patent segments the data distribution process into two phases: first-order distribution that rapidly moves data to balance storage ratios without restructuring, and second-order distribution that performs optimization restructuring. This segmentation allows the system to achieve storage ratio balance quickly through the first phase, thereby decreasing the consumption rate for remaining life, while the second phase subsequently refines the data layout without compromising the already-improved balance.
Data Source
AI summary
To provide a storage device by which distribution of data to an added memory device may be carried out in a short period of time.In a case where any new SSD is added to the storage device, a storage controller carries out first data distribution processing moving any piece of user data in a parity group from existing SSDs to the added SSD and second data distribution processing increasing the number of pieces of the user data configuring the parity group from a first number to a second number after the first data distribution processing and storing the user data in a plurality of memory devices SSDs.