Storage Controller Patrol Read Prioritization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing storage devices, such as flash memory systems, face challenges in maintaining reliability due to performance degradation over time, particularly in identifying and addressing memory cell blocks with poor reliability for effective patrol read operations.
Innovation Solution
A controller for storage devices that prioritizes patrol read operations based on reliability information, such as retention time and program-erase count, to efficiently identify and reclaim memory cell blocks with low reliability, thereby preventing performance degradation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If patrol read operations are performed on all memory cell blocks, then reliability detection coverage is improved, but operation time and system overhead increase
Solution Approach 1:
The patent segments memory cell blocks into different priority groups based on reliability information (retention time and program-erase count). Instead of uniformly processing all blocks, the system divides them into high-priority blocks (long retention time, high P-E count) and low-priority blocks, applying patrol read operations selectively to high-priority segments first.
Solution Approach 2:
The patent applies different patrol read strategies to different memory cell blocks based on their local characteristics. High-priority blocks undergo patrol read operations while low-priority blocks are temporarily excluded, allowing the system to focus resources on blocks most likely to exhibit reliability issues.
2Reliability
If patrol read operations are performed frequently, then reliability monitoring is improved, but productivity and effective storage capacity are reduced
Solution Approach 1:
The patent dynamically adjusts the patrol read schedule based on current system conditions and reliability priorities. The patrol read operation is performed on high-priority blocks when system resources are available, while low-priority blocks are excluded during periods when productivity is critical, creating a flexible, adaptive monitoring system.
Solution Approach 2:
The patent performs patrol read operations on only a subset of memory cell blocks (high-priority blocks) rather than all blocks, achieving sufficient reliability monitoring with reduced overhead. This partial action approach maintains adequate monitoring coverage while preserving productivity.
3Reliability
If memory cell blocks with long retention time and high program-erase count are prioritized for patrol read, then reliability of critical blocks is improved, but complexity of block management increases
Solution Approach 1:
The patent implements a self-service mechanism where memory cell blocks automatically accumulate reliability information (retention time and program-erase count) during normal operation. This information is maintained in metadata structures that enable automatic priority determination without requiring complex external management intervention.
Solution Approach 2:
The patent uses changes in reliability parameters (retention time increasing, program-erase count increasing) to automatically determine patrol read priority. As blocks age and undergo more operations, their parameters naturally evolve, triggering priority adjustments without requiring complex management logic.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A method of operating a controller for controlling a memory device that comprises a plurality of memory cell blocks including outputting block address information based on reliability information for each of the memory cell blocks, providing a patrol read command to the memory device, and controlling the memory device to perform the patrol read operation in response to the patrol read command wherein the block address information comprises an order of the patrol read operation for the memory cell blocks based on the reliability information may be provided.