Storage Device Read Reclaim Controller Wear Management
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current storage devices face inefficiencies in managing read operations, particularly in nonvolatile memory systems, where data retention and access speeds are compromised due to uneven wear and tear across memory blocks, leading to potential data loss from threshold voltage changes.
Innovation Solution
A storage device and method that utilize a memory controller with a read reclaim operation, which tracks read counts and migration levels across memory blocks, migrating data from heavily accessed blocks to other super blocks, selecting victim blocks with the highest migration levels from different memory dies to maintain data integrity and prevent loss.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If read operations are concentrated on specific memory blocks, then access speed is improved, but data retention deteriorates due to threshold voltage changes
Solution Approach 1:
The memory system is divided into multiple memory dies, each containing multiple memory blocks. The controller manages these segments independently, allowing read operations to be distributed across different segments (super blocks spanning multiple dies) rather than concentrating all reads on single blocks, thus maintaining access speed while reducing wear on any single segment
Solution Approach 2:
Different migration levels are assigned to different memory blocks based on their read count characteristics. Blocks with higher read counts receive higher migration levels, causing them to be selected as victim blocks more frequently for data migration. This local differentiation allows the system to adaptively manage wear across different regions, maintaining data retention while supporting high-speed access to frequently read data
2Reliability
If data migration is performed frequently, then data retention is improved, but device complexity increases
Solution Approach 1:
The system performs preliminary actions by proactively migrating data from blocks approaching high read count thresholds before actual data loss occurs. The controller monitors read counts and migration levels continuously, and triggers data migration operations in advance when blocks approach wear thresholds, preventing threshold voltage shifts that would compromise data retention
Solution Approach 2:
The memory system performs self-service through automatic data migration triggered by read count monitoring. When a memory block's read count exceeds a threshold, the system automatically identifies victim blocks, migrates their data to new locations, and updates mapping information without external intervention. This self-managing mechanism reduces the need for complex external control while maintaining data integrity
3Speed
If victim blocks are selected from the same memory die, then migration speed is improved, but data retention deteriorates due to uneven wear distribution
Solution Approach 1:
The system intentionally creates asymmetric wear distribution patterns by selecting victim blocks from different memory dies rather than uniformly distributing migrations. When a target block in one die needs data migration, the controller may select victim blocks from other dies, creating deliberate asymmetry in wear patterns. This asymmetric approach ensures that no single die becomes过度 worn while maintaining acceptable migration speeds
Data Source
AI summary
The present disclosure relates to an electronic device. A memory controller controlling a memory package including a plurality of memory dies each including a plurality of memory blocks, the plurality of memory blocks controlled in units of super blocks each including at least one memory block selected from each of the plurality of memory dies includes a reclaim information storage storing reclaim information including read counts and migration level information related to the read counts, and a read reclaim controller migrating data stored in a target block having a read count exceeding a threshold count, and victim blocks selected according to the reclaim information to another super block different from a super block to which the target block belongs, wherein the victim blocks include memory blocks whose migration level information is the highest among memory blocks included in memory dies different from a memory die including the target block.