Memory Controller Read Count Management for Power-Off Recovery

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing memory systems face reliability issues due to sudden power-offs, which can lead to data distortion and unreliability, especially when read operations exceed a threshold, causing read disturbance and potential data loss during recovery operations.

Innovation Solution

A controller for memory devices that obtains and updates read counts for open blocks, performs a sudden power-off recovery operation, and stores these counts to maintain data reliability by determining whether blocks are open or closed based on threshold values, and manages memory operations to prevent further data damage.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Speed

If read operations are performed on memory blocks, then data access speed is improved, but read disturbance occurs causing data distortion and reliability degradation

Engineering Contradiction:
Improvedata access speedVSAvoiddata reliability
Core Design Contradiction:
SpeedVSReliability

Solution Approach 1:

The patent applies preliminary action by updating read counts before sudden power-off recovery operations. The controller pre-calculates and stores updated read count values that account for potential read disturbance, so when power is restored, the system can immediately use these pre-computed values to make informed decisions about memory block reliability without performing additional read operations that would cause further disturbance.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent implements feedback by continuously tracking read counts for each memory block and using this information to determine block status (open/closed). The system monitors read operations, updates read counts, and uses this feedback to make decisions about data reliability and trigger recovery operations when thresholds are exceeded, creating a closed-loop control system that adapts to actual usage patterns.

Inventive Principle:
Principle #23Feedback

2Reliability

If sudden power-off recovery operation is performed, then data reliability is improved, but read counts may not be accurately reflected causing potential data loss

Engineering Contradiction:
Improvedata reliabilityVSAvoidread count accuracy
Core Design Contradiction:
ReliabilityVSLoss of information

Solution Approach 1:

The patent applies preliminary action by storing updated read count values in the memory device before sudden power-off recovery operations are triggered. These pre-updated read counts are saved to non-volatile storage, ensuring that when power is restored, the system retrieves accurate read count information without needing to re-count or estimate, thus preventing information loss during recovery.

Inventive Principle:
Principle #10Preliminary action

3Reliability

If read count threshold is used to determine block status, then data distortion is prevented, but additional read operations are required to update counts

Engineering Contradiction:
Improvedata integrityVSAvoidoperation efficiency
Core Design Contradiction:
ReliabilityVSProductivity

Solution Approach 1:

The patent merges multiple operations by combining read count updates with the sudden power-off recovery operation itself. Instead of performing separate read operations to update counts and then separately executing recovery operations, the system integrates these functions so that the recovery operation simultaneously updates read counts and determines block status, eliminating redundant operations and improving overall efficiency.

Inventive Principle:
Principle #5Merging (Combining)

Data Source

PatentUS10884669B2Controller, operation method of the controller and memory system
Publication Date: 2021.01.05 SK HYNIX INC
  • US10884669B2 patent drawing
  • US10884669B2 patent drawing
  • US10884669B2 patent drawing

AI summary

A method for operating a controller controlling a memory device, the method includes: obtaining open block information and read counts of open blocks of the memory device; updating each of the read counts by adding a variable value for each open block to each of the read counts; storing the updated read counts in the memory device; and performing a sudden power-off recovery operation on the memory device based on the open block information.