Memory Controller Defect Recovery via Data Migration

Solution Overview

Problem

Existing memory systems face challenges in maintaining availability when a defective memory device occurs, as the entire system is suspended to recover the defective device, potentially leading to data loss and system downtime.

Innovation Solution

A memory system with a controller that includes a detection circuit to identify defective devices, a selection circuit to choose available memory devices, and a processor to move target data from the defective device to an over-provisioning area of an available device, allowing for recovery while maintaining system availability.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If the entire system is suspended to recover a defective memory device, then the defective device can be recovered, but system availability decreases and data loss may occur

Engineering Contradiction:

Improvedefective device recoveryVSAvoidsystem downtime

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The memory system is segmented into multiple independent memory devices, each with its own user area and over-provisioning area. When a defect is detected in one device, only that specific device needs recovery, not the entire system. The controller can independently manage recovery operations for individual devices while others continue operating normally.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

Over-provisioning areas are pre-allocated in each memory device before defects occur. These reserved areas serve as ready-to-use storage destinations for migrating data from defective devices, eliminating the need to suspend system operations or search for available space during recovery operations.

Inventive Principle:

Principle #10Preliminary action

2Reliability

If the entire system is suspended to recover a defective memory device, then the defective device can be recovered, but system availability decreases

Engineering Contradiction:

Improvedefective device recoveryVSAvoidsystem availability

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The memory system is segmented into multiple independent memory devices, each with its own user area and over-provisioning area. When a defect is detected in one device, only that specific device needs recovery, not the entire system. The controller can independently manage recovery operations for individual devices while others continue operating normally.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

Over-provisioning areas are pre-allocated in each memory device before defects occur. These reserved areas serve as ready-to-use storage destinations for migrating data from defective devices, eliminating the need to suspend system operations or search for available space during recovery operations.

Inventive Principle:

Principle #10Preliminary action

3Loss of information

If data is moved to an over-provisioning area, then data integrity is maintained during recovery, but the over-provisioning area capacity is consumed

Engineering Contradiction:

Improvedata integrityVSAvoidover-provisioning area capacity

Core Design Contradiction:

Loss of informationVSQuantity of substance

Solution Approach 1:

Over-provisioning areas are pre-allocated in each memory device before defects occur. These reserved areas serve as ready-to-use storage destinations for migrating data from defective devices, eliminating the need to suspend system operations or search for available space during recovery operations.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The over-provisioning areas are designed to be reusable. After data migration from a defective device, the over-provisioning area can be cleared and reused for future recovery operations or normal system operation, maximizing the utilization of this reserved capacity.

Inventive Principle:

Principle #34Discarding and recovering

Data Source

PatentUS11036399B2Memory system and operating method of the memory system

Publication Date: 2021.06.15 SK HYNIX INC

AI summary

A memory system may include: a plurality of memory devices each including a user area and an over-provisioning area (OP area); and a controller configured for controlling the plurality of memory devices, wherein the controller includes: a detection circuit configured for detecting a defective memory device among the plurality of memory devices; a selection circuit configured for selecting an available memory device excluding the defective memory device among the plurality of memory devices; and a processor configured for moving target data stored in the defective memory device into the OP area of the available memory device.