Memory Controller Compresses Management Data to Lower Write Amplification

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

The existing memory systems, such as Solid State Drives (SSDs) with NAND flash memory, face a high write amplification factor (WAF) that accelerates the wear of NAND memory, as they write more data than the actual user data received from the host, leading to progressive memory wear.

Innovation Solution

A memory system comprising a nonvolatile NAND flash memory and a volatile RAM, where management information is compressed and stored in the NAND memory, reducing the amount of data written and thereby lowering the write amplification factor through efficient data management and compression techniques.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If management information is stored in uncompressed form in NAND memory, then data access and management operations can proceed normally, but the write amplification factor increases and memory wear accelerates

Engineering Contradiction:

Improvememory lifespanVSAvoidwrite amplification factor

Core Design Contradiction:

ReliabilityVSProductivity

Solution Approach 1:

The management information is divided into multiple tables (translation tables, mapping tables, etc.) that are stored separately in NAND memory. This segmentation allows selective compression and differential updating of individual tables, reducing the total amount of data written while maintaining access efficiency.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

Multiple levels of translation tables are implemented where upper-level tables map to lower-level tables, creating a hierarchical nested structure. This allows the system to manage large address spaces efficiently while minimizing the amount of data that needs to be written and updated in NAND memory.

Inventive Principle:

Principle #7Nested doll (Nesting)

2Productivity

If compression is applied to management information, then the amount of data written to NAND memory is reduced, but the device complexity increases due to compression and decompression operations

Engineering Contradiction:

Improvewrite amplification factorVSAvoidcompression processing complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The system dynamically adjusts compression parameters and algorithms based on the type of management information and current system state. Different compression ratios and methods are applied to different tables, optimizing the balance between write reduction and processing complexity.

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The memory controller automatically performs compression and decompression operations without requiring external intervention. The system monitors its own state and adjusts compression strategies accordingly, reducing the need for complex external control mechanisms.

Inventive Principle:

Principle #25Self-service

Data Source

PatentUS11609844B2Memory system with hierarchical tables

Publication Date: 2023.03.21 KIOXIA CORP

AI summary

A memory system includes a first memory that is nonvolatile, a second memory that is volatile, and a memory controller. The memory controller is configured to store first information in the second memory. The first information includes management information. The memory controller is further configured to compress the first information. The compressed first information is second information. The memory controller is configured to store the second information in the first memory.