Unit Zone Region Mapping for ZNS Storage Lifetime Extension

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Non-volatile memory devices experience decreased lifetime due to frequent garbage collection caused by random access storage methods, which do not support sequential write operations efficiently.

Innovation Solution

The implementation of unit zone regions within a storage device, each with a defined size, supports sequential write operations compliant with the zoned namespace (ZNS) standard, and manages these regions using a zone metadata table to optimize data allocation and reduce resource consumption.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If random access storage method is used in non-volatile memory devices, then data can be stored and accessed flexibly, but frequent garbage collection occurs causing decreased device lifetime

Engineering Contradiction:
Improvedata access flexibilityVSAvoiddevice lifetime
Core Design Contradiction:
Adaptability or versatilityVSReliability

Solution Approach 1:

The storage device divides the namespace into multiple zones with different access patterns (sequential write zones and random read zones). This segmentation allows the device to separate write operations into sequential zones that support ZNS standard, reducing garbage collection frequency and extending device lifetime, while maintaining random read capability in dedicated zones.

Inventive Principle:
Principle #1Segmentation

2Speed

If sequential write operations are not supported efficiently, then random access can be maintained, but garbage collection frequency increases reducing storage device lifetime

Engineering Contradiction:
Improvesequential write efficiencyVSAvoiddevice lifetime
Core Design Contradiction:
SpeedVSReliability

Solution Approach 1:

The storage device dynamically manages zone states and transitions between different operational modes. Zones can be opened for sequential writes, closed for consolidation, or reset when full. This dynamic zone management enables efficient sequential write operations while automatically consolidating data to extend device lifetime by reducing unnecessary garbage collection operations.

Inventive Principle:
Principle #15Dynamics

3Use of energy by moving object

If zone metadata table is not used, then resource consumption may be lower, but dynamic adjustments to namespace sizes and configurations become difficult

Engineering Contradiction:
Improveresource consumptionVSAvoidnamespace configuration flexibility
Core Design Contradiction:
Use of energy by moving objectVSAdaptability or versatility

Solution Approach 1:

The zone metadata table pre-allocates and tracks zone configurations, mapping relationships between logical block addresses and physical zones, and zone state information. This preliminary organization enables rapid dynamic adjustments to namespace sizes and configurations without extensive reallocation operations, balancing resource consumption with configuration flexibility.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentEP4459472B1Storage device allocating unit zone regions, and method of operating the same
Publication Date: 2026.02.04 SAMSUNG ELECTRONICS CO LTD
  • EP4459472B1 patent drawingFigure 1
  • EP4459472B1 patent drawingFigure 2
  • EP4459472B1 patent drawingFigure 3

AI summary

A method of operating a storage device which communicates with a host device includes allocating a plurality of unit zone regions each having a unit zone size, wherein each of the plurality of unit zone regions is mapped to at least one corresponding memory block among a plurality of memory blocks in the storage device and wherein each unit zone region of the plurality of unit zone regions supports a sequential write in compliance with a zoned namespace (ZNS) standard, receiving a first request indicating an allocation operation of a first zoned namespace in compliance with the ZNS standard from the host device, determining a first mapping ratio by dividing a first zone size of the first zoned namespace by the unit zone size, based on the first request, and storing the first mapping ratio in a zone metadata table of the storage device.