SSD Die Partitioning by Spare Blocks for Wear-Balanced Workloads

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing SSDs face inefficiencies due to varying numbers of available good blocks across NAND flash dies, leading to uneven wear and potential failure, which can be exacerbated by differing workload intensities without tailored block management.

Innovation Solution

Partition SSD dies into sets based on spare block availability and workload expectations, assigning write-intensive workloads to dies with more spare blocks and read-intensive workloads to those with fewer, applying customized garbage collection policies to extend drive lifespan.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Device complexity

If spare blocks are uniformly distributed across all dies, then management simplicity is improved, but wear unevenness increases leading to reduced reliability

Engineering Contradiction:
Improveblock management complexityVSAvoiddrive reliability
Core Design Contradiction:
Device complexityVSReliability

Solution Approach 1:

The patent applies local quality by creating distinct spare block pools for different die types (high-endurance dies with more spare blocks, low-endurance dies with fewer spare blocks). Each pool is tailored to the specific characteristics of its target dies, allowing customized wear management strategies rather than a uniform approach across all dies.

Inventive Principle:
Principle #3Local quality

Solution Approach 2:

The patent segments the spare block management system into multiple pools based on die endurance characteristics. By dividing the spare blocks into separate pools associated with specific die types, the system can independently manage wear for each pool, preventing wear unevenness that would occur with a unified spare block pool.

Inventive Principle:
Principle #1Segmentation

2Device complexity

If all dies handle all workloads equally, then workload distribution simplicity is improved, but wear unevenness increases reducing productivity

Engineering Contradiction:
Improveworkload distribution complexityVSAvoideffective storage capacity utilization
Core Design Contradiction:
Device complexityVSProductivity

Solution Approach 1:

The patent assigns different workload types to different die pools based on their endurance characteristics. High-endurance dies are assigned write-intensive workloads while low-endurance dies handle read-intensive or mixed workloads. This localized workload assignment optimizes the effective utilization of storage capacity by matching workload demands to die capabilities.

Inventive Principle:
Principle #3Local quality

3Ease of manufacture

If spare blocks are not tailored to die variations, then manufacturing simplicity is improved, but drive lifespan decreases due to wear unevenness

Engineering Contradiction:
Improvespare block allocation simplicityVSAvoidSSD lifespan
Core Design Contradiction:
Ease of manufactureVSDuration of action of stationary object

Solution Approach 1:

The patent performs preliminary classification of dies into different endurance pools during the manufacturing or initialization phase. By pre-identifying high-endurance and low-endurance dies and assigning them to appropriate pools with tailored spare block allocations, the system proactively prevents wear unevenness before it occurs, extending overall SSD lifespan without complex runtime adjustments.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentEP4070199B1Adaptive spare block usage in solid state drives
Publication Date: 2026.01.28 MICROSOFT TECHNOLOGY LICENSING LLC
  • EP4070199B1 patent drawingFigure 1
  • EP4070199B1 patent drawingFigure 2
  • EP4070199B1 patent drawingFigure 3

AI summary

In non-limiting examples of the present disclosure, systems, methods and devices for partitioning dies based on spare blocks and workload expectations are provided. Data from non-volatile storage media may be received. The data may comprise information identifying each of a plurality of dies included in the non-volatile storage media and a number of blocks included in each of the plurality of dies. A number of spare blocks included in each of the plurality of dies may be determined. First and second sets of the plurality of dies may be identified, wherein the first set has a higher number of spare blocks than the second set. A first workload may be assigned to the first set of dies, the first workload being classified as write-intensive. A second workload may be assigned to the second set of dies, the second workload being classified as read-intensive.