Storage Over-Provisioning Pools for Lower Write Amplification

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing storage devices face challenges in managing write amplification and data placement efficiency, leading to reduced performance and durability due to inefficient garbage collection and over-provisioning strategies.

Innovation Solution

Implementing a flexible data placement scheme that utilizes distinct over-provisioning pools and reclaim unit handles to manage storage operations, allowing for intelligent data placement and reduction of write amplification by selecting optimal storage units based on device conditions and host indications.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Device complexity

If a single over-provisioning pool is used for multiple reclaim unit handles, then device complexity is reduced and management is simplified, but write amplification increases and performance deteriorates due to inefficient garbage collection

Engineering Contradiction:
Improveover-provisioning pool managementVSAvoidwrite amplification
Core Design Contradiction:
Device complexityVSProductivity

Solution Approach 1:

The patent divides the over-provisioning pool into multiple distinct pools, with each pool dedicated to a specific reclaim unit handle. This segmentation allows independent management of OP resources for different RUs, enabling more efficient garbage collection operations and reducing write amplification by preventing interference between different RU operations.

Inventive Principle:
Principle #1Segmentation

2Adaptability or versatility

If data is updated by erasing and re-writing in NVM blocks, then data storage flexibility is improved, but performance deteriorates due to the need to copy valid data to different blocks

Engineering Contradiction:
Improvedata storage flexibilityVSAvoiddata update performance
Core Design Contradiction:
Adaptability or versatilityVSProductivity

Solution Approach 1:

The patent performs preliminary actions by maintaining multiple ready-to-use erased blocks within over-provisioning pools. When a block needs to be erased for data updates, pre-erased blocks are immediately available from the OP pools, eliminating the need to copy valid data during the erase process and reducing the performance impact of updates.

Inventive Principle:
Principle #10Preliminary action

3Quantity of substance

If garbage collection is performed to reclaim storage units, then storage capacity is restored and extended, but write amplification increases due to additional write operations

Engineering Contradiction:
Improvestorage capacityVSAvoidwrite amplification
Core Design Contradiction:
Quantity of substanceVSLoss of energy

Solution Approach 1:

The patent implements efficient discarding and recovering by using distinct over-provisioning pools that are pre-filled with erased blocks. When garbage collection is needed, valid data is moved to new blocks from the OP pools, and the old blocks are discarded and recovered as erased blocks in the OP pools, minimizing additional write operations and reducing write amplification.

Inventive Principle:
Principle #34Discarding and recovering

Data Source

PatentUS20260072831A1Systems, methods, and apparatus for over-provisioning allocation and garbage collection triggering in a storage device
Publication Date: 2026.03.12 SAMSUNG ELECTRONICS CO LTD
  • US20260072831A1 patent drawing
  • US20260072831A1 patent drawing
  • US20260072831A1 patent drawing

AI summary

An apparatus and method of a storage device including a storage medium are provided. An apparatus may include a storage device comprising a storage medium, and a controller configured to provide a first over-provisioning (OP) pool of storage units of the storage medium for use by a first reclaim unit handle (RUH); provide a second OP pool of storage units of the storage medium for use by a second RUH, wherein the first OP pool and the second OP pool are distinct from each other; perform a first storage operation associated with the first RUH using the first OP pool; and perform a second storage operation associated with the second RUH using the second OP pool.