Full Allocation Volume Migration to Deduplication via Virtual Address Range

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current storage systems face inefficiencies in migrating fully allocated volumes to deduplicated volumes, requiring multiple data copies or reading and writing data to new locations, which increases computational requirements and conflicts with underlying data.

Innovation Solution

A method and system that move physical allocations of stored data into a virtual address range in a deduplication domain, using spare computational power within the drive layer for deduplication hash calculations, allowing for low computational requirements and avoiding data movement or re-write operations, by setting up deduplication metadata as a passthrough and performing background deduplication processes.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If multiple copies of data are made during migration, then data can be moved from fully allocated volume to deduplicated volume, but computational requirements increase and storage capacity is consumed

Engineering Contradiction:
Improvemigration efficiencyVSAvoidcomputational requirements
Core Design Contradiction:
ProductivityVSUse of energy by moving object

Solution Approach 1:

The patent extracts the hash calculation function from the main storage controller and places it directly on the drive layer. This allows deduplication operations to be performed using the drive's existing computational resources without burdening the storage controller, thereby reducing overall computational requirements while maintaining migration productivity

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The drive layer performs hash calculations and deduplication operations on its own data without requiring external computational assistance. By utilizing spare computational power within the drive itself, the system achieves self-service capability that reduces the computational burden on the storage controller and eliminates the need for multiple data copies

Inventive Principle:
Principle #25Self-service

2Adaptability or versatility

If data is read and written to new locations during migration, then fully allocated volumes can be converted to deduplicated volumes, but computational requirements increase and conflicts with underlying data occur

Engineering Contradiction:
Improvevolume migration capabilityVSAvoidmigration process complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent introduces a virtualization layer that creates a virtual address range mapping between the fully allocated volume and the deduplicated volume. This dimensional transformation allows data to remain in its original physical location while logical access is redirected through the virtualization layer, eliminating the need for physical data movement and reducing migration process complexity

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

Solution Approach 2:

The virtualization layer acts as an intermediary between the fully allocated volume and the deduplicated volume. It manages the mapping and redirection of data access without requiring actual data movement, thereby simplifying the migration process and avoiding conflicts with underlying data while maintaining volume migration capability

Inventive Principle:
Principle #24Intermediary (Mediator)

Data Source

PatentUS12007968B2Full allocation volume to deduplication volume migration in a storage system
Publication Date: 2024.06.11 INTERNATIONAL BUSINESS MACHINE CORPORATION
  • US12007968B2 patent drawing
  • US12007968B2 patent drawing
  • US12007968B2 patent drawing

AI summary

A method, computer program product, and computer system for full allocation volume to deduplication volume migration in a storage system. The method includes moving a physical allocation of stored data associated with a full allocation volume into a virtual address range in a deduplication domain and setting up the deduplication metadata to be a passthrough. The method then performs a background deduplication process on the virtual address range once populated with the physical allocations using a drive query hash interface to perform hash calculations on physical drives at which the data is stored.