Cross-LUN Deduplication via Data Block Pool Merging
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional deduplication techniques for logical units (LUNs) in storage systems lead to inefficient resource utilization, as they fail to effectively combine and optimize storage space across multiple LUNs.
Innovation Solution
A storage system with a first storage processor that maintains unique data block pools for multiple LUNs and joins them based on a correspondence metric exceeding a predetermined threshold, forming combined LUNs and data block pools to eliminate duplicates and optimize storage space.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If conventional deduplication techniques are applied to individual LUNs, then storage space is reduced within each LUN, but resource utilization remains inefficient due to inability to combine and optimize across multiple LUNs
Solution Approach 1:
The patent merges multiple LUNs into a unified storage pool, allowing the storage system to track and manage unique data blocks across all LUNs collectively. This enables cross-LUN deduplication where duplicate data blocks are identified and consolidated across different LUNs, maximizing storage space efficiency while maintaining the ability to provision individual LUNs as needed.
2Quantity of substance
If LUNs are joined to form combined LUNs, then storage efficiency is improved through deduplication, but system complexity increases due to additional management requirements
Solution Approach 1:
The patent segments the storage system into independent LUNs that can be individually provisioned and managed, while maintaining a unified backing store for deduplication. This segmentation allows flexible LUN creation and deletion without affecting the overall deduplication mechanism, reducing management complexity compared to a fully unified approach.
Solution Approach 2:
The storage processor acts as an intermediary between the host systems and the physical storage devices. It maintains a mapping between LUNs and unique data blocks, handling the complexity of tracking which LUNs share which data blocks. This intermediary layer abstracts the complexity from individual LUNs while enabling efficient cross-LUN deduplication.
3Quantity of substance
If data block pools from multiple LUNs are combined, then duplicate data blocks are eliminated, but I/O performance may be affected due to increased data access complexity
Solution Approach 1:
The patent implements dynamic LUN provisioning where LUNs can be created, deleted, and reconfigured without affecting the deduplication infrastructure. The storage processor dynamically tracks data block mappings as LUNs are modified, allowing the system to adapt to changing storage needs while maintaining performance through efficient data block location tracking.
Data Source
AI summary
Systems and methods for efficient deduplication and/or provisioning of LUNs are disclosed. A first unique data block pool for a first LUN of a plurality of deduplicated LUNs is accessed, the first unique data block pool comprising a first plurality of unique data blocks for representing data stored on the first LUN. A second unique data block pool for a second LUN of the plurality of LUNs is accessed, the second unique data block pool comprising a second plurality of unique data blocks for representing data stored on the second LUN. It is determined a correspondence metric for the first unique data block pool and the second unique data block pool exceeds a pre-determined threshold. The first LUN and the second LUN are joined to form a first combined LUN. The first unique data block pool and the second unique data block pool are joined.