Affinity Based Allocation for Deduplicated Storage
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing backup systems that utilize deduplicated data stores face inefficiencies due to allocation schemes based on available space, leading to storage of duplicate data across multiple devices, counteracting the benefits of deduplication by erratic data distribution across different deduplication storage devices from various vendors.
Innovation Solution
Implementing an affinity-based allocation method that uses an affinity database to determine the most suitable deduplication storage device for backup operations, establishing relationships between data sources and targets based on past data storage, and employing methods like round-robin, least-recently-used, or available-space-per-disk-volume assignments when no affinity exists.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Volume of stationary object
If an allocation scheme based on available space per disk volume is used, then storage capacity utilization is improved, but data deduplication effectiveness deteriorates due to duplicate data being stored across multiple devices
Solution Approach 1:
The system performs preliminary actions by maintaining an affinity database that records historical data storage relationships between data sources and targets. Before allocating new backup data, the system queries this database to identify the most suitable data target based on past affinities, thereby preventing duplicate storage before it occurs
Solution Approach 2:
The system implements feedback mechanisms by continuously updating the affinity database with information about successful data storage operations. This feedback loop allows the system to learn from past allocations and improve future decisions, ensuring data is consistently routed to the most appropriate target to maintain deduplication effectiveness
2Adaptability or versatility
If data is distributed across multiple deduplication storage devices using traditional allocation schemes, then storage flexibility is improved, but deduplication principle effectiveness deteriorates due to erratic data distribution
Solution Approach 1:
The affinity database serves as an intermediary between data sources and multiple data targets. It mediates the allocation decision-making process by providing intelligence about historical relationships, enabling the system to flexibly distribute data across multiple devices while maintaining deduplication effectiveness through informed routing decisions
3Productivity
If backup data is stored on different storage devices without affinity consideration, then load balancing is improved, but storage efficiency deteriorates due to increased duplicate data copies
Solution Approach 1:
The system applies local quality by treating each data source-target pair uniquely based on their historical affinity relationships. Instead of applying a uniform load balancing approach, the system tailors allocation decisions to local conditions (specific data source and target relationships), routing each backup to the most appropriate target while maintaining overall system efficiency
Data Source
AI summary
A method, apparatus, and computer program product for implementing affinity based allocation for storage implementations employing deduplicated data stores is disclosed. According to an embodiment of the present invention, a backup manager determines if information associating a data source with a first data target of a plurality of data targets has been established. The first data target is a deduplication data store and the information associating the data source with the first data target indicates an increased likelihood of at least some information stored on the data source is already being stored on the first data target prior to performing a backup. If information associating the data source with the first data target has been established, the backup manager stores a set of data on the data target.