Storage Tiering via Segment Deduplication
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional data systems face inefficiencies when moving files between storage tiers, as these operations often lose the benefits of deduplication and require significant resources, as they typically involve transferring entire files rather than just the necessary segments.
Innovation Solution
The method involves segmenting files into deduplicated units, allowing for the transfer of only missing segments between tiers while maintaining deduplication benefits, using segment indices and fingerprints for efficient identification and verification, and applying policies for tier movement based on file access and modification.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If files are moved between storage tiers by transferring entire files, then file movement between tiers is achieved, but resource usage increases and deduplication benefits are lost
Solution Approach 1:
The patent segments files into smaller data blocks and uses deduplication to identify unique segments. When moving files between storage tiers, only the unique segments that don't already exist in the destination tier are transferred, rather than moving entire files. This segmentation approach maintains deduplication benefits and reduces resource usage during tier migration operations.
2Productivity
If files are moved between storage tiers by transferring entire files, then file movement between tiers is achieved, but deduplication benefits are lost
Solution Approach 1:
The patent segments files into smaller data blocks and uses deduplication to identify unique segments. When moving files between storage tiers, only the unique segments that don't already exist in the destination tier are transferred, rather than moving entire files. This segmentation approach maintains deduplication benefits and reduces resource usage during tier migration operations.
3Productivity
If segment indices and fingerprints are used for efficient identification and verification, then transfer of only missing segments is achieved, but system complexity increases
Solution Approach 1:
The patent creates simplified representations (fingerprints) of data segments that can be quickly compared to identify duplicates. Instead of comparing entire segments, the system uses these fingerprint copies to efficiently determine which segments need to be transferred, reducing the complexity of the comparison process while maintaining accuracy.
Data Source
AI summary
A method, article of manufacture, and apparatus for transferring data from a source tier to a target tier. In some embodiments, this may include dividing an object stored in the source tier into a plurality of segments, determining if the target tier is missing at least one of the segments, writing the missing segments to the target tier, and deleting the object from the source tier. In some embodiments, the object's metadata is updated to indicate that the object is in the target tier.


