Distributed Storage Allocation to Minimize Migration Overheads
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing data migration strategies in distributed storage systems result in high overheads during horizontal expansion due to flexible capacity-based migrations.
Innovation Solution
Construct an equipment room allocation model based on dependency relationships between storage objects to determine a target equipment room allocation strategy that minimizes migration overheads, using a mixed-integer linear programming technique to optimize the allocation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If flexible capacity-based migration strategy is used, then adaptability of storage system expansion is improved, but migration overheads increase
Solution Approach 1:
The patent applies preliminary action by pre-calculating migration evaluation results for multiple equipment room allocation strategies using a mixed-integer linear programming model before actual data migration occurs. The system evaluates different allocation scenarios in advance, identifies the optimal strategy that minimizes migration overheads, and then executes migration according to this pre-determined plan, thereby reducing the overheads associated with flexible expansion.
2Quantity of substance
If data migration is performed frequently during expansion, then storage capacity is improved, but migration costs increase
Solution Approach 1:
The patent applies parameter changes by transforming the migration optimization problem into a mixed-integer linear programming mathematical model with specific parameters representing storage objects, equipment rooms, and dependency relationships. By changing the approach from ad-hoc migration to parameterized optimization, the system can evaluate multiple allocation strategies and select the one that minimizes migration costs while achieving the required storage capacity expansion.
3Productivity
If storage objects are distributed across multiple equipment rooms, then load balancing is improved, but cross-equipment room access traffic increases
Solution Approach 1:
The patent applies feedback by incorporating dependency relationship information into the migration evaluation model. The system evaluates how different allocation strategies affect cross-equipment room access traffic based on the feedback from dependency analysis, and uses this information to optimize the allocation strategy. This ensures that storage objects with strong dependencies are kept together in the same equipment room, reducing access traffic while maintaining load balancing.
Data Source
AI summary
A data storage control method, a device, and a storage medium are provided. The method includes: constructing an equipment room allocation model for a distributed storage system based on a dependency relationship between storage objects in the distributed storage system, the equipment room allocation strategy is used to indicate a target equipment room allocated to the storage object in the distributed storage system, and the migration evaluation result is used to indicate overheads caused by data transition processing of migration from an original equipment room to the target equipment room for storage; determining, based on the equipment room allocation model, an equipment room allocation strategy corresponding to a minimum migration evaluation result as a target equipment room allocation strategy; and performing data migration on the distributed storage system based on the target equipment room allocation strategy.