Disk Partitioning for RAID Resiliency Set Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The challenge lies in determining an optimal combination of RAID Resiliency Sets (RRS) when the number of disks exceeds the upper limit, requiring efficient partitioning to maintain high storage capability and reliability, while ensuring optimal IO performance and available capacity.
Innovation Solution
A method that determines candidate combinations of disk sets by partitioning disks into subsets, ensuring each subset has a predetermined number of disks, and selecting a target combination that maximizes available capacity and minimizes unavailable capacity, thereby improving disk utilization and reducing computational resources.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If the number of disks in a RAID Resiliency Set exceeds the upper limit, then storage capability increases, but reliability decreases and a new RRS must be created
Solution Approach 1:
The patent applies segmentation by dividing a large number of disks into multiple RAID Resiliency Sets, each containing a limited number of disks within the upper limit. This allows the system to maintain reliability within each RRS while achieving high storage capability through the combined capacity of multiple RRSs. The method automatically partitions disks into optimal RRS combinations, ensuring each set maintains proper redundancy and reliability characteristics.
2Reliability
If multiple disk sets are created to maintain reliability, then reliability is preserved, but device complexity increases
Solution Approach 1:
The patent implements self-service by providing an automatic disk partitioning system that independently determines optimal RRS combinations without requiring manual intervention. The system automatically evaluates disk configurations, calculates optimal partitions, and creates RRS assignments, thereby reducing management complexity while maintaining reliability. This automated approach eliminates the need for administrators to manually manage complex multi-RRS configurations.
3Quantity of substance
If disks are partitioned into multiple subsets, then available capacity is optimized, but computational resources increase
Solution Approach 1:
The patent applies preliminary action by pre-calculating and storing optimal RRS combination configurations based on disk characteristics and capacity. When disks need to be partitioned, the system retrieves pre-computed optimal configurations rather than performing complex real-time calculations. This approach optimizes available capacity through careful pre-planning while significantly reducing the computational resources required during actual disk partitioning operations.
Data Source
AI summary
Techniques for managing disks involve: in response to a number of a plurality of disks to be partitioned being greater than a predetermined number of disks in a disk set, determining a plurality of candidate combinations of disk sets from the plurality of disks. The techniques further involve selecting a target combination from the plurality of candidate combinations, a first disk set of the target combination comprising at least a first subset corresponding to a first disk array, a second disk set of the target combination comprising at least a second subset corresponding to a second disk array, a number of disks in the first subset and a number of disks in the second subset being both equal to a first number and the disks in the first subset being different from the disks in the second subset. Accordingly, such techniques improve the storage efficiency of the disk array.