Rectangular Array Data Storage for Fast Recovery
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing data storage methods, such as RAID schemes, face inefficiencies in recovery rates and complexity when dealing with failures of multiple storage devices, particularly in rectangular array configurations.
Innovation Solution
The method involves forming data blocks into groups and assigning them to a rectangular array with calculated row and column parity blocks, allowing for faster recovery of data blocks by distributing parity blocks and data blocks across multiple storage devices, with optional additional parity blocks for enhanced redundancy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If data blocks are stored in a square array configuration with RAID 6, then complete recovery from two storage device failures is achieved, but the recovery rate for individual data blocks is slower
Solution Approach 1:
The patent applies asymmetry by transitioning from a symmetric square array configuration to an asymmetric rectangular array configuration where the number of rows differs from the number of columns. This asymmetric arrangement allows optimization of recovery paths by having more rows than columns, enabling faster parallel recovery operations while maintaining the ability to recover from multiple storage device failures.
Solution Approach 2:
The patent changes the structural parameter of the array configuration from square (n×n) to rectangular (r×c) where r > c. This parameter change fundamentally alters the recovery characteristics, allowing the system to achieve faster data block recovery rates while preserving the reliability property of recovering from up to two storage device failures through the maintained parity block structure.
2Reliability
If additional parity blocks are added to enable recovery from three storage device failures, then reliability is improved, but system complexity increases
Solution Approach 1:
The patent segments the redundancy protection into distinct layers: row parity blocks for single-row failures, column parity blocks for single-column failures, and diagonal parity blocks for combined failures. This segmentation allows the system to achieve recovery from three storage device failures by combining these segmented parity structures rather than using a single complex parity mechanism.
Solution Approach 2:
The patent employs a composite parity structure combining multiple types of parity blocks (row, column, and diagonal) working together. This composite approach achieves enhanced failure tolerance for three storage device failures by integrating different parity mechanisms, rather than relying on a single complex parity system.
Data Source
AI summary
A method for storing data blocks, including forming the data blocks into groups comprising N·M data blocks, where N and M are different positive integers. For every group, the N·M data blocks are assigned to correspond to elements of an array comprising N rows and M columns. A respective parity block is calculated for each of the N rows and M columns, to form (N+M) parity blocks. The resulting (N+M) parity blocks and N·M data blocks are stored in respective storage devices.