Global Stripe RAID Storage Using Orthogonal Latin Squares
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional storage array data organization methods, such as RAID5 and RAID6, result in isolated disk groups, leading to prolonged data reconstruction times and increased risk of data loss and performance decline when a disk fails, due to the inability of remaining disk groups to share the load effectively.
Innovation Solution
A RAID-based data storage system that utilizes orthogonal Latin squares to distribute data blocks and parity blocks evenly across disks, allowing for concurrent data reconstruction and self-healing capabilities, breaking resource isolation between disk groups and achieving balanced read and write loads.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional RAID data organization is used with isolated disk groups, then data reconstruction can be performed, but the reconstruction time becomes excessively long (tens of hours or days) and I/O performance deteriorates significantly
Solution Approach 1:
The patent merges previously isolated disk groups into a unified storage pool where all disks participate in a single global stripe. This allows any surviving disk to contribute to data reconstruction, transforming a sequential single-disk recovery process into a parallel multi-disk recovery process, thereby dramatically reducing reconstruction time from tens of hours to minutes.
Solution Approach 2:
The patent introduces a global stripe dimension that spans all disks in the storage pool, moving from traditional local stripe organization to a global organization. This dimensional change enables concurrent read operations across multiple disks during reconstruction, increasing the effective bandwidth and reducing recovery time.
2Reliability
If traditional RAID data organization is used with isolated disk groups, then data redundancy is maintained, but the remaining free disk groups cannot share the load of data reconstruction
Solution Approach 1:
The patent combines all disk groups into a single unified pool where every disk is part of the same global stripe. This merging enables any surviving disk to participate in reconstruction operations, distributing the reconstruction load across all available disks rather than concentrating it on a single hot spare disk.
Solution Approach 2:
The patent makes all disks universal participants in both data storage and reconstruction operations. Any surviving disk can serve as a reconstruction target, and any disk can contribute to the reconstruction process, creating a multi-functional system where all components are actively utilized.
3Stability of the object's composition
If traditional RAID data organization is used, then disk groups form isolated storage islands, but this isolation makes it difficult for remaining free disk groups to share reconstruction load and increases risk of data loss
Solution Approach 1:
The patent merges all previously isolated disk groups into a single unified storage pool organized as one global stripe. This eliminates the isolation that created vulnerability, as any disk failure now affects the entire pool uniformly, and all surviving disks can contribute to reconstruction, thereby reducing data loss risk.
Solution Approach 2:
The patent changes the fundamental organization parameter from multiple isolated stripe configurations to a single global stripe spanning all disks. This parameter change transforms the failure characteristics, making the system more resilient by distributing failure impact across the entire pool while enabling unified recovery operations.
Data Source
AI summary
The data storage system is a RAID-based data storage system in which resources are globally shared. This storage system includes the first number of disks, and the RAID mechanism is used to store data on each disk. The blocks on different disks form stripes, and at least one of the blocks on the stripe stores the parity information, wherein the width of the stripe is less than the first number. The data layout of the data storage system satisfies the following characteristics: any two physical blocks in the stripe are distributed on different disks; the data blocks distributed on each disk are the same, and the distributed parity blocks are also the same; other data in the stripe associated with any piece of disk data is evenly distributed across all the remaining disks. Normal data layout and degraded data layout can be implemented by orthogonal Latin squares. This system can remove the limitation that the number of disks in the normal data storage system is equal to the stripe width, and break the resource isolation between the disk groups. And in the event of a disk failure, this invention can achieve a complete equalization of the reconstructed read load.