RAID Volume Allocation Across Distributed Storage Network
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current storage systems face challenges in minimizing data reconstruction time and reducing overlap between RAID members on storage elements, leading to increased latency and potential data integrity issues during drive failures.
Innovation Solution
The method involves defining logical splits on storage elements, providing RAID protection, and distributing it across a distributed network to minimize overlap between RAID groups, using heuristics and matrix operations to optimize the placement of RAID members and ensure data redundancy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If RAID members are distributed across storage elements, then data redundancy is improved, but overlap between RAID groups increases
Solution Approach 1:
The patent divides storage elements into multiple logical splits, where each split can belong to different RAID groups. This segmentation allows RAID members to be distributed across storage elements while minimizing overlap between RAID groups, as each split is independently assignable to optimize the distribution pattern and reduce the number of common drives between different RAID groups.
Solution Approach 2:
The patent introduces a new dimension of organization by creating logical splits within storage elements. Instead of treating storage elements as atomic units, the patent operates at the split level, allowing RAID groups to be constructed from splits across multiple storage elements. This dimensional change enables finer-grained control over RAID member placement, reducing overlap while maintaining redundancy.
2Productivity
If logical splits are created on storage elements, then RAID group distribution is improved, but device complexity increases
Solution Approach 1:
The patent segments storage elements into logical splits, which are virtual partitions of physical storage capacity. This segmentation enables efficient RAID group distribution by allowing flexible assignment of splits to different RAID groups. The complexity is managed through software-based logical layering, where the physical storage elements remain unchanged but are virtualized into multiple logical units for optimized RAID construction.
3Reliability
If RAID members are placed on distinct storage elements, then data integrity is improved, but storage utilization decreases
Solution Approach 1:
The patent merges multiple logical splits from different storage elements into RAID groups, allowing efficient utilization of storage capacity while maintaining data integrity. By combining splits across multiple storage elements into unified RAID groups, the system achieves both redundancy and high storage utilization. The merging approach allows any failed split to be recovered from remaining members in the same RAID group, ensuring data integrity without requiring dedicated isolated storage for each RAID member.
Data Source
AI summary
A distributed network of storage elements (DNSE) is provided in which the physical capacity of each drive is split into a set of equal sized logical splits which are individually protected within the DNSE using separate RAID groups. To reduce restoration latency, members of the RAID groups having a member in common on a given drive are spread within the DNSE to minimize the number of sets of drives within the DNSE that have RAID members in common. By causing the splits to be protected by RAID groups, restoration of the splits may occur in parallel involving multiple drives within the DNSE. By minimizing the overlap between RAID members on various drives, failure of a given drive will not require multiple reads from another drive in the DNSE. Likewise, spare splits are distributed to enable write recovery to be performed in parallel on multiple drives within the DNSE.