RAID Drive Group Segmentation for Rebuild Risk Reduction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional data storage systems with RAID technology face limitations in adding new disks and increased rebuild times due to write bandwidth bottlenecks, and the risk of data loss during concurrent drive failures.
Innovation Solution
The system splits a group of physical data storage drives into partnership groups and adjusts the RAID mapping table to limit the risk of data loss by ensuring that rebuild operations only involve drives within the same partnership group, allowing for flexible addition of new drives and reducing the probability of simultaneous failures.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If the number of physical data storage drives in a RAID group is increased to improve storage capacity and rebuild parallelism, then storage capacity and rebuild speed are improved, but the probability of concurrent drive failures increases and the risk of data loss during rebuild increases
Solution Approach 1:
The patent divides a large RAID group into multiple smaller partnership groups, where each partnership group contains a limited number of drives (e.g., 4-6 drives). This segmentation limits the scope of rebuild operations to within each partnership group, reducing the probability that multiple concurrent failures will occur within the same rebuild scope. The RAID mapping table is相应ly divided into multiple partnership group mapping tables, each managing only its own partnership group's drive extents.
2Reliability
If traditional RAID systems require adding new disks in increments equal to the RAID stripe width (e.g., 5 disks for 4D+1P RAID-5), then data redundancy and fault tolerance are maintained, but storage capacity expansion flexibility is reduced
Solution Approach 1:
By segmenting the RAID group into multiple partnership groups, the patent enables independent capacity expansion within each partnership group. Users can add drives to a specific partnership group without needing to add drives to all groups simultaneously, allowing flexible capacity expansion in smaller increments while maintaining the required redundancy within each partnership group.
Solution Approach 2:
The patent implements dynamic partnership group management where the system can automatically balance drives between partnership groups based on capacity needs. The RAID mapping table can be dynamically reconfigured to redistribute drive extents across partnership groups, enabling flexible adaptation to changing storage requirements without rigid adherence to fixed stripe width increments.
3Reliability
If the size of partnership groups is reduced to decrease the probability of concurrent failures, then data loss risk during rebuild is reduced, but the number of partnership groups increases and system complexity increases
Solution Approach 1:
The patent implements a unified RAID mapping table structure that can represent multiple partnership groups using the same data structures and management logic. The partnership group mapping table format is consistent across all groups, allowing the system to manage multiple smaller groups through a single standardized interface, thereby minimizing the increase in system complexity despite having more groups.
Data Source
AI summary
In response to detecting that a total number of physical data storage drives in a group of physical data storage drives exceeds a maximum drive group size, the group of physical data storage drives is divided into a multiple partnership groups, and RAID extents in a RAID mapping table are divided into multiple RAID extent groups. Each one of the RAID extent groups contains multiple RAID extents and corresponds to one of the partnership groups of physical data storage drives. The RAID extents in each RAID extent group only indicate physical data storage drives contained in the corresponding partnership group of physical data storage drives, in order to ensure that data recovery and RAID extent rebuilding after a drive failure involve only the physical data storage drives within the same partnership group as the failed physical data storage drive.