Parallel RAID Rebuild Using Diagonal Spare Partitions
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In mass data storage systems, existing RAID configurations face challenges in efficiently utilizing spare storage capacity for rebuilding failed members across drives of different sizes, leading to increased rebuild latency and inefficiency.
Innovation Solution
The implementation of a storage array with a drive manager that creates M*G same-size partitions on non-volatile drives of varying sizes, allocates single diagonal spare partitions, and vertically distributes RAID group members within a single partition index across clusters, allowing for parallel distribution and utilization of spare capacity across multiple drives.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If traditional RAID configurations use same-size drives, then management is simplified, but spare capacity cannot be efficiently utilized across drives of different sizes
Solution Approach 1:
The patent segments drives of different sizes into standardized partition units (e.g., 100 GB partitions). Each drive is divided into M partitions where M depends on the drive size relative to the baseline drive size. This segmentation allows spare capacity to be uniformly managed across heterogeneous drives while maintaining the ability to handle different drive sizes.
Solution Approach 2:
The system changes the parameter of drive capacity representation from raw size to number of standardized partitions. By expressing all drive capacities in terms of a common partition unit, the system can uniformly allocate spares across drives of different sizes without dealing with the complexity of varying byte capacities.
2Productivity
If spare capacity is concentrated on single drives, then allocation is simple, but rebuild latency increases due to sequential rebuilding
Solution Approach 1:
The patent merges spare capacity resources from multiple drives into a unified spare pool. Instead of having spares confined to individual drives, the system combines available spare partitions across all drives to form a shared resource that can be allocated to any failed drive, enabling parallel rebuild operations.
Solution Approach 2:
The system transitions from a one-to-one mapping of spares to drives to a many-to-many relationship. By introducing the dimension of cross-drive spare allocation, multiple spares from different drives can simultaneously contribute to rebuilding a single failed drive, and multiple drives can be rebuilt in parallel using distributed spares.
3Quantity of substance
If drives of different sizes are used to increase storage capacity, then storage flexibility improves, but efficient use of spare capacity for rebuilding becomes difficult
Solution Approach 1:
The patent creates a universal spare allocation mechanism that works across drives of different sizes. The standardized partition approach allows the same spare allocation logic to be applied regardless of the underlying drive size, making the system universally applicable to heterogeneous storage environments while maintaining ease of operation.
Data Source
AI summary
Managed drives of a storage node with different size drives in a fixed arithmetic relationship are organized into clusters of same size drives. Every drive is configured to have M*G same-size partitions, where M is a positive integer variable defined by the arithmetic relationship and G is the RAID group size. The storage capacity of all drives can be viewed as matrices of G+1 rows and M*G columns, and each matrix is composed of submatrices of G+1 rows and G columns. Diagonal spare partitions are allocated and distributed in the same pattern over groups of G columns of all matrices, for increasing partition index values. Members of RAID groups are vertically distributed such that the members of a given RAID group reside in a single partition index of a single cluster. When a drive fails, protection group members of the failed drive are rebuilt in order on spare partitions characterized by lowest partition indices for increasing drive numbers across multiple clusters. Consequently, drive access for rebuild is parallelized and latency is reduced.