Disk Array Partitioned Spare Capacity Distribution
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The challenge lies in efficiently scaling storage capacity in data storage systems while minimizing excess storage capacity and associated costs, particularly as individual drive capacities and costs increase with technological advancements.
Innovation Solution
The method involves creating W=(D+P) partitions of equal size on W+1 drives, forming a first vertical protection group with D data and P parity members, and distributing W spares such that all protection group members on a failed drive can be relocated to spare drives without exceeding one member per drive, ensuring efficient use of spare capacity and scalability.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If storage capacity is increased by adding (W+1) new drives for a RAID (D+P) protection group, then total storage capacity of the data storage system is increased, but excess storage capacity that will not be utilized within a reasonable timeframe is introduced
Solution Approach 1:
The drive subset is divided into multiple partitions, with each partition capable of hosting protection groups. Spare capacity is segmented and distributed across multiple partitions rather than being集中 in a single spare drive, allowing finer-grained utilization of storage resources.
Solution Approach 2:
The patent introduces a new dimension of organization by creating multiple partitions across drives, transforming the traditional single-spare-drive model into a multi-partition spare capacity distribution model. This allows spare capacity to be allocated across different partitions and drives simultaneously.
2Quantity of substance
If storage capacity is increased by adding (W+1) new drives, then total storage capacity is increased, but cost associated with adding drives increases
Solution Approach 1:
Each drive in the subset of W+1 drives serves multiple functions: it can be a data member, a parity member, or a spare for different protection groups across different partitions. This multi-functionality reduces the need for dedicated spare drives, lowering overall costs.
Solution Approach 2:
The patent changes the parameter of spare capacity allocation from a fixed (W+1) model to a flexible model where spare capacity is distributed across multiple partitions. This allows the system to adapt spare capacity allocation to actual needs, reducing unnecessary costs.
3Reliability
If spares are distributed across partitions, then failover capability is improved, but system complexity increases
Solution Approach 1:
The patent uses an asymmetric distribution strategy where spares are placed in specific partitions based on mathematical criteria (e.g., partition indices that are powers of 2), creating an organized yet asymmetric pattern that simplifies management compared to completely symmetric distribution.
Solution Approach 2:
The system automatically manages spare capacity allocation and failover operations across partitions without requiring manual intervention. The distributed spare structure self-organizes to provide failover capability, reducing operational complexity.
Data Source
AI summary
A subset of drives with protection groups that have D data members and P parity members is created with (W+1) drives each having W partitions where W=(D+P). A single partition protection group is created in the lowest numbered partition of the W lowest numbered drives. Spares are created at drive X partition Y that satisfy X+Y=W+2. Members of additional protection groups with W members are symmetrically distributed on remaining partitions such that the protection group member at drive X partition index Y belongs to protection group N: if (X+Y)<(W+2), then N=(X+Y−2); and if (X+Y)>(W+2), then N=(X+Y−W−2). The spares are used to rebuild partitions in the event of drive failure. When a new drive is added the first W protection group members in the lowest numbered unrotated partition are rotated onto the new drive. The single partition protection group is excluded from rotation. Partitions vacated by rotated protection group members and a rotated spare are used to create a new protection group. The drive subset is split after enough new drives have been added.