Dynamic Remote Hot Spare Allocation for RAID Arrays
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current RAID storage systems lack an automated method for replacing failed hard disk drives, leading to degraded performance and potential data loss, as they rely on physical disk swapping and do not allow dynamic sharing of hot spares across servers.
Innovation Solution
A system and method that dynamically allocates available storage from a remote bank of HDDs connected via iSCSI, allowing data to be redirected to a spare HDD on another server, enabling continuous operation and rebuilding of the RAID array without the need for physical presence.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If physical disk swapping is used to replace failed HDDs, then the RAID array can be restored, but system downtime increases and manual intervention is required
Solution Approach 1:
The system performs preliminary actions by pre-configuring hot spare drives and automatically detecting failed drives. When a drive fails, the system immediately begins data reconstruction to the hot spare without waiting for manual intervention, thereby reducing system downtime while maintaining RAID array availability
Solution Approach 2:
The system enables self-service by implementing automated drive failure detection, hot spare identification, and data reconstruction processes. The RAID controller automatically manages the entire replacement workflow without requiring manual disk swapping, eliminating the need for physical intervention and minimizing downtime
2Reliability
If hot spares are dedicated to individual servers, then drive failure recovery is enabled, but storage resource utilization efficiency decreases
Solution Approach 1:
The system applies universality by enabling hot spare drives to serve multiple purposes: they can be dynamically allocated to any server in the network that experiences a drive failure, rather than being dedicated to a single server. This multi-functional approach allows the same hot spare pool to support multiple RAID arrays across different servers, improving storage resource utilization while maintaining drive failure recovery capability
Solution Approach 2:
The system implements dynamics by allowing hot spare allocation to be flexible and changeable based on real-time needs. The hot spare drives can be dynamically assigned to different servers as failures occur, and the system automatically manages the allocation and deallocation of these resources, optimizing storage utilization while ensuring recovery capability
3Productivity
If remote storage targets are used for data redirection, then continuous operation is enabled, but network dependency increases
Solution Approach 1:
The system uses the network as an intermediary to enable communication between servers and remote storage targets. By leveraging existing network infrastructure, the system can redirect data to remote hot spares located on other servers, enabling continuous operation without requiring direct physical connectivity or additional specialized hardware
Data Source
AI summary
One embodiment provides a system, including: one or more processors; a network interface for communication with a remote bank of available storage; a redundant array of independent disks (RAID) operatively coupled to the one or more processors; and a memory operatively coupled to the one or more processors and storing instructions executable by the one or more processors to: ascertain at least one unavailable hard disk drive (HDD) of the RAID; determine an available remote storage target; dynamically update a storage destination for data to be stored from the at least one unavailable HDD of the RAID to the available remote storage target; and send the data over the network interface to the available remote storage target. Other embodiments are described and claimed.