Disk Array Data Reconstruction via Virtual Disk Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The increasing capacity of disk arrays, such as RAID systems, leads to longer data reconstruction times, which increases data loss risks and negatively impacts file system performance, as traditional RAID architectures struggle to efficiently distribute read and write operations across disks.
Innovation Solution
The method involves virtualizing physical disks into virtual disks, applying data protection algorithms to obtain redundant information, and mapping data and redundancy across physical disks according to a predetermined policy, allowing all working disks to participate in data reconstruction when a disk fails, thereby breaking read and write bottlenecks.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If disk capacity is increased to provide larger storage capacity, then storage capacity is improved, but data reconstruction time becomes longer
Solution Approach 1:
The patent segments the disk array into multiple independent disk groups, where each disk group contains multiple disks and can perform reconstruction independently. This segmentation allows parallel reconstruction across multiple disk groups, reducing overall reconstruction time while maintaining large storage capacity.
Solution Approach 2:
The patent introduces a new dimension of parallelism by organizing disks into multiple disk groups that can simultaneously perform reconstruction operations. This transforms the traditional single-threaded reconstruction process into a multi-threaded parallel process, dramatically reducing reconstruction time for large-capacity arrays.
2Reliability
If traditional RAID architecture is used to store data, then data protection is provided, but read and write bottlenecks occur during data reconstruction
Solution Approach 1:
By dividing the disk array into multiple independent disk groups, the patent enables parallel reconstruction operations across groups. Each disk group maintains data protection independently through traditional RAID techniques, while the overall system achieves high reconstruction speed through parallel processing of multiple groups simultaneously.
Solution Approach 2:
The patent merges multiple disk groups into a single logical address space, allowing the system to maintain the data protection benefits of RAID while utilizing the combined storage capacity and parallel reconstruction capabilities of multiple independent groups working together.
3Reliability
If data reconstruction is performed on large capacity disks, then data loss risk is reduced, but file system performance deteriorates due to long reconstruction time
Solution Approach 1:
The patent segments reconstruction operations into multiple parallel tasks across different disk groups, significantly reducing the total time required for reconstruction. This shortened reconstruction time minimizes the period during which file system performance may be impacted, while still ensuring data recovery and reducing data loss risk.
Data Source
AI summary
A method, system, and computer program product for accelerating data reconstruction for a disk array, the disk array comprising a plurality of physical disks, the method, system, and computer program product including virtualizing the plurality of physical disks as a plurality of virtual disks, applying a data protection algorithm to the plurality of virtual disks to obtain redundant information on data to be stored, providing a map from the plurality of virtual disks to the plurality of physical disks, storing, based on the map, the data and the redundant information in the plurality of physical disks according to a predetermined allocation policy, and in response to at least one of the plurality of physical disks failing, implementing a data reconstruction for a disk array based on the redundant information and the data in working disks from amongst the plurality of physical disks.