Flexible RAID Scheme Parity Segmentation for Fast Rebuild
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional RAID5(8+1) data storage systems experience performance degradation and reliability issues during data rebuild due to the need to read all remaining data segments, and they are less efficient in storage utilization compared to RAID5(4+1) schemes, which require more storage space for parity.
Innovation Solution
A flexible RAID scheme is introduced that generates multiple parity segments, where a first parity segment is stored within the RAID stripe and a second parity segment is stored in designated free storage, allowing for data rebuild from half the number of data segments, reducing rebuild time and improving reliability while optimizing storage efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If RAID5(8+1) data protection scheme is used, then storage utilization efficiency is improved, but rebuild time increases and reliability decreases
Solution Approach 1:
The patent divides the parity calculation into two segments: a first parity segment calculated from all data segments and stored in the RAID stripe, and a second parity segment calculated from half of the data segments and stored in designated free storage. This segmentation allows the system to use RAID5(8+1) for efficient storage utilization while having a reduced parity set available for faster rebuild operations, thus resolving the contradiction between storage efficiency and reliability.
Solution Approach 2:
The system performs preliminary action by pre-calculating and storing both the first parity segment (from all data segments) and the second parity segment (from half of data segments) before any failure occurs. This preliminary preparation enables the system to quickly reconstruct lost data using only half the data segments and the second parity segment during rebuild operations, reducing rebuild time and improving reliability without sacrificing storage utilization efficiency.
2Quantity of substance
If RAID5(8+1) data protection scheme is used, then storage utilization efficiency is improved, but rebuild duration increases
Solution Approach 1:
The patent segments the parity information into two parts: a first parity segment stored within the RAID stripe and a second parity segment stored in designated free storage. During rebuild operations, the system uses only the second parity segment (derived from half the data segments) to reconstruct lost data, significantly reducing the number of segments that need to be read and processed, thus reducing rebuild duration while maintaining the storage efficiency of RAID5(8+1).
Solution Approach 2:
The system performs preliminary calculation and storage of the second parity segment (from half the data segments) in designated free storage before any failure occurs. This preliminary action enables rapid rebuild operations by avoiding the need to read and process all data segments, thereby reducing rebuild duration while preserving the storage utilization efficiency of the RAID5(8+1) scheme.
3Loss of time
If RAID5(4+1) data protection scheme is used, then rebuild time is shortened, but storage efficiency decreases
Solution Approach 1:
The patent merges the advantages of both RAID5(8+1) and RAID5(4+1) by storing both the first parity segment (from all data segments, similar to RAID5(8+1)) and the second parity segment (from half the data segments, similar to RAID5(4+1))). This combination allows the system to achieve fast rebuild times like RAID5(4+1) while maintaining the storage efficiency of RAID5(8+1), effectively resolving the contradiction between rebuild time and storage efficiency.
Solution Approach 2:
The patent creates a multi-functional parity system where the first parity segment provides full redundancy for any single disk failure, and the second parity segment provides accelerated rebuild capability. This multi-functionality allows the system to serve dual purposes: maintaining storage efficiency comparable to RAID5(8+1) while achieving fast rebuild times comparable to RAID5(4+1), thus resolving the contradiction between these two objectives.
Data Source
AI summary
A technique garbage collects user data within a storage system. The technique involves, in response to a request signal that directs the storage system to garbage collect user data, coalescing first user data and second user data to form new user data. The technique further involves generating first parity and second parity based on the new user data. The technique further involves storing the first parity and the new user data in a data uber of the storage system, the data uber providing redundant array of independent disks (RAID) protection. The technique further involves storing the second parity in designated free storage of the storage system, the designated free storage being separate from the data uber.