Virtual Storage Area for RAID Data Reconstruction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current RAID systems face bottlenecks in data reconstruction due to the significant difference between read and write speeds, particularly in SSD arrays, where write operations are slower than read operations, leading to prolonged vulnerability periods and potential secondary failures during disk failure recovery.
Innovation Solution
A method is introduced to allocate a virtual storage area with optimized write performance, based on the potential read performance of storage devices, allowing data from a failed device to be rebuilt and then migrated to a physical spare device, thereby mitigating the speed mismatch and reducing reconstruction time.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If data is rebuilt by writing to a single dedicated spare device, then data recovery is simplified, but write performance becomes a bottleneck due to the slower write speed of storage devices
Solution Approach 1:
The patent divides the write operation into two distinct phases: first writing reconstructed data to a virtual storage area in memory, then migrating the data to the physical spare device. This segmentation separates the fast write operation from the slower physical storage operation, allowing the system to achieve high data reconstruction speeds while maintaining simplified recovery procedures.
Solution Approach 2:
The patent introduces a virtual storage area as an intermediary between the data reconstruction process and the physical spare device. This intermediary buffer allows data to be quickly written during reconstruction and then gradually migrated to the physical spare device without impacting the overall reconstruction speed, effectively decoupling the two operations.
2Ease of operation
If data reconstruction uses a single spare device, then the process is straightforward, but the vulnerability period is prolonged due to write speed limitations
Solution Approach 1:
By segmenting the reconstruction process into a fast write phase to virtual storage and a separate migration phase to physical storage, the system minimizes the vulnerability period. The critical data reconstruction is completed quickly in memory, reducing the time the array is vulnerable, while the slower migration to physical storage occurs after the array is already protected.
Solution Approach 2:
The patent performs the critical data reconstruction action in advance by writing to the virtual storage area during the rebuild process. This preliminary action ensures data is recovered and protected before the slower migration to physical storage begins, reducing the vulnerability period and enhancing array reliability during the rebuild process.
3Speed
If read performance is optimized by reading from multiple devices in parallel, then data retrieval speed improves, but write performance remains limited by single device write speed
Solution Approach 1:
The patent segments the write operation to allow parallel read operations to continue while data is written to the virtual storage area. This segmentation enables the system to maintain high read performance from multiple devices in parallel while the write operation proceeds at the virtual storage speed, effectively decoupling read and write performance constraints.
4Productivity
If a virtual storage area is allocated for fast writing during reconstruction, then data reconstruction speed improves, but storage resource allocation becomes more complex
Solution Approach 1:
The virtual storage area serves multiple functions: it acts as a fast write target during reconstruction, a temporary buffer for migrated data, and can be dynamically allocated and released based on array needs. This multi-functionality justifies the additional complexity by providing versatile storage management capabilities that improve reconstruction performance while enabling flexible resource allocation.
Data Source
AI summary
Methods, apparatus and computer programs have been provided for mitigating a problem of non-optimal recovery from storage device failures. A method involves determining a required write performance for rebuilding data of a failed device, based at least partly on the potential read performance of storage devices in a data rebuild; and allocating a virtual storage area within available storage, which allocation of virtual storage is based at least partly on the required write performance. Data is rebuilt by writing to the allocated virtual storage area, and data recovery is completed by migrating this rebuilt data to at least one data storage device such as a spare physical storage device within the array.