Storage System Reconstruction via Access Load Prioritization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing storage systems face inefficiencies in reconstructing data when multiple storage devices malfunction, leading to potential unrecoverable data loss due to prolonged reconstruction times and the risk of additional device failures during the process.
Innovation Solution
A method that prioritizes reconstructing malfunctioning extents with lower access loads first, selecting destination extents from idle devices with lower access loads to ensure high writing speeds and adherence to RAID standards, and optionally adding backup storage devices to enhance reconstruction efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If data reconstruction is performed on malfunctioning storage devices, then data reliability is improved, but reconstruction time increases and risk of additional failures during reconstruction increases
Solution Approach 1:
The patent changes the parameter selection criteria for reconstruction by introducing access load as a key factor. Instead of random or simple FIFO reconstruction, the system evaluates access load metrics of both source extents and destination devices to dynamically select optimal reconstruction targets, thereby reducing reconstruction time while maintaining data reliability
Solution Approach 2:
The patent applies local quality by differentiating reconstruction priorities based on specific extent characteristics. Different extents are reconstructed based on their individual access load profiles, and different destination devices are selected based on their local access load conditions, rather than applying a uniform reconstruction approach across all data
2Productivity
If multiple extents are reconstructed simultaneously, then productivity is improved, but the risk of additional device failures increases
Solution Approach 1:
The patent implements partial action by selectively reconstructing only the most critical extents first (those with lowest access load), rather than attempting to reconstruct all extents simultaneously. This staged approach allows the system to recover most critical data quickly while minimizing the window of vulnerability to additional failures
3Device complexity
If destination extents are selected without considering access load, then device complexity is reduced, but reconstruction speed decreases
Solution Approach 1:
The patent introduces access load as a new parameter for destination selection, transforming the selection process from a simple available-space-based approach to one that evaluates performance characteristics. This parameter addition enables the system to identify high-speed destination devices, thereby improving reconstruction speed despite increased selection complexity
Data Source
AI summary
Techniques reconstruct a storage system. A first extent access load and a second extent access load of a first malfunctioning extent and a second malfunctioning extent in a malfunctioning storage device in the storage system are acquired, respectively. The first malfunctioning extent is selected as a source extent in response to determining that the first extent access load is lower than the second extent access load. Among multiple idle extents in the storage system, a set of destination extents that can be used as a reconstruction destination of the source extent are generated. A destination extent is selected from the set of destination extents as the reconstruction destination of the source extent. It is possible to preferentially select a reconstruction destination for a malfunctioning extent with a low access load, thereby increasing the reconstruction speed of the storage system.