Storage Mirroring via Wear-Aware Address Selection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current replication schemes in storage systems are limited in their ability to sustain errors, leading to data unavailability due to uniform wear across storage modules, resulting in increased read errors as modules approach the end of their life.
Innovation Solution
Implementing a mirroring scheme that uses information about the wear level of storage modules to select physical locations for data storage, dynamically updating active regions and adjusting change thresholds to distribute wear evenly across modules, thereby reducing the likelihood of simultaneous high wear and increasing the system's resilience.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If current replication schemes are used with uniform wear distribution, then data redundancy is maintained, but read errors increase as storage modules approach end of life
Solution Approach 1:
The patent applies local quality by differentiating the treatment of storage modules based on their individual wear levels. Instead of uniform replication, the system assigns data copies to modules with lower wear levels (better local quality), while modules near end-of-life are excluded from receiving new copies. This non-uniform distribution strategy maintains data availability while minimizing read errors by avoiding degraded modules.
Solution Approach 2:
The system dynamically changes the parameter of module selection based on wear level thresholds. When monitoring detects that a storage module's wear level exceeds a predefined threshold, the system alters its participation in replication schemes, preventing new data copies from being assigned to high-wear modules. This parameter change (from active to inactive status based on wear) resolves the contradiction by adapting replication behavior to current module conditions.
2Productivity
If storage modules are used until end of life, then capacity utilization is maximized, but simultaneous high wear across modules increases failure risk
Solution Approach 1:
The system performs preliminary action by proactively monitoring wear levels and preventing data replication to storage modules before they reach end-of-life. By establishing wear thresholds and excluding modules from replication schemes in advance, the system avoids the scenario where multiple modules simultaneously fail. This preliminary protective measure maintains system resilience while still utilizing available capacity from healthier modules.
Solution Approach 2:
The patent implements beforehand cushioning by creating a buffer zone through wear threshold monitoring. The system maintains a safety margin by refusing to replicate data to modules approaching end-of-life, even if they still have some remaining capacity. This cushioning approach ensures that no single point of failure can compromise the entire replicated dataset, thereby protecting system resilience while managing capacity utilization.
Data Source
AI summary
In general, embodiments of the technology relate to a method for storing data. The method includes receiving a request to write data. In response to the request, the method further includes, selecting a first physical address in a first region in a first storage module, selecting a second physical address in a second region in a second storage module, where an amount of wear associated with the first physical address is different than an amount of wear associated with the second physical address, writing a first copy of the data to the first physical address, and writing a second copy of the data to the second physical address.