Data Storage Devices With Differentiated Copy Risk Profiles
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing fault-tolerant data storage systems face high risks of simultaneous data loss when both copies of critical data are stored in hardware devices prone to similar failure conditions, leading to increased chances of data loss and prolonged recovery times.
Innovation Solution
Implement a host system that differentiates the risk profiles of primary and secondary data copies by instructing one data storage device to use a high risk of data loss (HRDL) profile and the other to use a low risk of data loss (LRDL) profile, and employs staggered maintenance and scanning strategies to reduce simultaneous failures.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If both primary and secondary copies of data are stored in separate hardware devices, then fault tolerance is improved, but simultaneous data loss risk increases when both devices encounter similar failure conditions
Solution Approach 1:
The patent applies local quality by differentiating the risk profiles of primary and secondary data copies. The host system identifies high-risk conditions (such as MLC meta blocks with high program-erase counts) and applies different write strategies locally to each copy - writing the primary copy to high-risk blocks while writing the secondary copy to low-risk blocks (SLC blocks or MLC blocks with low PEC). This localized differentiation ensures that when a failure occurs in high-risk blocks, the secondary copy remains intact, thereby reducing simultaneous data loss risk while maintaining fault tolerance.
Solution Approach 2:
The patent employs parameter changes by dynamically adjusting the storage parameters (risk profile) based on the condition of the storage medium. The host system monitors parameters such as program-erase count (PEC) and determines when to switch between high-risk and low-risk write profiles. By changing the parameter of risk profile assignment based on monitored conditions, the system adapts to varying storage conditions and prevents simultaneous data loss while maintaining efficient use of storage resources.
2Stability of the object's composition
If identical write operations are performed on both primary and secondary data copies, then data consistency is improved, but vulnerability to simultaneous failures increases under high-risk conditions
Solution Approach 1:
The patent applies local quality by implementing differentiated write operations for primary and secondary copies based on their assigned risk profiles. When the host system identifies high-risk conditions, it writes the primary copy to high-risk blocks (MLC meta blocks with high PEC) while writing the secondary copy to low-risk blocks (SLC blocks or MLC blocks with low PEC). This localized differentiation in write operations ensures data consistency is maintained through proper copy mechanisms while simultaneously protecting against failures by diverging the physical storage locations based on their risk characteristics.
Solution Approach 2:
The patent employs asymmetry by creating an asymmetric write strategy where primary and secondary copies are treated differently under high-risk conditions. Instead of symmetric identical write operations, the host system assigns asymmetric risk profiles - one copy goes to high-risk blocks while the other goes to low-risk blocks. This asymmetric approach breaks the symmetry of simultaneous failure vulnerability while maintaining the essential symmetry of data consistency through proper copy management.
3Productivity
If maintenance operations are performed on both data storage devices simultaneously, then system maintenance efficiency is improved, but the risk of simultaneous failures and prolonged recovery times increases
Solution Approach 1:
The patent applies periodic action by implementing phased maintenance schedules for primary and secondary data storage devices. Instead of performing maintenance operations simultaneously on both devices, the host system staggers the maintenance timing - when one device undergoes maintenance, the other device continues normal operations. This periodic, alternating maintenance approach ensures that at least one copy of the data is always available, reducing the risk of simultaneous failures while maintaining overall system maintenance efficiency through systematic rotation of maintenance tasks.
Data Source
AI summary
A data storage device and method for enhancing fault tolerance are disclosed. In one embodiment, a method is provided that is performed in a host in communication with first and second data storage devices. The method comprises: determining whether a condition under which primary and secondary copies of data are to be written to the first and second data storage devices, respectively, presents a relatively-high risk of loss of both the primary and secondary copies of the data; and in response to determining that the relatively-high risk is presented, causing the primary and secondary copies of the data to be written differently in the first and second data storage devices, respectively. Other embodiments are provided.