Storage Controller Failure Presage Detection and Redundant Copy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In RAID systems, data loss can occur when a disk fails during the rebuild or redundant copy process, and the time required for these processes increases with slower HDD rotational speeds or larger capacities, increasing the likelihood of additional failures.
Innovation Solution
A storage control device with a processor that detects impending failures, performs initial and secondary data copies into a backup region, and writes data to storage devices while managing backup regions to ensure data redundancy and minimize data loss.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If data is copied into a hot spare disk during rebuild or redundant copy process, then data redundancy is maintained, but the time required for the process increases and the possibility of additional disk failures during the process increases
Solution Approach 1:
The patent performs preliminary actions by detecting failure presages and initiating redundant copy operations before actual disk failures occur. The controller proactively identifies disks showing signs of deterioration and copies their data to hot spare disks in advance, preventing data loss without waiting for complete failure. This preliminary action reduces the urgency and time pressure during actual rebuild operations.
Solution Approach 2:
The patent employs multiple copying strategies: (1) redundant copy from member disks to hot spare disks when failure presages are detected, (2) rebuild copying from remaining healthy member disks to replace failed disks, and (3) copy-back operations from hot spare disks to new member disks. These copying operations maintain data redundancy while allowing flexible management of the copy process to optimize time consumption.
2Quantity of substance
If the rotational speed of HDD decreases or capacity increases, then storage capacity is improved, but the time required for rebuild and redundant copy processes increases
Solution Approach 1:
The system performs redundant copy operations in advance when failure presages are detected, rather than waiting for actual failures. This preliminary action allows the copy process to be initiated under controlled conditions, potentially during periods of lower system load, thereby reducing the impact of long copy times on system availability.
Solution Approach 2:
The patent maintains continuous data protection by implementing overlapping copy operations. While one redundant copy or rebuild process is ongoing, the system continues to monitor for additional failure presages and can initiate subsequent copy operations. This continuity ensures that data protection is maintained throughout the extended copy process required for large-capacity disks.
3Reliability
If the time required for rebuild and redundant copy increases, then the likelihood of additional member disk failures during the process increases, but data redundancy must be maintained
Solution Approach 1:
By detecting failure presages and performing redundant copy operations before actual failures occur, the system prevents the chain reaction of multiple failures. The preliminary copy creates a safety buffer that protects against additional failures during the rebuild process, as the critical data has already been secured in hot spare disks.
Solution Approach 2:
The patent implements a cushioning mechanism by maintaining hot spare disks with pre-copied data. When failure presages are detected, the system prepares redundant copies in advance, creating a protective cushion against potential additional failures. This beforehand cushioning ensures that even if additional disks fail during the extended copy process, data redundancy is preserved through the pre-prepared hot spare copies.
Data Source
AI summary
A storage control device includes a processor which performs first copy of copying first data stored in a first storage device into a first backup region upon detecting a failure presage in the first storage device. The processor performs first write of writing second data specified in a first write request to the first storage device and second write of writing the second data into the first backup region upon receiving the first write request while performing the first copy. The processor performs second copy of copying third data stored in the first backup region to a second storage device upon completing the first copy. The processor performs third write of writing fourth data specified in a second write request to the second storage device in place of the first storage device upon receiving the second write request after completion of the second copy.