Dropped Write Error Detection in Storage Arrays
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Dropped write errors in data storage systems go undetected, leading to data integrity issues as the storage controller is not aware of write failures, causing silent errors and potential data loss, especially in RAID configurations where data is spread across multiple drives.
Innovation Solution
A method that involves performing a parity check on strides during sequential read requests, changing the state of the stride to indicate a performed parity check, and using a cyclic schedule based on access frequency to efficiently detect and correct dropped write errors, reducing performance impact.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If parity check is performed on every read request, then dropped write error detection capability is improved, but system performance and resource consumption deteriorate
Solution Approach 1:
The patent implements periodic parity verification by maintaining a verification state (first state indicating no verification, second state indicating verification completed) for each stride. Parity checks are performed periodically based on access patterns rather than on every single access, reducing overhead while maintaining error detection capability. The verification state tracks whether the most recent write to a stride has been verified, and parity checks are triggered periodically for strides in the first state.
2Reliability
If parity check is performed frequently, then data integrity is improved, but resource consumption increases
Solution Approach 1:
The patent applies partial verification by selectively performing parity checks based on verification states rather than verifying every stride on every access. The system performs parity verification partially - only when needed based on the first/second state tracking - which reduces resource consumption compared to exhaustive verification of all data while still maintaining adequate data integrity through targeted checks of strides that may have dropped write errors.
3Productivity
If no parity check is performed, then system performance is maintained, but dropped write errors remain undetected
Solution Approach 1:
The patent implements preliminary error detection capability by maintaining verification states that track whether parity checks have been performed on each stride. This preliminary tracking mechanism is in place before actual parity verification occurs, allowing the system to identify which strides need verification and prepare for error detection without immediately performing the costly parity check operation, thus balancing performance and reliability.
Data Source
AI summary
A computer-implemented method for dropped write error detection is proposed. In the method, a read request for a stride stored in an array of storage drives is received. The stride includes segments of a data and a first parity associated with the data spreading across the storage drives in the array of the storage drives. In response to the read request being a predefined sequential read request and a state of the stride being a first state, a parity check is performed on the stride. The first state indicates that no parity check has been performed after the data is written into the array of storage drives. The state of the stride is changed to a second state, and the second state is different with the first state.