Disk Lubricant Sweep with Proactive Data Read Checking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
RAID arrays face data loss due to silent errors caused by unnoticed logical byte address corruption during rebuilds, as conventional data scrubbing is infrequent and may not detect errors until a read attempt, leading to incomplete rebuilds and data loss.
Innovation Solution
A disk drive control apparatus and method that combines a disk lubricant sweep with proactive data read checking, caching correct data, recording checked logical byte addresses, and error correction or reporting for soft or hard errors, thereby reducing overhead and enhancing system resilience.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional data scrubbing is used to detect silent errors, then error detection capability is improved, but the frequency of error detection deteriorates (errors may only be checked every 30 days or less frequently)
Solution Approach 1:
The patent performs data read checks during disk lubricant sweeps, which are routine maintenance operations. By integrating error detection into existing maintenance activities rather than relying on separate periodic scrubbing operations, the system proactively detects errors before they cause data loss during rebuild operations.
Solution Approach 2:
The patent combines two separate functions—disk lubricant sweeping and data integrity checking—into a single operational sequence. The read check component checks data during the lubricant sweep operation, eliminating the need for separate scrubbing operations and increasing detection frequency without adding significant overhead.
2Productivity
If frequent data scrubbing is implemented to increase error detection frequency, then error detection frequency is improved, but system overhead and performance cost increase
Solution Approach 1:
The patent merges data integrity checking with the routine disk lubricant sweep operation. Since lubricant sweeps are already performed periodically as maintenance, adding read checks during these operations leverages existing system activity, achieving frequent error detection without the overhead of separate scrubbing operations.
Solution Approach 2:
The system uses its own routine maintenance operations (lubricant sweeps) to simultaneously perform error detection. The disk drive's existing maintenance infrastructure serves dual purposes: maintaining the disk surface and checking data integrity, eliminating the need for additional dedicated error detection resources.
3Reliability
If data is not checked during rebuild operations, then system performance is maintained, but silent errors cause rebuild failures and data loss
Solution Approach 1:
The patent performs data integrity checks during routine lubricant sweeps before rebuild operations are initiated. By detecting and reporting errors in advance, the system prevents silent errors from causing rebuild failures, ensuring higher rebuild success rates without adding complexity to the rebuild process itself.
Data Source
AI summary
An apparatus and method for controlling a disk drive is provided. A disk lubricant sweep component for periodically initiates a disk lubricant spreading action. A disk data read check component checks data at one or more LBAs during the disk lubricant sweep. The apparatus may cache data from LBAs that have been checked by the disk data read check component and found correct and record LBAs that have been found correct, so that they can be omitted from subsequent operation of the read check component. The apparatus may further comprise an error checking and correcting component for checking and correcting data found incorrect by reason of a soft error, and an error reporting component for reporting on one or more LBAs that have been checked and found incorrect by reason of a hard error.