Storage Controller Write Error Diagnosis via ID Verification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current data storage systems struggle to accurately diagnose write miss errors in individual disk drives, particularly when new data overwrites old data with the same CRC, and cannot directly diagnose individual disk drives in RAID configurations, leading to incorrect failure detection.
Innovation Solution
A data storage system with a storage controller that attaches an ID value to write data, updates it for each write command, and compares the ID value in read data to detect write miss errors, allowing for immediate and accurate diagnosis of disk drive failures.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If CRC (Cyclic Redundancy Code) is used to diagnose write errors, then error detection capability is improved, but when old data and new data have the same CRC, write miss errors cannot be diagnosed accurately
Solution Approach 1:
The patent introduces an ID value as an intermediary marker that is attached to write data and read back to verify successful writing. This ID value serves as a unique identifier that distinguishes new data from old data, resolving the ambiguity that occurs when CRC values coincide between old and new data. The ID value acts as a mediator between the write operation and verification process, enabling reliable detection of write miss errors.
Solution Approach 2:
The patent copies the ID value from the write command into the write data that is sent to the disk drive. This copied ID value is then read back along with the data and compared against the original ID value to determine whether the write operation succeeded. This copying mechanism ensures that the verification process can independently confirm write success without relying solely on CRC comparison.
2Loss of information
If time stamp information is attached to distributed write data in RAID configuration, then data distribution tracking is improved, but individual disk drive failures cannot be diagnosed directly
Solution Approach 1:
The patent segments the verification process by associating ID values with specific disk drives in a RAID configuration. Each disk drive receives write data containing an ID value, and the system verifies each drive independently by reading back the data and comparing ID values. This segmentation enables individual disk drive failure detection while maintaining RAID distribution tracking capabilities.
Solution Approach 2:
The patent implements a feedback mechanism where the disk drive reads back the written data including the ID value and returns it to the controller. The controller then compares the returned ID value with the original ID value from the write command. This feedback loop provides direct information about whether each individual disk drive successfully wrote its assigned data, enabling precise failure diagnosis.
3Productivity
If write completion is reported without read verify operation to quicken write speed, then write performance is improved, but write miss errors occur without detection
Solution Approach 1:
The patent performs a preliminary action by attaching the ID value to the write data before sending it to the disk drive. This preliminary marking enables subsequent verification without requiring a full read-verify cycle immediately after writing. The ID value is prepared in advance, allowing for efficient asynchronous verification that maintains high write performance while ensuring data integrity.
Data Source
AI summary
A storage system has a plurality of disk storage devices and a controller for controlling the plurality of disk storage devices, and diagnosis of a write miss to a disk of the disk storage device. The controller for controlling the plurality of disk storage devices attaches an ID to write data, and after write access to the disk drive, the controller reads the write data from the disk drive, and compares the ID of the read data and the attached ID. The controller updates the ID for each write command. Therefore the old write data and the new write data can be identified, accurate diagnosis is possible, and the failure of an individual disk drive can be detected immediately.