SMR Drive Forward Corruption Detection and Bypass
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Shingled magnetic recording (SMR) drives face performance degradation due to forward corrupted tracks, which occur when a writing operation is interrupted, leading to unreadable sectors without immediate detection, causing read operation failures and prolonged retry times.
Innovation Solution
The implementation of a storage controller that performs boundary track read operations to detect and identify forward corrupted tracks by sampling sectors near the target track and adjacent tracks, categorizing corruption types, and maintaining a table of bad sectors to bypass corrupted areas during read operations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If boundary track read operations are performed to detect forward corrupted tracks, then detection accuracy improves, but device complexity increases
Solution Approach 1:
The detection process is segmented into multiple phases: initial read operation, boundary track sampling, corruption type classification, and selective retry. This segmentation allows the system to perform comprehensive detection only when necessary, reducing overall complexity while maintaining high detection accuracy for forward corrupted tracks.
Solution Approach 2:
The system performs preliminary boundary track read operations to sample sectors near the target track before attempting full recovery. This preliminary action identifies potential forward corruption early, allowing the system to prepare appropriate recovery strategies in advance without immediately invoking complex recovery procedures.
2Measurement precision
If multiple boundary track read operations are performed to identify corruption extent, then detection accuracy improves, but loss of time increases
Solution Approach 1:
The system performs a limited number of boundary track read operations (sampling specific sectors) rather than exhaustive scanning of entire tracks. This partial action provides sufficient detection accuracy to identify forward corruption and its extent, avoiding unnecessary time consumption from complete track scans while still achieving reliable detection.
Solution Approach 2:
The detection process is divided into sequential stages: initial failure detection, boundary sampling, corruption classification, and extent determination. Each stage builds on previous results, allowing the system to stop early if corruption is clearly identified, thus reducing average detection time while maintaining accuracy.
3Reliability
If the storage controller implements forward corruption detection and bypass mechanisms, then reliability improves, but device complexity increases
Solution Approach 1:
The storage controller maintains a data structure (table) that pre-stores information about bad sectors and forward corruption areas. This preliminary organization of corruption information allows rapid lookup and bypass decisions during read operations, improving reliability without requiring complex real-time analysis that would increase operational complexity.
Solution Approach 2:
The patent introduces an intermediary data structure that mediates between the physical storage medium and the read/write operations. This table acts as a lookup buffer that simplifies the interaction between the controller and corrupted sectors, allowing the system to handle reliability issues without directly implementing complex detection algorithms during every operation.
4Reliability
If the system performs comprehensive boundary track sampling to identify all corrupted sectors, then reliability improves, but productivity decreases
Solution Approach 1:
The system performs sampling of specific boundary sectors rather than comprehensive scanning of entire tracks. This partial sampling provides sufficient information to identify forward corruption areas with high reliability, while avoiding the productivity loss associated with exhaustive scanning of all sectors on affected tracks.
Solution Approach 2:
Once forward corruption is detected and the corruption area is identified, the system skips over the corrupted sectors using the pre-populated data structure, rushing through the problematic areas without attempting to read or process them. This skipping mechanism maintains reliability by avoiding corrupted data while preserving productivity by not wasting time on unrecoverable sectors.
Data Source
AI summary
Systems and methods for forward corrupted track detection and by-pass are described. In one embodiment, a storage system comprising a storage controller performs a read operation for a target track of a shingled magnetic recording (SMR) disk drive and detects a read operation failure of the read operation for the target track. The storage controller also performs a boundary track read operation on one or more tracks including or adjacent to the target track and detect a forward corruption area based on the boundary track read operation. In another embodiment, a method is provided that includes detecting a read operation failure of a read operation for a track of a disk drive and performing a boundary track read operation on one or more tracks including or adjacent to the target track. The method also includes detecting a forward corruption area based on the boundary track read operation.