Disk Ownership Replay for Storage Aggregates
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current data storage technologies lack mechanisms to ensure reliable disk ownership changes during failures such as power failures or takeover procedures, leading to situations where subsets of disks may have different ownership information, preventing them from being assimilated into a storage volume.
Innovation Solution
A method and apparatus that generate a replay request based on stored ownership data in persistent memory, comparing update counts to ensure all disks in an aggregate have the same ownership, allowing for reliable disk ownership changes even in the presence of failures.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If disk ownership changes are performed during normal operation, then data storage flexibility and resource allocation are improved, but system reliability deteriorates due to potential failures during the ownership change procedure
Solution Approach 1:
The system performs preliminary actions by logging ownership change requests in persistent memory before actually executing the ownership change on disks. This allows the system to prepare and record the intended ownership change state ahead of time, so that if a failure occurs during execution, the logged information can be used to recover and complete the ownership change reliably.
Solution Approach 2:
The system implements feedback mechanisms by comparing update counts between logged ownership change requests and actual disk states. After a failure and recovery, the system reads the logged ownership change information and compares it with the current disk ownership states, using this feedback to determine what actions are needed to restore consistency across all disks.
2Ease of operation
If ownership change procedures are simplified for ease of operation, then system usability is improved, but data integrity deteriorates due to lack of protection against incomplete ownership changes
Solution Approach 1:
The system introduces an intermediary mechanism in the form of persistent memory logging that sits between the ownership change command and the actual disk ownership modification. This intermediary layer automatically records the ownership change intent and provides protection against information loss, while requiring minimal user intervention beyond the initial ownership change command.
3Device complexity
If disk ownership changes are implemented without protection mechanisms, then device complexity is reduced, but system stability deteriorates due to potential dual-ownership situations
Solution Approach 1:
By logging ownership change requests in persistent memory before execution, the system establishes a preliminary record of the intended ownership state. This preliminary action creates a recovery path that prevents unstable dual-ownership situations without requiring complex protection mechanisms during normal operation.
Solution Approach 2:
The system implements self-service recovery mechanisms where the filer automatically detects ownership inconsistencies after failures and uses the logged ownership change information to self-correct the state. This eliminates the need for manual intervention or complex external protection mechanisms while maintaining aggregate stability.
Data Source
AI summary
In an embodiment of the invention, a method and apparatus permits the reliable disk ownership changes. The method and apparatus generate a replay request based on ownership data stored in a persistent memory device, in response to a failure occurrence when ownership is being changed for disks in an aggregate. The method and apparatus will compare an update count in the replay request with an update count in a disk in the aggregate. Based on the comparison of the update count, the ownership on the disk is changed so that each disk in the aggregate will be owned by a same node. The failure occurrence can be, for example, a power failure, a panic occurrence, or a takeover procedure.