Virtual Volume Subsystem I/O Control via Attribute-Based Write Order
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing storage systems lack effective methods for appropriately managing duplicated volumes in virtual storage subsystems, particularly in handling various states such as volume duplication failures or busy access paths, which can lead to performance deterioration and management complexities.
Innovation Solution
A storage system configuration where volumes from multiple physical storage subsystems are managed as pairs, with attribute information setting the write order and properties, allowing the system to determine and manage I/O operations based on these attributes, ensuring consistent processing regardless of system or volume states.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If volumes are duplicated among multiple physical storage subsystems to enhance fault tolerance and load distribution, then system reliability and performance are improved, but the complexity of managing different I/O processing states across subsystems increases
Solution Approach 1:
The patent introduces attribute information as a parameter to define write order and write propriety for duplicated volumes. This parameter-based approach allows the system to automatically determine appropriate I/O processing states based on volume attributes, simplifying the management of complex multi-subsystem operations while maintaining reliability through standardized control mechanisms.
2Adaptability or versatility
If different I/O processing methods are used for different system states and volume states, then appropriate handling of various scenarios is achieved, but the difficulty of detecting and measuring system state increases
Solution Approach 1:
The patent implements a feedback mechanism where the storage subsystem automatically detects volume states and I/O request types, then applies appropriate processing methods based on attribute information. The system monitors its own state (e.g., whether volumes are being duplicated, access path status) and adjusts processing accordingly, making state detection and response more manageable through automated feedback loops rather than manual state tracking.
3Stability of the object's composition
If attribute information is set for each volume to control write order and write propriety, then I/O processing consistency is improved, but the device complexity increases
Solution Approach 1:
The patent applies preliminary action by pre-setting attribute information for each volume before I/O operations begin. The write order and write propriety attributes are configured in advance, allowing the storage subsystem to automatically execute consistent processing without real-time decision complexity. This pre-configuration approach ensures I/O processing consistency while reducing the complexity of runtime state management.
Data Source
AI summary
A storage system according to one preferred embodiment of the present invention is composed of at least a first storage subsystem and a second storage subsystem. Write data from a host computer is duplicated to a first volume of the first storage subsystem and a second volume of the second storage subsystem, and the host computer is composed to be able to access both the first volume and the second volume. Attribute information which is information related to an order of write and/or write capability is set for each volume, and when an access command to the volume is received from the host computer, the storage subsystem determines whether I/O to the first volume and/or the second volume is required or not based on the attribute set for each volume.