Virtual Volume Migration in Clustered Storage Systems
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing data storage systems struggle with non-disruptive migration of virtual volumes between different storage appliances within a cluster, leading to resource imbalances and increased latency due to inadequate resource allocation and single protocol endpoint configurations.
Innovation Solution
The technology enables the migration of virtual volumes between storage appliances within a cluster by conveying a rebind request to the host computer, creating a new binding between the virtual volume and a protocol endpoint on a different storage appliance, and copying data independently of the host's data paths, allowing direct access and reducing latency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If virtual volume migration between storage appliances within a cluster is implemented, then resource balance and system flexibility are improved, but system complexity and migration overhead increase
Solution Approach 1:
A management interface acts as an intermediary between host computers and storage appliances, abstracting the complexity of virtual volume migration. The management interface receives migration requests, coordinates data copying between storage appliances, and manages binding updates, thereby enabling resource balancing without increasing host system complexity.
Solution Approach 2:
Virtual volume data is copied from the source storage appliance to the destination storage appliance during migration. This copying mechanism enables seamless migration while maintaining data integrity, allowing the system to balance resources across storage appliances without disrupting host operations.
2Device complexity
If a single protocol endpoint is exposed for the entire cluster, then device complexity is reduced, but I/O operation latency increases due to redirection requirements
Solution Approach 1:
The cluster is segmented into multiple storage appliances, each exposing its own protocol endpoint. This segmentation eliminates the need for centralized redirection of I/O operations, allowing hosts to directly access virtual volumes on any storage appliance in the cluster, thereby reducing I/O latency while maintaining manageable endpoint complexity through the management interface.
3Reliability
If virtual volume migration is performed without disrupting host operations, then system availability is improved, but data path management complexity increases
Solution Approach 1:
The management interface serves as an intermediary that handles data path management during virtual volume migration. It coordinates the copying of virtual volume data between storage appliances and manages binding updates, ensuring that host operations continue uninterrupted while the migration occurs in the background.
Solution Approach 2:
The virtual volume data is copied to the destination storage appliance before the binding is updated. This preliminary action ensures that when the migration completes, the host can immediately access the data from the new location without interruption, maintaining system availability throughout the migration process.
Data Source
AI summary
A virtual volume is initially provided from a first storage appliance within a cluster of storage appliances by providing access to the virtual volume over a data path between a host computer and a protocol endpoint hosted on the first storage appliance, based on an initial binding between the virtual volume and the protocol endpoint hosted on the first storage appliance. A rebind request is conveyed to the host computer, and in response to receiving a bind request for the virtual volume, a new binding is created between the virtual volume and a protocol endpoint hosted by the second storage appliance. The virtual volume is subsequently provided from the second storage appliance by providing the host computer with access to the virtual volume over a data path between the host computer and the protocol endpoint hosted on the second storage appliance based on the newly created binding.