Storage-Aware Virtual Machine Migration Target Selection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing virtual machine migration techniques select target machines based solely on processing capacity, leading to poor or overloaded connectivity to storage volumes, resulting in degraded performance.
Innovation Solution
A storage-aware selection method that determines storage volume connectivity and spare path capacity of candidate machines, preferentially selecting targets with sufficient processing, memory, network, and storage bandwidth, as well as optimal latency, to ensure efficient storage access for virtual machine migration.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If target machines are selected based solely on processing capacity, then CPU and memory allocation is optimized, but storage access performance deteriorates due to poor connectivity
Solution Approach 1:
The patent extends the selection criteria from traditional parameters (CPU, memory) to include storage-specific parameters (connectivity quality, path capacity, latency). This multi-parameter approach changes the selection function to optimize for both processing capacity and storage performance simultaneously, resolving the contradiction between these two requirements.
2Ease of operation
If VMs are migrated to machines with sufficient processing capacity, then resource allocation improves, but storage connectivity becomes overloaded leading to degraded performance
Solution Approach 1:
The system performs preliminary assessment of storage connectivity and path capacity before making migration decisions. By evaluating storage network conditions in advance and selecting target machines with adequate spare path capacity, the system prevents storage overload before it occurs, maintaining both ease of operation and productivity.
3Device complexity
If migration targets are chosen without considering storage connectivity, then migration simplicity is maintained, but performance degradation occurs due to storage bottlenecks
Solution Approach 1:
The patent creates a universal selection framework that simultaneously evaluates multiple criteria (processing capacity, storage connectivity, path capacity, latency) through a single integrated assessment mechanism. This multi-functional approach maintains procedural simplicity while ensuring comprehensive performance optimization.
Data Source
AI summary
A method and system selecting a target physical machine for a virtual machine (VM) migration is provided. Selecting a target physical machine for a VM migration involves determining storage volume connectivity and spare path capacity of one or more candidate physical machines, and preferentially selecting among the candidate physical machines a migration target with storage volume connectivity and spare path capacity to satisfy storage volume access requirements of the VM.


