Virtual Machine Hardware Reassignment in 5G Networks
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing virtualization technologies in 5G networks face limitations in dynamically reassigning hardware resources, particularly due to hard-coded resource allocation and compatibility issues with tools like SR-IOV, which restrict the ability to migrate virtual machines without rebooting and maintaining network access.
Innovation Solution
The system migrates virtual machines between servers by identifying direct device assignments, reserving replacement device assignments on target servers, and reconfiguring virtual machines to bypass host operating systems, enabling seamless migration without rebooting and maintaining direct device connections.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Power
If direct device assignment (SR-IOV) is used to improve performance by bypassing the host operating system, then network performance and bandwidth are improved, but the ability to migrate virtual machines to different computing resources is restricted
Solution Approach 1:
The system performs preliminary actions by reserving the target hardware device assignment before initiating virtual machine migration. The target server pre-configures the hardware device (e.g., NIC, GPU) and creates a placeholder assignment, ensuring the device is ready and reserved before the virtual machine actually migrates. This preliminary preparation eliminates the need to reconfigure hardware assignments during migration, enabling seamless transition while maintaining direct device access performance.
Solution Approach 2:
The system introduces an intermediary management layer (virtualization manager/orchestrator) that mediates between the virtual machine migration process and the hardware device assignment. This intermediary coordinates the transfer of direct device assignments from source to target server, manages the placeholder reservations, and ensures continuous connectivity. The intermediary abstracts the complexity of hardware reassignment, allowing virtual machines to migrate without losing their direct hardware access capabilities.
2Adaptability or versatility
If virtual machines are migrated to balance load across hardware, then resource utilization and flexibility are improved, but system complexity and coordination requirements increase
Solution Approach 1:
The system implements self-service mechanisms where the virtualization manager automatically discovers available hardware resources, pre-configures target assignments, and coordinates migration without requiring complex manual intervention. The target server autonomously reserves hardware devices and prepares placeholder assignments, while the migration process automatically transfers these assignments. This self-organizing behavior reduces the operational complexity of load balancing migrations.
Solution Approach 2:
The system creates universal hardware device assignments that can be dynamically allocated to different virtual machines across multiple servers. The hardware device assignment framework is designed to be server-agnostic and virtualization-platform-independent, allowing the same hardware resource to be assigned to different virtual machines on different servers through standardized interfaces. This universality simplifies load balancing by enabling seamless migration without server-specific reconfiguration.
3Reliability
If hard-coded resource allocation is used in virtualization infrastructure, then system stability and predictability are improved, but the ability to dynamically reassign resources is restricted
Solution Approach 1:
The system transforms static, hard-coded resource allocations into dynamic, flexible assignments. Instead of permanently binding hardware resources to specific virtual machines or servers, the system creates movable device assignments that can be dynamically transferred between servers and virtual machines. The hardware device assignment is decoupled from fixed infrastructure configurations, enabling real-time resource reassignment while maintaining system stability through controlled migration processes.
Solution Approach 2:
The system changes the fundamental parameter of resource allocation from fixed to variable. Hardware device assignments are no longer static configurations but dynamic parameters that can be modified, transferred, and reassigned based on workload requirements. The system manages these parameter changes through coordinated processes that update device assignments, transfer ownership between servers, and maintain system consistency throughout the transition, enabling adaptive resource management without sacrificing stability.
Data Source
AI summary
Systems, processes, and devices migrate virtual machines to new servers. An example process includes identifying a virtual machine for migration in response to a load on a host server running the virtual machine. A direct device assignment of the virtual machine may be detected. The virtual machine may communicate with a first hardware device of the host server using the direct device assignment to bypass a host operating system of the host server. A target server is identified, and a replacement device assignment is reserved on the target server. The replacement device assignment includes a link to a second hardware device of the target server configured to bypass a host operating system of the target server. The virtual machine running on the host server is reconfigured with data supporting the replacement device assignment on the target server. The virtual machine migrates to the target server.