Hypervisor-Agnostic Network Virtualization via Physical Overlay Switches
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing virtual switch-based solutions for network virtualization in data centers require cumbersome and non-uniform updates across multiple Hypervisor vendors, limiting the scalability and growth of virtual overlay networks.
Innovation Solution
Implementing a method where physical overlay switches at the edge of an IP network receive, encapsulate, and tunnel packets with VLAN IDs across the IP network, bypassing the need for updates to virtual switches by using Layer-3 operations and decapsulating packets to maintain VLAN IDs, thereby providing a Hypervisor-agnostic address discovery protocol.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If virtual switch-based solutions are used for network virtualization, then network virtualization functionality is provided, but updates to virtual switch software across multiple Hypervisor vendors become cumbersome and non-uniform
Solution Approach 1:
The patent introduces a physical overlay switch as an intermediary device between virtual machines and the network. This physical switch performs the address discovery protocol and packet encapsulation/decapsulation functions that were previously handled by virtual switches in the hypervisor. By moving these functions to a dedicated physical device, the system achieves uniform updates and management independent of multiple hypervisor vendors, while maintaining network virtualization capabilities.
2Reliability
If virtual switch software is updated individually across multiple Hypervisors, then functionality can be improved, but the process becomes cumbersome and execution becomes non-uniform
Solution Approach 1:
The physical overlay switch serves as a centralized intermediary that implements the address discovery protocol and tunneling functions. This consolidation allows for uniform updates and configuration management through a single device rather than individually updating virtual switch software across multiple hypervisor platforms, thereby improving operational ease while maintaining functional reliability.
3Adaptability or versatility
If physical overlay switches perform encapsulation and tunneling operations, then Hypervisor-agnostic address discovery is achieved, but device complexity increases
Solution Approach 1:
The physical overlay switch is designed as a universal device that can work with any hypervisor platform. It implements standardized packet encapsulation and decapsulation functions, performing address discovery and tunneling operations in a hypervisor-agnostic manner. This multi-functional design allows a single device type to serve multiple purposes across different virtualization environments, achieving adaptability without proportionally increasing complexity.
Data Source
AI summary
A method includes receiving a first packet having a first virtual local area network (VLAN) identifier (ID) directly from a first virtual switch using a first physical overlay switch located at an edge of an internet protocol (IP) network, encapsulating the first packet with an overlay header and tunneling the first encapsulated packet via Layer-3 operations across the IP network to a second physical overlay switch in response to a determination that a source of the packet is physically separated from a destination of the packet by the IP network, receiving a second encapsulated packet having a second overlay header from the second physical overlay switch, de-encapsulating the second encapsulated packet to create a second packet having a second VLAN ID, and sending the second packet having the second VLAN ID directly to the first virtual switch operating in the first hypervisor domain.