Hypervisor Address Resolution Suppression in Logical Networks
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In communications networks, address resolution processes lead to network flooding and security vulnerabilities due to the broadcast nature of address resolution protocols, especially when the SDN controller is unavailable, causing increased CPU and bandwidth consumption and potential malicious attacks.
Innovation Solution
A hypervisor in a virtualized computing environment learns protocol-to-hardware address mapping information from other hypervisors to suppress address resolution requests, eliminating the need for broadcast messages and maintaining network integrity even without SDN controller assistance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If address resolution requests are broadcast to resolve protocol addresses to hardware addresses, then address resolution can be achieved, but network flooding and increased bandwidth consumption occur
Solution Approach 1:
The system performs preliminary address resolution by proactively sending unicast requests to potential destinations before actual communication is needed. Hypervisors learn protocol-to-hardware address mappings in advance through these preliminary actions, so when real communication occurs, the addresses are already resolved and no broadcast is needed.
Solution Approach 2:
The patent introduces an intermediary mechanism where hypervisors act as mediators between virtual machines and the network. Instead of VMs directly broadcasting address resolution requests, the hypervisor intercepts and processes address resolution needs, using learned mappings to provide responses without actual broadcasts, thus reducing network traffic.
2Reliability
If broadcast address resolution requests are sent, then address resolution can be performed, but CPU consumption increases due to processing broadcast traffic
Solution Approach 1:
The system performs preliminary address resolution by proactively sending unicast requests to potential destinations before actual communication is needed. Hypervisors learn protocol-to-hardware address mappings in advance through these preliminary actions, so when real communication occurs, the addresses are already resolved and no broadcast is needed.
Solution Approach 2:
The hypervisor maintains local tables of learned protocol-to-hardware address mappings and uses these self-maintained resources to answer address resolution requests without external broadcasts. This self-service approach eliminates the need for VMs to send broadcast requests and for other VMs to process them, reducing overall CPU consumption.
3Reliability
If broadcast address resolution is used, then address resolution can be achieved, but security vulnerabilities and malicious attacks become possible
Solution Approach 1:
The patent extracts the address resolution function from the public broadcast domain and confines it to private unicast channels between hypervisors. By taking out the resolution process from the broadcast network and performing it through directed unicast messages, the system eliminates the security vulnerabilities inherent in broadcast-based address resolution while maintaining the capability.
Solution Approach 2:
The patent introduces an intermediary mechanism where hypervisors act as mediators between virtual machines and the network. Instead of VMs directly broadcasting address resolution requests, the hypervisor intercepts and processes address resolution needs, using learned mappings to provide responses without actual broadcasts, thus reducing network traffic.
4Ease of operation
If SDN controller is used for address resolution management, then centralized control is achieved, but system reliability decreases when SDN controller fails
Solution Approach 1:
The patent segments the address resolution functionality from the centralized SDN controller and distributes it to individual hypervisors. Each hypervisor maintains its own table of learned protocol-to-hardware address mappings and can independently perform address resolution without relying on the SDN controller, thus eliminating the single point of failure while maintaining operational capability.
Solution Approach 2:
The hypervisor maintains local tables of learned protocol-to-hardware address mappings and uses these self-maintained resources to answer address resolution requests without external broadcasts. This self-service approach eliminates the need for VMs to send broadcast requests and for other VMs to process them, reducing overall CPU consumption.
Data Source
AI summary
Example methods are provided for a first host to perform address resolution suppression in a logical network. The first host may support a first virtualized computing instance located on the logical network and a first hypervisor. The method may comprise the first hypervisor broadcasting a notification message within the logical network to trigger one or more control messages, and learning protocol-to-hardware address mapping information associated with multiple second virtualized computing instances located on the logical network based on the one or more control messages. The method may also comprise: in response to the first hypervisor detecting an address resolution request message that includes a protocol address associated with one of the multiple second virtualized computing instances, the first hypervisor generating and sending an address resolution response message to a first virtualized computing instance without broadcasting the address resolution request message on the logical network.