Ethernet Load Balancing via Virtual Network Segmentation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Ethernet networks, with their loop-free switching path and reverse path learning capabilities, face limitations in network recovery from failures, underutilized bandwidth, and inability to balance traffic across multiple paths, making them ineffective for high-performance computing and storage systems.

Innovation Solution

The implementation of virtual networks within Ethernet networks to create multiple paths between nodes while maintaining loop-free switching and reverse path learning, allowing for dynamic load balancing by selecting the most suitable path based on traffic conditions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If multiple paths are provided to enable load balancing, then load balancing capability is improved, but network complexity increases and loop-free switching may be compromised

Engineering Contradiction:
Improveload balancing capabilityVSAvoidnetwork complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent segments the network into multiple virtual networks (VLANs), each maintaining its own loop-free spanning tree. This allows multiple paths to exist at the virtual network level while preserving loop-free operation at each VLAN level. The segmentation principle enables load balancing across virtual networks without creating physical loops that would compromise reverse path learning.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent introduces virtual network dimensionality to the physical network topology. By multiplexing multiple virtual networks over the same physical infrastructure, the system achieves multiple paths without additional physical links. This dimensional approach allows load balancing while maintaining the loop-free property through proper VLAN tagging and switching.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

2Productivity

If multiple paths are provided to enable load balancing, then network capacity utilization is improved, but fault recovery time may be affected

Engineering Contradiction:
Improvenetwork capacity utilizationVSAvoidfault recovery time
Core Design Contradiction:
ProductivityVSReliability

Solution Approach 1:

By segmenting traffic into different virtual networks, the patent enables independent failure domains. When a link fails in one VLAN, only that virtual network is affected, and other VLANs continue operating. This segmentation allows rapid recovery by switching to alternative virtual networks without requiring complete network reconfiguration.

Inventive Principle:
Principle #1Segmentation

3Ease of operation

If loop-free switching is maintained, then reverse path learning functionality is preserved, but traffic load balancing is not achieved

Engineering Contradiction:
Improvereverse path learning functionalityVSAvoidtraffic load balancing
Core Design Contradiction:
Ease of operationVSAdaptability or versatility

Solution Approach 1:

The patent applies segmentation by creating multiple virtual networks that each maintain independent reverse path learning tables. Each VLAN preserves the loop-free switching mechanism and reverse path learning functionality, while collectively providing multiple paths for load balancing. Switches learn reverse paths within each VLAN context, enabling both simplicity and load balancing capability.

Inventive Principle:
Principle #1Segmentation

Data Source

PatentUS7463588B1Mechanism for enabling load balancing to be achieved in a loop-free switching path, reverse path learning network
Publication Date: 2008.12.09 FORTINET INC
  • US7463588B1 patent drawing
  • US7463588B1 patent drawing
  • US7463588B1 patent drawing

AI summary

A mechanism is disclosed for enabling load balancing to be achieved in a loop-free switching path, reverse path learning network, such as an Ethernet network. The network is divided into a plurality of virtual networks, with each virtual network providing a different path through the network from a source node to a destination node. When it comes time to send a set of information from the source node to the destination node, one of the plurality of virtual networks, and hence, one of the plurality of paths, is selected. The set of information is then updated to indicate the selected virtual network, and sent into the network to be transported to the destination node along the selected path. With multiple paths, and with the ability to select between the multiple paths, it is possible to balance the load imposed on the multiple paths.