Network Device Level Determination in Multi-Stage Fabrics
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current data center network configurations require manual configuration of switch levels, which can lead to errors and administrative burdens, and may not efficiently handle uneven stages in the network topology.
Innovation Solution
Network devices, such as routers in folded multi-stage structures, automatically determine their levels by receiving and propagating level information from neighboring devices, allowing them to form adjacency relationships and forward traffic based on their determined levels.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual configuration of switch levels is performed, then network topology can be established, but configuration errors and administrative burden increase
Solution Approach 1:
The patent implements automatic level determination where network devices autonomously discover their topology levels through receiving and processing level information from neighboring devices. This self-service mechanism eliminates manual configuration requirements, reduces human error, and allows the network to automatically adapt to uneven stages in the topology without administrator intervention.
Solution Approach 2:
The system employs feedback loops where devices continuously exchange level information with neighbors and adjust their own level determinations based on received data. This feedback mechanism ensures configuration accuracy by allowing devices to verify and correct their topology positions dynamically, resolving the contradiction between reliability and operational complexity.
2Ease of operation
If automatic level determination is implemented, then manual configuration burden is reduced, but device complexity increases
Solution Approach 1:
The automatic level determination process is segmented into discrete, manageable steps: receiving level information from neighbors, comparing received levels with local knowledge, determining relative position, and updating routing tables. This segmentation reduces device complexity by breaking down the complex automatic determination task into simple, standardized operations that can be executed efficiently.
Solution Approach 2:
The patent implements a universal level determination mechanism that works across different network device types and topology configurations. The same basic protocol and logic are applied universally to all devices, allowing them to automatically adapt to various network scenarios without requiring device-specific complexity, thereby simplifying implementation while maintaining ease of operation.
3Productivity
If traditional routing protocols are used, then network communication is maintained, but efficiency in handling uneven stages is reduced
Solution Approach 1:
The patent applies local quality by allowing each network device to independently determine its own level and adjust its routing behavior based on its specific position in the topology. Rather than using a one-size-fits-all routing approach, each device optimizes its routing decisions locally based on the uneven stage structure it encounters, thereby improving overall network efficiency while maintaining adaptability to diverse topology configurations.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A method includes receiving, by a first network device, messages from a plurality of network devices in a network, each of the messages indicating a level value of a respective sending network device in a network topology, determining, by the first network device and based on the respective levels indicated by the messages, a level value of the first network device in the network topology, determining, by the first network device and based on the determined level value, a mechanism by which to forward network traffic to one or more of the plurality of network devices, and forwarding the network traffic according to the determined mechanism.