Network Switch Adaptive Routing via Traffic Pattern Characterization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing adaptive routing technologies in data centers face fairness issues due to skewed perceived congestion during network saturation, leading to unfairness in traffic patterns, as they rely on static minimal path biases that do not adjust based on dynamic traffic patterns.
Innovation Solution
A network switch that characterizes network traffic patterns and adjusts the total congestion value to remove or restore the minimal path bias dynamically, based on the type of traffic pattern, to ensure fair routing decisions across output ports.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If static minimal path biases are used for routing decisions, then routing simplicity is maintained, but fairness in traffic patterns deteriorates during network saturation
Solution Approach 1:
The patent applies dynamics by transitioning from static minimal path biases to dynamic congestion values that adapt based on traffic patterns. The system monitors traffic patterns and adjusts congestion values in real-time, allowing the routing mechanism to respond to changing network conditions while maintaining fairness during saturation
Solution Approach 2:
The patent changes the parameter from fixed minimal path bias to variable congestion values. By modifying the congestion value parameter based on detected traffic patterns (such as permutation workloads), the system achieves fair routing decisions without sacrificing operational simplicity
2Reliability
If adaptive routing adjusts congestion values dynamically, then fairness in traffic routing is improved, but system complexity increases
Solution Approach 1:
The patent implements feedback by monitoring traffic patterns and using this information to adjust congestion values. The system continuously observes network conditions and feeds this information back into the routing decision-making process, achieving fairness through a closed-loop control mechanism that manages complexity systematically
Solution Approach 2:
The system performs self-service by automatically detecting traffic patterns and adjusting its own congestion values without external intervention. This autonomous adaptation reduces the need for complex manual configuration while maintaining fair routing decisions
Data Source
AI summary
Technologies for adaptive routing based on network traffic pattern characterization include a network switch configured to receive a network packet via one of a plurality of input ports and identify a set of the plurality of output ports associated with a path usable to forward the received network packet to a destination computing device along. The network switch is further configured to adjust a total congestion value for each of the set of output ports based on a type of the path to which each of the set of output ports corresponds and a value of a minimal path counter to which each of the set of output ports corresponds and enqueue the received network packet into an output buffer queue of one of the set of output ports based on the total congestion value. Other embodiments are described herein.