Traffic Manager for Data Center Routing Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Global foundation service teams face high costs and performance challenges in routing data traffic across wide area networks between geographically distributed data centers and internet service providers, with existing methods often relying on manual selection of default paths and lacking efficient optimization techniques.
Innovation Solution
A traffic manager system that identifies and measures available paths and source locations between online service providers and destination prefixes, optimizing data routing by selecting paths with minimized cost and performance values, and dynamically updating routing tables or DNS responses to implement the preferred path.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If manual selection of default paths is used, then ease of operation is improved, but productivity and cost efficiency deteriorate
Solution Approach 1:
The system automatically measures costs and performance metrics for multiple paths and autonomously selects optimal routing decisions without requiring manual human intervention. The traffic manager independently analyzes available paths, evaluates cost and performance characteristics, and implements routing optimizations, enabling the system to serve itself rather than relying on manual configuration.
Solution Approach 2:
The system dynamically changes routing parameters by selecting different paths based on measured cost and performance values. By continuously monitoring and comparing multiple path parameters (cost, round trip time, throughput, packet loss), the system adapts routing decisions to optimize productivity while maintaining operational simplicity through automation.
2Productivity
If multiple paths are manually evaluated, then productivity is improved, but device complexity and time consumption increase
Solution Approach 1:
The traffic manager automatically performs path evaluation and selection without requiring complex manual analysis. The system self-manages the complexity of evaluating multiple paths by autonomously measuring costs and performance metrics, thereby improving productivity while avoiding the complexity burden of manual multi-path evaluation.
Solution Approach 2:
The system replaces manual mechanical evaluation processes with automated digital measurement and analysis. Instead of human operators manually assessing multiple paths, the traffic manager uses automated tools to measure cost and performance parameters, substituting the mechanical manual process with an automated electronic system that achieves the same productivity goal with reduced complexity.
3Productivity
If automated path selection is implemented, then productivity is improved, but measurement precision requirements increase
Solution Approach 1:
The system continuously measures cost and performance parameters for available paths and uses this feedback to make automated routing decisions. By implementing feedback loops that monitor actual path performance and adjust selections accordingly, the system achieves improved productivity while managing measurement precision requirements through continuous validation and adaptation.
Data Source
AI summary
Techniques and systems for providing optimization of traffic routing for data centers are disclosed herein. In some embodiments, a method may include identifying a plurality of available source sites and paths or routes between an online service provider (OSP) and a destination prefix. A traffic manager may measure a cost for each of the plurality of available paths. In some instances, the traffic manager may also measure a performance value for each of the available paths. The traffic manager may then select one of the available source sites and paths as a preferred source site and path that has a minimized cost for an instance of the performance value when compared to other paths of the plurality of available source sites and paths. In further embodiments, the traffic manager may rewrite a routing table and DNS mapping to implement the preferred source site and path as the default source site and path between the OSP and the destination prefix.