Anycast Server Latency Measurement and Dynamic Rerouting

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

In Anycast network routing protocols, servers can become congested, leading to increased latency and performance issues, as clients are often directed to servers that may not be the most efficient due to lack of knowledge about alternative servers with lower latency.

Innovation Solution

A system and method that determines latency between a client device and multiple servers by initiating a redirect process, where the client sends requests to different servers, allowing the first server to measure and compare latency, and reroute subsequent requests to the server with lower latency if a threshold is met.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If a single IP address is associated with multiple servers in Anycast network routing, then network coverage and accessibility are improved, but server congestion and latency increase when clients are directed to overloaded servers

Engineering Contradiction:

Improvenetwork coverageVSAvoidlatency

Core Design Contradiction:

Adaptability or versatilityVSLoss of time

Solution Approach 1:

The system implements feedback by measuring latency between client devices and multiple servers, then using this measured data to dynamically redirect client requests. The latency measurement process provides real-time feedback about server performance, enabling the system to adapt routing decisions based on actual network conditions rather than static Anycast routing alone.

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The system transitions from static Anycast routing to dynamic routing by continuously measuring latency and redirecting client requests based on real-time conditions. The routing decision is no longer fixed but adapts dynamically based on measured performance metrics, allowing the system to respond to changing network conditions and server loads.

Inventive Principle:

Principle #15Dynamics

2Productivity

If latency measurement and redirect processes are implemented, then network performance and response time are improved, but system complexity and measurement overhead increase

Engineering Contradiction:

Improvenetwork performanceVSAvoidsystem complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The system performs self-service by having servers measure their own latency to client devices and autonomously make routing decisions based on these measurements. Each server independently measures latency, compares it with other servers, and redirects requests without requiring complex external control systems, thereby reducing overall system complexity while maintaining performance benefits.

Inventive Principle:

Principle #25Self-service

3Reliability

If multiple servers are used in Anycast network, then load distribution and network reliability are improved, but difficulty in determining optimal server selection increases

Engineering Contradiction:

Improvenetwork reliabilityVSAvoidoptimal server selection

Core Design Contradiction:

ReliabilityVSDifficulty of detecting and measuring

Solution Approach 1:

The system replaces complex manual or heuristic server selection mechanisms with automated latency measurement and comparison. Instead of relying on static routing tables or complex algorithms to determine optimal server selection, the system uses direct latency measurements to objectively identify the best server, simplifying the decision-making process while improving reliability.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS12015665B2Network optimization system using server latency measurements

Publication Date: 2024.06.18 SANDPIPER CDN LLC

AI summary

The present application describes a system and method for determining a latency between a client device and various servers of a networking system.