Virtual Tunnel Credit Routing for Low-Latency Network Throughput
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing flow congestion management systems in network-based systems are reactive, create feedback delays, and are not scalable, leading to inefficiencies in data packet transmission.
Innovation Solution
Implementing a virtual tunnel with multiple data flow paths and credit-based congestion prevention, allowing the source to adjust data packet scheduling and routing to reduce congestion and increase throughput.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If reactive flow congestion management is used, then congestion can be removed, but feedback delay and potential overshoot occur
Solution Approach 1:
The patent implements proactive congestion management by monitoring flow path conditions and adjusting transmission rates before congestion occurs. The system uses credit-based mechanisms and multiple flow paths to preemptively manage data transmission, avoiding the feedback delay inherent in reactive approaches. This allows the system to maintain optimal transmission rates without waiting for congestion to manifest and then respond.
2Productivity
If single flow path congestion management is used, then the managed flow path can be optimized, but scalability is limited
Solution Approach 1:
The patent segments the network traffic into multiple independent flow paths between source and destination endpoints. Each flow path can be independently managed and optimized, allowing the system to handle multiple concurrent flows simultaneously. This segmentation enables scalability as the system can dynamically allocate and manage multiple flow paths without being constrained to a single path.
Solution Approach 2:
The congestion management system is designed to universally handle multiple flow paths and different types of network traffic simultaneously. The credit-based mechanism and flow path management architecture can be applied across various network configurations and traffic patterns, making the system scalable and adaptable to different network scenarios beyond a single flow path.
3Productivity
If high transmission rates are used, then throughput can be increased, but congestion occurs in the flow path
Solution Approach 1:
The patent implements a credit-based feedback mechanism where the destination endpoint sends credits to the source endpoint based on available buffer space and flow path conditions. The source endpoint uses these credits to regulate transmission rates, dynamically adjusting to maintain high throughput while avoiding congestion. This continuous feedback loop enables the system to optimize transmission rates in real-time without causing congestion.
Solution Approach 2:
The system dynamically adjusts transmission rates across multiple flow paths based on real-time network conditions, credit availability, and flow path status. Rather than using a fixed transmission rate, the system continuously adapts its behavior to maintain optimal throughput while preventing congestion, making the transmission process flexible and responsive to changing network conditions.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A method for managing network traffic is shown. The method includes establishing a virtual tunnel between a source endpoint and a destination endpoint, the virtual tunnel including a plurality of data flow paths, each of the plurality of data flow streams connecting the source endpoint and the destination endpoint. The method includes providing, via the destination endpoint, a plurality of credits to the source endpoint, the plurality of credits provided via two or more of the plurality of data flow paths. The method includes updating, at the source endpoint, a data transmission sequence based on the received plurality of credits. The method includes providing a plurality of data packets based on the data transmission sequence to the destination endpoint.