Virtual Network Stack Transport Layer Selection

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current network configurations lack the ability to efficiently select and switch transport layer implementations on virtual network stacks with minimal downtime, which hampers network performance and flexibility.

Innovation Solution

The method involves obtaining and configuring multiple virtual network stacks, allowing for the selection and testing of different transport layer implementations on a host before deployment, enabling switching with minimal downtime by using virtual NICs and transport layer implementations that include tunables such as protocols and congestion control algorithms.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If multiple virtual network stacks are configured with different transport layer implementations, then network flexibility and performance optimization are improved, but device complexity increases

Engineering Contradiction:
Improvenetwork flexibilityVSAvoiddevice complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The network stack is segmented into multiple virtual network stacks (VNS), each capable of running independent transport layer implementations. This segmentation allows different transport protocols and congestion control algorithms to be tested and deployed in isolated environments without affecting the entire system, thereby improving network flexibility while managing complexity through modular organization.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The virtual network stack architecture provides multi-functionality by supporting multiple transport layer implementations (TCP, UDP, SCTP, etc.) and various congestion control algorithms within a single unified framework. This universal design allows the system to adapt to different network conditions and requirements without requiring separate dedicated systems for each protocol.

Inventive Principle:
Principle #6Universality (Multi-functionality)

2Productivity

If transport layer implementations are switched on virtual network stacks, then network performance optimization is improved, but network downtime increases

Engineering Contradiction:
Improvenetwork performanceVSAvoidnetwork downtime
Core Design Contradiction:
ProductivityVSLoss of time

Solution Approach 1:

Multiple transport layer implementations are pre-configured and loaded within the virtual network stack before runtime. This preliminary preparation allows the system to switch between implementations instantly when performance optimization is needed, without requiring lengthy reconfiguration or reloading processes, thereby minimizing network downtime while achieving performance optimization.

Inventive Principle:
Principle #10Preliminary action

3Adaptability or versatility

If multiple virtual network stacks are obtained and configured, then selection and testing of transport layer implementations is improved, but configuration complexity increases

Engineering Contradiction:
Improveselection and testing capabilityVSAvoidconfiguration complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

A virtualization layer acts as an intermediary between the physical network interface and multiple virtual network stacks. This intermediary manages the configuration, instantiation, and switching of multiple VNS instances, abstracting the complexity from the user while enabling comprehensive testing and selection of different transport layer implementations through standardized interfaces.

Inventive Principle:
Principle #24Intermediary (Mediator)

Data Source

PatentUS8447880B2Network stack instance architecture with selection of transport layers
Publication Date: 2013.05.21 ORACLE AMERICAN INC
  • US8447880B2 patent drawing
  • US8447880B2 patent drawing
  • US8447880B2 patent drawing

AI summary

A method for configuring a network on a host includes obtaining a first virtual network stack and a second virtual network stack on the host, configuring a first transport layer implementation on the first virtual network stack, configuring a second transport layer implementation on the second virtual network stack, receiving a packet by the host, sending a packet to the first virtual network stack, and processing the packet using the first transport layer implementation.