Arbitrating Mastership Between Redundant Control Planes

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Node virtualization in computer networks lacks hardware-level mastership arbitration, leading to 'split-brain' situations when multiple link faults occur, causing master and backup routing components to become isolated and resulting in service disruptions.

Innovation Solution

Implementing a mechanism where a management component detects reachability information and sends control messages to routing components, allowing them to arbitrate mastership based on this information, even in the presence of multiple link faults, thereby preventing split-brain conditions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If software-level arbitration is used for mastership between redundant control plane routing components, then hardware redundancy and node virtualization flexibility are improved, but the system becomes vulnerable to split-brain situations when multiple link faults occur

Engineering Contradiction:

Improvenode virtualization flexibilityVSAvoidmastership arbitration reliability

Core Design Contradiction:

Adaptability or versatilityVSReliability

Solution Approach 1:

The patent introduces a management component as an intermediary that mediates mastership arbitration between redundant control plane routing components. This component receives indications from both master and backup routing components and determines mastership based on these indications, preventing split-brain situations without requiring hardware-level arbitration mechanisms.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Reliability

If hardware-level mastership arbitration is used, then reliability against split-brain conditions is improved, but node virtualization and external server execution of routing components become impossible

Engineering Contradiction:

Improvemastership arbitration reliabilityVSAvoidnode virtualization capability

Core Design Contradiction:

ReliabilityVSAdaptability or versatility

Solution Approach 1:

The patent replaces hardware-level mechanical arbitration mechanisms with a software-based management component that performs mastership arbitration. This substitution enables external server execution of routing components and node virtualization while maintaining reliability through software-based indication reception and determination logic.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Productivity

If redundant control plane routing components are executed on external servers, then hardware resource utilization and flexibility are improved, but the risk of link faults causing isolation and split-brain conditions increases

Engineering Contradiction:

Improvehardware resource utilizationVSAvoidlink fault vulnerability

Core Design Contradiction:

ProductivityVSObject-affected harmful factors

Solution Approach 1:

The patent implements a feedback mechanism where the management component receives indications from redundant control plane routing components about their operational state. Based on these feedback indications, the management component determines and enforces mastership, allowing the system to adapt to link faults and prevent split-brain conditions while maintaining external server execution architecture.

Inventive Principle:

Principle #23Feedback

Data Source

PatentEP3515015B1Arbitrating mastership between redundant control planes of a virtual node

Publication Date: 2021.07.28 JUNIPER NETWORKS INC

Figure 1
Figure 2
Figure 3

AI summary

In one example, a management component executes on a network device, a first routing component executing on a first server device physically separate from the network device to provide control plane routing functionality for a virtual node on the network device, and a second routing component executing on a second server device physically separate from the network device to provide control plane routing functionality for the virtual node, wherein the first routing component and the second routing component operate as a redundant master-backup pair for the virtual node. The management component is configured to detect first reachability of the network device with a first routing component and second reachability of the network device with a second routing component, and send a control message to each of the first routing component and the second routing component, the control message specifying reachability information indicating the first reachability and the second reachability.