Hierarchical Control Plane for Switch Fabric Scalability

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing networking systems with centralized or distributed control planes face challenges in managing and sharing forwarding-state information efficiently, especially in large-scale networks, leading to cumbersome manual updates and unmanageable systems.

Innovation Solution

A hierarchical control plane architecture where a compute device communicates with access switches to receive and send forwarding-state information, acting as a route reflector between network control entities, allowing for efficient sharing and management of forwarding-state information across the network.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If a centralized control plane is used to manage forwarding-state information, then resource management is simplified, but the system becomes unmanageable when a large number of resources are included

Engineering Contradiction:
Improveresource managementVSAvoidsystem scalability
Core Design Contradiction:
Ease of operationVSDevice complexity

Solution Approach 1:

The control plane is segmented into multiple distributed control plane nodes instead of a single centralized node. Each node manages a portion of the forwarding-state information, allowing the system to scale horizontally by adding more nodes as resources increase, thus maintaining manageability while handling large-scale networks

Inventive Principle:
Principle #1Segmentation

2Ease of operation

If forwarding-state information is manually configured at each node in a distributed control plane, then system autonomy is reduced, but manual control is achieved

Engineering Contradiction:
Improvemanual controlVSAvoidupdate time
Core Design Contradiction:
Ease of operationVSLoss of time

Solution Approach 1:

The system implements automated feedback mechanisms where control plane nodes automatically exchange and synchronize forwarding-state information. When changes occur, the system automatically detects and propagates updates across the distributed network, eliminating manual configuration time while maintaining system coherence through automated feedback loops

Inventive Principle:
Principle #23Feedback

3Adaptability or versatility

If frequent updates are made to a large scale networking system, then system adaptability is improved, but manual configuration becomes cumbersome

Engineering Contradiction:
Improvesystem adaptabilityVSAvoidconfiguration effort
Core Design Contradiction:
Adaptability or versatilityVSEase of operation

Solution Approach 1:

The distributed control plane nodes operate autonomously to self-configure and self-update forwarding-state information. The system automatically adapts to changes in network topology and resources without requiring manual intervention, enabling frequent updates while maintaining ease of operation through automated self-service mechanisms

Inventive Principle:
Principle #25Self-service

Data Source

PatentUS10033585B2Methods and apparatus related to a switch fabric system having a multi-hop distributed control plane and a single-hop data plane
Publication Date: 2018.07.24 JUNIPER NETWORKS INC
  • US10033585B2 patent drawing
  • US10033585B2 patent drawing
  • US10033585B2 patent drawing

AI summary

In some embodiments, an apparatus includes a compute device to communicate with a network control entity at each access switch from a set of access switches that define a portion of a data plane having a switch fabric coupling as hierarchical peers each access switch from the set of access switches. The compute device is operable to define a portion of a control plane that includes the network control entities from the set of access switches such that the compute device is hierarchically removed from the network control entities from the set of access switches. The compute device is operable to receive forwarding-state information from a first access switch from the set of access switches. The compute device to send the forwarding-state information to a second access switch from the set of access switches.