Leaf Switch Route Sharing in Disaggregated Scheduled Fabrics

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional leaf-spine fabrics lack a mechanism to share route information across multiple network devices, leading to inefficient packet forwarding and resource utilization.

Innovation Solution

Implementing a packet routing logic in leaf switches to identify host devices, determine routes, assign encapsulation indexes, and establish iBGP sessions to share reachability and operational status data, enabling dynamic updates to routing tables.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Speed

If packet forwarding decisions are made locally at each leaf switch, then forwarding speed is improved, but route information cannot be shared across multiple network devices

Engineering Contradiction:
Improvepacket forwarding speedVSAvoidroute information sharing
Core Design Contradiction:
SpeedVSLoss of information

Solution Approach 1:

The patent introduces iBGP sessions as an intermediary mechanism between leaf switches to share route information. Each leaf switch establishes iBGP sessions with other leaf switches to exchange reachability data and operational status, enabling distributed route information sharing while maintaining local forwarding decisions.

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent implements feedback mechanisms where leaf switches periodically or event-driven exchange update messages containing route information and operational status through iBGP sessions. This feedback loop enables each switch to learn about network topology changes and adjust routing decisions accordingly.

Inventive Principle:
Principle #23Feedback

2Adaptability or versatility

If conventional leaf-spine fabric architecture is used, then network scalability is maintained, but resource utilization efficiency deteriorates

Engineering Contradiction:
Improvenetwork scalabilityVSAvoidresource utilization efficiency
Core Design Contradiction:
Adaptability or versatilityVSLoss of energy

Solution Approach 1:

The patent introduces dynamic route sharing through iBGP sessions that respond to real-time network conditions. Leaf switches dynamically exchange reachability data and operational status, enabling adaptive routing decisions that optimize resource utilization based on current network state while preserving the scalable leaf-spine architecture.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The patent changes the operational parameters of the leaf-spine fabric by introducing iBGP protocol parameters (session establishment, update messages, extended community attributes) that enable intelligent resource management and efficient utilization while maintaining architectural scalability.

Inventive Principle:
Principle #35Parameter changes

3Device complexity

If static routing configurations are used, then device complexity is reduced, but latency increases due to lack of dynamic updates

Engineering Contradiction:
Improverouting configuration complexityVSAvoiddata packet latency
Core Design Contradiction:
Device complexityVSLoss of time

Solution Approach 1:

The patent enables leaf switches to autonomously exchange route information and operational status through iBGP sessions without requiring complex centralized control. Each switch self-manages its routing by receiving update messages from peers, processing reachability data, and autonomously adjusting forwarding decisions to minimize latency.

Inventive Principle:
Principle #25Self-service

Data Source

PatentUS12615202B2Packet routing in disaggregated scheduled fabrics
Publication Date: 2026.04.28 CISCO TECHNOLOGY INC
  • US12615202B2 patent drawing
  • US12615202B2 patent drawing
  • US12615202B2 patent drawing

AI summary

Devices, networks, systems, methods, and processes for packet forwarding and routing are described herein. A network device may be connected to a host device. The network device can identify an interface associated with the host device and determine an operational status of the interface. The network device can determine a host route and assign an encapsulation index associated with the host route. The network device may generate an update message based on the operational status and the encapsulation index. The network device can transmit the update message to one or more other network devices. The network device can also update one or more routing or forwarding tables to include routing information associated with the host device. The other network devices can extract the routing information from the update message and may utilize the routing information to route or forward one or more data packets addressed to the host device.