Super POD Repairing Fallen Leaves in SDN Fabric
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In software defined networking (SDN) fabrics, discovering and repairing disconnections between nodes in the spine layer and leaf layer is challenging, particularly in partitioned fabrics where redundancy is reduced, leading to fallen leaves and unbalanced network capacity.
Innovation Solution
Designating a super POD in the SDN fabric with total network visibility, receiving link state information through northbound advertisements, and using this information to identify and repair disconnections between leaf and spine nodes, either by establishing a route or initiating negative disaggregation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If SDN fabric is partitioned into multiple PODs, then network scalability and modularity are improved, but discovery of disconnections between spine and leaf nodes becomes more difficult
Solution Approach 1:
A border leaf node is introduced as an intermediary between PODs to detect disconnections. The border leaf monitors connectivity between spine nodes and other leaf nodes across POD boundaries, enabling disconnection discovery in partitioned fabrics without requiring changes to all nodes.
Solution Approach 2:
The system implements feedback mechanisms where border leaves continuously monitor link states and report disconnections to the network. This feedback loop enables dynamic detection and response to connectivity changes, allowing the network to adapt to partitioning while maintaining visibility into connection status.
2Productivity
If redundancy is reduced in partitioned fabrics, then network efficiency is improved, but network resilience deteriorates leading to fallen leaves
Solution Approach 1:
The border leaf is pre-configured with knowledge of spine nodes in other PODs and potential alternative paths. When a disconnection is detected, the border leaf can immediately initiate repair actions by establishing alternative routes through adjacent PODs, preventing fallen leaves before they impact network resilience.
Solution Approach 2:
The system dynamically adjusts routing paths and redundancy allocation based on real-time connectivity conditions. When disconnections are detected, the network dynamically creates alternative paths through border leaves, maintaining resilience without permanently increasing redundancy in all paths.
3Reliability
If centralized control is implemented, then network performance is improved, but complexity of control plane increases
Solution Approach 1:
The control plane complexity is segmented by distributing specific monitoring functions to border leaf nodes while maintaining centralized control for overall network management. This segmentation allows centralized control to focus on high-level decisions while local nodes handle specific disconnection detection and initial response actions.
Data Source
AI summary
In one embodiment, a plurality of PODs is formed in a software defined networking (SDN) fabric, each POD comprising a plurality of leaf nodes and connected to a plurality of spine nodes in a spine layer of the SDN fabric. One of the plurality of PODs is designated as a super POD and link state information is provided for the entire fabric to the super POD by sending northbound advertisements in the fabric to the super POD. A disconnection is identified between a leaf node in the SDN fabric and a particular one of the spine nodes in the spine layer, based on the link state information provided to the super POD. The disconnection is repaired between the leaf node and the particular spine node in the spine layer.