Decentralized Control Plane for SDN Resilience
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Centralized control planes in software-defined networking (SDN) environments are prone to single points of failure, struggle with high memory usage and computing complexity, and fail to keep up with rapid changes in large-scale environments.
Innovation Solution
A decentralized control plane approach is implemented, where transport nodes maintain the state of the logical overlay network by communicating with each other, using a global list of nodes and neighbor index values to distribute updates, eliminating the need for a central controller.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If a centralized control plane is used, then control plane functionality is consolidated and management is simplified, but the system creates a single point of failure and increases memory usage and computing complexity
Solution Approach 1:
The control plane is segmented and distributed across multiple transport nodes in the overlay network. Each transport node maintains a portion of the network state and participates in control plane operations, eliminating the single point of failure while maintaining coordinated control through the global list and neighbor index mechanisms
2Ease of operation
If a centralized control plane is used, then control decisions are centralized, but memory usage and computing complexity increase significantly in large scale environments
Solution Approach 1:
The network state and control plane functionality are segmented and distributed across multiple transport nodes. Each node maintains only the portion of state relevant to its neighbors, reducing individual memory usage and computing complexity while maintaining overall network control through coordinated updates via the global list and neighbor index
3Ease of operation
If a centralized control plane is used, then control updates are managed centrally, but the system fails to keep up with rapid changes in large scale environments
Solution Approach 1:
Control update management is segmented and distributed across multiple transport nodes. Each node independently processes and propagates updates to its neighbors, enabling parallel update propagation that keeps pace with rapid changes in large scale environments while maintaining coordinated control through the global list and neighbor index mechanisms
Solution Approach 2:
The control plane becomes dynamic and adaptive, with transport nodes continuously updating their state and propagating changes through the overlay network. The system dynamically responds to rapid changes by distributing update propagation across multiple nodes rather than relying on a single centralized controller
Data Source
AI summary
The disclosure provides an approach for decentralizing control plane operations in a network environment that includes transport nodes configured to implement a logical overlay network. A method includes transmitting a global list of transport nodes to each of the plurality of transport nodes from a management plane, the global list including an ordered list of the plurality of transport nodes. The method also includes transmitting a neighbor index value to each of the plurality of transport nodes, where the transport nodes each compute a corresponding list of neighbor transport nodes based on the neighbor index value and the global list of transport nodes. The method also includes, based on determining an update to a state of the logical overlay network has occurred by a first transport node, transmitting an update message from the first transport node to each transport node in the first transport node's list of neighbor transport nodes.