Dynamic Switch Fabric Control Plane Resource Allocation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing networking systems with distributed control planes are not dynamically configured, leading to underutilization of some nodes and overutilization of others, resulting in inefficient operation.
Innovation Solution
A switch fabric system with multiple access switches, where ports are managed by different network control entities based on available processing capacity, allowing automatic reconfiguration to optimize resource allocation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If a centralized control plane is used to manage resources, then resource management capability is improved, but system complexity and scalability deteriorate when large numbers of resources are connected
Solution Approach 1:
The control plane is segmented into multiple distributed control entities, each managing a subset of resources. This divides the monolithic centralized control into smaller manageable units that can operate independently, reducing overall system complexity while maintaining resource management capabilities.
Solution Approach 2:
The patent introduces a hierarchical dimension to control plane architecture, with control entities organized in layers. This dimensional transformation allows the system to scale by adding control entities at different hierarchical levels rather than simply expanding a single centralized controller.
2Adaptability or versatility
If a distributed control plane is implemented at various nodes, then scalability is improved, but resource utilization efficiency deteriorates due to static configuration causing underutilization and overutilization
Solution Approach 1:
The control plane configuration is made dynamic through automatic initiation and termination of control entities based on real-time workload conditions. This allows the system to adapt resource allocation dynamically, preventing both underutilization and overutilization by scaling control entities according to actual needs.
Solution Approach 2:
The system implements feedback mechanisms that monitor workload conditions and automatically adjust control entity configuration. When workload increases, new control entities are initiated; when workload decreases, entities are terminated, creating a self-regulating system that optimizes resource utilization.
3Device complexity
If static distributed control plane configuration is used, then system simplicity is maintained, but operational efficiency deteriorates due to inability to adapt to changing workload conditions
Solution Approach 1:
The control plane implements self-service through automatic initiation and termination of control entities based on monitored workload conditions. This self-regulating mechanism eliminates the need for manual reconfiguration while maintaining operational simplicity, allowing the system to adapt efficiently to changing conditions without increasing complexity.
Data Source
Figure 1
Figure 2~3
Figure 4
AI summary
In some embodiments, a switch fabric system includes multiple access switches configured to be operatively coupled to a switch fabric. The multiple access switches include multiple ports each to be operatively coupled to a peripheral processing device. A first set of ports from the multiple ports and a second set of ports from the multiple ports are managed by a first network control entity when the switch fabric system is in a first configuration. The first set of ports is managed by the first network control entity and the second set of ports is managed by a second network control entity when the switch fabric system is in a second configuration. The second network control entity is automatically initiated when the system is changed from the first configuration to the second configuration.