Stacked Switch LAG Routing Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In stacked switch configurations, the sub-optimal use of stacking link bandwidth leads to potential data drop due to bandwidth limitations, as standard ECMP routing techniques distribute data unevenly across member ports, overwhelming the available links.
Innovation Solution
An enhanced ECMP routing technique calculates a relative cost for each path and uses a minimum cost algorithm to reduce the number of stacking links data crosses, optimizing bandwidth utilization by selecting egress ports with reduced relative costs, and dynamically adjusting the topology in case of link failures.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If standard ECMP routing techniques are used to distribute data across member ports, then load balancing is achieved, but stacking link bandwidth is overwhelmed causing data drops
Solution Approach 1:
The patent changes the routing parameter from equal-cost distribution to variable-cost distribution based on stack depth. By calculating relative cost as 2^(stack depth), the system dynamically adjusts path selection parameters to prefer shallower paths, preventing bandwidth overwhelm while maintaining load balancing across multiple paths.
Solution Approach 2:
The patent creates a virtual copy of the routing decision process by implementing an enhanced ECMP algorithm that simulates multiple routing scenarios. The system calculates relative costs for different stack depths and uses hash-based selection to choose optimal egress ports, effectively copying the routing logic to account for bandwidth constraints without physical modification of the network topology.
2Adaptability or versatility
If data is forwarded through multiple stacking links to reach egress ports, then port availability is increased, but bandwidth limitations are exceeded
Solution Approach 1:
The system changes the cost parameter associated with each path based on stack depth. By assigning exponentially increasing costs (2^depth) to deeper paths, the routing algorithm naturally prefers shallower paths that consume less bandwidth, while still providing access to all egress ports through the stacked switch fabric.
3Productivity
If equal cost multipath routing is implemented, then path diversity is achieved, but uneven traffic distribution overwhelms certain links
Solution Approach 1:
The patent transforms the equal-cost routing parameter into a variable-cost parameter by calculating relative cost based on stack depth. This creates a graduated cost structure where shallower paths have lower costs and deeper paths have higher costs, guiding traffic distribution to be more efficient while maintaining path diversity.
Solution Approach 2:
The system implements feedback by continuously monitoring stack depth and adjusting routing decisions accordingly. The hash-based selection process incorporates real-time cost calculations that reflect current path characteristics, creating a feedback loop that optimizes traffic distribution based on actual network conditions and path costs.
Data Source
AI summary
A stacked switch includes two or more individual network switches connected to each other in a ring or daisy chain topology over stacking links, and at least one port on two or more of the individual switches comprising the stacked switch is a member of a LAG configured on the stacked switch. Each of the individual switches comprising the stacked switch include control plane and data plane functionality that operates to maintain switching tables and to process network data ingressing to the switch to determine how to forward the network data through the switch to an egress point. The control functionality included in each of the switches comprising the stacked switch also includes an enhanced ECMP functionality that operates to optimize the use of stacking link bandwidth on the stacking links connecting the two or more individual switches to each other.