Leaf Spine Network Congestion Notification via Control Flags
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing network congestion management techniques, such as back off algorithms and prioritization, are inadequate for addressing congestion in leaf and spine networks, which can lead to inefficiencies in data transfer.
Innovation Solution
A method is introduced where control information with flags indicating link congestion is used to determine whether to create a flow entry or avoid a spine node, allowing for intelligent routing decisions based on congestion levels, with the 'Flow Learn Flag' and 'Flow Freeze Flag' indicating specific threshold conditions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If back off algorithms and prioritization are used for congestion avoidance, then some level of congestion management is achieved, but the solution is inadequate for leaf and spine networks and does not adequately address congestion conditions
Solution Approach 1:
The patent implements congestion management tailored specifically for leaf and spine network topologies by introducing topology-aware routing that considers the hierarchical structure. Different routing behaviors are applied based on the network role (leaf vs. spine) and congestion conditions at specific locations, rather than applying uniform congestion avoidance algorithms across the entire network.
Solution Approach 2:
The system dynamically adjusts routing decisions based on real-time congestion conditions detected through control information exchange between leaf and spine switches. The routing path is not static but adapts continuously according to current network state, allowing the system to respond to changing congestion patterns in the leaf-spine topology.
2Productivity
If traditional congestion avoidance methods are applied, then general congestion control is provided, but data transfer efficiency in leaf and spine networks is not optimized
Solution Approach 1:
The patent establishes a feedback mechanism where leaf switches send control information to spine switches about congestion conditions, and spine switches respond by adjusting their routing decisions. This closed-loop feedback system enables continuous optimization of data transfer efficiency while maintaining adequate congestion control through iterative adjustments based on actual network performance.
3Ease of operation
If congestion is addressed using conventional algorithms, then basic congestion control is achieved, but intelligent routing decisions based on congestion levels cannot be made
Solution Approach 1:
The system performs preliminary actions by having leaf switches proactively send control information to spine switches before congestion becomes severe. This advance notification allows spine switches to prepare alternative routing paths and make intelligent routing decisions before congestion impacts data transfer, reducing the need for complex real-time reaction mechanisms.
Data Source
AI summary
Methods and systems to alleviate congestion in leaf and spine network topologies. Control information may be advertised by spines regarding the leaves to which it is connected. The control information is advertised to other leaf switches connected to the advertising spine. The control information may include a destination leaf ID, an enroute spine ID, an FL flag and an FF flag. The FL flag is a “Flow Learn Flag,” that is set by the advertising spine that a leaf switch toward which the spine may be facing congestion above at a first predetermined threshold level. The FF flag is a “Flow Freeze Flag,” that is set when all links to the corresponding destination leaf identified are congested, and the congestion level has crossed a second predetermined threshold level.