Edge Router Migration for Cloud Network Load Balancing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current VPN solutions in public cloud VPCs face performance degradation due to oversubscription of north-south bandwidth, especially with smaller packet sizes, and are limited in optimizing resource utilization across multiple compute gateways, leading to inefficient scaling and management of edge routers.
Innovation Solution
A method for configuring edge routers in a network by deploying higher-level and lower-level edge routers, with controllers monitoring load thresholds and migrating lower-level edge routers to optimize resource distribution across compute nodes, ensuring efficient handling of north-south and east-west traffic.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If a single edge cluster is used for all VPNs including T0 and T1, then resource sharing is achieved, but performance degrades due to bandwidth oversubscription
Solution Approach 1:
The patent segments the single edge cluster into multiple edge clusters, each dedicated to specific gateway types (T0 or T1). This segmentation prevents resource contention between different VPN types while maintaining resource sharing within each cluster, thereby resolving the performance degradation caused by oversubscription.
2Reliability
If north-south bandwidth limit is set to 1 Gbps for each CFC T1 gateway, then QoS is ensured, but SDDC north-south bandwidth is oversubscribed
Solution Approach 1:
The patent applies local quality by setting different bandwidth limits for different gateway types based on their specific requirements. T0 gateways receive higher bandwidth allocation while T1 gateways receive lower allocation, optimizing overall bandwidth utilization while ensuring each gateway type receives appropriate QoS guarantees.
3Stability of the object's composition
If VPN on edge gateway is limited to approximately 7 Gbps, then system stability is maintained, but scaling to multiple SDDCs is restricted
Solution Approach 1:
The patent transitions from a single-dimension limitation (7 Gbps per edge gateway) to a multi-dimensional architecture where multiple edge clusters can be deployed across different SDDCs. This dimensional expansion allows the system to scale horizontally while maintaining stability through distributed architecture and load balancing.
4Quantity of substance
If multiple lower-level edge routers are deployed on a single compute node, then resource consolidation is achieved, but load imbalance and overload occur
Solution Approach 1:
The patent implements dynamic load balancing and automated router migration capabilities that allow lower-level edge routers to be dynamically relocated between compute nodes based on real-time load conditions. This dynamic adjustment prevents overload while maintaining high router density through efficient resource consolidation.
Data Source
AI summary
Some embodiments provide a novel method for configuring edge routers in a first network. The method configures on a first compute node of the first network (1) a first higher-level edge router and (2) a set of lower-level edge routers. Each lower-level edge router is configured for a different set of subnetworks defined in the first network and is connected to an external second network through the first higher-level edge router. The method detects a condition that requires a particular lower-level edge router for a particular subnetwork to be moved to another compute node. The method configures the particular lower-level edge router to operate on a second compute node below a second higher-level edge router operating on the second compute node to connect the particular lower-level edge router to the external second network.