Dynamic CIDR Block Remapping for Edge Gateway Traffic Balancing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In software-defined data centers (SDDCs), traffic oversubscription at edge service gateways (ESGs) leads to congestion, increased latency, and packet drops due to uneven traffic distribution across active edges, which is exacerbated by horizontal scaling that can result in some edges being oversubscribed while others remain underutilized.
Innovation Solution
A method that involves monitoring traffic metrics to detect congestion, dividing classless inter-domain routing (CIDR) blocks between oversubscribed and underutilized active edges, and updating the routing table to redistribute IP addresses and alleviate congestion by remapping CIDR blocks from congested edges to less busy ones.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If horizontal scaling is implemented by adding more active/standby edge pairs to support higher bandwidth, then the bandwidth capacity increases, but traffic oversubscription occurs at certain active edges while other edges remain underutilized
Solution Approach 1:
The patent implements dynamic load balancing by continuously monitoring traffic metrics (packets per second, bandwidth utilization) at active edges and automatically remapping CIDR blocks from oversubscribed edges to underutilized edges. This dynamic adjustment resolves the contradiction by maintaining balanced traffic distribution across scaled edge infrastructure, preventing oversubscription while preserving the increased bandwidth capacity.
Solution Approach 2:
The system changes routing parameters (CIDR block assignments) based on real-time traffic conditions. When traffic metrics indicate oversubscription at an active edge, the system remaps portions of the CIDR block to different active edges, thereby adjusting the traffic distribution parameters to eliminate congestion while maintaining overall bandwidth capacity.
2Productivity
If traffic is concentrated at certain active edges, then those edges can handle high PPS, but congestion and packet drops occur due to oversubscription
Solution Approach 1:
The patent segments the CIDR block into multiple sub-CIDR blocks and redistributes them across different active edges based on traffic conditions. This segmentation prevents any single active edge from becoming oversubscribed by dividing the traffic load, thereby maintaining both high PPS handling capability and packet delivery reliability through balanced distribution.
Solution Approach 2:
The system implements feedback mechanisms by continuously monitoring traffic metrics at active edges and using this information to make real-time remapping decisions. When congestion is detected (high PPS causing packet drops), the system responds by remapping CIDR blocks to reduce load on congested edges, thus maintaining reliability while preserving productivity.
3Device complexity
If CIDR blocks are statically assigned to active edges, then routing configuration is simple, but traffic imbalance occurs leading to congestion and increased latency
Solution Approach 1:
The patent transitions from static CIDR block assignment to dynamic remapping based on real-time traffic metrics. The system automatically adjusts CIDR block assignments to balance traffic load, preventing congestion and reducing latency. This dynamic approach increases routing configuration complexity only minimally while dramatically improving traffic latency performance.
4Reliability
If multiple active/standby edge pairs are deployed, then high availability is achieved, but some edges become oversubscribed while others remain underutilized
Solution Approach 1:
The patent merges the traffic loads across multiple active edges by dynamically remapping CIDR blocks from oversubscribed edges to underutilized ones. This merging of traffic flows ensures that all active edges in the high-availability configuration are utilized efficiently, preventing waste of infrastructure resources while maintaining the reliability provided by multiple active/standby pairs.
Data Source
AI summary
An example method of mitigating oversubscription of traffic to edge services gateways in a data center includes: receiving, by a host of the data center, traffic metrics corresponding to the ESGs; determining traffic congestion at a first active edge of the ESGs in response to the traffic metrics; dividing, in response to the traffic congestion, a classless inter-domain routing (CIDR) block assigned to the first active edge into a first CIDR block and a second CIDR block; and creating, in a routing table of a router, a first route between an internet protocol (IP) address of the first active edge and the first CIDR block, and a second route between an IP address of a second active edge of the ESGs and the second CIDR block.