SD-WAN Load Balancing Using Link State Path Selection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing SD-WAN solutions face challenges in reliable and resilient load balancing due to varying network path characteristics such as packet loss, latency, and jitter, which affect quality of service and experience across multisite deployments.
Innovation Solution
A method for network-aware load balancing in SD-WANs that utilizes link state data to select destination machines and datapaths based on criteria like packet loss, latency, jitter, and quality of experience, combined with load balancing policies to optimize data message distribution.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If load balancing is based on geo-proximity or destination machine load, then load distribution is simplified, but network path characteristics such as packet loss, latency, and jitter are not considered, degrading quality of service
Solution Approach 1:
The system performs preliminary probing of network paths to collect link state data (packet loss, latency, jitter) before making load balancing decisions. This advance information gathering allows the load balancer to select optimal paths based on actual network conditions rather than just geo-proximity or server load, thereby improving quality of service without significantly increasing operational complexity
Solution Approach 2:
The system continuously monitors network path characteristics and uses this feedback to dynamically adjust load balancing decisions. Link state data is collected from multiple probes and used to update the selection of destination machines and datapaths, ensuring that quality of service is maintained by adapting to changing network conditions in real-time
2Reliability
If multiple network links are used for redundancy, then resilience is improved, but network path variability in packet loss, latency, and jitter increases, affecting quality of experience
Solution Approach 1:
The system changes the selection parameters for load balancing from static criteria (geo-proximity) to dynamic parameters that account for network path characteristics (packet loss, latency, jitter). By monitoring and responding to variations in these parameters across multiple links, the system can select the most stable path for each data message, thereby maintaining resilience while minimizing the harmful effects of network variability on quality of experience
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Some embodiments of the invention provide a method for network-aware load balancing for data messages traversing a software-defined wide area network (SD-WAN) (e.g., a virtual network) including multiple connection links between different elements of the SD-WAN. The method includes receiving, at a load balancer in a multi-machine site, link state data relating to a set of SD-WAN datapaths including connection links of the multiple connection links. The load balancer, in some embodiments, provides load balancing for data messages sent from a machine in the multi-machine site to a set of destination machines (e.g., web servers, database servers, etc.) connected to the load balancer over the set of SD-WAN datapaths. The load balancer selects, for the data message, a particular destination machine (e.g., a frontend machine for a set of backend servers) in the set of destination machines by performing a load balancing operation based on the received link state data.