Scrambling Function for Load Balancer Traffic Fairness
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Load balancers using hash functions like CRC32 often result in unfair traffic distribution when dealing with non-uniform sequential data sets, leading to uneven workload distribution among compute nodes in data centers.
Innovation Solution
A software-based scrambling function is applied to re-map assignments of network traffic to load balancer bins, mitigating uneven distributions by identifying and addressing unfairness scenarios through a transparent layer that configures the underlying load balancer hardware without requiring modifications.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If a hash function like CRC32 is used for load balancing, then load balancing efficiency is improved, but traffic distribution fairness deteriorates with non-uniform sequential data sets
Solution Approach 1:
A software-based scrambling function is introduced as an intermediary layer between the hardware load balancer and the network traffic. This scrambling function processes the hash output from CRC32 before final destination mapping, transforming the unfair distribution pattern into a fair one while maintaining the efficiency benefits of hardware-based hashing.
Solution Approach 2:
The patent changes the parameter of the hash function by combining CRC32 with a scrambling function. Instead of using CRC32 alone, the system applies an additional transformation step that modifies the distribution characteristics of the hash output, converting non-uniform sequential distributions into uniform distributions across destinations.
2Device complexity
If hardware-based hash functions are programmed for cost considerations, then device complexity is reduced, but adaptability to different traffic patterns deteriorates
Solution Approach 1:
The software scrambling function serves multiple purposes: it corrects unfairness in sequential data distributions, maintains compatibility with existing hardware load balancers, and can be configured to handle different traffic patterns. This single software layer provides universal adaptability without requiring multiple hardware implementations.
Solution Approach 2:
The software scrambling function acts as a flexible intermediary that can be programmed to handle various traffic patterns and distribution scenarios, allowing the hardware load balancer to remain simple while the system as a whole becomes highly adaptable to different conditions.
Data Source
AI summary
Technologies for applying a scrambling function in unfair load balancing scenarios include a network device having a communication circuitry and compute engine executing software on the network device. The compute engine is to determine, using a load balancing function, a distribution for data sets to each of multiple bins. Each bin maps to a destination. The network device determines, as a function of the distribution, an unfairness score indicative of the distribution being unequal among each of the destinations. In response to a determination that the unfairness score exceeds a specified threshold, the network device enables a scrambling function to be performed during configuration of the plurality of bins with the destinations.