DNS-based Ingress Load Balancing: An Experimental Evaluation

TL;DR

This paper experimentally evaluates DNS-based ingress load balancing at Georgia Tech, demonstrating that a window-based measurement scheme can achieve accurate load distribution despite known DNS limitations.

Contribution

It provides an empirical assessment of simple load balancing algorithms in real-world DNS-based systems, highlighting the importance of window configuration for accuracy.

Findings

Window-based measurement can be accurate with proper configuration

DNS load balancing effectiveness depends on workload characteristics

Simple algorithms can be robust despite DNS-related issues

Abstract

Multihomed services can load-balance their incoming connection requests using DNS, resolving the name of the server with different addresses depending on the link load that corresponds to each address. Previous work has studied a number of problems with this approach, e.g., due to Time-to-Live duration violations and client proximity to local DNS servers. In this paper, we experimentally evaluate a DNS-based ingress traffic engineering system that we deployed at Georgia Tech. Our objective is to understand whether simple and robust load balancing algorithms can be accurate in practice, despite aforementioned problems with DNS-based load balancing methods. In particular, we examine the impact of various system parameters and of the main workload characteristics. We show that a window-based measurement scheme can be fairly accurate in practice, as long as its window duration has been appropriately configured.