Spotlight: Scalable Transport Layer Load Balancing for Data Center Networks

TL;DR

Spotlight is a scalable, distributed load balancing system for data center networks that improves traffic distribution efficiency by using real-time load information and maintains connection consistency.

Contribution

It introduces a novel stateful flow dispatcher with distributed control and in-band dispatching, enabling scalable and efficient load balancing in data centers.

Findings

More efficient traffic distribution compared to existing methods

Achieves near-optimal service utilization

Operates effectively with low polling frequency (around 100ms)

Abstract

Load Balancing plays a vital role in modern data centers to distribute traffic among instances of network functions or services. State-of-the-art load balancers such as Silkroad dispatch traffic obliviously without considering the real-time utilization of service instances and therefore can lead to uneven load distribution and suboptimal performance. In this paper, we design and implement Spotlight, a scalable and distributed load balancing architecture that maintains connection-to-instance mapping consistency at the edge of data center networks. Spotlight uses a new stateful flow dispatcher which periodically polls instances' load and dispatches incoming connections to instances in proportion to their available capacity. Our design utilizes distributed control plane and in-band flow dispatching and thus scales horizontally in data center networks. Through extensive flow-level simulation and packet-level experiments on a testbed, we demonstrate that compared to existing methods Spotlight distributes the traffic more efficiently and has near-optimum performance in terms of overall service utilization. Moreover, Spotlight is not sensitive to utilization polling interval and therefore can be implemented with low polling frequency to reduce the amount of control traffic. Indeed, Spotlight achieves the mentioned performance improvements using O(100ms) polling interval.