KnapsackLB: Enabling Performance-Aware Layer-4 Load Balancing

TL;DR

KnapsackLB is a performance-aware layer-4 load balancing system that dynamically optimizes backend response latency without requiring agents, scaling efficiently to large systems, and significantly reducing latency.

Contribution

It introduces a generic, agentless load balancing approach that uses active probes and ILP optimization to adapt to backend performance variations.

Findings

Reduces average latency by up to 45% in experiments.

Works with various load balancers and scales to many DIPs.

Does not require agents on DIPs, LBs, or clients.

Abstract

Layer-4 load balancer (LB) is a key building block of online services. In this paper, we empower such LBs to adapt to different and dynamic performance of backend instances (DIPs). Our system, KNAPSACKLB, is generic (can work with variety of LBs), does not require agents on DIPs, LBs or clients, and scales to large numbers of DIPs. KNAPSACKLB uses judicious active probes to learn a mapping from LB weights to the response latency of each DIP, and then applies Integer Linear Programming (ILP) to calculate LB weights that optimize latency, using an iterative method to scale the computation to large numbers of DIPs. Using testbed experiments and simulations, we show that KNAPSACKLB load balances traffic as per the performance and cuts average latency by up to 45% compared to existing designs.