Google's New Load Balancer, PReQuaL: Beyond CPU Load Balancing

Google Research presented PReQuaL (Probing to Reduce Queuing and Latency), a novel load balancer, at NSDI 2024. Unlike traditional CPU load balancing, PReQuaL actively probes server latency and active requests to select servers, dramatically reducing tail latency, error rates, and resource consumption in systems like YouTube. Deployed in YouTube for over a year, PReQuaL has significantly improved system utilization. This innovative approach challenges conventional wisdom and offers a new paradigm for high-performance distributed systems.