Coursera Spring Sale
40% Off Coursera Plus Annual!
Grab it
Learn from hard-won lessons in designing and operating a large-scale Level 4 load balancing service in this 34-minute conference talk from SREcon25 EMEA. Discover critical design decisions including the choice of DPDK over eBPF/XDP for the data plane, implementation of BGP path prepending for safer node degradation, adoption of local health checks, and construction of a decentralized peer-to-peer control plane designed to survive network partitions. Explore how focusing observability on Critical User Journeys (CUJs) enhanced monitoring and incident response capabilities. Gain practical insights into building robust, scalable infrastructure with real-world trade-offs and operational strategies applicable across distributed systems, presented by Linhua Tang and Jayaganesh Kalyanasundaram from Huawei Ireland Research Center for engineers, SREs, and architects working on high-performance, resilient, and reliable systems.
