Bio

My broad area of research is distributed systems and networking. I seek to build systems that both advance the state-of-the-art as well as the state of practice. At VMware Research, I’m currently leading efforts to simplify cluster management for large-scale distributed systems. I am currently driving two projects. Sieve (OSDI 22, KubeCon NA 21, HotOS 21) automatically tests Kubernetes controllers for reliability issues, and has discovered 40+ reliability bugs in popular open-source controllers. DCM (OSDI 20, HotOS 19) simplifies cluster manager development using declarative programming, allowing one to build things like high-performance Kubernetes schedulers using SQL. I have also worked on other topics like failure detection, programmable networking, remote memory, scalable data systems, and low-latency measurement. During my PhD, I invented techniques to deliver predictable performance for certain classes of distributed systems. C3 ships with ElasticSearch and OpenSearch, and influenced the design of Spotify’s ELS. Wisp is an end-to-end rate limiter for micro-services settings, currently being considered in some SaaS contexts. More info about my research and publications can be found here: https://lalith.in/research/