Harvesting Randomness to Optimize Distributed Systems

We view randomization through the lens of statistical machine learning: as a powerful resource for offline optimization. Cloud systems make randomized decisions all the time (e.g., in load balancing), yet this randomness is rarely used for optimization after-the-fact. By casting system decisions in the framework of reinforcement learning, we show how to collect data from existing systems, without modifying them, to evaluate new policies, without deploying them. Our methodology, called harvesting randomness, has the potential to accurately estimate a policy's performance without the risk or cost of deploying it on live traffic. We quantify this optimization power and apply it to a real machine health scenario in Azure Compute. We also apply it to two prototyped scenarios, for load balancing (Nginx) and caching (Redis), with much less success, and use them to identify the systems and machine learning challenges to achieving our goal. Our long-term agenda is to harvest the randomness in distributed systems to develop non-invasive and efficient techniques for optimizing them. Like CPU cycles and bandwidth, we view randomness as a valuable resource being wasted by the cloud, and we seek to remedy this.