Serverless promises on-demand, optimal performance for a fixed cost. Yet, we see that the current serverless platforms do not always hold up this promise in practice; serverless applications can suffer from cold starts, platform overhead, and unreliable performance.
In his talk, Erwin investigates optimizations techniques used in current FaaS platforms and research that helps to optimize the trade-off between cost and performance. He reviews function reuse, autoscaling, resource pooling, function locality, predictive scheduling, and autoscaling.
To illustrate these practices along the way, he uses Fission, the open source, Kubernetes-native FaaS platform to demonstrate how you can achieve specific goals around latency, throughput, resource utilization, and cost.
He then takes a look at what’s to come for Serverless applications: where the opportunities and challenges lie, and how we cam make FaaS even faster?
To learn how to go FaaSter with serverless on Kubernetes, watch Erwin’s talk below:
To learn more about Fission and to install the open source Serverless framework, visit https://fission.io/