Thanos Unleashed: Mastering the Challenges of Production-Scale Metrics - Joel Verezhak, Open Systems

Don't miss out! Join us at our next Flagship Conference: KubeCon + CloudNativeCon Europe in Paris from March 19-22, 2024. Connect with our current graduated, incubating, and sandbox projects as the community gathers to further the education and advancement of cloud native computing. Learn more at kubecon.io
Thanos Unleashed: Mastering the Challenges of Production-Scale Metrics - Joel Verezhak, Open Systems
As a core component in our technology stack, Thanos has become indispensable to our customer-facing services, providing critical metrics that empower our service engineers to make informed decisions, and acting as the powerhouse behind our unified alerting pipeline. With more than 100 million metrics flowing from over 10'000 edge devices and 5'000 Kubernetes workloads into our central Kubernetes cluster, the scale of our deployment demands careful planning and diligent optimization. In this talk, we will dive into the practical challenges we encountered when bringing Thanos into production at a performance level that meets our customer's needs. We will discuss strategies for achieving high scalability, availability, and performance of the framework, both on the query and ingestion paths. The topics should be of interest to seasoned Thanos users and newcomers alike, whether the motivation is to optimize an existing deployment, or experience a case-study of how to use Thanos in production.