Container Checkpoint/Restore at Scale for Fast Pod Startup Time

Using Container Checkpoint/Restore in Kubernetes to achieve fast pod startup time and pre-warming of container-based applications for faster cold start performance.

• Container Checkpoint/Restore can achieve both fast startup time and pre-warming of container-based applications for faster cold start performance
• MathWorks has been using Container Checkpoint/Restore at high scale since 2016
• Lessons learned and best practices for supporting container checkpoint/restore non-natively in Kubernetes
• Future enhancements for native support for CRIU in Kubernetes

Cold start is a main challenge that makes it difficult to achieve all three goals of a scalable system. One option is to scale out on demand with usage, but this does not do well with the goal of fast startup time. Another option is to keep the containerized application warm and ready to go, which involves initializing the application. Container Checkpoint/Restore can achieve both fast startup time and pre-warming of container-based applications for faster cold start performance.

Are you interested in a faster startup time for your container-based application? Are you also interested in pre-warming your container-based application for faster cold start performance? You can have your cake and eat it too!   In this talk, Ritesh Naik will talk about how MathWorks cloud infrastructure was able to achieve *both* of these seemingly contradictory goals, fast startup time and pre-warming, using Container Checkpoint/Restore. With several years of experiencing using this technique in production, Ritesh will share design considerations, lessons learned and best practices for supporting container checkpoint/restore non natively in Kubernetes. He will also share a vision for what native support for CRIU in Kubernetes can look like. If you are interested in improving system scalability and utilization, this session is for you!