As a k8s cluster admin your app teams have a certain expectation of your cluster to be available to deploy services at any time without problems. SLOs (Service Level Objectives) allow you to describe this as a contract and enables you to ensure that your k8s clusters are always available and ready to handle the desired workload.
While there is no shortage on metrics in k8s, it’s important to have the right metrics to alert on issues and give you enough data to react to potential availability issues. eBPF is the perfect technology that fulfills that requirement as it gives us information down to the kernel level.
Join this session and learn about:
- The important eBPF metrics suitable for SLOs
- How to collect them via Prometheus using the epbf_exporter by CloudFlare
- How to use them for SLOs that allow you to always provide a healthy k8s cluster to your dev teams