Feb 24
Loading video player...
In this AMA session, Viktor and Scott dive into a wide range of DevOps and platform engineering topics submitted by their live audience. They explore the pros and cons of push versus pull-based observability models, discussing when Prometheus and OpenTelemetry each make sense, particularly in Kubernetes environments. The conversation covers the evolving role of Kubernetes engineers, with both hosts emphasizing that Kubernetes is becoming table stakes and the industry is shifting toward broader platform engineering responsibilities. The duo tackles questions about replacing OpenShift with alternatives like Spectro Cloud and Rancher, the value of certifications like Red Hat's RHCSA and the CKA, and feature flagging solutions built on the OpenFeature spec. They also discuss progressive delivery strategies using tools like Argo Rollouts, the relationship between service mesh and canary deployments, and practical tips for implementing Carpenter for node autoscaling. The session wraps up with insights on Backstage as an internal developer platform, the growing importance of MCP servers in agentic workflows, and recommendations for keeping internal components updated using Renovate or Dependabot. ▬▬▬▬▬▬ ⏱ Timecodes ⏱ ▬▬▬▬▬▬ 00:00 Intro (skip to first question) 10:30 Push vs pull-based observability in Kubernetes 18:00 Future of Kubernetes engineer jobs in 2026 22:47 Alternatives to OpenShift for bare metal clusters 29:44 Is Red Hat RHCSA certification worth getting? 32:00 Preferred feature flagging solution or platform 35:44 Canary releases: Argo Rollouts vs Istio service mesh 42:00 Using Agones for video game servers on Kubernetes 42:40 Should I learn to develop a Kubernetes operator? 43:51 Tips for adding Karpenter to a cluster 48:59 Will building MCPs be required for DevOps/infra? 54:40 OpenShift with HA Proxy for canary deployments 56:18 Does progressive delivery help release safely? 59:15 Key features that make Backstage stand out 1:07:02 Migrating EC2 services to Kubernetes with KubeVirt 1:10:11 Best technique to keep internal components updated