Kubenatives | Sharon Sahadevan | Substack

Architecture Template: vLLM Production Deployment on Kubernetes

Copy, configure, deploy. Every YAML file you need to run vLLM in production with monitoring, autoscaling, and model caching.

20 hrs ago • Sharon Sahadevan

Production Runbook: etcd NOSPACE Emergency Recovery

Your cluster just went read only. Here is how to fix it in under 10 minutes.

20 hrs ago • Sharon Sahadevan

Stacked vs External etcd: The Production Decision Nobody Explains

Why kubeadm’s default isn’t what you’ll find in production — and when it actually matters.

Mar 13 • Sharon Sahadevan

Production Runbook: GPU Pod Stuck in Pending

Debug runbook for GPU pods stuck in Pending on Kubernetes. GPU Operator failures, scheduling filters, MIG config, capacity planning, and prevention…

Mar 7 • Sharon Sahadevan

How Kubernetes Schedules GPUs: Device Plugins, MIG, and Time-Slicing

Kubernetes treats a $30K A100 like a CPU core as a simple integer. Here’s what actually happens when you request nvidia.com/gpu: 1 — and how to stop…

Mar 6 • Sharon Sahadevan

Most Popular

How I Solved a $50K Certificate Outage in 15 Minutes Using OSI Layers

Jul 22, 2025 • Sharon Sahadevan

The OSI Model: Not Academic BS - Here's Why It Matters in Production

Jul 17, 2025 • Sharon Sahadevan

DevOps to MLOps

Dec 16, 2025 • Sharon Sahadevan

SSL/TLS in Kubernetes: The Complete Mental Model

Jul 16, 2025 • Sharon Sahadevan

Kubenatives

About Archive Recommendations Sitemap

#nojs-banner { position: fixed; bottom: 0; left: 0; padding: 16px 16px 16px 32px; width: 100%; box-sizing: border-box; background: red; color: white; font-family: -apple-system, "Segoe UI", Roboto, Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol"; font-size: 13px; line-height: 13px; } #nojs-banner a { color: inherit; text-decoration: underline; } This site requires JavaScript to run correctly. Please turn on JavaScript or unblock scripts