Disruption budgets and the capacity left behind
Plan an inference-service node drain with a scoped disruption budget, replacement-capacity checks and a practical maintenance worksheet.
Guides, news and explanations about AI and reliable systems.
Product & project coverage
Read our reporting and practical analysis of Kubernetes. Explore the articles below for the product details, examples and source material behind each story.
Not sure where to begin? Choose a short reading path, or browse at your own pace.
Plan an inference-service node drain with a scoped disruption budget, replacement-capacity checks and a practical maintenance worksheet.
Memory throttling may keep an inference process alive while its answer arrives late. Follow the effective settings, memory pressure and completed requests together.
An upgrade can keep records flowing while searches and paging routes lose their match. Follow a known task through Kubernetes metadata to its responding team.
Follow a packaged program through Kubernetes placement, health checks and resources, then trace the customer job it still needs to finish.