De Nederlandse Kubernetes Podcast

• #120 Let Them Cook — Inside the Kubernetes Recipes Cookbook

  In this episode, we sit down with Luca Berton and Grzegorz (Greg) Stencel, authors of the brand-new book Kubernetes Recipes — a 400+ page cookbook packed with real, practical solutions for everyday Kubernetes challenges.Luca and Greg explain how the idea for the book started: most Kubernetes books do a great job explaining theory, but very few show how to solve the messy, real-world issues engineers actually face. So instead of writing “yet another reference manual,” they chose the cookbook format: 👉 a problem, 👉 a clear solution, 👉 and deeper explanations when needed.We discuss:How they co-wrote the book late at night while balancing work, family life, and open source contributions.Why enterprise Kubernetes, especially in heavily regulated environments like finance, is a completely different beast.How their recipes cover everything from beginner topics to advanced CRDs, operators, networking, storage, NFS, stateful apps, and multi-cloud clusters.The tools that actually help developers — from KubeLens to vCluster.Why writing a book forces more accuracy and consistency than video tutorials.How they used real questions (including many from Stack Overflow) to choose the most relevant scenarios.We also talk about the future of Kubernetes:Luca sees AI workloads, better observability, and complexity-reducing tooling as the next big wave.Greg stresses that developer experience must improve — especially for developers suddenly expected to “learn Kubernetes” overnight. And yes, cluster upgrades remain painful.A fun and insightful conversation about practical Kubernetes knowledge, open source culture, and what engineers actually need today.Stuur ons een bericht.ACC ICT Specialist in IT-CONTINUÏTEIT Bedrijfskritische applicaties én data veilig beschikbaar, onafhankelijk van derden, altijd en overalSupport the showLike and subscribe! It helps out a lot.You can also find us on:De Nederlandse Kubernetes Podcast - YouTubeNederlandse Kubernetes Podcast (@k8spodcast.nl) | TikTokDe Nederlandse Kubernetes PodcastWhere can you meet us:EventsThis Podcast is powered by:ACC ICT - IT-Continuïteit voor Bedrijfskritische Applicaties | ACC ICT

  --------  

  24:02

  --------

  24:02
• #119 Your Web App Scaling Tricks Don’t Work for LLMs

  In this episode, we talk with Abdel Sghiouar and Mofi Rahman, Developer Advocates at Google and (guest) hosts of the Kubernetes Podcast from Google. Together, we dive into one central question: can you truly run LLMs reliably and at scale on Kubernetes?It quickly becomes clear that LLM workloads behave nothing like traditional web applications:GPUs are scarce, expensive, and difficult to schedule.Models are massive — some reaching 700GB — making load times, storage throughput, and caching critical.Containers become huge, making “build small containers” nearly impossible.Autoscaling on CPU or RAM doesn’t work; new signals like GPU cache pressure, queue depth, and model latency take over.LLMs don’t run in parallel, so batching and routing through the Inference Gateway API become essential.Device Management and Dynamic Resource Allocation (DRA) are forming the new foundation for GPU/TPU orchestration.Security shifts as rootless containers often no longer work with hardware accelerators.Guardrails (input/output filtering) become a built-in part of the inference path.And then there’s the occasional request from customers who want deterministic LLM output — to which Mofi dryly responds: “You don’t need a model — you need a database.”Powered by: ACC ICTStuur ons een bericht.ACC ICT Specialist in IT-CONTINUÏTEIT Bedrijfskritische applicaties én data veilig beschikbaar, onafhankelijk van derden, altijd en overalSupport the showLike and subscribe! It helps out a lot.You can also find us on:De Nederlandse Kubernetes Podcast - YouTubeNederlandse Kubernetes Podcast (@k8spodcast.nl) | TikTokDe Nederlandse Kubernetes PodcastWhere can you meet us:EventsThis Podcast is powered by:ACC ICT - IT-Continuïteit voor Bedrijfskritische Applicaties | ACC ICT

  --------  

  36:19

  --------

  36:19
• #118 Why Ceph Still Rules Cloud-Native Storage

  In this episode of De Nederlandse Kubernetes Podcast, we talk with Travis Nielsen, one of the original creators of the Rook project, about the evolution of cloud-native storage and how Rook and Ceph make reliable, distributed storage accessible to Kubernetes users.Travis shares the story of how Rook started back in 2016 when Kubernetes was still young and how it became the bridge that made Ceph, a powerful but complex storage system, usable in the cloud-native era.We discuss:What Ceph actually is and why it remains one of the most trusted open-source storage platforms.How Rook simplifies Ceph deployment and management inside Kubernetes clusters.The difference between NFS and CephFS, and when to use each.The best ways to run databases on Ceph and how to balance performance, consistency, and replication.Multi-tenancy, scaling, and failure domains  how Ceph handles massive distributed systems.Common mistakes people make when setting up Ceph and how to avoid them.The future of storage in the Kubernetes ecosystem and why Ceph remains essential for stateful workloads.A deep dive into the intersection of data durability, Kubernetes, and open source innovation  from someone who helped build it all.Stuur ons een bericht.ACC ICT Specialist in IT-CONTINUÏTEIT Bedrijfskritische applicaties én data veilig beschikbaar, onafhankelijk van derden, altijd en overalSupport the showLike and subscribe! It helps out a lot.You can also find us on:De Nederlandse Kubernetes Podcast - YouTubeNederlandse Kubernetes Podcast (@k8spodcast.nl) | TikTokDe Nederlandse Kubernetes PodcastWhere can you meet us:EventsThis Podcast is powered by:ACC ICT - IT-Continuïteit voor Bedrijfskritische Applicaties | ACC ICT

  --------  

  39:50

  --------

  39:50
• #117 How Policy as Code Is Changing Kubernetes Forever

  In this episode of De Nederlandse Kubernetes Podcast, we talk with Jim Bugwadia, founder and CEO of Nirmata, and Shuting Zhao, Staff Engineer and one of the maintainers of Kyverno — the CNCF project for Kubernetes policy management.Jim and Shuting share how Kyverno was born from Nirmata’s commercial work and has since become one of the most widely adopted open source projects in Kubernetes governance, with over 3.4 billion image pulls.We explore the real question: Why does Kubernetes need policies if it’s already declarative? Jim explains how policy as code helps developers, operators, and security teams collaborate on cluster configuration at scale — from pod security to resource quotas, network policies, and automation.Shuting dives deeper into how Kyverno enables granular control, policy exceptions, and flexible enforcement modes — from audit to enforce. They discuss how large organizations use policy automation to improve compliance, security, and even cost efficiency, citing use cases like Adidas saving 50% in dev/test environments using policy-driven resource management.We also touch on:🧠 The evolution of policy as code and its parallels with infrastructure as code (like Terraform)🧩 The role of AI in simplifying policy authoring (“I don’t want to run as root — just write the policy for me”)⚙️ Nirmata’s Control Hub, a collaboration layer for DevSecOps teams🔒 Shift-down security, where platform teams integrate security directly into Kubernetes itselfA deep-dive episode into how Kyverno and Nirmata are shaping the future of secure, automated Kubernetes governance — blending open source, AI, and DevSecOps collaboration.Stuur ons een bericht.ACC ICT Specialist in IT-CONTINUÏTEIT Bedrijfskritische applicaties én data veilig beschikbaar, onafhankelijk van derden, altijd en overalSupport the showLike and subscribe! It helps out a lot.You can also find us on:De Nederlandse Kubernetes Podcast - YouTubeNederlandse Kubernetes Podcast (@k8spodcast.nl) | TikTokDe Nederlandse Kubernetes PodcastWhere can you meet us:EventsThis Podcast is powered by:ACC ICT - IT-Continuïteit voor Bedrijfskritische Applicaties | ACC ICT

  --------  

  36:46

  --------

  36:46
• #116 Running AI on Kubernetes: From GPUs to CRO

  In this episode of De Nederlandse Kubernetes Podcast, we talk with Carlos Santana, Principal Partner Solution Architect at AWS and long-time contributor to the Kubernetes and AI communities.Carlos joins us to explore what it really takes to run AI workloads on Kubernetes, from GPU scheduling to scaling inference and training efficiently across clusters. We discuss how AI and machine learning are transforming the cloud-native ecosystem — and why orchestration is becoming just as important as the models themselves.He shares insights into:💡 The challenges of scheduling and sharing GPUs in multi-tenant Kubernetes clusters⚙️ Why Kubernetes Resource Orchestrator (CRO) could be the next big abstraction layer🚀 The balance between performance, cost efficiency, and developer experience🧠 His hands-on experiments with Jetson devices, edge computing, and model optimization🌐 How open source projects and cloud providers are shaping the future of AI infrastructureA forward-looking conversation about where AI, Kubernetes, and cloud-native engineering are heading — from someone building that future at scale.Stuur ons een bericht.ACC ICT Specialist in IT-CONTINUÏTEIT Bedrijfskritische applicaties én data veilig beschikbaar, onafhankelijk van derden, altijd en overalSupport the showLike and subscribe! It helps out a lot.You can also find us on:De Nederlandse Kubernetes Podcast - YouTubeNederlandse Kubernetes Podcast (@k8spodcast.nl) | TikTokDe Nederlandse Kubernetes PodcastWhere can you meet us:EventsThis Podcast is powered by:ACC ICT - IT-Continuïteit voor Bedrijfskritische Applicaties | ACC ICT

  --------  

  42:23

  --------

  42:23

Meer Zaken en persoonlijke financiën podcasts

Trending Zaken en persoonlijke financiën -podcasts

Over De Nederlandse Kubernetes Podcast