KubeCon + CloudNativeCon Europe 2025
2025-04-01..2025-04-04
London, United Kingdom
[KubeCon + CloudNativeCon Europe 2018, KubeCon + CloudNativeCon Europe 2019, KubeCon + CloudNativeCon Europe 2020, KubeCon + CloudNativeCon Europe 2021, KubeCon + CloudNativeCon Europe 2022, KubeCon + CloudNativeCon Europe 2025, KubeCon + CloudNativeCon Europe 2026]
as the organisers put it
Register Submit to the CFP SPONSOR Explore The Schedule CNCF-hosted Co-located Event Schedule See Who’s Attending View The Transparency Report KubeCon + CloudNativeCon Europe 2025 is a wrap!
| title | author | length |
|---|---|---|
| Highlights from London | 01m | |
Recap focuses on concrete outcomes: lists recent project graduations and status changes for incubating and sandbox projects, shows a live demo of multi-cluster… | ||
| Highlights from London | 01m | |
Keynotes present a 10 year CNCF retrospective plus specific updates on platform engineering and new community programs, including a announced golden cubes… | ||
| Highlights from London | (unnamed speaker in transcript) | 01m |
Conference sessions surface deeper technical talks and concrete end‑user case studies that demonstrate running Kubernetes innovation for artificial… | ||
| Highlights from London | 01m | |
Recap of London lists concrete takeaways: hundreds of attendees, several dozen sessions, and a visible push to blend cloud native and AI with demos of… | ||
| Keynote: Closing Remarks | (unnamed speaker addressing audience) | 02m |
Announcements highlight a DEI community hub running Wednesday through Friday with allyship and advocacy workshops and details on skedd.com, a post-break social… | ||
| Keynote: CNCF at 10: Navigating Challenges, Embracing Opportunit... | J. Sandoval, L. Rice, K. Gamanji | 16m |
CNCF marks ten years by pointing to concrete pivots: standardized OCI and runtime/network interfaces that enabled vendor neutrality and Kubernetes’ dominance… | ||
| Keynote: Welcome Back + Opening Remarks | 01m | |
Morning welcome marks the final day of KubeCon + CloudNativeCon Europe 2025 and announces winners: Damian Dasu and Michael Ryan Baff for the poster session… | ||
| Keynote: Cloud Native Evolution in Telec... | Faseela K, Tom Kivlin, Philippe Ensarguet, Joel Studler | 11m |
Cloud-native becomes the operational backbone for telco 5G and 6G planning, citing 2.3 billion 5G subscriptions in 2024 and a shift from roughly 10%… | ||
| Keynote: Closing Remarks | 02m | |
A brief wrap lists logistics and transitions: a scholarship photo at 10:30 and a reminder that the solution showcase closes at 2 p.m., plus pick up a KubeCon… | ||
| Cortex: Insights, U... | Friedrich Gonzalez, Daniel Sabsay, Charlie Le, Alolita Sharma, Daniel Blando | 30m |
Cortex is a horizontally scalable, multi-tenant long‑term store for Prometheus with an active 1.19 release: OpenStack Swift moves from experimental to… | ||
| Beyond Kubernetes: Adapting To Spe... | Rags Srinivas, Dawn Chen, Sachi Desai, Vara Bonthu, Erin A Boyd | 38m |
Panelists describe concrete work: open sourcing KAITO/Kai and Skyhook for runtime tuning, a proposed gang/coscheduling and topology‑aware scheduler plugin… | ||
| Quantum-Ready Kubernetes: How Do We Get There? | Nikhita Raghunath, Natalie Fisher, Paul Schweigert, Ricardo Rocha, Tomas Gustavsson | 34m |
Kubernetes must adapt for hybrid classical/quantum workloads, not be replaced: CERN runs an open quantum institute and quantum technology initiative (phase… | ||
| SIG Security: Succession Pla ... | Cailyn Edwards, Iain Smart, Rory McCune, Tabitha Sable, Mahé Tardy | 24m |
Kubernetes SIG Security runs an official CVE feed (JSON + RSS), operates a HackerOne bounty and a third-party audit program (2018, 2021, now 2025 third-party… | ||
| Tutorial: Mind Your Pod's Business: Netwo... | Surya Seetharaman, Miguel Duarte Barroso, Keith Burdis | 01h 21m |
Hands-on workshop showing OVN‑Kubernetes + CNI + KubeVirt on KIND clusters to achieve regulatory UDN per-namespace isolation where pods and VMs get separate IP… | ||
| etcd V3.6.0 and etc... | Benjamin Wang, Ivan Valdes Castillo, Siyuan Zhang, Arka Saha, Ciprian Hacman | 32m |
etcd v3.6.0 ships with downgrade support (manual validate → enable → rolling binary swap) and drops v2 store migration toward a v3 bootstrap path; upgrading… | ||
| How Do You Measure Devel... | Jennifer Riggins, Cat Morris, Akshaya Aradhya, Laura Tacho, Helen Greul | 31m |
Panelists argue developer productivity equals measurable system outcomes not lines of code, centering on time to impact, low cognitive load and fast feedback… | ||
| What's New With Kubectl and Kustomiz... | Eddie Zaneski, Maciej Szulik, Marly Salazar, Yugo Kobayashi | 29m |
Overview of concrete changes and asks: kubectl adds an opt‑in interactive delete (-i) driven by a new per‑user preferences file in ~/.kube (alpha in 1.33) and… | ||
| Simplifying the Networking and Secur... | Bill Mulligan, Anna Kapuścińska, Bowei Du, Amir Kheirkhahan | 29m |
Cilium now claims production scale up to 65,000 nodes with control-plane tweaks to handle pod churn spikes around 500 lifecycle events/sec, and a high-scale… | ||
| Streamlined Efficiency: Unshackling Kubernetes Image Volumes for Rapid A... | Esteban Rey, Yifan Yuan | 25m |
Claims a way to mount OCI image volumes without repackaging or full pulls by streaming remote objects via a reference list (source path, mount path, ETag… | ||
| Stateful Superpowers: Explore High Performa... | Alex Chircop, Chris Milsted, Alex Reid, Lori Lorusso | 30m |
Demonstrations show TiKV serving 1 million RPS from a 12‑node cluster (12 storage nodes, 5× replication) over local NVMe while Grafana dashboards confirm… | ||
| Orchestrating AI Models in Kubernetes: Deploying Ollama as a Nati... | Samuel Veloso, Lucas Fernández | 32m |
Shows a working pipeline that runs Ollama models natively on Kubernetes by making models OCI images and adding a custom containerd runtime. Uses GGUF packer go… | ||
| Taming the Traffic: Select... | Spencer Hance, Arko Dasgupta, Christine Kim, Kate Osborn, Mike Morris | 29m |
Nearly 30 Gateway API implementations exist and the panel gives a practical decision path: start with a feature-parity spreadsheet (use the conformance report… | ||
| Project Lightning Talk: Closing | Jorge Castro | 01m |
Rapid-fire five-minute demos of multiple CNCF projects show concrete use: short walkthroughs of observability stacks using Prometheus and Grafana, service mesh… | ||
| Project Lightning Talk: Capsule: Launching Multi-Tenancy to New Kubernetes Horizons | Dario Tranchitella | 05m |
Project Capsule provides multi-tenancy by adding a tenant CRD and an operator that reconciles RBAC, ResourceQuotas, LimitRanges, NetworkPolicies and replicated… | ||
| Project Lightning Talk: Sailing Multi-Host Inference with LWS | Kante Yin | 06m |
LWS delivers multi-host model-parallel inference by grouping one leader pod with its worker pods into a single superpod (example diagram shows four superpods… | ||
| Project Lightning Talk: Revolutionizing Legacy Migrations with Konveyor AI | Jonah Sussman | 04m |
Konveyor AI (Kai) automates legacy-to-cloud migrations by combining Conveyor static analysis data with an agentic LLM workflow that calls compilers, linters… | ||
| Project Lightning Talk: Stir to Combine: Creating Porter Mixins | Sarah Christoff | 05m |
Porter packages apps and configs into OCI-compatible bundles (cloudnative application bundles, capab) and uses YAML-defined actions to run tools via mixins… | ||
| Project Lightning Talk: You Can Score It! Shift Down to the Platform. Do Not Shift Left to the Developers. | Mathieu Benoit | 06m |
Defines an open workload spec called Score workload specification that developers keep unchanged while platform engineers map it to runtimes; shows concrete… | ||
| Project Lightning Talk: OpenFGA: The Cloud Native Way to Implement Fine Grained Authorization | Andres Aguiar | 06m |
OpenFGA is a relationship-based authorization server with ready SDKs, CLIs, APIs and ID integrations to store relationship tuples and answer permission checks… | ||
| Project Lightning Talk: Essential Resources for gRPC Development | Jung-Yu (Gina) Yeh | 04m |
gRPC now publishes four new user guides with runnable example code across C++, Java, Go, Python and Node.js, and the project adds 39 new videos on a dedicated… | ||
| Project Lightning Talk: Strimzi – What's New and What's Next | Gantigmaa Selenge | 04m |
Strimzi is an operator for running Apache Kafka on Kubernetes that automates install, upgrades, cert management, scaling and monitoring and integrates Cruise… | ||
| Project Lightning Talk: Container Builds at Scale with Buildpacks | Joe Kutner | 05m |
Explains how cloudnative buildpacks handle tens of millions of images by keeping app layers unchanged and only swapping base OS layers via a rebase that edits… | ||
| Project Lightning Talk: Flux - What is it & What's New? | Tamao Nakahara | 06m |
Flux claims to have created GitOps and now ships concrete upgrades in Flux v2.5 (2025) adds CEL-based health checks, improves multicluster and multi-tenant… | ||
| Project Lightning Talk: Dapr: Start Building Distributed Applications with Ease Using Building Block APIs | Marc Duiker | 04m |
Dapr claims about 30% faster development by exposing 13 building-block APIs that run in a sidecar and decouple apps from infra; the project is five years old… | ||
| Project Lightning Talk: Extend Large Language Model Training Beyond Single Kubernetes Cluster | Klaus Ma | 05m |
Demonstrates running LLM training across clusters by combining Volcano and Karmada to overcome single-cluster limits (default ~5,000 nodes) and huge GPU +… | ||
| Project Lightning Talk: Quick Intro to CI/CD Observability with OpenTelemetry | Dotan Horovits | 06m |
OpenTelemetry now includes a CI/CD SIG that defines semantic conventions for pipeline attributes like pipeline_run_id, deployment_name and result and surfaces… | ||
| Project Lightning Talk: Kepler Project Updates | Sunyanan Choochotkaew | 05m |
Kepler collects lightweight real-time resource metrics and attributes power using five-grain power modeling (host, socket, core, container, process) and… | ||
| Project Lightning Talk: Transforming your Application Behavior to Kubernetes Objects | Matthias Bertschy | 05m |
Kubescape records runtime behavior as Kubernetes objects using eBPF and stores them as ApplicationProfiles; initial CRDs balloon from ~100 KB to 100 MB CRD… | ||
| Project Lightning Talk: Perses Update | Augustin Husson | 04m |
Perses reports a v0.51 beta release that adds a rewritten plugin system and live plugin dev CLI, enables external data sources beyond Prometheus/Tempo… | ||
| Project Lightning Talk: Chaos Unleashed: LitmusChaos and Its Journey Towards CNCF Graduation | Vedant Shrotria | 05m |
LitmusChaos is a chaos-engineering toolkit that reports 2 million+ installations and 68 million docker pulls, with 250+ enterprise customers, 2,500+ community… | ||
| Project Lightning Talk: Detect and Respond to Threats in Your Cloud Infrastructure With Falco | Luca Guerra | 05m |
Falco is a CNCF-graduated runtime security tool that inspects syscall-based rules at the kernel level and emits text alerts that include Kubernetes and cloud… | ||
| Project Lightning Talk: Prometheus 3.0 Speedrun | Ben Kochie | 04m |
Prometheus 3.0 is released with a new UI and dozens of feature flags flipped on by default; migration from 2.x is mostly non-breaking despite ~10,000 commits… | ||
| Project Lightning Talk: What's New in Kubernetes Storage | Xing Yang | 05m |
SIG Storage moves three concrete items toward GA and removal: volume populators targets GA in 1.33 and adds a new dataSourceRef in the PVC spec to allow… | ||
| Project Lightning Talk: Empowering Data Protection for Stateful Applications on Kubernetes with Kanister | Mark Lavi | 06m |
Kanister is a CNCF Sandbox project that provides a Helm-installable controller and three CRDs — Blueprint CRD, ActionSet CRD and Profile CRD — to orchestrate… | ||
| Project Lightning Talk: Project Copacetic | Jeremy Rickard | 05m |
Project Copacetic claims it cuts image patch time from weeks to minutes by parsing scanner output and applying OS package updates as a new layer rather than… | ||
| Project Lightning Talk: A Hitchhiker's Guide to the CNCF Landscape | Lori Larusso, Gerald Venzl | 15m |
CNCF now lists about 200+ projects with 31 graduated projects and a community of roughly 257,000 contributors across 756 members; the landscape lets users… | ||
| Project Lightning Talk: Kubeflow Helm Chart | Krzysztof Romanowski | 05m |
Community-driven Helm chart that deploys only Kubeflow core components and integration manifests, aiming to replace heavy kustomize stacks with a minimalist… | ||
| Project Lightning Talk: Simplifying Cloud-Native Security: eBPF-Powered Encryption in Sidecarless Service Mesh | Muyang Tian | 04m |
K mesh is an eBPF-based kernel dataplane that implements sidecarless service mesh with two modes: kernel mode offloads L4 and simple L7 policies into the… | ||
| Project Lightning Talk: Empowering Federated Learning with Multi-Cluster Management for Privacy and Efficiency | Meng Yan | 04m |
Shows an end-to-end integration of Open-Cluster-Management with Federated Learning that moves model updates not data, cutting cross-cluster bandwidth and… | ||
| Project Lightning Talk: What's New in k8gb: CNCF's Multicluster Global Balancer | Bradley Andersen | 05m |
k8gb is a Kubernetes-native global service load balancer that updates DNS from cluster health via a GSLB CRD and operator-to-operator sync, avoiding no… | ||
| Project Lightning Talk: Multi-Cluster Configuration Management with KubeStellar | Andy Anderson | 05m |
KubeStellar presents a fleet management system that centrally defines inventory, workloads and binding policies and actually deploys them to remote clusters… | ||
| Project Lightning Talk: Kubernetes Ontologies With Meshery | Yash Sharma | 05m |
Meshery offers a visual drag-and-drop Kanvas to build Kubernetes infra without YAML, auto-generates models from Artifact Hub, and enforces context-aware… | ||
| Project Lightning Talk: Scheduling AI Workload Among Multiple Clusters | Josh Packer | 05m |
Open Cluster Management uses a hub‑and‑spoke inventory, a placement CRD and add‑ons to map cluster capabilities; a GPU/TPU resource collector addon computes an… | ||
| Project Lightning Talk: Multi-Arch KubeVirt and CDI | C. A. Fillekes | 05m |
KubeVirt and Containerized Data Importer (CDI) run as operators across x86, ARM64 and s390x nodes, enabling a concrete workflow: import via CDI on x86 using… | ||
| Project Lightning Talk: Karmada Updates and Use Cases | Hongcai Ren | 04m |
Karmada is a multi‑cluster Kubernetes control plane that is open sourced in 2021 and moved to incubation in 2023, with about 700 contributors and 36 public… | ||
| Expanding Crossplane’s Reach - Providers, Bridges, and Exten... | Ariel Septon | 05m |
Built a provider-http Crossplane provider that turns any HTTP API into a Crossplane managed resource, used to replace manual DB provisioning and spreadsheets… | ||
| API Management in the CRD World: What Linkerd Has Learned | Phil Henderson | 10m |
Linkerd reports that its control plane and Rust-based data plane run with minimal footprint and zero-config mTLS, but the real focus is CRD pain points… | ||
| What's New in Istio? | Mitch Connors | 06m |
Istio now ships ambient mode GA since November that runs proxies only where needed while continuing to support sidecars, and it installs with a one-command… | ||
| Protect your Kubernetes Clusters with Ratify and Attestations | Yi Zha | 06m |
Ratify is a CNCF sandbox verification engine that verifies signatures, SBOMs and vulnerability reports and enforces policy via Rego; demo shows it validating… | ||
| external-secrets: Zero Trust Secrets Management with ESO | Moritz Johner | 05m |
Operator runs inside the cluster, reaches out to external vaults and creates Kubernetes Secret objects, using uses Kubernetes service accounts (JWTs) instead… | ||
| What's New in K3s? (and How You Can Help!) | Orlin Vasilev | 04m |
K3s is a lightweight Kubernetes distribution that is a single binary under 7 MB and boots a cluster in roughly 10–15 seconds on stage demos; it joined the… | ||
| Maturing Bare Metal Provisioning With Metal3 | Ádám Rozmán | 06m |
Metal3 now reports concrete milestones: about 34 releases since last November, roughly 5,500 commits since joining the sandbox, and 10,000 GitHub events… | ||
| Kairos Timelapse: 12 Months of Open Source in 5 Minu... | Dimitris Karakasilis | 05m |
Kairos becomes a CNCF sandbox project and implements trusted boot (secure boot + measured boot + full disk encryption) to guarantee untampered boots and… | ||
| Notary Project: Securing Binary Artifacts with Fine-grained Control | Yi Zha | 06m |
Notary Project demonstrates a concrete toolchain for signing non-OCI binaries: Notation implements OCI 1.1, supports JWS and COSE signature formats, and adds… | ||
| A Security Engineer’s Guide to TAG Security | Brandt Keller | 07m |
TAG Security outlines concrete processes: a self-assessment tool projects use to document controls, a hands-on joint assessments workflow that pairs assessors… | ||
| ORAS: Create and Distribute a Multi-platform Image with Secu... | Andrew Block | 05m |
ORAS CLI builds a single OCI reference that combines AMD64 and ARM64 images by creating a manifest index locally, then pushes that multi-platform artifact to… | ||
| What’s New in Kuma: Advanced Service Mesh Capabilities | Marcin Skalski | 04m |
Kuma remains an Envoy-based control plane focused on multitenancy, multicluster and brownfield VM support and now adds a new data plane kind so Kubernetes pods… | ||
| Spiderpool Updates For AI Workloads: DRA, NRI, and RDMA Obser... | Weizhou Lan | 05m |
Spiderpool adds a DRA resource claim to declare RDMA devices and network interfaces so Pod YAML no longer needs manual PCIe names, and uses NRI dynamic… | ||
| CRI-O: Container Runtime Intensifies | Sascha Grunert | 04m |
Project updates show CRI-O 1.33 adding OCI artifact support so cryo and cryctl can pull, list, inspect and remove registry artifacts alongside images, storing… | ||
| Kubewarden: Leveraging and Extending CEL for your Cluster... | Robert Sirchia | 03m |
Kubewarden reuses the upstream CEL interpreter and compiles CEL into WebAssembly so policies are compiled into WASM and remain backwards compatible with… | ||
| The Super Fast TAG Runtime Wasm Review | Taylor Thomas | 05m |
30 second blitz of the CNCF WASM ecosystem that lists concrete projects and artifacts: Hyperllight as a tiny VM wrapper for constrained environments, spin as a… | ||
| A Hitchhiker's Guide to the CNCF Landsc... | Katherine Druckman, Lori Lorusso | 15m |
The CNCF landscape is a searchable map of over 190 CNCF projects that shows status (sandbox, incubating, graduated), contributor counts and stars, latest… | ||
| Opening + Welcome | Jorge Castro | 05m |
Quick briefing on format and goals: lightning demos run every 7 minutes with each project allotted five minutes, highlighting concrete tools and use cases… | ||
| Autonomous Al Agents for Cloud Cost Analysis | Ilya Lyamkin | 11m |
Describes a Spotify system that uses LangGraph to orchestrate specialized agents: a self‑healing SQL expert tuned for BigQuery (up to three automatic repair… | ||
| Closing Remarks | 01m | |
Schedule notes a sponsored demo theater in the solutions showcase with live demos starting now and details on skare.com. Two new projects, CubeFS and Into, are… | ||
| Harbor and LFX Mentorship Projects | Vadim Bauer | 04m |
The LFX Mentorship program runs over 2.5 years and produces concrete outcomes: 12 mentees across two Harbor subprojects (Harbor Satellite and Harbor CLI)… | ||
| Vitess: Unlimited Database Scalability | Shlomi Noach | 05m |
Vitess is a sharded distributed layer on MySQL that claims to serve many millions of queries per second for users like Slack, GitHub and Cash App. It avoids… | ||
| Keynote: Welcome Back + Opening Remarks | (unnamed speaker) | 01m |
Opening remarks note a final count of 13,000 attendees and set the conference theme squarely on end users, promising concrete examples rather than high-level… | ||
| Efficient Transparent Checkpointing of AI/ML Workloads in Kub... | R. Stoyanov, A. Reber, V Spišaková | 32m |
Extends Kubernetes checkpointing with CRIU plugins and a CUDA/AMD GPU checkpoint path to capture unified CPU+GPU state without API interception, producing ~11… | ||
| Streamlined Efficiency: Unshackling Kubernetes Image Volumes for Rapid AI Model... | E. Rey, Y. Yuan | 25m |
Introduces a concrete system that mounts OCI image volumes without repackaging by storing a reference list (CSV/JSON of source path, mount path, ETag, size) in… | ||
| Quantum-Ready Kubernetes: How Do We Get There? | Nikhita Raghunath, Natalie Fisher, Paul Schweigert, Ricardo Rocha, Tomas Gustavsson | 34m |
By 2035 US procurement requires quantum-safe solutions and NIST already standardized first post‑quantum algorithms last August, so Kubernetes stacks need… | ||
| Graduated Project Updates | Open Policy Agent (OPA) | 05m |
Cilium announces Cilium 1.17 with new eBPF networking features, performance gains, Hubble dynamic metrics, Tetragon runtime security auditing eBPF operations… | ||
| Keynote: Welcome + Opening Remarks | Chris Aniszczyk | 17m |
CNCF marks its 10th year and this opening lists concrete metrics and launches: 12,500 attendees onsite, 275,000 contributors across 200+ projects from 190… | ||
| Keynote: Into the Black Box: Observability in the Age of LLMs | Christine Yen | 15m |
LLM-backed features are inherently nondeterministic so production success depends on capturing inputs, context and outputs end-to-end: capture prompt and token… | ||
| Sponsored Keynote: The Cloud (And Your $$$) is Not Infinite: Dynamic Scheduling at Every Layer | Corentin Debains, Laura Lorenz | 05m |
Kubernetes moves from static pools to on‑demand placement that claims to cut cost and handle scarce hardware by letting pods express hardware needs and… | ||
| Keynote: AI Enabled Observability Explainers - We Actually Did Something With AI! | Vijay Samuel | 15m |
eBay builds deterministically reliable observability “explainers” that combine algorithms and LLMs: trace explainer prunes traces via a critical path algorithm… | ||
| Sponsored Keynote: Evolving the Kubernetes User Experience | Andrew Randall | 07m |
Claim that Headlamp is now part of the Kubernetes SIG UI and the GitHub repo move completed yesterday, and that it can provide a single web and desktop… | ||
| Keynote: Rust in the Linux Kernel: A New Era for Cloud Native Performance and Security | Greg Kroah-Hartman | 10m |
Linux kernel adds Rust to reduce reviewer errors by making the compiler enforce lifetimes, locking and error checks, replacing repetitive C unlocks and frees… | ||
| Keynote: Empowering Accessibility Through Kubernetes: The Future of Real-Time Sign Language Interpretation | Rob Koch | 15m |
Demonstrates a real-time sign‑to‑speech system deployed on Kubernetes that uses CubeFlow pipelines, computer‑vision landmark extraction via MediaPipe/MM Labs… | ||
| Keynote: The Observability Platform Engineering Advantage: From Zero-Code to Monitoring as Code | Kasper Borg Nissen | 15m |
Demo deploys two apps: Spring Boot with MySQL and Go with PostgreSQL, auto-instrumented by the OpenTelemetry Operator; two collectors run (node DaemonSet and… | ||
| Lessons Learned From Architecting the Highest-scale Operational Systems in the World | Artur Bergman | 27m |
Fastly runs the global edge that serves about 1M requests per second for open‑source packages and peaks near 40M req/s with ~400+ Tbps capacity, and the… | ||
| Dapr in 2025: Durable Execution for AgenticAI Systems and Becoming the Backbone of App Platforms | Yaron Schneider, Roberto Rodriguez | 39m |
Dapr 1.15 introduces a conversation API with built‑in circuit breakers, auth middleware and prompt caching kept in the sidecar to eliminate external egress and… | ||
| What's New in gRPC | Kevin Nilson | 24m |
gRPC reports growth like 24M weekly Python downloads and rising GitHub stars, and ships concrete features: REST support with a preview at gRPC‑comp in August… | ||
| Scalable DNS With CoreDNS Plugins: A Deep Dive | Yong Tang, John Belamaric | 27m |
Demo plugin returns different A records based on source IP (internal 172. → 1.1.1.1, external → 8.8.8.8), implemented with three Go functions (init, setup… | ||
| KEDA: Unlocking Advanced Event-Driven Scaling for Kubernetes | Zbynek Roubalik, Jorge Turrado | 37m |
KEDA presents concrete features: 70+ scalers (RabbitMQ, Prometheus, Kafka, SQS via community PRs), a scale-to-zero flow that uses a ScaleObject to extend HPA… | ||
| Rook: Intro and Deep Dive With Ceph Storage | Travis Nielsen, Madhu Rajanna, Artem Torubarov, Deepika Upadhyay, Sebastien Han | 31m |
Rook is a Kubernetes operator that runs Ceph to provide block, shared filesystem and S3 object storage and claims production scale with examples: a reported… | ||
| Flux Ecosystem Evolution | Stefan Prodan, Sanskar Jaiswal | 33m |
Overview of recent Flux ecosystem changes including concrete features and demos: Flux adds Flux Operator to declaratively bootstrap and manage Flux at scale… | ||
| What's New in Knative Eventing: Security, Discovery, Integrations, and JobSink | Pierangelo Di Pilato, Christoph Stäbler | 31m |
Knative Eventing now adds HTTPS addressables with strict/permissive modes using cluster-manager for certs, plus OIDC tokens via per-source Kubernetes service… | ||
| Prometheus Deep Dive: What’s New in v3.0 and Beyond | Saswata Mukherjee, Fiona Liao | 27m |
Prometheus 3.0 (released November last year, seven years after v2) ships a React+Mantine UI, a PromQL AST endpoint powering a visual query explanation, and a… | ||
| Mastering Efficiency in Argo CD: Scaling Smarter, Not Costlier | Alexander Matyushentsev | 29m |
A measured GCP experiment runs Argo CD on a 3‑node control plane managing 800 apps and costs ~$40/day (~$1.49/app, ~30% network). Key levers: host Argo CD on a… | ||
| Buildpacks: Pragmatic Solutions To Quick and Secure Image Builds | Juan Bustamante, Aidan Delaney | 31m |
Demos show pack/kpack builders (Paketo, Heroku) producing OCI images from source without Dockerfiles: a monorepo image running both Go backend and Node front… | ||
| How To Gateway With Ingress - 140 Days InGate | Marco Ebert, James Strong | 27m |
Project builds a fresh Gateway API implementation called Ingate on top of NGINX, targeted for a testable v1 by Atlanta and project archive by 2027; current… | ||
| The State of Backstage in 2025 | Ben Lambert, Camila Loiola, Fredrik Adeloew, Patrik Oldsberg, Vincenzo Scamporlino | 33m |
Backstage reports ~3,400 adopters, ~230 plugins, and nearly 30,000 stars while shipping a stable backend 1.0 and pushing the new frontend toward a stable… | ||
| SIG-Node: Intro and Deep Dive | Sergey Kanzhelev, Francesco Romani, Peter Hunt | 38m |
SIG-Node reports concrete progress: in-place pod resize beta ships (handles allocatable checks and blocks resizes when node reserved resources are… | ||
| Enhancing CRI-O With CDI: Streamlining Device Integration in Kubernetes | Harshal Patil | 24m |
CRI-O reads CDI spec files to convert vendor device descriptions into concrete container changes: it reads /etc/cdi and /run/cdi, locates fully qualified… | ||
| Wasm I Right or Wasm I Wrong? a Review of the Wasm Ecosystem | Taylor Thomas, David Justice | 29m |
Wasm is already in production across CNCF projects: runtimes like Spin and WASMCloud, DB UDFs, proxy‑Wasm filters and tooling such as Zed and Inspector Gadget… | ||
| OpenTelemetry Project Update | Daniel Gomez Blanco, Severin Neumann, Alolita Sharma, Trask Stalnaker, Pablo Baeyens | 33m |
Project reports rapid growth: 7,000 contributions weekly, 550+ active developers, 80+ repos and contributors from 100+ countries; graduation prerequisites are… | ||
| Optimizing Training Performance for Large Language Model(LLM) in Kubernetes | Klaus Ma, Peng Gu | 29m |
Volcano adds a HyperNode CRD and topology-aware scheduling (hard/soft modes) to confine LLM jobs to rack/row boundaries, tested in a simulated cluster using… | ||
| Beyond CloudEvents: Endpoints, Messages, Schemas – CNCF XRegistry | Manuel Ottlik | 29m |
Defines an xRegistry core spec for versioned groups/resources and provides concrete specs for endpoints, messages, schemas plus a REST API, a static-file… | ||
| Jaeger V2: OpenTelemetry at the Core of Modern Distributed Tracing | Jonah Kowall | 26m |
Jaeger v2 replatforms the backend on OpenTelemetry and ships as a single binary that remains backward compatible with Jaeger v1 data and APIs. It embeds the… | ||
| Simplifying Apache Kafka on Kubernetes With Strimzi | Paolo Patierno, Gantigmaa Selenge | 31m |
Strimzi packages Kafka on Kubernetes with concrete automations: KRaft migration removes ZooKeeper and Strimzi 0.46 will require KRaft while 0.45 is the last ZK… | ||
| SIG Cloud Provider Deep Dive: Testing Cloud Controller Managers | Michael McCune, Bridget Kromhout, Walter Fender | 38m |
SIG Cloud Provider reports over a million lines removed from in-tree cloud code and replaces the old SSH tunnel with an API server network proxy reference… | ||
| Cloud Native Storage and Data: The CNCF Storage TAG Projects, Technology & Landscape | Raffaele Spazzoli, Alex Chircop | 31m |
CNCF Storage TAG is consolidating eight tags to five to handle rapid growth from about 40 projects to 215 projects (33 added last year), and it publishes… | ||
| Standardizing CI/CD Observability With OpenTelemetry: Insights From the CI/CD Observability SIG | Dotan Horovits, Adriel Perkins | 24m |
OpenTelemetry CI/CD SIG standardizes a concrete schema of semantic attributes for pipelines, deployments, VCS, tests and artifact attestations, and provides… | ||
| OpenFeature Update From the Maintainers | Thomas Poignant, Lukas Reining, Alexandra Oberaigner | 32m |
OpenFeature adds code generation via CLI that turns flags into typed variables (currently experimental for Go and React using a JSON flag manifest), and two… | ||
| Attesting and Verifying Your Software Supply-Chain With In-toto | Alan Chung Ma, Justin Cappos | 33m |
in-toto provides cryptographic attestations for build steps and a layout language that enforces who may run each step; a production-ready toolchain includes… | ||
| Leveraging the Little Known Features of Artifact Hub | Matt Farina | 32m |
Artifact Hub exposes concrete features: supply an artifacthub-package.yaml or annotations to control name, changelog entries, custom markdown install… | ||
| Kubernetes Data Protection WG Deep Dive | Dave Smith-Uchida | 28m |
Working Group delivers a white paper and updated 2024 report and maps concrete backup/restore workflows that require backing up Kubernetes metadata plus PV… | ||
| A Practical Guide To Kubernetes Policy as Code | Jim Bugwadia, Rita Zhang, Andy Suderman, Joe Betz | 30m |
Practical steps and tradeoffs for running Policy as Code: use ValidatingAdmissionPolicy for fast, in-server checks and MutatingAdmissionPolicy (alpha) only… | ||
| SIG Instrumentation Introduction and Deep Dive | Damien Grisonnet, Pranshu Srivastava, Yongrui Lin, Richa Banker | 28m |
SIG Instrumentation enforces consistent signals across Kubernetes: metrics use the Prometheus metric format with stability annotations to avoid breaking… | ||
| Advancements in AI/ML Inference Workloads on Kubernetes From WG Serving and Ecosystem Projects | Yuan Tang, Eduardo Arango Gutierrez | 31m |
WG Serving reports one year of work: it ships an inference-perf benchmark library (Python, VRM support, CR GPT dataset) to identify autoscaling metrics and… | ||
| Kubernetes CRD Design for the Long Haul: Tips, Tricks, and Lessons Learned | Christian Schlotter, Fabrizio Pandini | 28m |
Advice: avoid embedding external types that will force unplanned version bumps; instead copy, adapt and evolve external configs and convert at runtime so one… | ||
| Tutorial: Exploring Multi-Tenant Kubernetes APIs and Controllers With Kcp | Robert Vasek, Nabarun Pal, Varsha Prasad Narsing, Marko Mudrinić, Mangirdas Judeikis | 01h 15m |
Hands-on walkthrough that proves KCP can expose cluster APIs as a multi-tenant DBaaS: attendees run KCP locally, use GitHub Codespaces, create hierarchical KCP… | ||
| Reliable K8s Resource Submission & Bookkeeping | Tiancheng Yin, Yao Lin | 20m |
Bloomberg describes a concrete system: a user API writes actions to a source‑of‑truth DB and a message stream (Apache Kafka) while a submitter consumes… | ||
| How the SIG-Multicluster API Specifications Are Used for Real World Multicluster Management | August Simonelli, Ryan Zhang | 41m |
SIG-Multicluster defines four usable APIs—About API, ClusterProfile API, Work API—plus a Multicluster Services pattern (service export/import) that OCM-io and… | ||
| gRPC: 5 Years Later, Is It Still Worth It? | Konstantin Ostrovsky | 28m |
Five years of gRPC at a Go microservices shop powers millions of automations per day and yields unified, generated clients and strict backward-compatibility… | ||
| Building WebAssembly Like It's 2011 | David Justice, Terence Lee | 31m |
Claim: applying Buildpacks applied to Wasm gives a one‑liner build that installs Wasm toolchain, composes components and emits an OCI image. Uses the pack CLI… | ||
| From 0 To Production-Grade With Kubernetes Native Development | Thomas Vitale, Kevin Dubois | 30m |
Step-by-step demo shows source-to-image using Buildpacks (pac CLI) and running images locally with Podman Desktop, pushing to a kind cluster and… | ||
| Dapr + Score: Mixing the Perfect Cocktail for an Enhanced Developer Experience | Mathieu Benoit, Kendall Roden | 31m |
Concrete demo of a Dapr + Score pipeline: a five-service order workflow runs locally using dapr init and dapr run with sidecars, Zipkin, actor placement and a… | ||
| Museum of Weird Bugs: Our Favorites From 8 Years of Service Mesh Debugging | Alex Leong | 30m |
Eight years of Linkerd debugging yields concrete fixes: a CRD/schema mismatch causes an infinite patch loop and 780 MB leak because a generated Rust struct… | ||
| Why Allyship Matters and Your Role in Creating a More Diverse Cloud Native Community | Catherine Paganini, Milad Vafaeifard, Sandeep Kanabar, Anastasiia Gubska, Rob Koch | 37m |
Panel argues that simple concrete steps drive inclusion: creators adding captions added by creators and mentors adding subtitles to tutorial videos enable… | ||
| OSS = Open Source ... Strategy!? Google Is Doubling Down on K8s in the AI Era, and You Should Too! | ago Macleod | 30m |
Google commits to doubling down on Kubernetes for AI workloads, claiming it must scale to the next trillion core hours and already supports large fleets (GKE… | ||
| The Bricks That Make Us – How the LEGO Group Avoids 50 Mediocre Kubernetes Implementations | Thomas Øther Rasmussen, Paul Farver | 32m |
LEGO builds a single opinionated Novous container platform and enforces GitOps enforced for all apps, replacing one internal platform while aiming to avoid 50… | ||
| Navigating the Waters: Balancing Open Source Activities in Corporate Environments | Kim McMahon, Amanda Katona | 25m |
Creates a team charter after 15–30 fifteen-minute interviews, maps three strategic objectives to OKRs, and tracks key results in a spreadsheet with… | ||
| KubeEdge Graduation Journey: Creating a Diverse and Collaborative Open Source Community From Scratch | Yue Bao, Hongbing Zhang | 23m |
Launched in 2018 and donated to CNCF in 2019, the project claims CNCF graduation and lists 8,000 GitHub stars with ~1,500 contributors from 100+ organizations… | ||
| A Comparative Analysis of Kueue, Volcano, and YuniKorn | Wei Huang, Zhang Shiming | 32m |
Compares Kueue, Volcano, and Apache YuniKorn with concrete benchmarks: 10,000-pod workloads across patterns (many single-pod jobs, few multi-pod jobs, gang… | ||
| Logs, Metrics, Traces and Mayhem: An Interactive Observability Adventure Game | Jay Alexander Clifford, Tom Glenn | 27m |
A playable text adventure is built as a Python script instrumented with the OpenTelemetry SDK and routed through an OTLP collector into Prometheus, Loki and… | ||
| Learning Kubernetes Through the Lens of Metrics | Priyanka Saggu, Mario Jason Braganza | 23m |
Creates a tiny kind cluster and curl to 6443 to read the API server metric kubernetes_feature_enabled, then installs Prometheus via Helm and queries… | ||
| K8s in Wonderland: Why? Many of Unknown Code in My Workload? | Hoon Jo | 32m |
Explains concrete Kubernetes defaults and why they exist, using kubectl explain and small scripts that actually pull images and measure behavior against Docker… | ||
| "Izzy Saves the Birthday" - A Story-Driven Live Demo Exploring the Magic of Service Mesh | Lin Sun, Faseela Kundattil | 29m |
Storybook characters map to concrete service-mesh actions: a demo deploys Kubernetes with Istio ambient mode, Prometheus, SPIFFE identities, waypoint proxies… | ||
| Choose Your Own Adventure: The Dignified Pursuit of a Developer Platf... | Whitney Lee, Viktor Farcic | 34m |
Live demo builds an Internal Developer Platform using Crossplane for Kubernetes APIs, which turns a 10-line SQL claim into AWS VPC, subnets and security… | ||
| Yes You Can Run LLMs on Kubernetes | Abdel Sghiouar, Mofi Rahman | 27m |
Deploys a Gemma 3 1B model as a Kubernetes Deployment using vLLM image on GKE Autopilot, requesting 4 CPU, ~20GB RAM, 1 GPU and 20GB ephemeral storage; model… | ||
| Explain How Kubernetes Works With GPU Like I’m 5 | Carlos Santana | 30m |
Homelab rebuild of the full stack from bare metal to running GPU-accelerated containers using an NVIDIA Jetson NUC, showing that with correct vendor drivers… | ||
| How Green Is My OpenTelemetry Collector? | Nancy Chauhan, Adriana Villela | 28m |
Kepler exports a metric called kepler container_joules_total which the demo converts to kWh to measure collector energy use; experiments compare a single… | ||
| An Exemplary Path: Leveraging EBPFs and OpenTelemetry To Auto-instrument for Exemplars | Charlie Le, Kruthika Prasanna Simha | 35m |
Demo shows an eBPF agent (BA) attached to the kernel that auto-instruments exemplars by translating network/syscall events into OpenTelemetry metrics and… | ||
| Asimov's Zeroth Law of Robotics: Observability for AI | Nicole van der Hoeven | 32m |
Argues a zeroth law: AI must be observable so other laws can be verified, and shows a concrete instrumentation stack: OpenTelemetry, OpenLit, Prometheus… | ||
| Deep Dive To AI Agent Observability | Guangya Liu, Karthik Kalyanaraman | 31m |
OpenTelemetry is used to trace prompts and completions, model settings and tool calls, plus vector DB queries and ranked scores so traces become production… | ||
| Enhancing Database Observability With OpenTelemetry | Marylia Gutierrez | 22m |
OpenTelemetry marks the database semantic conventions as a stable release candidate and defines about 15 attributes for database spans; metrics are still under… | ||
| Expanding eBPF’s Reach: From Batteries-Included Auto-Instrumentation To E2E Observability Pipelines | Dom Del Nano | 25m |
Argues eBPF should be batteries included but removable: Pixie and Inspektor Gadget add Kubernetes enrichment, structured APIs and domain-specific… | ||
| First Day Foresight: Anomaly Detection for Observability | Prashant Gupta, Kruthika Prasanna Simha | 31m |
Claim: useful anomaly detection runs on day one without full ML training by combining simple stats, synthetic data, and transfer learning. Uses z‑score rules… | ||
| Flink on Karmada: Building Resilient Data Pipelines on Multi-Cluster K8s | Michas Szacillo, Wang Li | 25m |
Bloomberg runs 1,000 Flink jobs across multiple Kubernetes clusters and builds a Karmada extension that preserves Flink state for automated cross‑cluster… | ||
| Unleashing the Power of Init Containers: Reducing Database Management Toil at Yelp | Muhammad Junaid Muzammil | 28m |
Yelp runs init containers to automate and speed Cassandra operations across 70+ clusters and >1,000 nodes, cutting scale-up duplicates by bootstrapping new… | ||
| Trino and Data Governance on Kubernetes | Sung Yun, Aki Sukegawa | 32m |
Centralized platform deploys Trino on Kubernetes using a custom controller that exposes Trino CRDs (catalog, service, access-control) and mounts catalogs… | ||
| The Future of Data on Kubernetes: From Database Management To AI Foundation | Rob Strechay, Nimisha Mehta, Gabriele Bartolini, Brian Kaufman | 31m |
DoK now runs >50% of workloads in production and 75% of those are advanced; expect concrete tactics not theory: use local SSD caching to cut GPU idle time… | ||
| Scaling Shopify's Search: Enhancing Elasticsearch Resilience With Kubernetes and KE... | Leila Vayghan | 32m |
Shopify isolates heavy maintenance writes by hosting production and reindex workloads on separate GKE nodepools and autoscaling the reindex pool with KEDA… | ||
| The Next Generation of DaemonSet Autoscaling | Adam Bernot, Bryan Boreham | 36m |
Prototype implements per-pod VPA for DaemonSets by adding a scope field so each pod on each node gets its own recommendation rather than one value for all… | ||
| The Life (or Death) of a Kubernetes API Request, 2025 Edition | Abu Kashem, Stefan Schimanski | 31m |
Chronicles the literal request path from kubectl to storage and back, showing how the HTTP server builds a handler chain, populates request context and audit… | ||
| Superpowers for Humans of Kubernetes: How K8sGPT Is Transforming Enterprise Ops | Alex Jones, Anais Urlichs | 28m |
K8sGPT is a CNCF sandbox project (started 2023) that scans clusters with codified SRE knowledge, offers 11 AI backends, and runs as CLI, operator or server to… | ||
| The API Gateway Maturity Matrix: Where Do You Rank? | Joel Hans | 29m |
Framework maps API gateway capability to five phases — Build, Operate, Scale, Improve, Adapt — and shows concrete steps: adopt GitOps workflows, implement… | ||
| The Explorer's Guide To Cloud Native GenAI Platform Engineering | Max Korbacher, Alexa Nicole Griffith | 31m |
Maps a practical path from a 15‑minute Thinnest Viable Platform (Canoe/Argo CD/Backstage) to an MVP running KServe for LLM inference and an advanced platform… | ||
| The GPUs on the Bus Go ‘Round and ‘Round | Natalie Bandel, Ryan Hallisey | 29m |
NVIDIA GPU Cloud runs 60,000+ GPUs across 40+ clusters and sees roughly 120–200 GPU failures per 24 hours (about 0.6% of devices), so reliability is… | ||
| A Fork to Reckon With: Minimizing Friction When Adopting OSS | Alexander Perlman, Narayanamurthi Mari | 32m |
Enterprise platforms face four concrete choices for closing gaps in OSS: contribution, forking, wrapping, mutation. Examples include QFlow wrapping Argo… | ||
| Don't Write Controllers Like Charlie Don't Does: Avoiding Common Kubernetes Controller Mistakes | Nick Young | 32m |
Shows that homegrown clients that call get/list on every reconcile burn API server cycles and that uncontrolled status writes create hundreds of status updates… | ||
| Day-2’000 - Migration From Kubeadm+Ansible To ClusterAPI+Talos: A Swiss Bank’s Journey | Clément Nussbaumer | 28m |
Claim: migrate 35 on‑prem air‑gapped clusters with custom PKI from kubeadm+Ansible+Puppet to ClusterAPI+Talos without downtime. Steps: provision VMs with… | ||
| Dashboards & Dragons: Crafting SLOs To Tame the AI Platform Cha... | Alexa Nicole Griffith, Ankita Chaudhari | 31m |
A multi-cluster AI inference platform is instrumented with Envoy, kserve, OpenTelemetry and Prometheus to turn noisy metrics into actionable SLOs and… | ||
| Production-Ready LLMs on Kubernetes: Patterns, Pitfalls, and Performa... | Priya Samuel, Luke Marsden | 28m |
Deploys running on 1–2 A100 GPUs using Helm, Open Web UI, Ollama for quick tests and vLLM for production-grade inference with Mistral 7B; finds 4-bit… | ||
| More Nodes, More Problems: Solving Multi-Host GPU/TPU Scheduling With Dynamic Resource Allocation | John Belamaric, Morten Jæger Torkildsen | 31m |
DRA beta in Kubernetes 1.32 enables modeling and claiming devices that span nodes, so a 16‑node cluster with 4 TPUs each (64 TPUs total) can advertise… | ||
| Slinky: Slurm in Kubernetes, Performant AI and HPC Workload Management in Kubernetes | Tim Wickberg | 39m |
Slinky is a toolkit (open source Apache 2 on GitHub) that embeds Slurm into Kubernetes via a Slurm operator, a slurm bridge, a client library and a Prometheus… | ||
| Scaling GPU Clusters Without Melting Down! | Alay Patel, Ryan Hallisey | 30m |
Cluster API server hits OOM when two concurrent list calls fetch 5,000 large secrets (~0.2 MB each); mitigation is API Priority and Fairness limiting… | ||
| Making the Leap: What Gateway API Needs To Support Ingress-NGINX Users | Rob Scott, James Strong | 28m |
Migration plan targets the 118 annotation-driven features of Ingress-NGINX: only 35% implemented in Gateway API today, ~55% marked "supported soon", and many… | ||
| Uncharted Waters: Dynamic Resource Allocation for Networking | Miguel Duarte Barroso, Lionel Jouin | 27m |
Kubernetes-native Dynamic Resource Allocation (DRA) exposes network interfaces as schedulable resources using the GR resource model, NRI hooks, and a DRA CNI… | ||
| The Great Sidecar Debate | William Morgan | 29m |
Sidecars remain a concrete engineering tradeoff: Kubernetes now has native sidecar support (merged 2023) and init containers with restartPolicy=Always… | ||
| Was Leslie Lamport Right? | Sarah Christoff, Nic Jackson | 32m |
Shows why Paxos → Raft lineage still matters, proves Byzantine consensus needs 3m+1 nodes and t+1 voting rounds, and demos the 4‑general case where the… | ||
| The Ultimate Container Challenge: An Interactive Trivia Game on OCI, Podman, Docker... | Aurélie Vache, Sherine Khoury | 28m |
Interactive live quiz with demos that proves three practical surprises: a locally built image shows 22 MB while the pushed registry copy is ~10 MB because the… | ||
| Signed, Sealed, Delivered - Sign and Verify All the Things | Jeremy Rickard | 31m |
Mirrors every external image into a controlled OCI registry, signs artifacts, scans and patches vulnerable images, and enforces acceptance in-cluster using… | ||
| Securing AI Workloads: Building Zero-Trust Architecture for LLM Applications | Rohit Ghumare, Joinal Ahmed | 30m |
Claims a practical zero‑trust stack for LLMs with concrete tools and attacks: apply AI gateway enforce ABAC/OIDC via Keycloak and OPA, use Guardrail AI… | ||
| Trust No One: Secure Storage With Confidential Containers | Aurélien Bombo | 30m |
Claim: confidential containers secure storage so cloud providers cannot read data by keeping keys and encryption inside a TEE-backed VM. Implementation uses… | ||
| Scale Smarter Not Harder: How Extending Cluster Autoscaler Saves Millions | Rahul Rangith, Ben Hinthorne | 28m |
Datadog builds an instance type adviser that runs Kubernetes scheduling simulations and benchmarks CPU/memory/network to score every candidate instance… | ||
| Platform Engineering for Software Developers and Architects (Redux) | Daniel Bryant | 32m |
Argues a three‑layer platform: a Backstage‑style application portal, a platform orchestration middle layer (cratics, Crossplane, Argo/Flux) and infrastructure… | ||
| Making CRDs Delightful: Beyond the Pitfalls | Evan Anderson | 35m |
Ten practical rules for authoring CRDs with concrete examples: use status for humans and machines (include enums, human descriptions, and resource references)… | ||
| Leveraging Internal Knowledge: Building AiKA at Spotify | Majd Salman, Jofre Mateu Matesanz | 26m |
Spotify builds AiKA, a RAG-based internal knowledge platform using embeddings, a vector database, multiple LLM providers, a custom inference and… | ||
| Many Cooks, One Platform: Balancing Ownership and Contribution for the Perfect Broth | Lian Li | 30m |
Built an internal developer platform for the Dutch judiciary (Evo Respra) on OpenShift 4.16 → 4.17, running across four clusters (2 dev, 2 prod) plus a… | ||
| More Data Please: Hands on Green Cloud Experiments | Leonard Vincent Simon Pahlke, Antonio Di Turi | 28m |
A four-node bare‑metal setup runs a k3s cluster (Cilium) on Intel mini‑PCs and measures energy with both a plug meter and Scafandra software, revealing plug… | ||
| "Working Code Wins": Win Big With a Cloud Native Hackathon Start... | P. Morton, A. Bangser | 51m |
Run a companywide cloud native hackathon using only open source tooling and get a reusable platform blueprint: a Backstage Portal front end, OpenTofu-managed… | ||
| Tutorial: Build, Operate, and Use a Multi-Tenant AI Cluster Based Entirely on Open Source | C. Misale, O. Tardieu, D. Grove | 01h 15m |
Open-source stack shows a concrete recipe: deploy Nvidia GPU Operator, Kueue for workload-aware queuing and quotas, scheduler plugins for gang and… | ||
| Taking Care of Your Control Plane With API Priority and Fairness and Resource Quotas | Matteo Ruina, Ayaz Badouraly | 32m |
Datadog runs APF and quota tuning across hundreds of clusters (thousands of workloads, hundreds of thousands of pods on tens of thousands of nodes) and shows… | ||
| Taming 50 Billion Time Series: Operating Global-Scale Prometheus Deployments on Kubernetes | Orcun Berkem, Alan Protasio | 31m |
Claims operating 50 billion active time series across 20 regions using Cortex on Kubernetes and scaling each cell to ~1 billion active series, with per-cell… | ||
| Where’s All My Memory Gone? Mapping K8s Memory Metrics To Physical Resources | Mahé Tardy | 28m |
Prometheus reads container_memory_working_set_bytes from cAdvisor (exposed by kubelet), which computes it from cgroup stats: on v2 memory.current minus… | ||
| Kubernetes Backup Legitimized: CSI Changed Block Tracking Has Arrived | M. Lavi, C. Braganza, X. Yang | 32m |
Kubernetes now exposes Changed Block Tracking via KEP-3314 with an implementation in CSI that is end-to-end tested and available in Kubernetes 1.33 alpha. The… | ||
| Keynote: Mind the Gap: Bridging Cloud Native Innovation with Real-World Use | Carlo Fisicaro, Stephen Connolly, Fabio Airoldi, Tyson Sing | 18m |
HSBC reports 600 million hits a day across ~7,000 production services on about a dozen clusters, using sharded markets, blue‑green rehydration for upgrades… | ||
| Keynote: Open Source in Apple’s Private Cloud Compute | Katie Gamanji | 05m |
Private Cloud Compute deploys Apple silicon servers and routes gRPC bidirectional streaming from device to server with payloads encrypted and device-rooted end… | ||
| Keynote: Awards Ceremony | (unnamed speaker) | 16m |
Announcements list concrete outcomes and numbers: the CNCF end user community now includes 150 organizations and an end‑user advisory board with NYT, Apple… | ||
| Keynote: Driving Innovation at Michelin: How We Scaled Cloud & On-Prem Infrastructure While Cutting Costs | G. Quennesson, A. Pons | 05m |
Michelin re-architects a Kubernetes platform to run 441 business applications across 62 cloud and on‑prem clusters, automating lifecycle and infra provisioning… | ||
| Sponsored Keynote: The Weight of Data: Rethinking Cloud-Native Systems for the Age of AI | V. Caldeira, H. Cummins | 06m |
Argues cloud-native must shift from stateless to state-aware systems because AI agents produce high-volume, shared, mutable context and traditional failure… | ||
| Sponsored Keynote: Hand Meet Glove: Why Kubernetes Will Become the Platform of Choice for Agentic Architectures | I. Levine, K. Babo | 09m |
Solo.io open-sources several components and donates them to CNCF: K gateway (formerly Glue) enters the sandbox and includes Glue AI gateway features for model… | ||
| Sponsored Keynote: Redefining MLOps at Scale on Top of Kubernetes | Randy Bias | 03m |
Claims a runnable demo: Cordant as a super control plane running on the KZ Kubernetes distribution deploys OpenStack plus a G-core control plane and CNCF… | ||
| Keynote: Adventures of Building a Platform as a Service for the Government | H.K. Flaatten, A.F. Strand | 13m |
NAV builds and open-sources nice, a Kubernetes-based PaaS used by 100+ product teams and backed by 300 in-house developers, 3,000 public GitHub repos, and 10… | ||
| SIG Docs and You: Modernizing API Reference Generation | Kat Cosgrove, Xander Grzywinski | 10m |
Process requires cloning multiple repos, setting GOPATHs, and running a brittle generator that must run generation twice for Kubernetes and kubectl. The bash… | ||
| Unlocking the Future of Kubernetes Policy as Code With Kyverno | Vishal Choudhary, Frank Jogeleit | 33m |
Kyverno extends Kubernetes admission with new CRD policy types (validating and image-validating now; mutating, generate, cleanup coming) and adopts CEL… | ||
| Emissary-ingress: Version 4 and the Road Ahead | Flynn | 21m |
Emissary 3.10 ships as the last 3.x release and Emissary 4 aims to replace CRD group ambassador.io with new API group emissary.dev, remove conversion webhooks… | ||
| Linkerd Update: Gateway API, Client-Specific Policy, Federated Services, Multicluster, Rust, & More! | Alex Leong | 30m |
Linkerd ships a Rust micro-proxy and weekly production-ready edges; recent releases (2.16–2.18) add IPv6, an egress network CRD for outbound observability and… | ||
| The Immediate and Lasting Benefits of TAG Security Assessments | Brandt Keller, Ben Hirschberg | 30m |
TAG Security provides a self-assessment template and a volunteer-led joint review process that check concrete controls, not vague promises. Cubescape runs as a… | ||
| Open Source Malware or a Vulnerability? The Philosophical Debate and How To Mitigate | Brian Fox, Madelein van der Hout, Santiago Torres-Arias | 30m |
Claims that the ecosystem already hosts 828,000 malicious components and that attackers publish about 18,000 new packages per week (mostly npm, then Python)… | ||
| How We Solved TLS at Scale: Self-Service, Multi-Tenant Cert-manager | Erik Godding Boye, Tim Ramlot | 31m |
A production setup issues short‑lived mTLS certificates for a thousand microservice workloads across shared clusters and enables true self‑service by… | ||
| Generative AI Model Data Pre-Training on Kubernetes: A Use Case St... | Alexey Roytman, Anish Asthana | 27m |
Demonstrates a production LLM data stack that uses Kubeflow Pipelines to orchestrate Ray jobs via KubeRay and a Data Prep Kit (DPK) for reusable transforms… | ||
| Tutorial: Rock, Paper, Scissors! Build an AI-powered Interactive Game With Argo CD and Kubeflow | Natale Vinto, Daniel Oh, Roberto Carratala, Alex Soto Bueno, Hind Azegrouz | 55m |
Live multiuser Rock Paper Scissors is deployed as a production‑grade microservice stack with Argo CD, Kubeflow pipelines and KServe Model Mesh serving a CPU… | ||
| From Hours To Minutes: The Evolution of Platform Engineering at Decathlon | Adrien Gillard, Christophe Furmaniak | 25m |
Decathlon scales a platform for 5,000 users that delivers 20 minutes to provision environments by running YAML descriptors and Terraform under the hood to… | ||
| Practical Zombie Hunting for Kubernetes Users | Holly Cummins | 31m |
Claims that ~25–30% of servers do no useful work and average utilization sits at ~12–18%, costing an estimated $26B in always‑on cloud waste in 2021 and… | ||
| Building a Platform Framework: Lessons Learned From Developing a Multi-Cluster Kubernetes Operator | Cat Morris, Jake Klein | 22m |
Kratix is an open source platform framework that implements a promise CRD (YAML) to declare services and orchestrates multi-cluster delivery by writing… | ||
| Simplify Kubernetes Operator Development With a Modular Design Pattern | Mostafa Hadadian, Alexander Lazovik | 19m |
Presents a concrete design: split large CRDs into smaller trait CRDs and replace monolithic controllers with focused microcontrollers coordinated by a… | ||
| Open Policy Agent (OPA) Intro & Deep Dive | Charlie Egan, Anders Eknert | 29m |
Open Policy Agent is a general-purpose policy engine that takes JSON in and JSON out, evaluates Rego policies and writes decisions to a decision log for audit… | ||
| Vitess: Schema Changes at Scale | Rohit Nayak, Shlomi Noach | 38m |
Vitess performs coordinated non‑blocking schema changes by creating a shadow table, copying billions of rows while replaying binlog events, and then renaming… | ||
| Kubespray: Driving Cost-Efficiency for AI on Kubernetes | Antoine Legrand, Mohamed Zaian | 12m |
Kubespray manages cluster lifecycle across cloud and bare metal and is used to avoid vendor lock‑in while mixing providers for cost savings. CI routinely… | ||
| In the Eye of Falco: Transforming Your View of Linux Kernel Security | Luca Guerra, Jason Dellaluce, Aldo Lacuku, Leonardo Grasso, Aurélie Vache | 30m |
Falco moves to a smaller default Wolfie minimal image to cut build-time CVE noise, ships low‑level optimizations (clang/zig and allocator changes) that yield… | ||
| Multi-cluster Orchestration System: Karmada Updates and Use Cas... | Hongcai Ren, Joe Nathan Abellard | 27m |
Karmada is a multicluster Kubernetes control plane that propagates configmaps, secrets and CRDs, provides cluster and application failover and an… | ||
| TUF-en up Your Software Supply Chain | Marina Moore, Kairo De Araujo | 29m |
Explains how TUF prevents replay and tampering by layering metadata (root.json, snapshot, timestamp) and multi‑sig root keys and shows a live flow: ingest… | ||
| SIG API Machinery: Project Updates and Release Planning | Joe Betz | 30m |
SIG API Machinery updates specific: ordered namespace deletion deletes pods first to avoid last‑second pod churn; snapshotable API server cache serves all list… | ||
| SIG-Multicluster Intro and Deep Dive | Jeremy Olmsted-Thompson, Laura Lorenz, Stephen Kitt, Ryan Zhang | 30m |
SIG-Multicluster presents concrete APIs and projects: a read-only cluster profile API (properties + credentials work pending), an about API for naming… | ||
| Guiding Kubernetes: The Steering Committee's Role in Project Evolution | Maciej Szulik, Stephen Augustus | 29m |
Kubernetes steering committee oversees non‑technical governance: elections for committees, charter approval, funding decisions and delegating responsibilities… | ||
| Redesigning Ingress: Docker’s Transition To the Next-Gen Gateway API | Kateryna Nezdolii, Ryan Hristovski | 26m |
Docker migrates HAProxy and Nginx to Envoy Gateway, consolidating auth, rate limiting and tracing into a single proxy and moving global rate limits to an Envoy… | ||
| Istio: The Past, Present and Future of the Project and Communi... | Lin Sun, Louis Ryan, Raymond Wong | 35m |
Istio announces GA ambient mode with a two‑layer ambient sidecar-less data plane (zero‑trust layer 4 tunnel plus layer‑7 waypoint proxy), claiming highest TCP… | ||
| WG-Batch Updates: What’s New and What Is Next? | Marcin Wielgus | 34m |
WG-Batch reports concrete progress: Kueue hits about 50 releases and offers workload-level scheduling with topology-aware placement, two fair-sharing modes… | ||
| Kubeflow Ecosystem: What’s Next for Cloud Native AI/ML and LLMOps | Johnu George, Andrey Velichkevich, Amber Graner, Yuki Iwai, Yuan Tang | 32m |
Kubeflow announces the 1.0 release and stitches concrete LLMOps pieces: a donated Spark Operator now in the ecosystem with a benchmark of 60,000 Spark apps… | ||
| Helm 4 You | Matt Farina, Andrew Block | 37m |
Helm 4 introduces explicit breaking changes: CLI APIs are refactored so commands become an importable package, deprecated Kubernetes APIs (eg Kubernetes… | ||
| Kubernetes WG Device Management - GPUs, TPUs, NICs and More With DRA | Kevin Klues, Patrick Ohly | 30m |
DRA reaches beta in Kubernetes 1.32 and the WG moves features toward GA (targeting 1.34); scheduler-side logic, kubelet drivers and the pod resources API are… | ||
| Securing the Gateway: A Deep Dive Into Envoy Gateway's Advanced Security Pol... | Huabing Zhao | 26m |
Envoy Gateway v1.3 exposes a SecurityPolicy CRD that maps to Envoy configs and enforces CORS, Basic Auth, API Key, External Auth, OIDC via Amazon, and JWT… | ||
| Strengthening Auth in Kubernetes: Image Pulling, DRA Admin Access & Pod Certificates | Rita Zhang, Stanislav Láznička | 31m |
Kubernetes Auth SIG lands concrete features: v1.33 GA adds bound ServiceAccount tokens with node and jti claims for replay protection; cluster trust bundles… | ||
| From the Observability TAG: Designing a Common Query Language for Observability Data | lolita Sharma, Pereira Braga, Chris Larsen | 34m |
Observability TAG finalizes a semantic query spec in 2025 that uses SQL as the baseline and recommends a federated, select-only subset with an intermediate… | ||
| Platform Engineering Loves Security: Shift Down To Your Platform, Not Left To Your Developers! - Maxime Coquerel, Royal Bank of Canada | Maxime Coquerel, Mathieu Benoit | 26m |
Argues that platform teams must shift down to the platform by baking security controls into templates, CI and the developer UX rather than offloading them to… | ||
| Starting and Scaling a Platform Engineering Team | Camille Fournier, Ian Nowland | 32m |
Recommendation: start a platform team when shared “glue” becomes a bottleneck around 50–250 engineers; platform work must combine software engineering… | ||
| Workload Identity for Humans: A Twelve-Factor Approach | Vish Abrams | 29m |
Proposes platform-managed, connection-scoped credentials that rotate every 30–60 minutes to avoid long-lived secrets and confused-deputy risks, using existing… | ||
| Encryption, Identities, and Everything in Between; Building Secure Kubernetes Networks | Lior Lieberman, Igor Velichkovich | 31m |
Explains why cluster-scale segmentation fails today and which tools actually close the gaps: Cilium NetworkPolicy and Istio AuthorizationPolicy add L4/L7… | ||
| How We Moved Spotify To a Proxyless gRPC Service Mesh | Erik Lindblad, Erica Manno | 31m |
Spotify replaces DNS-based discovery with a proxyless gRPC mesh using XDS, scaling to 1.5 million Kubernetes pods, and builds traffic splitting, zone-aware… | ||
| Journey at the New York Times: Is Sidecar-Less Service Mesh Disappearing Into Infrastructure? | Lin Sun, Ahmed Bebars | 31m |
The New York Times migrates from sidecars to Istio ambient mode, running a node-level Rust Z tunnel for mTLS and an Envoy-based waypoint per namespace for… | ||
| Debugging Envoy Tunnels: A Deep Dive | Carlos Sanchez, Alexandra Stoica | 29m |
Adobe runs Envoy tunnels with mTLS across 60+ Azure clusters serving 31,000 customer environments and 200,000+ K8s deployments; this session reproduces… | ||
| Image Snapshotters for Efficient Container Execution in Particle Physics | Clemens Lange, Valentin Volkl | 29m |
Benchmarks compare containerd snapshotter plugins—stargz, SOCI, and CVMFS—against overlayFS measuring startup time and bytes pulled; lazy snapshotters start… | ||
| GPU Sharing at CERN: Cutting the Cake Without Losing a Slice! | Diana Gaponcic | 30m |
Centralize GPUs with Kubernetes DRA 1.42 beta and an NVIDIA DRA driver to allocate time-slice, MPS or MIG without node relabels; benchmarks on an A1 40GB card… | ||
| Get WITty: Evolving Kubernetes Scheduling With the WebAssembly Component Model | Dejan Pejchev, Jonathan Giannuzzi | 27m |
Claims that adopting the WebAssembly Component Model makes Kubernetes scheduler plugins language‑agnostic; attempted a component refactor that auto‑generates… | ||
| Dynamic Multi-Cluster Controllers With Controller-runtime | Marvin Beckers, Stefan Schimanski | 35m |
Introduces a practical extension to controller-runtime that lets controllers reconcile across a dynamic fleet by plugging in a provider concept that discovers… | ||
| eBPF and Wasm: Unifying Userspace Extensions With Bpftime | Yusheng Zheng | 31m |
Claims a userspace eBPF runtime called BPF time that uses dynamic binary instrumentation, bytecode verification and hardware isolation to extend eBPF into… | ||
| Beyond the Limits: Scaling Kubernetes Controllers Horizontally | Tim Ebert | 31m |
Demonstrates a working sharding system that partitions controller work by injecting a shard label via a mutating webhook and tracking membership with… | ||
| A Cloud Native Workflow for Hardware-in-the-Loop Software Development | Miguel Angel Ajo Pelayo | 31m |
Jumpstarter automates hardware-in-the-loop CI by leasing physical devices from Kubernetes: a Go controller with Python client drivers exposes exporter CRDs… | ||
| Weaving a VEX Feed Through the Kubernetes Project | Adolfo García Veytia | 26m |
Kubernetes publishes a machine-readable VEX feed that combines three sources: maintainer assessments turned into signed OpenVEX attestations via a Vexflow… | ||
| Redefining Access Control: Scaling Policy as Code for Humans and AI Agents | Raz Cohen | 30m |
Argues that Policy as Code scales authorization to both humans and AI agents by enforcing a four‑perimeter pipeline: prompt filtering, RAG data protection… | ||
| SPIFFE in Practice: Universal Identity for WebAssembly Workloads | Joonas Bergius, Colin Murphy | 26m |
Project integrates SPIFFE/SPIRE into wasmCloud to give each WebAssembly component a short‑lived identity, using the delegated identity API so workloads… | ||
| Mind the Gap: Bridging Supply Chain Policy With Git-less GitOps and GUAC | Michael Lieberman, Andrew Martin | 33m |
Live demo shows an exploited dependency introduced, an SPDX SBOM generated with Trivy and uploaded into OpenSSF GUAC which indexes dependencies so a single… | ||
| IAM, Agent: Identity for Autonomous AI | Matthew Bates | 33m |
Prototype chat agent calls two tools (get_orders, get_order_details) via Langraph and Gemini Flash on Vertex AI and successfully returns order data in the… | ||
| Identity-based Trust - Till Death Do We Part? | John Kjell, Kairo De Araujo | 28m |
Sigstore is used for identity signing but append-only Rekor means illegitimate certificates stay forever; the talk demonstrates an emergency release where a… | ||
| Building & Operating a Large-scale HPC AI Cluster on Kubernetes | Kalyan Saladi, Chandan Avdhut | 41m |
Shares how a cloud research cluster with 12K GPUs runs Slurm on Kubernetes by keeping slurm daemon on the host, containerizing control-plane components, and… | ||
| Balancing Cost and Efficiency: Day2 Optimization of Multi-Cluster AI Infrastructure | Kevin Wang | 27m |
Describes running Karmada plus Volcano to optimize multi‑cluster AI scheduling, comparing a lightweight resource model (graded node status) with a slower but… | ||
| AI Pipelines With OPEA: Best Practices for Cloud Native ML Operati... | Ezequiel Lanza, Melissa McKay | 28m |
Open Platform for Enterprise AI (OPEA) provides composable, Kubernetes-first pipelines with concrete artifacts: 20+ blueprints (Docker Compose and Helm) that… | ||
| A Practical Guide To Benchmarking AI and GPU Workloads in Kubernetes | Yuan Chen, Chen Wang | 32m |
Step-by-step Kubernetes benchmarking that actually deploys servers, runs load, and returns metrics: uses NVIDIA Triton (HTTP/gRPC), the Triton Performance… | ||
| Chaos Engineering Practice Under Ultra-large-scale Cloud Native Edge Computing | Yue Bao, Yue Li | 21m |
KubeEdge claims stable operation at 100,000 edge nodes and management of over one million pods by using a multi‑instance cloud‑core / edge‑core design, an… | ||
| Defusing the Kubernetes API Performance Minefield | Madhav Jivrajani, Marek Siarkowicz | 35m |
Explains why controllers that list large CRDs trigger massive allocations (five allocations per list -> one when served from cache) and how recent changes cut… | ||
| A Huge Cluster or Multi-Clusters? Identifying the Bottleneck | Paco Xu, Saiyam Pathak | 34m |
Compares concrete limits and fixes: tested guidance for 5,000+ node clusters, Google’s 65,000-node demo, ByteDance’s Kubebrain at 20k, and when to split into… | ||
| Dancing With the Pods: Live Migration of a Database Fleet While Serving Millions of Queries | Jayme Bird, Manish Gill | 23m |
ClickHouse migrates a legacy fleet of thousands of customer clusters over ~6 months with zero downtime by replacing single StatefulSets with a… | ||
| Cloudy With a Chance of Kubernetes: Going From One To Three Cloud Providers | Laurent Bernaille, Maxime Visonneau | 34m |
Datadog moves from one region on AWS to six regions and 29 edges across three cloud providers by running hundreds of clusters and tens of thousands of nodes on… | ||
| How We Progressively Deliver Changes To Kubernetes Using Canary Deployments and Feature Flags | Bob Walker | 28m |
1,600 customer instances run across eight Kubernetes reefs and updates move through staff → insiders → early adopters → stable, with a rotating 5% canary… | ||
| Breaking Free From the Cloud: Banking on Self-Hosted Kubernetes | Kārlis Akots Gribulis, Per Hedegaard Christiansen | 25m |
Global investment bank moves from managed cloud to on‑prem Kubernetes and reports ~85% compute+storage cost savings, 15–20x faster cluster creation, and… | ||
| Set Your Developers Free: Fleet Management at Spotify | Stefan Särne | 25m |
Spotify runs fleet automation that updates dependencies and resources across thousands of repos and over 10,000 components, claiming a Log4J patch rolled… | ||
| Building a 5* Kubernetes Hotel | Dean Fuller, Rachael Wonnacott | 32m |
Fidelity builds an internal “Kubernetes Hotel” on Amazon EKS to give 2,500 developers a Cloud Foundry–like platform; the MVP ships as a one-star motel then… | ||
| Extending Kubernetes Resource Model (KRM) Beyond Kubernetes Workloads | Mangirdas Judeikis, Nabarun Pal | 29m |
Argues that KRM can become KRM++ by externalizing APIs into a multi‑tenant control plane (kcp) that splits API provider versus consumer and implements API… | ||
| Automating Kubernetes Cluster Updates: Achieving Zero Downtime Effortlessly | Haitao Zhang, Ling Ling, Wei Jiang, Baofa Fan | 18m |
Automates Kubernetes control-plane and node upgrades using Karpenter to replace nodes with zero downtime on AWS, Azure and AlibabaCloud, with examples of… | ||
| A Journey To Modernizing a Regulated Cloud Control Plane | Pranita Praveen, Steven Borrelli | 26m |
Macquarie moves a legacy AWS pipeline into a multi‑cloud control plane running on EKS + Crossplane with Argo Workflows/Argo CD for CI/CD, Gatekeeper for… | ||
| A Day in the Life of a Kubernetes Engineer | Rajas Kakodkar, Nikhita Raghunath, Amine Hilaly, Shane Lawrence, Kasper Borg Nissen | 32m |
Day-to-day work centers on real incidents: an engineer accidentally drains an entire cluster during a parallel script run, another upgrade removes pods until a… | ||
| Can You Maintain 1000 Apps? WasmCloud & K8s: The Ultimate Golden Template | Liam Randall | 31m |
Demonstrates that by replacing heavyweight container templates with a platform harness built on wasmCloud and Kubernetes, platform teams can manage 1,000… | ||
| Conveying the Importance of Platform as a Product in the Cloud Native Ecosystem | Valentina Rodriguez Sosa, Danielle Cook, Simon Forster, Colin Griffin | 27m |
Argues that treating an internal platform as a product (not a time‑boxed project) drives measurable business value by funding, operating, and iterating it long… | ||
| From Metal To Apps: LinkedIn’s Kubernetes-based Compute Platform | Ahmet Alp Balkan, Ronak Nathani | 40m |
LinkedIn runs Kubernetes on bare metal across 500,000+ servers and 1.5M containers, using a gRPC compute broker and inventory manager to allocate heterogeneous… | ||
| How To Rename Metrics Without Impacting Somebody’s Observabili... | Bartłomiej Płotka, Arianna Vespri | 31m |
Prototype implements on-the-fly metric versioning for Prometheus by attaching an OpenTelemetry-style schema URL label and applying autogenerated transformation… | ||
| Optimizing Metrics Collection & Serving When Autoscaling LLM Workloads | Vincent Hou, Jiri Kremser | 35m |
Demonstrates that switching to push-based metrics with KServe, an OpenTelemetry collector sidecar and a KEDA OTLP add-on yields much faster, configurable… | ||
| Observability Pipeline Query Languages: Present and the Future | Jacek Migdal | 33m |
Proposes collapsing many vendor languages into a SQL-centered approach (semantic standard first) and demos a proof-of-concept: an open source Grafana plugin… | ||
| Limitless Possibilities, Consistent Design: Crafting Dashboards With Perses DAC | Nicolas Takashi, Antoine Thébaud | 30m |
Perses presents Dashboard-as-Code with concrete tooling: Go and Cue SDKs generate Kubernetes-style YAML/CRD, a Perses operator or simple Docker/Helm deployment… | ||
| How To Adopt OpenTelemetry in an Enterprise Where Incumbent Vendor Tools Reign Supre... | Chris Weldon | 37m |
Three-year enterprise rollout uses OpenTelemetry to cut MTTR dramatically — a production incident post-instrumentation goes from hours to under 15 minutes — by… | ||
| Pushing the Limits of Prometheus at Etsy | Chris Leavoy, Bryan Boreham | 35m |
A single Prometheus instance runs on 128 cores, 4 TB RAM and sustains peaks near 500 million series and 5 million samples/sec, but suffers remote_write lag and… | ||
| OTel Sucks (But Also Rocks!) | Juraci Paixão Kröhling, OllyGarden, Daniel Dyla | 22m |
Config SIG now simplifies SDK configuration but auto instrumentation for .NET and Java sometimes creates extremely high cardinality spans that overload… | ||
| Challenges of and Solutions for Migrating Spark From Legacy Hadoop Clusters To Kubernetes | Neha Singla, Rasik Pandey | 38m |
Case study of migrating Spark from bare metal YARN and Mesos to Kubernetes and then adding Unicorn scheduler to regain queuing, gang scheduling, priority… | ||
| OTel Me How To Get My Open Source Community Taken Seriously: Lessons Learned as an OTel Maintainer | Reese Lee, Adriana Villela | 28m |
Built an OTel End User SIG out of a 2021 working group, with its own GitHub, YouTube, and CNFC Slack channel; runs monthly OTel Me sessions (live‑streamed via… | ||
| Navigating the Inevitable: Kubernetes Breaking Changes Behind the Scenes | Marko Mudrinić | 30m |
Kubernetes runs a strict KEP-driven process with a ~13–14 week release cadence, production readiness freeze ~11 weeks before, enhancements freeze ~10 weeks… | ||
| Hot Takes: Kubernetes Paintainers Bring the Heat | Ian Coldwater, Marly Salazar, Taylor James Dolezal, Kat Cosgrove, Xander Grzywinski | 37m |
Kubernetes maintainers describe concrete wins and pain points: adoption churn from the Docker shim deprecation that forced long migrations and prompted… | ||
| Building a Ubiquitous Cloud Native: Beyond the Intersectionality | Carol Valencia, Pawel Piwosz, Satyam Soni, Anita Ihuman, Audra Montenegro | 44m |
Local chapters report concrete numbers and tactics: New Delhi scales to 200 attendees and struggles with check‑in, AV, and catering; São Paulo runs 30–100… | ||
| A Practical Guide To Cloud Native Solutions: Demonstrating ROI and Business Impact | Danielle Cook, Simon Forster | 23m |
Proposes building a lightweight platform from CNCF open source components in about six weeks, staffed by two engineers for 30 days at ~£36k plus ~£10k training… | ||
| Harbor Project - The Maintainers Session | Orlin Vasilev, Vadim Bauer | 27m |
Harbor 2.13 RC1 ships with about 50 fixes/features, enhanced audit logging tracking ~14–15 event types and toggles, plus first-class display for CloudNativeAI… | ||
| Kubernetes SIG Storage: Intro & Deep Dive | Xing Yang, Jan Šafránek | 27m |
SIG Storage maintains core APIs and is shipping concrete changes: auto-remove PVCs from StatefulSets is graduated, recovery-from-resize-failure has reached… | ||
| Driving Chaos Engineering Forward: What’s New and Next With LitmusCha... | Sarthak Jain, Saranya Jena | 30m |
LitmusChaos reports concrete progress: 2M+ installations and 68M Docker pulls with a 300% year growth, 21 maintainers and 250+ adopters; recent 3.7.0 adds… | ||
| Longhorn: Intro, Deep Dive and Q&A | David Ko | 32m |
Longhorn ships a new v2 data engine based on SPDK that shows clear IOPS and throughput gains over v1 in CNF-sponsored benchmarks, scaling with 1–4 CPU cores… | ||
| SIG Network Intro and Updates | Dan Winship, Nadia Pinaeva, Bowei Du, Daman Arora | 26m |
Gateway API 1.3 adds core support, retry budgets, listener sets and percentage/fractional request mirroring, and recommends returning a 421 to avoid TLS… | ||
| Wasm Whiplash: WasmCloud's Wild Ride To Standards | Brooks Townsend | 27m |
Started in 2019 with a proprietary FFI, IDL and codegen stack that forced writing SDKs for Rust Go TypeScript Zig and Swift, the project spends four years on a… | ||
| Expanding the Contributor Pipeline Through Inclusion | Khallai Taylor, Sandeep Kanabar, Stephane Este-Gracias, Nancy Chauhan, Josh Berkus | 33m |
Projects that want more contributors adopt specific practices: record and document every meeting, publish simple CONTRIBUTING docs with diagrams that include… | ||
| KubeCon FamilyFortune, Episode 2 | Tim Hockin, Lucy Sweet | 32m |
A live Family Fortune game runs on a tiny GKE cluster with real buzzers and an overengineered controller, driven by a survey of 100 contributors that produces… | ||
| High Availability With '503: Unavailable' | Robert-Jan "RJ" Huijsman | 05m |
Claims that embracing 503s as cheap, retryable failures and building apps with Envoy Istio and gRPC drastically reduces HA complexity while keeping user-facing… | ||
| Kueue: Save Some QPS for the Rest of Us! How To Manage 100k Updates Pe... | P. Bundyra | 05m |
Kueue faces updating position for up to 100,000 jobs and avoiding saturating the API server, so it rejects per-workload position CRD updates as too many etcd… | ||
| Observability Diet: Your 5-Step Plan To Trim the Data Fat | Pranay Prateek | 06m |
Many orgs send terabytes of telemetry while using only 20% of it, so the plan focuses on concrete volume cuts: run OpenTelemetry Collector processors to… | ||
| Resource Roulette: Winning the Kubernetes Allocation Game | Daniele Polencic | 05m |
Static requests and limits cause either wasted CPU reserved but unused or cluster-wide contention when real use exceeds them; adaptive allocation that divides… | ||
| Rust Here, Rust There, Rust Everywhere! How a Crab Conquers the Cl... | Sascha Grunert | 05m |
Rust shows concrete footholds in cloud native: 250 million lines of Rust across 370 CNCF repos, ranking #6, partial rewrites (CRI-O, containerd) work but force… | ||
| Scaling To the Stars: Simulating Massive Clusters With KWOK | Soumya Balakrishnan | 05m |
NVIDIA uses KWOK to simulate very large clusters on a laptop and validate rollout logic before touching production. A watchdog script for daemonsets initially… | ||
| There Is a New Volume Type in Town! | Mario Loriedo | 06m |
New Kubernetes volume type "image" mounts an OCI image (or generic OCI artifact) into a container so you can mount models as OCI images and serve a small LLM… | ||
| Extending Envoy With WebAssembly | Yuki Ito | 05m |
Envoy gains small WebAssembly modules that run as HTTP filters using the Proxy-WASM ABI, built with the Proxy-WASM SDK and authored in Rust and Go. Real… | ||
| Solving Real-World Edge Challenges With K0s, NATS, and Raspberry Pi Clu... | P. Ramhit | 05m |
A floating, IP68 submersible buoy running Raspberry Pi hardware with an 18 W solar panel, LiPo battery, multiple sensors and a 3G modem collects temperature… | ||
| Cloud Native Wheel of Fortune: 5 Spins for 5 Topics! | Steve Wade, Matteo Bianchi | 30m |
Airgapped environments require a local image registry strategy (bootstrapping Kubernetes is easier than hosting images), while eBPF tooling like Falco (eBPF)… | ||
| Containerd: Project Update and Deep Dive | M. Pavlenko, A. Suda, L. Brehm, S. Karp, J. Zhou | 34m |
containerd 2.0 lands after an 18‑month effort to remove legacy v1 runtimes, deprecations, and stabilize APIs introduced in 1.7 while adding transfer service… | ||
| Cloud Native Communities in Action: How Japan Shaped Its Path To KubeCon | Kohei Ota, Shu Muto, Yuichi Nakamura, Sunyanan Choochotkaew, Noriaki Fukuyasu | 32m |
Japan creates a formal CNCF Japan chapter 18 months ago, runs upstream training since 2019 with 12 events and 275 trainees (30% contributing to CNCF projects… | ||
| Beyond Security: Leveraging OPA for FinOps in Kubernetes - Sathish Kumar Venkatesan | Sathish Kumar Venkatesan | 26m |
Shows how Open Policy Agent plus Gatekeeper enforce FinOps guardrails in Kubernetes by denying expensive choices and mutating requests and by auditing existing… | ||
| AI Workload Preemption in a Multi-Cluster Scheduling System at Bloomberg - Leon Zhou & Wei-Cheng Lai | Leon Zhou, Wei-Cheng Lai | 28m |
Bloomberg implements Karmada priority and preemption to schedule tens of thousands of GPU training jobs across multiple on‑prem bare‑metal Kubernetes clusters… | ||
| ⚡Lightning Talk: Scheduling Success: Precision Updates for Continuous Manufacturing Operations | J.C. Orozco | 05m |
Cloud-hosted cluster and node updates trigger a cron job checks provider updates which starts CI pipelines that deploy vendor versions to integration… | ||
| BoF | Fueling Cloud Native: The Data We Have, the Data We Need - Hilary Carter, SVP Research | Hilary Carter | 30m |
LF Research catalogs 78 studies on data.world under the Community Data License (CDLA 2.0) and publishes concrete findings: 89% cloud native adoption… | ||
| Keynote: LLM-Aware Load Balancing in Kubernetes: A New Era of Efficiency | Clayton Coleman, Jiaxin Shan | 16m |
New Kubernetes APIs called Gateway API inference extension turn Gateways into inference routers and plug into Envoy via Envoy xDS callout to run a realtime… | ||
| Sponsored Keynote: The Science of Winning: Oracle Red Bull Racing’s Formula with Open Source, Kubernetes and AI | Sudha Raghavan | 07m |
Claims that Oracle Red Bull Racing runs trackside, factory and cloud workloads on Kubernetes to deliver real-time insights for race strategy and post-race FIA… | ||
| Keynote: Cutting Through the Fog: Clarifying CRA Compliance in Cloud Native | Eddie Knight, Michael Lieberman | 15m |
European Cyber Resilience Act goes into full effect in 2027 with a first enforceable reporting duty on Dec 11, 2026 for known exploitable vulnerabilities… | ||
| Sponsored Keynote: Lessons Learned in LLM Prompt Security | Jakub Suchy | 05m |
HAProxy load balancers run prompt-classification models at the edge to detect jailbreaks and PII but performance becomes the bottleneck: 150–200 ms per 500… | ||
| Keynote: 221B Cloud Native Street | Ricardo Rocha, Katie Gamanji | 13m |
CNCF reports 214 projects with 134 sandbox / 36 incubated / 31 graduated and 13 archived, and it doubles its project count faster than before (100 in six… | ||
| Keynote: Science at Light Speed: Cloud Native Infrastructure for Astronomy Workloads | Carolina Lindqvist | 14m |
Square Kilometre Array regional infrastructure prototypes a cloud-native stack that glues heterogeneous sites into a federated SRCNet, claiming… | ||
| Fluent Bit v4: A Decade of Innovation and What’s Next | Leonardo Alminana | 33m |
Fluent Bit v4, released Monday, focuses on concrete wins: trace sampling adds probabilistic head sampling plus tail/table buffering to keep all failure traces… | ||
| Contributing To Kubernetes in Its Second Decade - How ContribEx Enhances the Journey! | Nabarun Pal, Mario Fahlandt, Madhav Jivrajani, Priyanka Saggu | 34m |
SIG ContribEx reports roughly 95,000 contributors, ~4.5 million repo activities and about 8,000 reviewers, and runs concrete programs: a monthly New… | ||
| Crossplane Intro and Deep Dive - The Cloud Native Control Plane Framework | Jared Watts, Nic Cope | 31m |
Crossplane v2 preview ships now and reworks scope and composition: composite resources (XRs) and managed resources become namespaced so apps, deployments… | ||
| Discover CNCF TAG Runtime: Advancing Cloud-Native Innovation from AI to Edge | Ricardo Aravena, Stephen Rust, Rajas Kokodkar, Alexander Kanevskiy, Danielle Tal | 26m |
Covers concrete outputs and near-term plans: CDI spec 1.0 released for device exposure in containers, OCI runtime and network interface work proceeding, and… | ||
| Bridge the Gap To OSS Adoption With Documentation: A Kubernetes Story | Natali Vlatko, Divya Mohan | 32m |
Kubernetes documentation practices prioritize measurable choices: docs maintainers own structure while KE owners own technical content, docs use second-person… | ||
| Beyond Classical Cryptography: Building Quantum-Resistant Cloud Native Infrastructure With SPIFFE | Andres Vega, Hugo Landau | 34m |
Demonstrates a working Kubernetes proof-of-concept that integrates post-quantum cryptography into SPIFFE/SPIRE, Cilium and Envoy to deliver Kyber KEM hybrid… | ||
| Ensuring Quality in Kubernetes: The Graduation Process From Alpha To GA | Antonio Ojea, Benjamin Elder | 32m |
Kubernetes enforces graduation with concrete steps: CI runs use Ginkgo v2 labels and the centralized feature registry to select tests, CI presubmit aims for ~1… | ||
| Authz as a Dev Workflow: Architecting Better Cloud Native Apps | Dan "phrawzty" Maher | 32m |
Argues authorization belongs in the critical path and treated as a dev workflow with concrete patterns: policy as a service and sidecar deployments, plus… | ||
| Data Processing Efficiency: Optimizing Batch Workloads on Kubernetes With Custom Schedulers | Hichem Kenniche | 29m |
Built an open-source city cycling navigation platform and runs Apache Spark on Kubernetes across multi-cloud clusters using Volcano and Apache YuniKorn as… | ||
| Don't Let Your Kubernetes Cluster Go Wild: Ensuring Etcd Reliability | Arka Saha, Chun-Hung Tseng | 26m |
Etcd v3.6 gains a robustness test framework that injects faults and checks strict serializability by running randomized valid workloads against a clean… | ||
| Data Gravity and Kubernetes: Managing Large-Scale Data Ingest With Minimal Latency | Abhishek Bhattacharjee, Arya Soni | 07m |
Claims that combining CSI-backed PVs, edge compute, and service mesh/CNI cuts ingest latency and bandwidth use; demonstrates wiring CSI drivers into Kubernetes… | ||
| Consistent Volume Group Snapshots, Unraveling the Magic | Leonardo Cecchi, Xing Yang | 33m |
VolumeGroupSnapshots claim to take write‑order consistent snapshots of multiple PVCs at the same logical time and is being promoted to beta in Kubernetes. It… | ||
| SIG Scheduling Intro & Updates | Maciej Skoczeń, Kensei Nakada | 30m |
Kube-scheduler adds concrete performance changes: queuing hints let the queue ignore irrelevant node events so pending Pods retry far less often, async… | ||
| Notary Project: The Key To Secure Software Supply Chain | Yi Zha, Guillaume Gill | 29m |
Notary Project signs and verifies OCI artifacts and arbitrary blobs using the Notation CLI and a plugin model that plugs into AWS KMS, Azure Key Vault… | ||
| Cloud Native AI: Harness the Power of Advanced Scheduling for High-Performance AI/ML Training | William Wang, Xuzheng Chang | 30m |
Volcano adds a hyper node API that models nested, switch-aware groups of Kubernetes nodes so schedulers can place tightly communicating LLM training pods on… | ||
| CubeFS in Action: Empowering Users Through Case Studies | Leon Chang | 29m |
CubeFS is a CNCF‑graduated, cloud native filesystem with S3 and POSIX interfaces, two storage engines (multi‑replica and erasure coding), and Raft‑based strong… | ||
| The NATS Stack - Libraries Extensions and the Execution Engine | Tomasz Pietrek, Jordan Rash | 35m |
NATS announces NATS 2.11 features (per-message TTL, consumer pause/impose, batch direct get) plus client-side Orbit extensions for request-many scatter/gather… | ||
| Managing Data at Scale: Best Practices and Evolution of SIG-Apps | Maciej Szulik, Janet Kuo | 30m |
SIG Apps reports concrete changes: pod disruption budgets gain a field to count ready-only PDB counting so nonready pods can be evicted; ReplicaSet downscales… | ||
| Kubernetes SIG Architecture Intro and Updates | John Belamaric, Davanum "Dims" Srinivas | 27m |
SIG Architecture enforces concrete rules: it curates API conventions, runs conformance tests closed gap in 1.31/1.32, vets enhancement proposals with… | ||
| Evolving OpenID Connect and Observability in Keycloak | Ryan Emerson, Takashi Norimatsu | 27m |
Keycloak adds experimental support for RFC 9449 PoP to make stolen access tokens useless and experimental OID4VCI for wallet-based verifiable credentials… | ||
| KubeEdge DeepDive: Architecture, Use Cases, and Project Graduation Updates | Fei Xu, Hongbing Zhang | 28m |
KubeEdge shows a production-grade extension of Kubernetes for intermittent networks: a cloud controller plus an edgecore that embeds a light kubelet, a mapper… | ||
| How We Tackle KubeVirt’s Growth and Scalability | Ľuboslav Pivarč, Alay Patel | 28m |
KubeVirt adopts a lightweight virtualization enhancement process to spread design review across SIGs and produce a roadmap, automates daily scale benchmarking… | ||
| CNCF TAG Network and Cloud Native Network Landscape | Zhonghu Xu, Nic Jackson | 27m |
CNCF is consolidating groups so TAG Network merging into TAG Infrastructure while keeping the same network focus and community channels; expect biweekly… | ||
| Failure Is Not an Option: Durable Execution + Dapr = 🚀 | Marc Duiker | 30m |
Claim: durable execution with Dapr Workflow and Dapr resiliency policies makes long running distributed workflows automatically recoverable. The demo runs C#… | ||
| Tutorial: Hacking up a Storm With Kubernetes | Rory McCune, Marion Mccune, Iain Smart | 53m |
Hands-on lab builds a local kind cluster, applies supplied manifests and shows how a mis-scoped service account token + kubectl exec lets a developer create a… | ||
| Tutorial: Workshop: Developing as a Team for Kubernetes With Nix and Flox | Leigh Capili, Tanja Ulianova | 01h 14m |
Workshop shows a concrete pipeline: a Go + ImageMagick + Postgres app built from a checked-in Flox environment, activated with flux activate, and run locally… | ||
| From Chaos To Control: Migrating Access Control To OpenFGA in a Multi-Tenant World | Jo Guerreiro, Poovamraj Thanganadar Thiagarajan | 29m |
Grafana migrates its legacy access control to OpenFGA, starting with folders and dashboards and using per-tenant stores to avoid cross-tenant leaks and reduce… | ||
| Compliance at the Speed of Innovation: Leveraging AI-Driven Automation for Real-Time Regulatory Read | Larry Carvalho, Simon Metson, Robert Ficcaglia, Anca Sailer, Yuji Watanabe | 30m |
Claims a shift from periodic audits to continuous compliance using OSCAL-based tooling and agentic GenAI; teams report building knowledge graphs and graph-RAG… | ||
| Smooth Scaling With the OpAMP Supervisor: Managing Thousands of OpenTelemetry Collectors | Evan Bradley, Andy Keller | 26m |
OpAMP Supervisor uses the OpAMP protocol and an out‑of‑process supervisor to manage collectors, demonstrating a live rollout to 50 Dockerized OpenTelemetry… | ||
| The State of Prometheus and OpenTelemetry Interoperability | Arthur Silva Sens, Juraj Michálek | 27m |
Prometheus and OpenTelemetry now exchange concrete features: Prometheus 3.0 adds UTF8 support and an OpenTelemetry remote receiver (behind a security flag) so… | ||
| The Missing Metrics: Measuring Memory Interference in Cloud Native Systems | Jonathan Perry | 34m |
Cloud-native nodes suffer cache eviction and memory-bandwidth contention that repeatedly inflates P95/P99 by 4–14x and cuts CPU efficiency by ~25%; major… | ||
| Wait! Can Your Pod Survive a Restart? | Aya Ozawa | 26m |
Shows two live demos: an HTTP server and an Operator with leader election and proves how to get zero- or low-downtime restarts. Explains using Dockerfile… | ||
| Taming the Beast: Advanced Resource Management With Kubernetes | Lucy Sweet, Dawn Chen | 36m |
Kubernetes 1.30–1.32 adds concrete controls: pod-level resource limits let multiple containers share a single CPU/memory budget (reducing overprovisioning)… | ||
| Demystifying Why the World Is Built on Kubernetes: Learning To Leverage Bespoke CRDs and Controllers | Abby Bangser, Sébastien Blanc | 27m |
Claims that a single CRD schema plus one reconcile loop unlocks platform power and that controllers are just pods doing event-driven work. Shows Crossplane… | ||
| Surviving Day2 : Picking the Right Tool To Secure Your Kubernetes Habitat | Bruno Gabriel da Silva, Henrique Santana | 27m |
CNCF security landscape lists about 80 projects and keeps growing; expect concrete tactics not platitudes. Image scanning uses Trivy to extract layers, build a… | ||
| Public End User Technical Advisory Board (TAB) Town Hall | Bob Killen | 27m |
Public End User Technical Advisory Board exists just over a year and focuses on tangible outcomes: producing reference architectures, standardizing project… | ||
| Public Technical Oversight Committee (TOC) Meeting | Chris Aniszczyk | 31m |
Technical Oversight Committee explains concrete changes: a new cohort of TOC shadows, a tag reboot consolidating TAGs and time-scoped initiatives, and plans to… | ||
| Into the Shopfloor: Moving Manufacturing Execution Systems To Kubernetes | Manuel Peuster, Andrei Traian Cucuruzac | 35m |
Bosch Connected Industry documents migrating Nixie MEES from VM-based Windows deployments through Docker‑Compose and Ansible into Kubernetes, turning ~30… | ||
| EVAPorating Kubernetes Security Risk: Adopting Validating Admission Policy at Scale | Kaitlyn Lee, Jordan Conard | 29m |
Datadog replaces OPA Gatekeeper webhooks with ValidatingAdmissionPolicy evaluated in-process across 100+ clusters (10k nodes, 100k pods), translating a… | ||
| Do Your Containers Even Lift – A Hardening Guide for K8s Containers | Cailyn Edwards, Daniel Murphy | 32m |
Scans find secrets and high‑severity CVEs (studies cite ~28,000 images with secrets and >1M exposed components); the demo uses Trivy and Truffle Hog to show a… | ||
| Fresh Secrets From the Docks: Lessons Learnt From Analyzing 180,000 Public DockerHub Images | Guillaume Valadon | 28m |
Analysis scans 180,000 public DockerHub images and finds 35,000 secrets in 18,000 images, with over 6,000 valid at test time (AWS, GCP, OpenAI, GitHub). The… | ||
| Container Runtimes... on Lockdown: The Hidden Costs of Multi-tenant Workloads | Lewis Denham Parry, Caleb Woodbine | 34m |
Compares concrete runtimes (runc, crun, containerd, gVisor, Kata, Firecracker, WASM/WoM) and shows tradeoffs: gVisor intercepts syscalls to shrink attack… | ||
| Why Don’t We Have Both? Track Build- and Run-time Information for Security With Kubescape and GUAC | Jeff Mendoza, Ben Hirschberg | 29m |
GUAC ingests Kubescape SBOM custom resources via a Cubescape collector that watches the Kubernetes API and stores image, build, source and filtered SBOM… | ||
| Transparent, Infra-Level Checkpoint and Restore for Resilient AI/ML Workloads | Ganeshkumar Ashokavardhanan, Bernie Wu | 37m |
Demonstrates a Kubernetes operator that uses CRIU, CRI-O, a modified runc and cuda-checkpoint to transparently checkpoint and hot-restart distributed PyTorch… | ||
| Thousands of Virtual Kubelets: 1-to-1 Mapping a Supercomputer To Kubernetes With Supernetes | Dennis Marttinen | 30m |
Supernetes performs a 1-to-1 mapping of Slurm nodes to v1/Nodes and Slurm tasks to v1/Pods, runs on LUMI, and tolerates strict HPC limits (no root, no… | ||
| Testing AI Containers for Digital Twins in Science: A Cloud-HPC Workflow | Matteo Bunino, Diego Ciangottini | 28m |
CERN and INFN build a CI/CD pipeline that uses Dagger + k3s + interTwin’s interlink adapters to submit containerized tests to SLURM HPC (Vega) from GitHub… | ||
| How To Supercharge AI/ML Observability With OpenTelemetry and Fluent Bit | Celalettin Calis | 18m |
Combines OpenTelemetry OTLP with Fluent Bit head/tail sampling to capture logs, traces and metrics from an EKS demo cluster with two GPU nodes running two LLMs… | ||
| Unlocking How To Efficiently, Flexibly, Manage and Schedule Seven AI Chips in Kubernetes | Xiao Zhang, Mengxuan Li | 21m |
Kubernetes middleware that manages seven different AI accelerators and provides device sharing via an injected library that hijacks CUDA calls (requires CUDA… | ||
| Kubernetes and AI To Protect Our Forests: A Cloud Native Infrastructure for Wildfire Prevention | Andrea Giardini | 32m |
Startup moves from JupyterHub notebooks to a Kubernetes-based stack using Daxter + Kubernetes, GKE, Google Cloud Run, Pub/Sub, Grafana and BigQuery, plus GPU… | ||
| Kubernetes Meets Climate Science: Building Large-scale Feature Detection From Climate Data Records | Armagan Karatosun, Roope Tervo | 28m |
European Weather Cloud hosts a Kubernetes platform on OpenStack with Rancher, JupyterHub, Label Studio, Nucleo and a cloud‑native Postgres/PostGIS feature DB… | ||
| Optimizing Model Serving on Kubernetes With Model Streaming | Ekin Karabulut, Ronen Dar | 21m |
Open-source Run:ai Model Streamer parallelizes reads and GPU transfers of SafeTensors so large weights stream into GPU memory instead of loading sequentially… | ||
| Are You Covered? Falling in Love With E2E Testing | Scott McAllister | 28m |
Demo builds a tiny burger-list app and proves end-to-end coverage by running Cypress tests inside a container that hits the real ingress, with three to four UI… | ||
| AI Beyond Autocomplete: Using LLMs To Create 1000 Kubernetes Controllers | Justin Santa Barbara, Walter Fender | 32m |
Claims building 1000 controllers for Google Cloud resources by running custom fine-tuned LLMs at build time to generate KRM types, mocks, OpenAPI schemas and… | ||
| No Code Needed: From Emojis To Glory on the Contribution Ladder | Nancy Chauhan, Carol Valencia | 27m |
Concrete roadmap for non-code contribution: read the project’s CONTRIBUTING guide, find first-timer issues, open a small create-a-docs-PR (localize glossary… | ||
| Stateful Connections in Kubernetes: The Scaling Secrets Nobody Talks About | André Mocke, Rodrigo Fior Kuntzer | 31m |
Miro rebuilds its WebSocket routing by deploying a custom WebSocket manager on EKS, fronted by AWS ALB + target group binding, replacing Fabio and console… | ||
| Breaking Barriers: Bringing Application Developers Closer To the CNCF | Thomas Vitale, Mauricio Salatino | 30m |
Five concrete friction points get listed and addressed with demos and tools: reproducible dev environments, onboarding, inner loop speed, service integration… | ||
| How Millennium Bcp Leverages Radius To Empower Developer + Operator Collaboration | Nuno Guedes, Jonathan Smith | 31m |
Millennium bcp adopts Radius as an application model, deploys production workloads starting December, and integrates with Flux for GitOps. Recipes (Bicep… | ||
| Type-safe Feature Flagging in OpenFeature: Lessons Learned From Using Feature Flags at Google | Michael Beemer, Florin-Mihai Anghel | 25m |
Google reports ~150k feature flags and ~70% developer usage and adopts a policy that flags must exist in the flag system before appearing in code; reflective… | ||
| Zero Trust at Shopify Scale: Automating MTLS Across Thousands of Services | Dani Santos, Michelle Mali | 36m |
Shopify automates mTLS for thousands of services across millions of pods, thousands of nodes, and hundreds of clusters using Google Cloud Certificate Authority… | ||
| Green AI in Cloud Native Ecosystems: Strategies for Sustainability and Efficiency | Vincent Caldeira, Tamar Eilam | 30m |
Cloud-native AI platforms focus on cutting inference costs because 65% of operational carbon often comes from inference; data distillation can cut training… | ||
| From High Performance Computing To AI Workloads on Kubernetes: MPI Runtime in Kubeflow TrainJob | Andrey Velichkevich, Yuki Iwai | 30m |
Kubeflow TrainJob integrates an MPI runtime that runs MLX and DeepSpeed workloads on Kubernetes, exposing a Python Qflow SDK so data scientists call one… | ||
| From Chaos To Control: Building ML Platform | George Markhulia, Steve Larkin | 33m |
Abacus is an internal ML platform built on Kubernetes that automates onboarding (creates GitHub repo, Kubernetes namespace, Harbor image registry, LakeFS repo… | ||
| Empowering AI-Driven Drug Discovery: Overcoming Challenges in Building a ML Platform on Kubernetes | Marius Tanawa Tsamo, Gustav Rasmussen | 25m |
Built a Kubernetes platform that sits next to the DGX superpod Geon (almost 200 H100 nodes, ranked 21st) and exposes GPU capacity via MIG slicing… | ||
| Using eBPF for Non-invasive, Performant, Instant Network Monitoring | Mario Macías, Marc Tudurí | 29m |
Grafana Baila uses eBPF to extract L3–L7 signals without redeploying apps, injecting many small probes into kernel and user space, storing events in eBPF maps… | ||
| Extending Kubernetes for AI | Lessons Learned From Platform Engineering | Susan Wu, Lucy Sweet, Andrea Giardini, Etienne Dilocker, Tim Wickberg | 25m |
Teams describe extending Kubernetes with GKE, Cloud Run, and open source like Daxter for data workflows, plus custom controls for pod-level resources and… | ||
| Enhancing Software Composition Analysis Resilience Against Container Image Obfuscation | Agathe Blaise, Jacopo Bufalino | 35m |
Empirical analysis of eight scanners including Trivy Syft Grype Snyk and major cloud services shows that every tested scanner fails at least one obfuscation… | ||
| C.A.L.L.I.N.G. Now I'm Calling You, Calling You Now | Mario Macías | 25m |
eBPF daemonset collectors query the Kubernetes API for pod metadata and drive the API from tens/sec to ">2 million requests/s" with error spikes around 10,000… | ||
| Resilient Multi-Cloud Strategies: Harnessing Kubernetes, Cluster API, and Cell-Based Architecture | T. Rahman, J. Mosquera | 36m |
New Relic runs a cell-based Kubernetes platform across 270+ clusters and ~18,000 nodes, using Cluster API for declarative bootstrapping, kind jobs + clusterctl… | ||
| nothing matches | ||