OpenInfra Summit Berlin 2022
2022-06-07..2022-06-09
Berlin, Germany
as the organisers put it
The OpenInfra Summit is back in Berlin! June 7-9, 2022. Collaborate directly with the people building and running open source infrastructure using OpenStack, Kubernetes and 30+ other technologies.
| title | author | length |
|---|---|---|
| LOKI (Linux, OpenStack, Kubernetes, Infrastructure) | Tytus Kurek | 25m |
Claims 70% of organisations integrate OpenStack and Kubernetes (OpenStack User Survey 2021) and shows a concrete Canonical stack on Ubuntu: charmed OpenStack… | ||
| Intro to the Open Compute Project OCP | Steve Helve | 21m |
Open Compute describes concrete designs and measurable outcomes: 250+ member companies and ~8,000 hardware engineers produce 200+ contributions that must have… | ||
| OpenInfra Summit 2022 Berlin: Keynote Day 1 | Jonathan Bryce, Allison Price, Mark Collier, Dmitry Margolin, Horace Li, Xu Wang, Eric Ernst, Samuel Ortiz, Fabiano Fidencio, Nicolae Paladi, Tytus Kurek, Frederic Lardinois, Dr. Franziska Brantner, Daniel Melin, Andreas Falkner, Sunny Cai | 01h 31m |
Day 1 opens with a foundation strategy claiming the cloud can grow 20x from today’s $3.6T IT market, backed by concrete community scale: 25 million cores… | ||
| Using BGP at OpenStack to interconnect workloads across clouds | Daniel Alvarez Sanchez, Luis Tomas Bolivar | 39m |
A Python daemon named ovn-bgp-agent runs on every compute node, reads the OVN southbound DB, and programs a per‑node BGP speaker via FRR to advertise VM… | ||
| GitOps with OTC, Terraform, Helm, and Argo CD | Ulrich Max Schneider, Victor Getz | 30m |
An empty Open Telekom Cloud account becomes a running Kubernetes environment with cert-manager, Traefik gateway, Kafka and Elastic Stack using Terraform to… | ||
| StarlingX 101 | Babak Sar Ashki | 29m |
StarlingX is a hardened distro that deploys Kubernetes across dedicated servers and scales from a single-server simplex to a duplex controller and full… | ||
| The Challenges of Maintaining an Edge Deployment at Scale – and How StarlingX Solves Them | Eddy Raineri | 36m |
StarlingX upgrades its control plane first then orchestrates edge subclouds to upgrade themselves, staging images to local repos for air‑gapped sites and… | ||
| What is OpenStack and what services do I need? | Amy Marrich | 28m |
Quick OpenStack primer: project began 2010 and just hit its 25th release (Yoga) with 13,500 code changes, 680 contributors from 125 companies across 44… | ||
| Ceph on Windows | Alessandro Pilotti | 28m |
Librados, librbd and CephFS run natively on Windows Server 2016/2019/2022 and Windows 10/11 via a new kernel driver called WMBBD that exposes RBD devices as… | ||
| OpenInfra Summit 2022 Berlin: Keynote Day 2 | Allison Price | 01h 48m |
Day 2 summarizes concrete outcomes and tools: the foundation reports 100,000 members across 187 countries and 450 organizations as its hosting model scales… | ||
| Cloud native Confidential: Isolating Kubernetes Pods with Confidential Computing | Samuel Ortiz | 38m |
Confidential Containers runs each Kubernetes pod inside per-pod confidential micro-VMs built on Kata Containers and hardware enclaves (AMD SEV, Intel TDX, IBM… | ||
| How To Install StarlingX | Babak Sar Ashki | 27m |
Virtualized install shows a system controller and a subcloud connected via a gateway using the StarlingX tools project and build guide, producing an ISO for… | ||
| Redfish Deep Dive | Richard Pioso, John Leung, Slawek Putyrski | 34m |
Redfish provides a RESTful HTTP+JSON management API with machine-readable JSON Schema, OpenAPI and OData outputs, and has been deployed at scale (notably 500… | ||
| Fearless automation Deploying OpenStack on top of Kubernetes | Marvin Titus, Jonas Schäfer, Felix Huettner | 23m |
Yaook is an open source lifecycle manager that runs OpenStack on Kubernetes using Kubernetes operators to implement a global control loop and reconcile… | ||
| Bifrost 101, I want to deploy! | Daniel Mellado, Dmitry Tantsur | 39m |
Bifrost is a collection of Ansible playbooks that installs a minimal Ironic environment and then deploys OS images to hardware; it uses IPMI and Redfish… | ||
| Magma 5G Virtual Lab on OpenStack | Shubham Tatvamasi | 28m |
Shows a working Magma 5G virtual lab deployed on OpenStack using AWX + Ansible to run Kubernetes for the orchestrator (split into ~10 Helm charts), an access… | ||
| OpenInfra Summit 2022 Berlin | 01m | |
Machine captions contain only fragments of music and a single syllable so there is no technical claim, toolkit, result, or demo to evaluate. The uploader… | ||
| If your future is on the edge, StarlingX wants you | Paul Miller | 32m |
StarlingX packages a low‑latency CentOS-based host with a real‑time kernel, containerd and Kubernetes to run containerized OpenStack via Helm and mix VMs and… | ||
| Multi Cloud Observability for 5G | Eric Lajoie, Fatih E. Nar | 34m |
Argues that sidecar/service-mesh tracing adds unacceptable overhead at telco scale and instead demonstrates host-level collection: daemonsets plus an agentless… | ||
| SmartNIC DPU Enablement in OpenStack with OVN | Dmitrii Shcherbakov, Frode Nordahl, James Page | 18m |
OpenStack and OVN patches move OVN/OVS control plane onto DPU hosts using PCIe VPD discovery in Nova, Neutron binding and devlink representative‑port lookup… | ||
| Build an inexpensive carrier-WiFi network on your laptop with Magma | Wojciech Nawrot | 46m |
Claims a fully functional carrier‑WiFi lab running on a single laptop using Magma (Orchestrator, NMS, Federation gateway, Carrier‑WiFi access gateway) plus… | ||
| OpenStack in 0 to 45 seconds. Engineering at the speed of light | Jadon Naas | 26m |
OpenMetal delivers On‑Demand Private OpenStack clouds that become fully usable in 45 seconds by handing over preprovisioned three‑node hyperconverged clouds… | ||
| How we designed an OpenStack Public Cloud at Scale with Fabric Networking | Abhisak Chulya Charnsilp, Chinprasert Jeeraput | 44m |
Nipa Cloud migrates its new Victoria cluster into production using Tungsten Fabric to replace brittle Neutron overlays after hitting scale pain at ~10–20 racks… | ||
| Migrating the Neutron backend to OVN in production | Jakub Libosvar | 36m |
Migration replaces the ML2 OVS mechanism with OVN by running a bash wrapper that calls TripleO + Ansible playbooks to deploy OVN DBs and controllers, stop ML2… | ||
| Modernizing your Red Hat OpenStack Platform’s operational | Eoghan Glynn, Maria Bracho | 46m |
Red Hat converges the OpenStack control plane onto Kubernetes using OpenShift so control services run as fine‑grained pods managed by operators and Ansible… | ||
| Volvo and Zuul CI | Johannes Foufas | 27m |
Volvo makes Zuul the default CI and shifts from a garage setup to production: it scales from 200→600 projects, runs about 4500 jobs/day, averages ~150 active… | ||
| Azimuth - self service cloud platforms for reducing time to science | Matt Pryor, Stig Telfer | 30m |
Azimuth provides a self-service portal that lets researchers deploy curated OpenStack-backed platforms (JupyterHub, Slurm clusters, Kubernetes) using Ansible… | ||
| Anomaly Detection System for the CERN Cloud | Domenico Giordano, Stiven Metaj, Antonin Dvorak | 26m |
A production anomaly detection system for the CERN cloud ingests collectd metrics, runs a Spark ETL and Dockerized analytics pipeline orchestrated by Airflow… | ||
| Project Gating with Zuul | James E. Blair | 34m |
Zuul is a CI/CD project gating system that tests the future state by speculatively merging proposed changes and their dependencies before committing them… | ||
| Past, present and future of the storage in the CERN private cloud | Jose Castro Leon | 37m |
CERN runs a private cloud since 2013 with ~9,000 servers and 48 Nova cells backed by multiple Ceph clusters (about eight), migrated from mixed NetApp/Hyper‑V… | ||
| How to create beautiful cloud native landscapes? | Christian Berendt | 14m |
23KE uses Gardener-based Kubernetes-as-a-Service to make clusters look identical across AWS, Azure, GCP, OpenStack, HNA, VMware and bare metal, automating… | ||
| Linux distributions as an ultimate challenge of continuous integration and how we solve it. | Aleksandra Fedorova | 28m |
Fedora ELN creates a continuously rebuilt Fedora Rohhide subset using RHEL-like build flags so enterprise compatibility is tested early, and CentOS Stream… | ||
| No gain without pain a story of scaling CI with Zuul | Thomas Zink, Simon Westphahl, Felix Edel | 26m |
Company CI moves from one brittle scheduler to 9 schedulers and shifts queues and pipeline state into Zookeeper for queues and state, enabling rolling upgrades… | ||
| Your ReadWriteMany (RWX) Storage in k8s with Manila CSI | Christian Schwede, Goutham Pacha Ravi | 25m |
Manila CSI delivers dynamic RWX provisioning for Kubernetes by wiring the Manila controller plugin to Manila and a node plugin that proxies to existing CSI… | ||
| How companies use LOKI to run their business | Maria Bracho, Alain Elengesa | 01h 02m |
Proximus runs a large Loki stack: 15 OpenStack clusters each with roughly 900 computes, 3 PB storage, 50,000 vCPUs and ~4,000 VMs, and 10 OpenShift clusters on… | ||
| Manage your kubernetes cluster in the GITOPS way !! | Nishant Kumar, Uday T Kumar | 30m |
Shows a working Argo CD demo that deploys an nginx app from a Git repo, then updates replicas from 2 to 4 and performs a manual sync so two new pods appear… | ||
| OpenStack brings Kubernetes to the Edge | Emilien Macchi, Maysa de Macedo Souza, Krzysztof Janiszewski | 01h 12m |
A push-button Kubernetes platform running on OpenStack deploys to many small sites, recommending one cluster per site and avoiding stretched clusters; live… | ||
| Source of truth for open infrastructure management with open-source netbox | Chien Pham Tuong, Cong Ha Minh | 16m |
Viettel runs NetBox as the single source of truth and builds an auto-discovery service that finds subnets, IP ranges, VRFs, IP addresses, compute hosts and VMs… | ||
| Hardware Onboarding and Burn in with Ironic in the CERN | Arne Wiebalck | 37m |
CERN automates hardware onboarding with Ironic: nodes auto-register via IPA, send introspection to S3/Ceph and populate OpenDCIM; cleaning becomes burn-in via… | ||
| Anatomy of a Kubernetes Cloud Provider | Matthew Booth | 26m |
Explains exactly how Kubernetes integrates with OpenStack using machine controller (via Machine API/Cluster API) to create Nova instances, kubelet bootstraps… | ||
| Seamless Management of VM and Container for NFV | Hirofumi Noguchi, Masaki UENO | 27m |
Tacker manages VNFs and CNFs across mixed VM and container platforms using OpenStack Heat + Kubernetes drivers and management scripts (infra and management… | ||
| Ironic Cube: bringing two worlds together | Dmitry Tantsur, Iury Gregory Melo Ferreira | 26m |
Metal3 integrates Kubernetes with Ironic and adds concrete pieces: it implements HTTP basic auth for non‑Keystone environments, introduces verify steps to run… | ||
| Ironic Operations at CERN: Our top 5 challenges and how we handle(d) them | Arne Wiebalck, Maryna Savchenko | 17m |
CERN runs Ironic since 2017 and manages almost 9,000 physical nodes; five concrete fixes are described: enrolling live servers by using fake drivers to pass… | ||
| Adopting heterogeneous computing resources: How we embrace ARM as a flavor and to accelerating cloud | Gihun Jung, yongjoon kong | 21m |
Kakao runs ~100,000 OpenStack instances across five to six regions with 70% used by Kubernetes and 95% of services containerized, sees low CPU but high memory… | ||
| OpenStack Plugin for Vault | Kristian Kucerak, Artem Goncharov | 29m |
An OpenStack plugin for HashiCorp Vault that actually issues Keystone tokens, creates temporary users and tokens with project/domain scopes, and returns a full… | ||
| Honey, I Blew Up the Cloud | Tyler Stachecki | 01h 12m |
Bloomberg rapidly scales single-cell OpenStack clusters to tens of thousands of VMs with Ceph-backed volumes and thousands of security groups, and describes… | ||
| Accelerating the Next Gen Datacenter with DPUs Continued | Toby Owen | 31m |
Fungible presents a DPU-based stack: a chip and OS that offloads data paths to enable a composable datacenter. The storage cluster uses two DPUs per chassis… | ||
| Workday's Next Generation Private Cloud | Jan Gutter, Silvano Buback | 41m |
Workday runs an OpenStack private cloud at ~1M+ physical cores on ~16,000 nodes across 5 data centers (87 clusters ≈300 nodes each) and migrates from… | ||
| Unikernels for Serverless Computing | Charalampos Mainas, Anastassios Nanos | 18m |
They build a tiny hypervisor called KVMM hypervisor that moves the VMM into the Linux kernel to cut mode switches, run unikernel images extremely fast, and… | ||
| How we integrated L3 services into one of the biggest OpenStack Public Clouds - OVHcloud case study | Mohankumar Navaneethan, Dawid Deja, Michał Żyłowski | 30m |
OVHcloud integrates distributed virtual routers, floating IPs and external gateways into a massive OpenStack deployment running 4,100 instances across 30+… | ||
| Building a sustainable OpenStack Cloud with Open Compute Project platforms | John Leung, Christoph Streit, Sven Anders, Frank Gemein | 28m |
Deployment uses Open Compute Project servers and Facebook Wedge 100G switches in a spine‑leaf fabric, OpenStack and Ceph with 25GbE backends and NVMe‑only Ceph… | ||
| Deep Dive into Architecture of a 5G Ecosystem | Guilherme Steinmüller, Hind Naser | 17m |
OpenStack Wallaby runs across five Canadian data centers (Montreal hub with three controllers, two compute nodes per site) connected by 100 Gbps fiber to host… | ||
| Edge Deployment of Kubernetes Cluster | Craig Griffin | 21m |
StarlingX performs a zero-touch deployment of a remote Kubernetes subcloud using Redfish and Deployment Manager, pushing an ISO to a BMC, running an Ansible… | ||
| The Robots Are Coming (But Not Yet), or, Don't Make Smart People Do Dumb Things | Shaun O'Meara | 30m |
Argues that AIOps today detects and alerts but rarely remediates autonomously, using ML to correlate Prometheus, Kubernetes and OpenStack logs and predict… | ||
| Build an MLOps platform on top of OpenStack | Torsten Deutsch, Ferenc Kuszka, Dr. Beibel | 32m |
Model Arts runs on Open Telecom Cloud (OpenStack) and provides data labeling, versioning, AutoML (called XML), built-in algorithms and Docker/Jupyter support… | ||
| NFVI Upgrades and NFV Migrations with Live Critical Telco | Gerardo Martinez | 36m |
Two years of lab work produce a repeatable NFVI CI/CD program that performs NFVI upgrades with live traffic (OpenStack VMs and CNFs on Kubernetes) every ~3… | ||
| Numerical Weather Prediction (NWP) & EO data processing and computational workloads in the Cloud | Vasileios Baousis, Charalampos Kominos | 31m |
ECMWF builds a community European Weather Cloud using OpenStack (Rocky → Usuri) and Ceph Nautilus with 23 monitors, hosting a 300 PB archive that grows ~250… | ||
| OpenStack public clouds - 7 reasons to become a local cloud | Maciej Mazur, Tytus Kurek | 09m |
Shows concrete deployments: a factory in India opens tens of millions of dollars of GPU capacity that sits idle ~12 hours to partners as a public cloud running… | ||
| Dude where's my vm? | Scott Solkhon, Ross Martyn | 33m |
G‑Research describes using OpenStack (Train -> Xena), Kolla Ansible, Ironic and Kyobi to pass whole GPUs and raw NVMe into VMs via PCI passthrough, plus nvme… | ||
| Observability in OpenStack Learnings and building blocks from the SIG Monitoring at SCS | Felix Kronlage-Dammers, Mathias Fechner | 23m |
SCS teams standardize on Prometheus + Grafana for metrics, reuse the Awesome Alert Rules repo, and run behavior checks that measure the time to create… | ||
| API Performance A journey down the rabbit hole | Julia Kreger | 28m |
A real investigation finds the bottlenecks: a table grows from ~20 to 58 columns with only a few indexes so queries scan too much, RBAC policy checks run twice… | ||
| Challenges of scaling a upstream Openstack Cloud | Guillaume Allard, Florian Leduc | 18m |
Société Générale runs an upstream OpenStack private cloud with 18k VMs across 4 regions and ~450 compute hosts (≈350 in Paris), sees ~1,500 instance… | ||
| More MEC, less DHCP:PXE, with ZTP and Ironic | David Paterson, Richard Pioso, Akhilesh Thyagaturu | 33m |
Claims horizontal scaling of a MEC site with zero‑touch provisioning that removes PXE and DHCP by using Ironic plus Redfish virtual media and ramdisk… | ||
| Power Savings & NFV: How to reconcile these 2 constraints ? | Christophe Fontaine, David Marchand | 18m |
Testbed with six cores, Open vSwitch + DPDK, 10Gb ports and T-Rex traffic shows concrete wins: BIOS static low power drops CPU draw to ~9.5 W but cannot reach… | ||
| Towards an open operations data community | Oindrilla Chatterjee, Aakanksha Duggal | 31m |
AI4CI collects open CI/CD data from Prow, TestGrid and GitHub, stores it on Ceph S3, and runs Jupyter notebooks automated with Kubeflow Pipelines to compute… | ||
| SRE implementation in a cool company | Antoine Vauvy, Andry Ramiandrasoa | 17m |
OVHcloud runs a fully integrated, water‑cooled infrastructure with 450k instances, 360 PB of storage and 40 regions, and adopts an SLO‑driven SRE model backed… | ||
| OpenStack in 0 to 45 seconds - Engineering at the speed of light | Jadon Naas | 13m |
OpenMetal claims a one‑click OpenStack private cloud that finishes in 45 seconds — a live demo provisions a fully isolated cloud on three nodes with a… | ||
| Cheops - Can a "service mesh" be the right solution for the Edge? | Geo Johns, Antony Marie Delavergne, Baptiste Jonglez | 36m |
Prototype Cheops claims to make existing microservice apps edge‑compliant without changing their code by decorating APIs with a small DSL (scope +… | ||
| OpenStack for Computational workloads | Jon Thor Kristinsson | 12m |
Practical checklist of OpenStack changes that improve real HPC/ML performance: enable NUMA awareness and huge pages to cut memory latency, use CPU pinning and… | ||
| Optimising resource allocation in hyperconverged infrastructure | Brett Milford | 35m |
Three case studies show concrete failure modes and fixes: Ceph filestore causes kernel hung tasks from delayed reclaim resolved by manual drop/compaction and… | ||
| How Obsolete is your Cloud? | Christian Huebner | 23m |
Five to six year old OpenStack clouds built on E5-era servers show clear bottlenecks: monitoring and upgrades stall on HDD boot and journaling, Ceph’s move… | ||
| Contributing to Neutron 101 | Elvira García Ruiz | 26m |
Neutron lets newcomers land meaningful patches without mastering every networking concept by using concrete tools and a repeatable workflow: deploy a… | ||
| Using Lens to Collaborate on Managed Kubernetes Clusters | Wassim Soualhi | 14m |
Lens is a desktop Kubernetes IDE that connects to managed clusters (EKS/AKS) via kubeconfig, adds clusters in seconds, and if no metrics exist it installs… | ||
| Confidential Computing in the Control Plane (case study using Barbican) | Kai Martius, Josephine Seifert | 35m |
Built a containerized Barbican that runs inside an SGX enclave using Graphene and Scontain SCONE with a CAS + LAS attestation chain, and moves the key… | ||
| Security Champions The What, Why, and How | Ann Marie Fred | 16m |
Known vulnerabilities outpace fixes — 18,000+ CVEs and 66+ zero-days in 2021 — so the solution is to scale security inside teams by training local experts… | ||
| Enforcing a Secure Supply Chain on Kubernetes | Raúl Cabello Martín, Víctor Cuadrado Juan | 36m |
Shows how to enforce image provenance on Kubernetes by signing images with the Sigstore stack and verifying them in an admission controller that rejects… | ||
| Building Workday's Next Generation Private Cloud with Zuul | Jan Gutter, Simon McGuinness | 17m |
Workday runs 87 OpenStack clusters totaling about 2 million cores, 12 PB RAM and ~60,000 concurrent VMs with ~240,000 VM recreates weekly, and builds a… | ||
| An Open Operations concept | Kurt Garloff, Felix Kronlage-Dammers | 34m |
Sovereign Cloud Stack claims operations barriers drop when teams share code, processes and culture not just tools. The project ships Ansible playbooks and a… | ||
| Advanced Zuul Features as used by OpenDev | Clark Boylan | 15m |
Zuul powers OpenDev’s CI/CD by doing speculative gating of build artifacts so container images built in a merge preview are recorded and reused across build… | ||
| Lotsa security - confining the extra security layer | Fabiano Fidencio | 32m |
Kata Containers adds host‑side SELinux confinement by shipping a new container_kvmt policy and wiring label propagation through CRI runtimes and the OCI spec… | ||
| OpenInfra Summit Feedback | Erin Disney, Kendall Nelson | 26m |
Summary of feedback: venue works but tight: rooms hit capacity so fire code enforces one-in-one-out capacity limits and floor seating is forbidden; sessions… | ||
| NeSI's Flexible HPC-A programmable infrastructure for science | Sean Matheny, Michal Nasiadka, Blair Bethwaite | 23m |
NeSI builds FlexiHPC: a multi-tenant bare metal platform combining OpenStack, Magnum/Kubernetes and cloud-native stacks to offer on-demand and dedicated… | ||
| One stop talk for kubernetes security !! | Nishant Kumar | 24m |
Overview of concrete practices: encrypt etcd at rest and block public control-plane access, enable TLS and RBAC, and apply PodSecurityAdmission (replaces PSP… | ||
| NFVI Upgrades and NFV Migrations with Live Critical Telco Workloads: Learnings and Challenges | Gerardo Martinez | 17m |
Two plus years of lab work runs NFVI upgrades with simulated traffic against an OpenStack plus Kubernetes stack and produces concrete lessons: upgrades are… | ||
| Troubleshooting - a bunch of examples of real world issues and how they were identified and fixed | Magnus Bergman | 22m |
Public OpenStack clouds show two concrete fixes: a Heat stack becomes undeletable when Nova rejects user-data larger than 64KB and Heat then tries to store… | ||
| Digital sovereignty Why open infrastructure matters | Eduard Itrich | 28m |
Project SCS (surveying cloudsec), funded by Germany’s Ministry and hosted by the Open Source Business Alliance, defines four concrete layers of digital… | ||
| Interoperable Hardware Acceleration for Serverless | Anastassios Nanos, Charalampos Mainas | 34m |
vxl is a framework that decouples function calls from hardware implementations so a single binary runs on Jetson Nano/Xavier, Intel NCS, Nvidia T4 and custom… | ||
| Ghosting the Spectre | Allison Randal | 33m |
Research prototypes three concrete hardware approaches: RISC-V cores synthesized on Amazon FPGAs via Firesim/FireMarshall to measure costs and protections… | ||
| Bringing in Compliance for Public | Dmitriy Rabotjagov, Jean-Philippe Evrard | 27m |
Implementation uses Barbican + HSM with Castellan and PKCS#11: HSM stores a master key and HMAC, per-project keys are encrypted by the master, and secrets… | ||
| Extending Network Quality of Service support in OpenStack | Balazs Gibizer, Lajos Katona | 32m |
OpenStack adds a minimum guaranteed packet rate QoS implemented through Neutron, Nova and Placement so VMs are scheduled only to hosts that report enough… | ||
| Intent-based holistic data center management | Christian Berendt | 33m |
Open source OSISM implements an intent-based GitOps pipeline that turns YAML in Git into physical changes: NetBox as live state API, Git as source of truth… | ||
| Managing Third Party Software in your GitOps Setups | Sascha Siegl | 15m |
A reusable, cloud‑agnostic CI/CD pipeline that treats third‑party OSS like first‑class code: it uses GitLab CI + Helm + Docker with six stages (pre, lint… | ||
| Lessons learned from multarchitecture, multinetwork OpenStack installation | Olaph Wagoner | 18m |
An OpenStack lab runs across x86 and IBM Power hardware and yields four concrete lessons: a linux-bridge crash on x86 is solved by increase ulimit for… | ||
| Building a Framework for Big Infra Decisions | Wassim Soualhi | 42m |
Practical rules for picking VMs, containers, or both: VMs win for lift‑and‑shift, non‑standard telecom protocols (SIP/GTP) and mixed OS stacks; containers win… | ||
| “Project Necromancy” How we are bringing Keystone and Barbican back from the dead | Dave Wilde | 23m |
Describes concrete steps to revive Keystone and apply them to Barbican: reinstating weekly IRC meetings, running weekly review-a-thons over Google Meet, using… | ||
| Continuous Integration and Continuous Delivery Pipelines: Just the Basics | Ann Marie Fred | 29m |
Explains CI/CD stage-by-stage and shows a concrete Tekton pipelines example with about 35 steps that builds, generates SBOM generation, signs and publishes… | ||
| Enforcing a Secure Supply Chain on Kubernetes | Raul Cabello, Martin Víctor Cuadrado Juan | 15m |
Explains a concrete pipeline: use cosign + Fulcio + Rekor to produce signatures (including keyless OIDC signing from GitHub Actions), push signatures to OCI… | ||
| A peek into Elastic Secure Data Centers | Trammell Hudson, Jon Stumpf, Tzu-Mainn Chen, Orran Krieger | 42m |
During the Wednesday Keynote, we spoke of Elastic Secure Data Centers, their importance, and provided a glimpse into the work ahead.
Many of the projects… | ||
| LOKI Cloud-Native Data Protection Should Not be Low-Key | Kevin Jackson | 35m |
Trilio installs as a platform service (OpenStack endpoint or Kubernetes operator via CRDs) and performs agentless service backups of VMs, containers and PVCs… | ||
| OpenInfra Community Dashboards - Overview of the OpenInfra and Bitergia Partnership | Georg Link, Thierry Carrez | 12m |
OpenInfra partners with Bitergia as its official metrics provider, combining Bitergia’s 10 years of open-source analytics with OpenInfra project knowledge to… | ||
| Enabling MEC platforms in Healthcare & Smart Hospitals | Sunku Ranganath, Francesc Guim, Sindhura Gaddam | 31m |
A containerized edge platform demonstrates deployable AI inferencing for digital pathology using an OpenVINO model server and DLStreamer pipeline server on… | ||
| From DevOps to DataOps - Cloud based Software Development | Yuri Demchenko | 18m |
Research groups report that ~80% of data projects never deploy and up to 90% of effort is data preparation, so the work builds a cloud-focused pipeline and… | ||
| Would you tip your cloud provider? Canonical’s Cloud Pricing Survey 2022 results | Tytus Kurek | 11m |
Canonical’s Cloud Pricing Survey 2022 interviews more than 300 cloud specialists (40 questions, run Apr 7–May 21) and finds cost is the main driver: 57% say… | ||
| Enabling Big Memory workloads to run | Bernard Wu | 30m |
MemVerge demonstrates a user-space software-defined memory platform that augments DRAM with persistent memory and integrates with Loki/OpenStack, using… | ||
| Sturdy Clouds Creating Resilient Software Defined Data Centers | Daniel Virassamy, Christian Huebner | 30m |
Argues that resilience requires concrete choices: deploy OpenStack and Kubernetes with repeatable automation, treat automation is everything, avoid exotic… | ||
| Use it, or lose it Recycling waste heat at the edge | Jegor van Opdorp, Stig Telfer | 16m |
Leafcloud runs OpenStack control planes in a Tier‑3 core and pushes compute into dozens of water‑cooled edge “leaf” sites that dump server heat into building… | ||
| Teaching padawans to chop wood and carry water in their open source journey | Stephen Finucane | 32m |
Mentoring programs onboard beginners through concrete steps: four students per university working three months on constrained, iterative tasks, with weekly… | ||
| A novel Cloud High Performance Computing infrastructure for user | Giuseppa Muscianisi, Andrea Vanni | 16m |
Cloud HPC runs OpenStack on a partition of the Galileo100 Tier‑1 system, using Intel Platinum Xeon 8260 nodes with ~700 GB RAM per node, a 100 Gb/s low‑latency… | ||
| What the Cloud? | Krzysztof Janiszewski, Julio Villarreal Pelegrino | 33m |
Argues that "cloud" is a service not just tech and contrasts OpenStack vs AWS vs OpenShift as concrete IaaS/PaaS/CaaS options, explains the public-cloud shared… | ||
| Changing the Game in Open Data with a Container Infrastructure | Patrick Beaucamp | 17m |
Platform runs as OpenShift container images hosting CMS, CKAN, dashboards, maps, LimeSurvey and data-analysis pods; frontend uses Drupal and the stack uses… | ||
| Enabling Big Memory workloads to run | Bernard Wu | 19m |
MemVerge’s software-defined memory layers above Linux, auto-tiers pages between DRAM and Intel Optane persistent memory, and provides copy-on-write memory… | ||
| Digital sovereignty: Why open infrastructure matters | Eduard Itrich | 12m |
Claims that “digital sovereignty” requires more than data residency and legal compliance: a funded sovereign cloud stack project maps four layers — legal… | ||
| Squashing Diversity, Equity, and Inclusion Bugs in Open Source | Georg Link | 34m |
Frames diversity problems as DEI bugs and applies a bug‑squash workflow: discover (walk in newcomers’ shoes), understand (where contribution flows break), and… | ||
| nothing matches | ||