Operations | Monitoring | ITSM | DevOps | Cloud

What is RDMA over Converged Ethernet (RoCE)?

Previous articles walked through RDMA (Remote Direct Memory Access) as a programming model and InfiniBand as the fabric that was built around it. Both led to the same conclusion, even if it was never stated outright: moving data, not compute, becomes the bottleneck once systems scale. So what happens when you want RDMA, but you’re already running an Ethernet network you’re not keen to replace? That’s usually where RDMA over Converged Ethernet (RoCE) enters the conversation.

NVIDIA Approach for Achieving ASIL B Qualified Linux | Ubuntu Summit 26.04

Can a general purpose, open source operating system like Linux be deployed in safety-critical products? Can it achieve certifications to standards like ISO 26262? This question has become increasingly common in recent years. In this talk, Bryan provides a safety integrity qualification approach for Linux. It is composed of Linux Kernel, user space libraries (like libc) and user-space components (like init processes), up to ASIL B according to ISO 26262:2018.

Beyond tokens per watt - using Ubuntu 26.04 LTS for AI

Tokens per watt (TpW) – the measure of useful AI work produced per watt of energy consumed – is the metric at top of mind for CEOs, heads of AI, and infrastructure teams alike. With the tremendous cost of GPU clusters, extracting as much value as possible from the expense is critical. But in the pursuit of tokens, it’s important to remember that hardware efficiency isn’t the only factor influencing data center operating costs, or the output of useful, revenue-generating AI work.

A look into Ubuntu Core 26: Deploying AI models on Renesas RZ/V series for production

Welcome to this blog series which explores innovative uses of Ubuntu Core. Throughout this series, Canonical’s Engineers will show what you can build with our releases, highlighting the features and tools available to you. In this blog, Asa Mirzaieva, engineer from the Silicon Alliances team, will show you how to deploy optimised AI models on Renesas RZ/V series hardware using the Dynamically Reconfigurable Processor for AI (DRP-AI).

Configure Ubuntu with YAML | Ubuntu Summit 26.04

Learn how to configure Ubuntu at launch using declarative, idempotent instructions stored in a version-controlled YAML file. In this talk, Rajan explains how this approach minimizes arbitrary commands, reduces risks of command injection and privilege escalation, and ensures validation and error handling. This is relevant on major public and private clouds, and virtualization solutions ranging from VMware, WSL, LXD, Multipass, Proxmox, and more.

uPKI: improving certificate revocation on Linux | Ubuntu Summit 26.04

What is uPKI? While web browsers automatically check if an HTTPS certificate has been revoked, other Linux command-line tools and applications usually skip this check. That leaves applications vulnerable to compromised or misissued certificates many months after this is discovered. In their talk, Joe Birr-Pixton and Dirkjan Ochtman will be introducing uPKI: a new effort to bring browser-grade certificate infrastructure to Linux. This effort is funded by Canonical, engineered by the maintainers of rustls, and builds on foundational work from Mozilla.

RISC-V profiles - why is RVA23 significant?

One of the important offerings of the RISC-V Instruction Set Architecture (ISA) is the ability to customize and extend the base instruction set. An initial reaction to hearing this is often to worry about software portability and compatibility, since if every RISC-V CPU offers a slightly different set of instructions, software won’t be portable.

NVIDIA Earth-2: OSS and Science for AI Weather and Climate | Ubuntu Summit 26.04

Discover how NVIDIA Earth-2 brings open source software and open science to weather and climate forecasting. Niall Robinson (NVIDIA) introduces a new way of making production-ready weather AI fully accessible for organizations to run, fine-tune, and deploy on their own infrastructure: NVIDIA Earth-2.

Level up your Code on Arm and Ubuntu | Ubuntu Summit 26.04

What are the latest developments in Arm tooling on Ubuntu? In this talk, David explores Arm tooling to analyze and optimize workload performance, and how AI-assisted development using agentic AI and static analysis can accelerate porting and tuning applications for the Arm architecture. About David David Haikney is a Technical Product Director at Arm. He is responsible for Arm Performix, a free performance toolkit that helps developers understand and improve real-world performance on Arm architectures.

What is InfiniBand?

When distributed workloads stall because nodes cannot exchange small messages quickly and consistently, the network is the limiting factor. How do you solve that problem? InfiniBand offers one solution. InfiniBand is an interconnect, meaning the end-to-end communication system that links compute, storage, and accelerator nodes. It is implemented as a purpose-built network fabric, the switching and transport layer engineered to deliver high bandwidth and low, predictable latency between those nodes.

Massive Open Source Success: A Step-By-Step Guide | Ubuntu Summit 26.04

Not all open source projects gain traction -- but a few become movements. In this talk, Nariman, Founder of Puter, shares what actually separates the two, based on his experience of growing Puter to 40K+ stars, gaining hundreds of contributors, and over 500K installations. He breaks down how to gain momentum from a project's foundation, attract contributors, and design projects that capture the imagination.

How to deploy Canonical Managed Kubeflow on Microsoft Azure?

Learn how to deploy Canonical Managed Kubeflow on Microsoft Azure step by step. Canonical's Managed Kubeflow on Azure gives enterprise and startup AI teams a fully operational, open source MLOps platform in under an hour. It is managed 24/7 by Canonical's engineers. This means you can focus entirely on building models rather than running infrastructure.

How Canonical Support solves hard Linux performance bugs - even in 12-year old code

Some support cases are straightforward. Others lead deep into legacy code, where a single logic bug can quietly turn a routine command into a major performance problem. This series looks at how Canonical Support and Sustaining Engineering work together to investigate, patch, and upstream difficult issues that standard troubleshooting alone cannot solve.