Loading…
Open Source Summit + Embedded Linux Conference North America...
May 18-20, 2026
Minneapolis, MN
View More Details & Registration
Note: The schedule is subject to change.

The Sched app allows you to build your schedule but is not a substitute for your event registration. You must be registered for Open Source Summit North America 2025 to participate in the sessions. If you have not registered but would like to join us, please go to the event registration page to purchase a registration.

This schedule is automatically displayed in Central DaylightTime (UTC -5). To see the schedule in your preferred timezone, please select from the drop-down menu to the right, above "Filter by Date."

IMPORTANT NOTE: Timing of sessions and room locations are subject to change.


Company: Intermediate clear filter
arrow_back View All Dates
Tuesday, May 19
 

11:00am CDT

From PLC–SCADA To Digital Twins: Architecting Real-Time Industrial Systems for Scale and Resilience - Avadh Nagaralawala, Independent Consultant
Tuesday May 19, 2026 11:00am - 11:40am CDT
Industrial control systems built on PLC and SCADA architectures power critical infrastructure worldwide, yet most remain siloed, reactive, and difficult to scale for modern operational demands. As industries adopt digital twins for prediction, optimization, and resilience, a key challenge emerges: how to integrate real-time control systems with digital twin architectures without compromising safety, determinism, or reliability.

This session presents a practical, architecture-driven approach to integrating PLC–SCADA systems with digital twins in large-scale industrial environments. Drawing from real-world automation modernization programs, the talk explores data synchronization patterns, control boundaries, latency considerations, and open-source tooling strategies that enable production-grade digital twins rather than visualization-only pilots.

Attendees will gain a systems-level understanding of how embedded Linux platforms, open communication protocols, and control system design principles can support scalable digital twins for industrial operations. The session emphasizes architecture, interoperability, and lifecycle design, not vendor-specific solutions.
Speakers
avatar for Avadh Nagaralawala

Avadh Nagaralawala

Independent Consultant
Avadh Nagaralawala is a Mining Automation & Control Engineering Consultant with over 12+ years of experience driving innovation in mining, electrification, and digital transformation. Avadh is an active member of professional associations including IEEE, SME, CIM, and PMI, and frequently... Read More →
Tuesday May 19, 2026 11:00am - 11:40am CDT
208C+D (Level Two)
  Embedded Linux Conference

11:00am CDT

Optimizing Power Consumption in Embedded Linux: Techniques and Tradeoffs - Kendall Willis, Texas Instruments
Tuesday May 19, 2026 11:00am - 11:40am CDT
Modern embedded systems look to minimize power consumption without compromising the performance of the system. To address this challenge, Linux provides comprehensive frameworks for dynamic power management that adapt system performance in response to workload demands. This talk explores the pieces that form the foundation of Linux power optimization and demonstrates how to leverage these tools in real-world scenarios.
The key principles for reducing the power consumption of the embedded system include turning off inactive devices, reducing clock frequency, and lowering supply voltage. Linux provides frameworks such as Runtime PM to suspend inactive devices, CPUIdle for intelligent idle state management, DevFreq for memory and device frequency optimization, and CPUFreq for dynamic CPU frequency scaling. By leveraging these tools, systems can reduce power dissipation while still meeting the demands of the application use case, without sacrificing performance. Through a practical case study on a TI AM62L SoC running a display application, this talk explores how different power optimization techniques interact and sometimes conflict, requiring iterative tuning to find optimal operating points.

Attendees will gain actionable optimization strategies, awareness of common pitfalls when subsystems interact, and practical debugging approaches applicable to their own embedded Linux projects.

Speakers
avatar for Kendall Willis

Kendall Willis

Software Engineer, Texas Instruments
Kendall Willis is an Embedded Software Engineer working at Texas Instruments. She primarily focuses on power management in ARM SoCs by enabling various low power modes in the Linux kernel.
Tuesday May 19, 2026 11:00am - 11:40am CDT
205C+D (Level Two)
  Linux

11:00am CDT

Connecting the Dots With Context Graphs - Stephen Chin, Neo4j
Tuesday May 19, 2026 11:00am - 11:40am CDT
AI systems need more than intelligence; they need context that persists. Without it, even strong models can misinterpret information, lose decision rationale, or repeat the same mistakes. Context Graphs have emerged as a practical pattern for agentic AI: a living graph that captures not only what was retrieved or known, but how context led to actions through tool calls, constraints, policies, and outcomes, stitched across entities and time so precedent becomes searchable.

This talk explores context engineering as the discipline of designing that context layer, and shows how context graphs complement retrieval by enabling multi-hop, structured context assembly (building on GraphRAG-style hierarchical summaries) while improving explainability and evaluation. Attendees will leave with a practical understanding of how to build context pipelines that combine contextual retrieval with persistent memory and provenance, and why context graphs are becoming central to trustworthy, enterprise-ready AI systems.
Speakers
avatar for Stephen Chin

Stephen Chin

VP of Developer Relations at Neo4j, Open AI & Data Program Chair

Tuesday May 19, 2026 11:00am - 11:40am CDT
211A+B (Level Two)
  Open AI & Data

11:35am CDT

Lightning Talk: It's Friday! - Alon Nisser, Zencity
Tuesday May 19, 2026 11:35am - 11:45am CDT
It's Friday afternoon, and you've got plans for this evening. You've just finished the feature. you push to main and click deploy. OR DO YOU?
Let's talk about Friday deployments and what they can teach us.
Speakers
avatar for Alon Nisser

Alon Nisser

Principal engineer, Zencity
Software developer. currently in Zencity.io. Writing software as a hobby and as a profession. Strong opinions on things. Open source aficionado. Trying to make a difference.
Sometimes software makes we wonder if I'd be better off being a farmer
Tuesday May 19, 2026 11:35am - 11:45am CDT
200C (Level Two)
  cdCon

11:50am CDT

Platform Engineering: Herding the Electric Sheep - Brett Smith, SAS
Tuesday May 19, 2026 11:50am - 12:15pm CDT
A talk about platform engineering, DevOps, DevSecOps, sprawl, chaos, compliance, and security. Why engineer an Internal Developer Platform when I have DevOps? DevOps works fine when you are a 20 person start-up but it often doesn't scale to Enterprise level development efforts. When you have 3000 developers with different needs and you are responsible for EO compliance and security a modular self-service platform is a good choice to build. In this talk I cover the challenges we have faced in a 3000 developers enterprise and how we are working to address them. I also cover how we are working on automating, integration, and scaling the creation of our internal developer platform. Leveraging SBOMs, SLSA, and other tools to help build out a secure and compliant platform. Attendees will learn the benefits and challenges of Platform Engineering
Attendee Takeaways
Answers for the following questions:
- Do we need a Platform Engineering Team?
- Is an IDP the right solution for my situation?
- What does a large scale IDP look like?
- What does it take to support a large scale IDP?
- What does security and compliance look like in an IDP?
Speakers
avatar for Brett Smith

Brett Smith

Distinguished Software Developer, SAS
Distinguished Software Architect/Engineer/Developer with 25+ years of experience.
Specialties: Event Driven Automation, Continuous Integration/Delivery/Testing/Deployment, Supply Chain Security, AI Security
Expertise: Linux, packaging, and tool design.

Currently Engineering an... Read More →
Tuesday May 19, 2026 11:50am - 12:15pm CDT
200C (Level Two)
  cdCon

11:55am CDT

Unified Database Provisioning and Management on Kubernetes - Kyle Avants, Percona
Tuesday May 19, 2026 11:55am - 12:35pm CDT
Running production-grade databases on Kubernetes is becoming increasingly common, but managing their lifecycle remains fragmented and complex for SRE and DevOps teams. Critical operations—scaling, RBAC, monitoring, backup, and restore—currently require navigating distinct, database-specific APIs and tools. This complexity prevents teams from fully realizing the operational efficiency and uniformity that Kubernetes provides.

This talk introduces OpenEverest, the open-source platform designed to address this operational gap. OpenEverest provides a single, unified UI and CLI to manage SRE functions for popular open-source databases such as PostgreSQL and MySQL deployed on Kubernetes. It abstracts away database-specific differences, offering standardized control for scaling, integrated observability, granular RBAC, and reliable data protection.

Join us to learn how OpenEverest simplifies the path to production readiness, reduces operational toil, and is building a pioneering open-source database management layer.
Speakers
avatar for Kyle Avants

Kyle Avants

Senior Solutions Engineer, Percona
Tuesday May 19, 2026 11:55am - 12:35pm CDT
200F (Level Two)
  Cloud + Orchestration

11:55am CDT

Easy Bring-up Your RISC-V SBC Using Yocto Project - RISC-V Architecture Layer - Khem Raj, Comcast
Tuesday May 19, 2026 11:55am - 12:35pm CDT
There are several different RISC-V based single board computers out in market and coming in future. Yocto project, is a leading embedded linux framework, and RISCV is first tier architecture supported in project, core supports RISCV64 QEMU and runs all tests. This talk will discuss using meta-riscv layers to add the support for new RISCV SBCs. meta-riscv has best practices and pre-existing support for known SBCs which can be used as template to bring-up the new board quickly. The talk will cover the content of meta-riscv in detail and the project setups using Kas and the SBC specific documentation using markdown files, detailing the flashing and build instructions, sharing common details but clearly differentiating board specific intructions.
This talk will also cover the challanges and future roadmap for meta-riscv and RISCV architecture support in Yocto Project.
Speakers
avatar for Khem Raj

Khem Raj

Fellow, Comcast
Khem Raj is a yocto project maintainer and long time OpenSource contributor to many projects e.g. LLVM, Glibc, Musl, OpenEmbedded etc., he has been helping several open source initiatives in industry. He is guiding the company's adoption of open source software, and becoming an active... Read More →
Tuesday May 19, 2026 11:55am - 12:35pm CDT
208A+B (Level Two)
  Embedded Linux Conference

11:55am CDT

From Physics To EBPF: Quantifying Flash Wear in Embedded Systems - Blake Hildebrand, Nordic Semiconductor
Tuesday May 19, 2026 11:55am - 12:35pm CDT
Flash memory is the literal foundation of an embedded system, yet it is a finite resource. Every log entry, database commit, and firmware update inches the device closer to its end of life. For developers managing fleets of devices, the question is not just if the flash will fail, but when and which process is the culprit.

This session dives deep into the lifecycle of a write, from a high level look at the physics behind flash memory, to how we can get an estimation of lifetime by tracking number of bytes written. We will start at the hardware level, explaining the physical degradation of NAND cells and why eMMC controllers use wear leveling to manage this reality. Next, we will bridge the gap between hardware specs and software reality using the Total Bytes Written (TBW) metric to estimate remaining life.

Moving into the Linux kernel, we will explore the built-in metrics found in procfs and sysfs to monitor disk I/O. Finally, we will level up our observability by using eBPF to build a per process "write shaming" tool. This allows us to pinpoint exactly which application or daemon is burning through our hardware lifespan.
Speakers
avatar for Blake Hildebrand

Blake Hildebrand

Software Engineer, Nordic Semiconductor
Blake has been using Linux since installing Ubuntu Breezy on his dad’s old office PC. Since then, he’s worked on everything from smartwatches to large-scale web services. As an Software Engineer at Memfault, he focuses on improving device reliability and performance. Previously... Read More →
Tuesday May 19, 2026 11:55am - 12:35pm CDT
208C+D (Level Two)
  Embedded Linux Conference

11:55am CDT

SPDX and SBOM Work for the Linux Kernel - Tim Bird, Sony Electronics
Tuesday May 19, 2026 11:55am - 12:35pm CDT
Due to increased interest in fine-grained analysis of kernel composition and security (due to the CRA and other recent cybersecurity legislation), there have been a number of recent projects to 1) generate SBOMS for the linux kernel, and 2) finish adding the remaining SPDX-License-Identifier lines to the kernel source tree. In this talk, Tim will describe the current status of both of these efforts. Good progress has been made to add missing SPDX id lines, but more work is needed to complete this project. Tim proposes a kselftest test to make sure there are no regressions in this area. The status of different kernel SBOM generation tools, and upstream status, will be described.

This work should be of interest to companies interested in complying with cybersecurity requirements, as well as those involved with license compliance efforts.
Speakers
avatar for Tim Bird

Tim Bird

Principal Software Engineer, Sony Electronics
Tim Bird is a Principal Software Engineer for Sony Corporation, where he helps Sony use Linux and other open source software in their products. Tim is the organizer of the Linux Boot-Time Special Interest Group, a contributor to the Linux kernel, and is involved with numerous Linux... Read More →
Tuesday May 19, 2026 11:55am - 12:35pm CDT
205C+D (Level Two)
  Linux

11:55am CDT

How Apache Superset Reinvented (and Re-engineered) Its World of Documentation - Evan Rusackas, Preset, Inc
Tuesday May 19, 2026 11:55am - 12:35pm CDT
Learn how Apache Superset, the top open-source project in Business Intelligence, re-tooled their entire world of user/admin/developer documentation.

Our new Extensions architecture gave us the chance to re-imagine how we WANT our docs to work. This isn't AI-generated docs... it's using AI to re-engineer how our docs build themselves.

Learn how we managed to:
• Federate scattered readmes/wikis/etc. under one roof
• Independently version areas for different release cycles and intents
• Automate screenshots and content to "keep up" with the codebase
• Bring API docs, React Story book, and more into a centralized interactive portal
• Leverage AI to maintain docs... for people AND for humans
• Syndicate content from third party sources to be the end-all-be-all of Superset documentation
• Adding AI tools (for free!) to provide chat-based support AND learn where our docs are falling short from the result
• Use the codebase itself to build and maintain long-tail aspects of the docs

We've learned a lot of hard lessons over the years, and we're happy to share the process, ideas, and tools we've used to take things to the next level.
Speakers
avatar for Evan Rusackas

Evan Rusackas

Head of Community, Preset, Inc
Evan is a community lead and software engineer with Preset, Inc. and works closely with the Apache Superset community. Evan's interests lie in UI design, data visualization, and frontend engineering. He spends the bulk of his time growing and engaging with the Superset community... Read More →
Tuesday May 19, 2026 11:55am - 12:35pm CDT
200E (Level Two)

11:55am CDT

Package Testing Across Distributions and Architectures at Scale: A Molecule and QEMU Approach - Yash Panchal, Percona
Tuesday May 19, 2026 11:55am - 12:35pm CDT
This session will demonstrate a scalable approach to testing Linux packages across multiple distributions and architectures using Molecule and QEMU/KVM.

Attendees will learn how to build automated testing pipelines that validate linux packages on diverse platforms including x86_64, ARM64, RHEL, Ubuntu, and Debian.

We'll cover practical implementation of Molecule test scenarios, integration with Jenkins CI/CD pipelines, efficient use of QEMU/KVM for multi-architecture testing, and image pre-baking strategies to significantly reduce test execution time.

The talk includes real-world examples from database and toolkit package testing at Percona, demonstration of creating optimized base images, comparisons with cloud instances, Docker and Firecracker alternatives, and best practices for maintaining test infrastructure.

Key takeaways: Setting up Molecule package testing frameworks, managing QEMU instances, implementing image pre-baking workflows, handling cross-architecture testing challenges, and achieving speed and cost savings in testing linux packages.
Speakers
avatar for Yash Panchal

Yash Panchal

SDET III, Percona
Yash Panchal is an SDET III at Percona, where he specializes in automating and testing database and toolkit packages across supported linux distributions and architectures.

A seasoned open-source speaker, Yash presented a session on package testing with Molecule and Jenkins at... Read More →
Tuesday May 19, 2026 11:55am - 12:35pm CDT
200G (Level Two)

11:55am CDT

Sponsored Session: Driftless: An Open Source Agentic Reconciliation Framework Proven At Scale - Manfred Moser, Chainguard
Tuesday May 19, 2026 11:55am - 12:35pm CDT
Our new software factory framework adopts the reconciliation pattern and includes numerous bots that use traditional and agentic AI eval approaches. And since we are open sourcing the framework, reliable use of your own agentic reconciliation automation at massive scale could be your future too.

At Chainguard we build and maintain over 2000 unique containers, hundreds of thousands of package versions, and hundreds of CVE patch backports. Our old event-driven architecture was complex and brittle. We drowned in event notifications, brittle queues, duplicate build failures, work item conflicts and losses, and other problems. We had to rethink our approach.

In this session Manfred, open source veteran and author, shares details about a new specification-driven system called “Driftless” that increases efficiency and reliability at scale. A work queue is fed by events and tackled by a large number of bots. They constantly reconcile the discovered state changes from code repositories, security feeds, and other sources to the desired state - up to date containers with zero known CVEs. Manfred talks about our hard-earned lessons and how you can make the bots work for you as well.


In order to facilitate networking and business relationships at the event, you may choose to visit a third party's booth or access sponsored content. You are never required to visit third party booths or to access sponsored content. When visiting a booth or participating in sponsored activities, the third party will receive some of your registration data. This data includes your first name, last name, title, company, address, email, standard demographics questions (i.e. job function, industry), consenting to receipt and use of such data by the third-party recipients, which will be subject to their own privacy policies. 
Speakers
avatar for Manfred Moser

Manfred Moser

Sr Principal Dev Rel Engineer, Chainguard
Manfred Moser is a Sr Principal DevRel Engineer at Chainguard, bringing a profound focus on software supply chain security to the open source world. A dedicated community leader and published author, his technical expertise spans decades as a software engineer and advocate. He has... Read More →
Tuesday May 19, 2026 11:55am - 12:35pm CDT
200I (Level Two)

11:55am CDT

Multi-robot Air-Ground Collaboration With PX4 and Opportunistic Communications - Fernando Cladera, University of Pennsylvania - Devester
Tuesday May 19, 2026 11:55am - 12:35pm CDT
A team of aerial and ground robots operating in a coordinated way is the key to large-scale operations in kilometer-scale environments. Nonetheless, significant challenges, such as orchestration, intermittent communications, and command-and-control of the team, need to be solved.
This talk will explore an application where a team of ground robots performs a search mission, with an UAV acting as an eye in the sky and a data mule between the different ground robots. We will focus on the challenges for this task and how PX4 can be used in a heterogeneous team of aerial and ground robots. We will show examples of the system in large-scale urban and rural environments. Finally, we will mention how large foundational models can enable more complex tasks for a robot team.
Speakers
avatar for Fernando Cladera

Fernando Cladera

PhD Student, University of Pennsylvania - Devester
Fernando is a PhD student at the University of Pennsylvania, working on robotics perception, autonomy, and field robotics. He focuses on incorporating novel perception sensors into flying vehicles, such as event cameras, and on the applications these sensors would enable. Additionally... Read More →
Tuesday May 19, 2026 11:55am - 12:35pm CDT
200D (Level Two)
  PX4 Dev Summit

12:20pm CDT

Lightning Talk: Where Deployment Authority Lives: A Cloud Native Design Pitfall in GitOps - Kim Schaefer, Game Plan Tech
Tuesday May 19, 2026 12:20pm - 12:30pm CDT
Many cloud-native GitOps systems quietly treat a Git merge as both a change proposal and a deployment authorization. While this works in low-risk environments, it collapses two very different responsibilities into a single decision. As systems grow more complex, that shortcut creates ambiguity around authorization, accountability, and audit trails that many environments simply cannot tolerate.

In this lightning talk, we’ll reframe that assumption as a cloud-native architectural concern, not just a tooling or security issue. Using GitOps as the example, we’ll look at how proposal, approval, and enforcement often become unintentionally coupled, and why that coupling makes it harder to reason about who is actually allowed to deploy.

The talk will walk through the architectural implications of letting Git act as the final authority, including where deployment decisions truly occur and how auditability and accountability can be lost when authority boundaries are unclear. We’ll then show how treating deployment authorization as a first-class architectural concept leads to clearer responsibility boundaries and more defensible cloud-native systems.
Speakers
avatar for Kim Schaefer

Kim Schaefer

Senior DevOps Engineer, Game Plan Tech
Kim Schaefer is a Senior DevOps and Cloud Engineer specializing in Kubernetes, GitOps, and secure platform engineering. Kim designs and operates production Kubernetes platforms on Google Cloud, including approval-gated GitOps systems that balance automation with explicit deployment... Read More →
Tuesday May 19, 2026 12:20pm - 12:30pm CDT
200C (Level Two)
  cdCon

2:10pm CDT

Off-Grid Cloud Native: Building Trustworthy Sponsor-to-School Delivery With Kubernetes - Vuyo Mhlotshane, Loakit
Tuesday May 19, 2026 2:10pm - 2:50pm CDT
In many rural communities, the hardest part of funding education is not raising money. It is knowing with confidence that resources reached the right school and were used as intended.

In this session, I share a real-world, open-source reference architecture for a pay-on-proof delivery pipeline where sponsor funds are released only after delivery can be verified. The system is designed for low-bandwidth and intermittent connectivity environments and uses Kubernetes, event-driven workflows, cryptographic proofs, and auditable logs to close trust gaps between sponsors, vendors, and schools.

We will walk through key design decisions, how to think about offline-first systems, and where trust commonly breaks in real deployments, along with practical ways to address those gaps without heavy infrastructure.

Attendees will learn:

- How to model sponsor to vendor workflows using events and state
- Patterns for building offline-friendly, cloud native systems
- Practical digital trust controls including identity, auditability, and proof of delivery

This talk is for platform engineers, SREs, and open source practitioners building systems that must work in real-world conditions.
Speakers
avatar for Constance (Vuyo) Mhlotshane

Constance (Vuyo) Mhlotshane

Cloud Native Engineer, Loakit
Vuyo Mhlotshane is a Cloud Native Engineer and open source practitioner focused on building resilient, trustworthy systems. She works hands-on with Kubernetes, infrastructure as code, and cloud security, and is the founder of Loakit — an initiative exploring how open source technology... Read More →
Tuesday May 19, 2026 2:10pm - 2:50pm CDT
200F (Level Two)
  Cloud + Orchestration

2:10pm CDT

From Malloc To Box: A Practical Guide To Rustification - Christina Quast, Independent
Tuesday May 19, 2026 2:10pm - 2:50pm CDT
Moving from the manual memory management of C to the strict ownership model of Rust is more than a syntax swap; it is a fundamental shift in engineering philosophy. This talk provides a pragmatic roadmap for developers navigating this transition. We move beyond the academic "why" of memory safety to dive deep into the "how" of refactoring legacy systems.

The session explores the practicalities of Rustification, comparing the pitfalls of malloc and free—such as use-after-free and double-free vulnerabilities—with the compile-time guarantees provided by Rust’s Box, Arc, and Borrow Checker. Furthermore, we tackle the topics of how to translate manual pointer arithmetic into safe abstractions, practical strategies for using the Foreign Function Interface (FFI) to let Rust and C coexist during a gradual migration as well as a real-world example of "Rustifying" a C module, from initial profiling to stable deployment.
Speakers
avatar for Christina Quast

Christina Quast

Embedded Systems Engineer, $NONE
After finishing her master's degree in Electrical Engineering at TU Berlin, Christina is currently working as an Embedded Systems Engineer at for various companies. In her spare time, she submits patches to the Linux Kernel or learns new programming languages.
Tuesday May 19, 2026 2:10pm - 2:50pm CDT
208C+D (Level Two)
  Embedded Linux Conference

2:10pm CDT

Automating Linux Kernel Crash Analysis With LLMs - Chris Arges, Cloudflare
Tuesday May 19, 2026 2:10pm - 2:50pm CDT
This talk explores using Large Language Models (LLMs) to automate Linux kernel crashdump analysis at scale. At Cloudflare, we operate Linux across hundreds of thousands of servers. At this scale, kernel crashes are inevitable.
Typical crash analysis requires deep kernel expertise and significant time investment, slowing down time to resolution.
I'll share our journey building an LLM-powered agent that performs initial crash analysis autonomously. First, I'll cover our infrastructure for collecting and managing crashdumps across our fleet. Then I'll explain crashdump analysis fundamentals: using the crash utility, interpreting stack traces, identifying common failure patterns, and correlating crashes with kernel subsystems.
This talk focuses on teaching an LLM agent to replicate expert analysis workflows. I'll show how we structured prompts and created skills. I'll show examples of the agent analyzing real crashes.
Speakers
avatar for Chris Arges

Chris Arges

Senior Systems Software Engineer, Cloudflare
Currently a Senior Systems Software Engineer at Cloudflare. I like to build things. I have a master's degree in Computer Engineering and 18 years of experience in software development and leadership both writing code and leading teams.

My mission is to make the world better where I can. Through my work I want to make the Internet more secure and reliable for everyone. In my free time I enjoy coaching and inspiring a future generation to grow, innovate and create a better world... Read More →
Tuesday May 19, 2026 2:10pm - 2:50pm CDT
205C+D (Level Two)
  Linux

2:10pm CDT

Beyond Static RAG: Building Self-Correcting Agentic Pipelines With Open Source Databases - Ben Grieser, MariaDB
Tuesday May 19, 2026 2:10pm - 2:50pm CDT
As LLMs shift from chatbots to autonomous agents, the limits of "single-shot" RAG are surfacing. Static retrieval often introduces irrelevant context that misleads models. To solve this, developers are adopting Corrective (CRAG) and Adaptive RAG, requiring databases to act as active reasoning runtimes rather than simple stores.

This session explores building self-correcting AI agents using an open-source relational stack. We will demonstrate how to bridge the gap between semantic search and structured data using the Model Context Protocol (MCP) and native MariaDB vector indexing.

Technical topics include:

The Critic Loop: Implementing self-correcting architectures that validate retrieved documents before LLM synthesis.

Hybrid Querying: Combining vector indexing with relational SQL in single ACID transactions to reduce agentic loop latency.

Standardizing Communication: Using the MariaDB MCP Server for secure, tool-based access to live data.

Scaling State: Managing concurrent agent sessions without sacrificing data integrity.

Attendees will leave with a blueprint for building reliable, autonomous systems using open-source database patterns that move beyond basic vector search.
Speakers
avatar for Ben Grieser

Ben Grieser

Sr Solutions Engineer, MariaDB
As a technologist and database expert, Ben Grieser works at the intersection of open source innovation and product engineering. In his role at MariaDB, he regularly talks with team using open source technology to bring complex data products to life. Ben is passionate about making... Read More →
Tuesday May 19, 2026 2:10pm - 2:50pm CDT
211A+B (Level Two)
  Open AI & Data

2:10pm CDT

Architecting for Onboarding: Building a "Docs-as-Code" Pipeline for Open Source Sustainability - Sai Sravan Cherukuri, Independent Contributor
Tuesday May 19, 2026 2:10pm - 2:50pm CDT
In open source, a project's survival depends on its contributor funnel. If developers can't build, test, or grasp your project in the first ten minutes, they'll leave. Documentation is the primary interface for that experience, but is often the most neglected part of the repository.
This session goes past the basic README to show how maintainers can set up a clear Documentation Development Life Cycle. We will explore the 'Docs-as-Code' idea, treating documentation like code by keeping it in Git, peer-reviewing it, and checking it with CI/CD pipelines.
Key takeaways include:
The Pipeline: Setting up automated linters (Vale, Markdownlint) to enforce style and technical accuracy.
The Process: Make sure every new feature includes updated documentation to prevent it from becoming outdated.
The Community: Learn ways to help non-coders contribute, and manage docs with people all over the world.
Join this session to learn actionable steps you can implement right away to make your open-source project more welcoming, robust, and future-proof. Start applying these strategies today and transform your documentation process.
Speakers
avatar for Sai Sravan Cherukuri

Sai Sravan Cherukuri

Open-Source Enthusiast and DevSecOps Architect, Independent Contributor
Engineering for Accessibility: The Human Element of Infrastructure
Sai Sravan is an architect of systems and a champion for the people who build them. As a dedicated open-source advocate, Sai bridges the gap between high-level technical development and community accessibility, ope... Read More →
Tuesday May 19, 2026 2:10pm - 2:50pm CDT
200E (Level Two)

2:45pm CDT

Lightning Talk: Offensive and Defensive Strategies for Addressing Open-Source Vulnerabilities - Tracy Ragan, DeployHub, Inc.
Tuesday May 19, 2026 2:45pm - 2:55pm CDT
Open-source software is foundational to modern application development, but it has also become one of the fastest-moving and hardest attack surfaces to defend. For years, organizations have relied on “shift-left” security to catch vulnerabilities early in the lifecycle. While necessary, this approach alone is no longer sufficient. New vulnerabilities are disclosed daily, often long after software is deployed, leaving IT teams struggling to understand what is truly at risk in production and how quickly they must respond.

In this session, Tracy reframes software supply chain security around the realities of live systems. She explains why teams must move beyond offensive, prevention-only strategies and refocus on rapid detection, prioritization, and response for newly reported vulnerabilities attacking live systems. Tracy also addresses how the pursuit of a zero-vulnerability posture has driven alert fatigue and burnout among developers, security teams, and CIOs.

Attendees will learn how to manage vulnerability alert noise, shorten response times, and focus remediation, protecting open-source-driven systems without slowing delivery or exhausting the teams responsible for them.
Speakers
avatar for Tracy Ragan

Tracy Ragan

CEO, DeployHub
Tracy is a recognized expert in software supply chain security and DevSecOps, specializing in managing complex, decoupled architectures. She is the CEO of DeployHub, a scalable post-deployment vulnerability detection platform that empowers software to 'self-heal' by automatically... Read More →
Tuesday May 19, 2026 2:45pm - 2:55pm CDT
200C (Level Two)
  cdCon

3:05pm CDT

Lightning Talk: Reliability at the Edge: Fail-Safe Multi Cluster Orchestration With Kubestellar - Munachimso (Muna) Nwaiwu, Cornell University
Tuesday May 19, 2026 3:05pm - 3:15pm CDT
Managing a single Kubernetes cluster is a solved problem. However, extending Kubernetes to the edge introduces a fundamental systems crisis. In remote environments, network partitions are guaranteed. When orchestrators demand real-time synchronization, routine network drops lead to configuration drift and control-plane breakdown.

This session analyzes how KubeStellar (a CNCF Sandbox project) attempts to solve this reliability crisis. Evaluated from a systems and network perspective, we dissect how KubeStellar abandons synchronous replication for an asynchronous, hub-and-spoke model. By decoupling its Workload Description Space (WDS) from the transport layer, it leverages eventual consistency to treat disconnected edge nodes as expected, not a fatal error.

To ground this theory in reality, we explore our ongoing research at Cornell University’s Smart Farms. In remote agriculture, long-term partitions are daily realities. We will outline our progress using KubeStellar to manage geographically dispersed clusters, presenting an architectural roadmap for how eventual consistency can ensure local workloads survive extended disconnects and deterministically reconcile upon reconnection.
Speakers
avatar for Muna Nwaiwu

Muna Nwaiwu

Researcher, Cornell University
Munachimso Victor Nwaiwu is a PhD student at Cornell University researching distributed systems and edge orchestration, building upon a highly accomplished career as a Network Automation Engineer. Before his academic research, he made significant contributions to next-generation network... Read More →
Tuesday May 19, 2026 3:05pm - 3:15pm CDT
200F (Level Two)
  Cloud + Orchestration

3:05pm CDT

Microseconds Matter : Benchmarking Thread Synchronization - Gautham Ponnu, The MathWorks
Tuesday May 19, 2026 3:05pm - 3:45pm CDT
This talk aims to analyze the performance of most common Linux synchronization primitives under PREEMPT_RT, comparing their behavior across a range of workloads. We’ll explore how each primitive scales with thread count, handles contention, and impacts determinism. Expect graphs, latency histograms, and a few surprises. If you’re building real-time systems or tuning performance, this session will help you make smarter, faster, and safer decisions.
Speakers
avatar for Gautham Ponnu

Gautham Ponnu

Principal Software Engineer & Manager of Engineering, The MathWorks
Gautham Ponnu is a Principal Software Engineer for Real-Time Systems at MathWorks, where he leads development of real-time simulation and hardware-in-the-loop testing tools. With over a decade of experience in embedded and real-time systems, Gautham specializes in real-time synchronization... Read More →
Tuesday May 19, 2026 3:05pm - 3:45pm CDT
208A+B (Level Two)
  Embedded Linux Conference

3:05pm CDT

Fork, Explore, Commit: Linux Primitives for AI Agents Exploration - Cong Wang, Multikernel Technologies & Yusheng Zheng, eunomia-bpf
Tuesday May 19, 2026 3:05pm - 3:45pm CDT
AI agents don’t execute a single path, they explore many. They try different code changes, commands, or configurations in parallel, then keep the one that works. Today, running this safely on Linux requires fragile combinations of temp directories, git tricks, containers, or VM snapshots.

This talk introduces branch contexts, a new Linux execution model built for AI agents. A branch context gives each exploration path an isolated, copy-on-write filesystem and coordinated process group, with a simple lifecycle: fork, explore, commit or abort. The first successful branch commits atomically; all others are automatically invalidated.

We present two Linux implementations: BranchFS, a FUSE-based branching filesystem with O(1) branch creation and atomic commit without root privileges, and branch(), a proposed Linux syscall that composes filesystem branching, namespaces, and process lifecycle management into a single atomic operation.

We’ll explain why existing Linux mechanisms fall short for agent workloads and how fork/explore/commit semantics fit naturally into the future of Linux process and filesystem design.
Speakers
avatar for Cong Wang

Cong Wang

Founder and CEO, Multikernel Technologies
Cong Wang is a professional Linux kernel developer mainly focuses on Linux networking and eBPF, he is also a Linux kernel maintainer for the networking traffic control subsystem. He has contributed over 1000 patches to the Linux kernel project.
avatar for Yusheng Zheng

Yusheng Zheng

OSS developer, eunomia-bpf
Yusheng Zheng is an OSS maintainer and researcher focused on systems understanding and extensions. As a co-founder of the eunomia-bpf community and a PhD student, Yusheng integrates eBPF and AI to enhance the Linux kernel and userspace applications. Yusheng frequently presents these... Read More →
Tuesday May 19, 2026 3:05pm - 3:45pm CDT
205C+D (Level Two)
  Linux

3:05pm CDT

Identity Management for AI Agents - Abdel Fane, OpenA2A
Tuesday May 19, 2026 3:05pm - 3:45pm CDT
Every enterprise has identity management for humans—SSO, MFA, RBAC, audit logs. But AI agents? They run with API keys, no verified identity, no behavioral tracking, no audit trail.

This talk bridges the gap between traditional IAM and the emerging world of autonomous AI agents:

What we learned from human IAM:

- Why identity must be cryptographic, not just credentials

- How least-privilege access control prevents lateral movement

- Why audit trails matter for compliance and incident response

Applying it to AI agents:

- Agent identity: Ed25519 keypairs vs API keys

- Capability-based access: what tools can this agent call?

- Behavioral trust scoring: detecting compromised agents

- MCP server attestation: verifying the tools agents connect to

We'll examine real attack scenarios—agent impersonation, tool injection, privilege escalation—and show how identity-first security prevents them.

Live demo using AIM (Agent Identity Management), an Apache-2.0 open-source platform. All patterns are framework-agnostic and applicable to LangChain, CrewAI, AutoGen, or raw MCP implementations.

Attendees leave with actionable security patterns for their AI agent deployments.
Speakers
avatar for Abdel Fane

Abdel Fane

CEO & Founder, OpenA2A
Abdel is a cybersecurity architect with 17+ years of experience securing enterprise environments across healthcare, finance, and government sectors. He has led security initiatives at Grail, Booz Allen Hamilton, Protiviti, and Allstate, specializing in cloud security & DevSecOps.
... Read More →
Tuesday May 19, 2026 3:05pm - 3:45pm CDT
211A+B (Level Two)
  Open AI & Data

3:05pm CDT

The Code Is the Contract: How Linux's Architecture Sheds Light on GPL Compliance - Sabir Ibrahim, Dev Legal
Tuesday May 19, 2026 3:05pm - 3:45pm CDT
This session demystifies the GPL by exploring the "architecture of intent"—the deliberate design choices made by kernel maintainers that define the legal boundaries between open source code licensed under the GPL and closed source code that may interface with the Linux kernel while maintaining its own licensing. As a lawyer with a deep interest in open source software and expertise in OSS licensing and compliance, I will bridge the gap between code and copyright. My goal is to provide developers with a practical framework for navigating GPL compliance as it pertains to Linux.

This talk is designed specifically for a technical audience. It is not a dry legal lecture. Instead, it is a practical, developer-focused guide that uses code, architecture, and real-world examples to illuminate complex legal concepts. We will walk through three common scenarios where proprietary software interfaces with the Linux kernel, analyzing each from both a technical and legal perspective.

Attendees will leave with the ability to identify high-risk integration patterns and make more informed development decisions.
Speakers
avatar for Sabir Ibrahim

Sabir Ibrahim

Managing Attorney, Dev Legal
Sabir is an attorney and OSS enthusiast. He has advised clients ranging from startups to Fortune 50 companies on issues relating to OSS. He is a former associate at the law firm of Greenberg Traurig, a former corporate counsel at Amazon, and a former senior counsel at Roku.

Sabir has his own law practice, Dev Legal, and is co-founder of Chinstrap Community. Chinstrap Community is a free resource center for entrepreneurs, investors, and others interested in OSS entrepreneurship... Read More →
Tuesday May 19, 2026 3:05pm - 3:45pm CDT
200H (Level Two)
  Open Source 101

3:05pm CDT

It's Not Rocket Science, It's a Flywheel: Engineering OS Communities With DevEx - Jeremy Meiss, WWT
Tuesday May 19, 2026 3:05pm - 3:45pm CDT
It's no secret that building and sustaining thriving open source communities requires moving beyond sporadic contributions and fostering an ecosystem of engaged members. That process is not simple, and requires a lot of time and effort, which is not often something a maintainer has, which more often than not leads to maintainer burnout or project stagnation.

In this talk, Jeremy will connect the principal of a "flywheel" that we see in everyday life with the principles of Developer Experience, and discuss what a "DevEx Flywheel" should look like. He will explore how things like feedback loops, "time to joy", onboarding, and documentation all contribute to an experience that can enhance contributions, which in turn improves project health, value, and more.

This session will explore what the DevEx Flywheel looks like, and provide actionable strategies for:
- Creating seamless onboarding experiences and amazing documentation
- Implementing tooling and automating workflows by reducing friction
- Fostering welcoming communication and effective feedback loops

Stop hoping for community growth; start engineering it through Developer Experience.
Speakers
avatar for Jeremy Meiss

Jeremy Meiss

Technical Solution Architect, AI Native, WWT
Jeremy is an international speaker and is a Technical Solution Architect, AI Native, at WWT, previously leading Developer Advocacy at OneStream Software, CircleCI, Solace, and Auth0. Jeremy is active in the DevRel and DevOps communities, a co-creator of DevOpsPartyGames.com, and organizer... Read More →
Tuesday May 19, 2026 3:05pm - 3:45pm CDT
200J (Level Two)

3:05pm CDT

Talking To Drones: Natural Language Control of PX4 Using a Phone, MCP, and ChatGPT Realtime API - Godfrey Nolan, RIIS LLC
Tuesday May 19, 2026 3:05pm - 3:45pm CDT
PX4-based drones are powerful, but interacting with them typically requires specialized ground control software and trained operators. This talk presents a new interaction model: controlling and querying a PX4 drone using natural language from a standard mobile phone.

The system combines a Model Context Protocol (MCP)–style interface (inspired by ROS 2 MCP implementations) to expose PX4 capabilities as structured, machine-readable commands, with OpenAI’s real-time ChatGPT API to interpret user intent. A phone call or voice interaction—handled via Twilio—becomes the primary user interface, allowing operators to issue commands such as “take off to 10 meters,” “orbit that location,” or “what’s your battery state?” and receive immediate spoken feedback.

The talk will cover:

* How PX4 commands, telemetry, and state are exposed through an MCP-like abstraction
* Real-time bidirectional communication between phone, AI model, and drone using Twilio and RealTime API
* Safety considerations, command validation, and constraints when using AI-mediated control
* Practical use cases, fly missions, object detection all using hands free control
* Lessons learned, what worked and didn't work
Speakers
avatar for Godfrey Nolan

Godfrey Nolan

President, RIIS LLC
Godfrey Nolan is founder and president of RIIS LLC a mobile development firm in the Detroit Metro area. He is also author of Agile Swift (Apress), Agile Android (Apress), Bulletproof Android (Pearson), Android Best Practices (Apress), Decompiling Java (Apress) and Decompiling Android... Read More →
Tuesday May 19, 2026 3:05pm - 3:45pm CDT
200D (Level Two)
  PX4 Dev Summit

3:25pm CDT

Lightning Talk: Built Clean. Receipts Attached - Adolfo García Veytia, Carabiner Systems & Alex Zenla, Edera
Tuesday May 19, 2026 3:25pm - 3:35pm CDT
Security frameworks such as SLSA require software builds to run in isolated environments to guarantee they are “free of unintended external influence”. In practice, this means full control of the runtime environment and every dependency entering a build, ensuring no malware slips into released software
But how can you verify isolation after the fact? How do you know a container image or binary was compiled in a truly hermetic environment, free from tampering processes or hidden tooling? Can you confidently prove your release used only the dependencies declared in your SBOM?
In this talk, Marina and Puerco will demonstrate practical techniques to verify build isolation and runtime characteristics. Want cryptographic proof of hermetic builds? We’ll show it. Need confidence in software components and complete SBOM coverage? Covered. Trace provenance to the exact VM that executed the build? Absolutely.
Using Cocoon, an open source build packager running inside Edera Protect isolated zones, we will verify attested machine identity via SPIFFE SVIDs, environment features, and SBOM completeness, all enforced with reusable policy code powered by technologies like in-toto, SLSA and Sigstore.
Speakers
avatar for Alex Zenla

Alex Zenla

CTO, Edera
Alex is a Founder & CTO at Edera, building technology for securing containers using hypervisors in Rust. She has contributed to many open source projects including Chromium, Chromium OS, Dart, and Ubuntu, some as early as 11 years old. Alex started in the corporate world at the age... Read More →
avatar for Adolfo Garcia Veytia

Adolfo Garcia Veytia

Founding Engineer, Carabiner Systems
Adolfo García Veytia (@puerco) is one of the Kubernetes SIG Release Technical Leads and actively works on the Release Engineering team. He specializes in improving the software that drives the automation behind the Kubernetes release process. He is also the creator of the OpenVEX... Read More →
Tuesday May 19, 2026 3:25pm - 3:35pm CDT
200C (Level Two)
  cdCon

3:25pm CDT

Lightning Talk: Taking a U-Turn for Caches: Moving Back From Remote To Local - Aditya Mohan, Amazon
Tuesday May 19, 2026 3:25pm - 3:35pm CDT
With the growth of CPU compute and larger memory heaps, many cloud-native workloads that traditionally relied on remote caches like Redis and Memcached can now benefit from in-process caching using open source libraries.

In this session, we focus on Java-based cloud-native services and show how local caches, such as Caffeine, can colocate cache with application logic, reducing network overhead, simplifying consistency management, and improving latency. Drawing on large-scale production experience, we’ll explore cache invalidation, freshness guarantees, near-cache patterns, and scalability trade-offs, along with practical lessons for handling staleness, TTLs, and other caching challenges while reducing operational complexity and cost.

Finally, we’ll discuss how emerging open source tools like Databricks’ Dicer apply these caching and orchestration principles at scale for real-time services, representing the next frontier. Attendees will learn methods to design low-latency, high-throughput, maintainable, and cost-efficient caching solutions for cloud-native architectures using open source tools.
Speakers
avatar for Aditya Mohan

Aditya Mohan

Amazon Senior Machine Learning Engineer at Amazon Advertising Sponsored Products, Amazon
Aditya Mohan is a Senior Machine Learning Engineer at Amazon Advertising with 11+ years of experience and tech lead for agentic advertiser campaigns. He specializes in large-scale ML and semantic search, using LLMs and LangGraph to optimize campaigns and ensure observability, accountability... Read More →
Tuesday May 19, 2026 3:25pm - 3:35pm CDT
200F (Level Two)
  Cloud + Orchestration

3:35pm CDT

Lightning Talk: Confidential Virtual Machines in KubeVirt With Hardware-Backed Trusted Environments - Basavaraju G & Rishika Kedia, IBM
Tuesday May 19, 2026 3:35pm - 3:45pm CDT
Multi cloud deployments and shared infrastructure enhance data privacy and security issues, with containerized workloads becoming mainstream in Kubernetes, there is a need to host containers securely in addition to virtual machines (VMs) to safeguard hardware-level workloads.
KubeVirt is a cloud native virtualization platform that comes with Confidential Virtual Machines for the most sensitive use cases. They take advantage of Trusted Execution Environments such as AMD SEV, Intel TDX, and IBM Secure Execution to provide data-in-motion encryption for their workloads and defend against subverted host admins as well as against system attacks.
In this session, we will cover KubeVirt methodology for Confidential VMs, including the design of the architecture, challenges of implementation, and deployments. We will examine how the VMs protect sensitive workloads using memory encryption, workload isolation while being placed within Kubernetes orchestration and automation.
Speakers
avatar for Rishika Kedia

Rishika Kedia

STSM, Chief Product Owner- OpenShift, BM India Private Ltd
Rishika Kedia is the Product Owner for OpenShift and an Architect for Red Hat OCP on IBM Z at India Systems and Development Labs. With 18+ years of experience, she has led efforts to enable OpenShift and open-source technologies on IBM Z and LinuxONE systems. Rishika has designed... Read More →
avatar for Basavaraju G

Basavaraju G

Architect, IBM
Basava Raju.G is a Currently working at IBM, specializing in IBM Kubernetes Service and Openshift Container Platform. Basava has authored 3 IEEE publications, holds 2 Patents in domain of machine learning and Containers domain. Currently, Basavaraju is working on IBM Labs as the Product... Read More →
Tuesday May 19, 2026 3:35pm - 3:45pm CDT
200F (Level Two)
  Cloud + Orchestration

4:20pm CDT

Hardening QEMU With Self-Correcting Fuzzing Pipelines - Navid Emamdoost, Google
Tuesday May 19, 2026 4:20pm - 5:00pm CDT
This session explores a dual-phase strategy for hardening the QEMU Virtual Machine Monitor (VMM) through advanced fuzzing and AI-driven automation. We begin by detailing a manual hardening effort that expanded QEMU’s testing surface from 18 to 60 active targets, increasing device line coverage by more than 30%. While effective, manual target creation is a resource-intensive process that struggles to scale across the hundreds of virtualized devices supported by QEMU.

To address these scaling challenges, we introduce an AI-driven agentic pipeline designed to automate the generation and validation of fuzzing targets. This system leverages Large Language Models (LLMs) to analyze device source code and memory regions, generating candidate C++ targets for the QEMU fuzzing engine.

We will discuss the implementation of a self-correcting feedback loop where the agent captures compilation and runtime errors to iteratively refine its output until a stable target is produced. Attendees will see how this approach aims to reach >80% device line coverage by automating the remaining hardware targets that currently lack dedicated fuzzing.
Speakers
avatar for Navid Emamdoost

Navid Emamdoost

Software Engineer, Google
Navid Emamdoost is a Software Engineer at Google focused on infrastructure security. He holds a PhD from the University of Minnesota, where his research uncovered over 200 Linux kernel bugs and 40 CVEs. His career includes maintaining OSS-Fuzz for open source projects and hardening... Read More →
Tuesday May 19, 2026 4:20pm - 5:00pm CDT
200F (Level Two)
  Cloud + Orchestration

4:20pm CDT

Optimize Linux Kernel To Fit Microcontrollers With 1 MB RAM - Jim Huang & Chisheng Chen, National Cheng Kung University
Tuesday May 19, 2026 4:20pm - 5:00pm CDT
Running the Linux kernel on microcontrollers with severely constrained RAM has long been viewed as impractical. Conventional embedded Linux builds still assume tens of megabytes of memory, excluding a wide class of resource-limited hardware such as Arm Cortex-M and certain Cortex-R devices. This talk presents recent work on adapting and optimizing the Linux kernel to operate within a 1 MB RAM budget.

We examine the challenges of reducing Linux’s memory footprint for microcontroller-class systems and the techniques that enable Linux to run in sub-megabyte environments. Topics include:
* Memory profiling of core kernel subsystems
* Removing or deferring optional features to reduce RAM usage
* Streamlining kernel image layout and data structures
* Adjusting build configurations and boot flow for extreme constraints
* Runtime trade-offs between functionality and footprint

The session demonstrates how mainline Linux can be reshaped to fit far smaller footprints than traditionally assumed. This approach expands the reach of embedded Linux and provides practical strategies for optimizing memory usage on highly constrained platforms.
Speakers
avatar for Jim Huang

Jim Huang

Assistant Professor, National Cheng Kung University
Drawing from his contributions to the Android Open Source Project (AOSP), Jim specializes in real-time performance tuning and optimization of Linux-based automations. Additionally, he is a co-founder of the LXDE project, a lightweight desktop environment widely utilized in embedded... Read More →
avatar for Chisheng Chen

Chisheng Chen

Student, National Cheng Kung University
Chisheng Chen, a.k.a rota1001, is an embedded system developer transitioned from a CTF player. These days, he wrote firmwares on some microcontrollers and did some DOOM and Linux ports. He is currently pursuing the B.S. degree in Computer Science in National Cheng Kung University... Read More →
Tuesday May 19, 2026 4:20pm - 5:00pm CDT
208C+D (Level Two)
  Embedded Linux Conference

4:20pm CDT

Why Demand Is Growing for Linux as a Real Time OS in Embedded IEC 61508/ISO 26262-compliant Systems - Dylan Dawson, Elektrobit
Tuesday May 19, 2026 4:20pm - 5:00pm CDT
As automotive E/E architectures evolve toward centralized high-performance computing (HPC) real-time operating systems (RTOS) need better visibility into system timing behavior. Additionally software defined vehicle (SDV) trends where open, flexible, non-proprietary software stacks are the goal. In this landscape, legacy concepts like dedicated microcontrollers in-service to HPC safety are being challenged. ADAS workloads are balancing HPC compute power with strict time constraint requirements in real-time behavior. Combining mixed-critical workloads on a single HPC platform is a viable solution for OEMs and Tier 1s building perception, control, and safety-relevant HPC domain controller functions. However, the struggle to ensure real-time performance and deterministic timing is an ongoing challenge.
This presentation will demonstrate how Linux can provide measurable, stable, and predictable real-time performance, enabling ADAS teams to run time-critical functions on a modern automotive-grade Linux stack. The audience will gain confidence in a concept which accelerates development for SDV without proprietary RTOS islands, and charters a path to ASIL B/SIL 3 certification
Speakers
avatar for Dylan Dawson

Dylan Dawson

Director of Cross-portfolio Growth & Strategic Alliances - North America, Elektrobit
Dylan Dawson is a North American Director at Elektrobit. His focus is strategic partnerships and product evangelism across in automotive. His experience spans securing design wins with OEMs, expanding market reach for emerging software products, and building strategic alliances across... Read More →
Tuesday May 19, 2026 4:20pm - 5:00pm CDT
208A+B (Level Two)
  Embedded Linux Conference

4:20pm CDT

NixOS for Deterministic Distributed-System Benchmarking - B. Cameron Gain, ReveCom
Tuesday May 19, 2026 4:20pm - 5:00pm CDT
Reproducibility remains one of the largest challenges in benchmarking distributed systems, especially when hardware, kernel-level parameters and dependency versions vary between tests. This talk presents a NixOS-based approach for constructing deterministic, portable benchmark environments for large-scale data infrastructure. We show how Nix’s declarative system configuration, content-addressed builds and reproducible packaging model allow engineers to isolate performance variables.

We look at how Nix offers a much more reproducible environment when producing different applications for testing. While Docker containers isolate user-space dependencies, they remain tied to the host kernel's version and configuration.

Using Apache Cassandra as the primary case study, the talk demonstrates how NixOS can define and reproduce complete cluster environments. Attendees will learn practical patterns for packaging workloads, pinning dependencies, and generating ephemeral benchmark nodes.

The session concludes with a live demo of how we can initiate benchmark tests on Nix and then kill the entire infrastructure in just a few seconds.


Speakers
avatar for B. Cameron Gain

B. Cameron Gain

Analyst, ReveCom
B. Cameron Gain is co-founder and publisher of ReveCom Media.
Tuesday May 19, 2026 4:20pm - 5:00pm CDT
200G (Level Two)
 
  • Filter By Date
  • Filter By Venue
  • Filter By Type
  • Audience Experience Level
  • Timezone

Share Modal

Share this link via

Or copy link

Filter sessions
Apply filters to sessions.
Filtered by Date -