Open Source Summit Europe 2024: Full Schedule

September 16-18, 2024
Vienna, Austria
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 Europe 2024 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 European Summer Time (UTC/GMT +2). 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.

11:20 CEST

Doing for Sustainability, What Open Source Did for Software - Asim Hussain, Green Software Foundation

Monday September 16, 2024 11:20 - 12:00 CEST

Room 2.15 (Level 2)

In the realm of sustainability, grassroots initiatives often emerge as powerful catalysts for change, driven by the collective wisdom of practitioners. Enter Impact Framework, an open-source tool designed to quantify the environmental impact of software. It takes observations you can easily gather from running systems such as CPU utilization, page views, installs, and prompts, and induces them into environmental impacts like carbon, waste, and water. Drawing parallels to the evolution of open-source software, Impact Framework embodies the ethos of openness—open source, open standards, and open data—as the bedrock of its mission. In this talk, I'll explain the history of Impact Framework and its core concepts and take the audience through a live exercise to demonstrate how to use it to measure the environmental impacts of a piece of software. As we embark on this journey, we echo the sentiment of our community: to do for sustainability what open source did for software—a seismic shift rather than a mere agreement. Join us as we explore the transformative power of open-source principles in driving sustainable impact at scale.

Speakers

Asim Hussain

Executive Director, Green Software Foundation

Asim is a seasoned developer, author, and speaker with over 25 years of experience in the technology industry, spanning the European Space Agency, Intel, Microsoft, and prominent investment banks like Morgan Stanley and JP Morgan. He is the Executive Director of the Green Software... Read More →

Monday September 16, 2024 11:20 - 12:00 CEST
Room 2.15 (Level 2)

CloudOpen

Audience Level Beginner

12:15 CEST

Demystifying Secure Application Communication with Zero Trust and Istio Without Sidecars - Lin Sun, solo.io

Monday September 16, 2024 12:15 - 12:55 CEST

Room 2.15 (Level 2)

Modern cloud-native applications are frequently distributed across multiple Kubernetes clusters or virtual machines. But what exactly are the requirements for securing communication among these cloud native applications? Is encryption alone sufficient? Do applications require unique identities? How can we ensure the integrity of our applications' data? Do we need to control who can access what? And what are the considerations when dealing with multi-cluster environments? This presentation will explore the essentials of securing application communications within a zero-trust architecture framework. Lin will explain how mutual TLS (mTLS) meets these requirements through its handshake and record protocols. Moreover, she’ll demonstrate live how you can implement mTLS for applications by simply labeling their namespaces, without any restart of applications or sidecars using Istio's ambient mesh.

Speakers

Lin Sun

Head of Open Source, solo.io

Lin is the Head of Open Source at Solo.io, and a CNCF TOC member and ambassador. She has worked on the Istio service mesh since the beginning of the project in 2017 and serves on the Istio Steering Committee and Technical Oversight Committee. Previously, she was a Senior Technical... Read More →

Monday September 16, 2024 12:15 - 12:55 CEST
Room 2.15 (Level 2)

CloudOpen

Audience Level Beginner

14:15 CEST

Panel Discussion: eBPF: A New Era in Cloud Infrastructure Tools - Liz Rice, Isovalent; Frederic Branczyk, Polar Signals Inc.; Hemanth Malla, Datadog; Yusheng Zheng, EUNOMIA INC.; and Richard Simon, T-Systems International

Monday September 16, 2024 14:15 - 14:55 CEST

Room 2.15 (Level 2)

eBPF has become something of a buzzword recently, but why is it being used in so many tools for observability, security and networking? What does it bring that other approaches don't offer? How can you leverage the power of eBPF in your organization? Join this session to learn from the creators and maintainers of leading open source eBPF projects about how this kernel technology enables high-performance, scalable cloud infrastructure tools.

Speakers

Liz Rice

Chief Open Source Officer, Isovalent at Cisco

Liz Rice is Chief Open Source Officer with eBPF specialists Isovalent, creators of the Cilium project. She was chair of the CNCF's Technical Oversight Committee 2019-2022, and Co-Chair of KubeCon + CloudNativeCon in 2018. She is also the author of "Learning eBPF" and "Container Security... Read More →

Hemanth Malla

Senior Software Engineer, Datadog

Hemanth Malla is a Senior Software Engineer working on Kubernetes and container networking at Datadog. He is also a Cilium CNCF maintainer. Previously he worked on various distributed systems in industries like e-commerce, fintech and high frequency trading. Apart from computers... Read More →

Frederic Branczyk

Founder, Polar Signals Inc.

Frederic is the founder of Polar Signals. Before founding Polar Signals he was a senior principal engineer and main architect for all things Observability at Red Hat, joining through the CoreOS acquisition. Frederic is a Prometheus & Thanos maintainer and tenured as a tech lead for... Read More →

Yusheng Zheng

eunomia-bpf - Open Source Developer, EUNOMIA INC.

Yusheng Zheng is an active open source contributor and the founder of the eunomia-bpf lab. With a focus on eBPF, she has developed notable projects, including userspace eBPF runtime for Uprobe and Syscall hooks that align with kernel eBPF standards and integrating eBPF with WebAssembly... Read More →

Richard Simon

CTO, T-Systems International

Richard has 34 years of IT industry experience. He has been working in Cloud Computing for 15 years. He's done various roles (Systems Engineer, Senior Kubernetes Architect, Principal Consultant and now CTO). He's worked for a number of prestigious IT vendors and service providers... Read More →

Monday September 16, 2024 14:15 - 14:55 CEST
Room 2.15 (Level 2)

CloudOpen

Audience Level Intermediate

14:15 CEST

Sponsored Session: Building the IDE Golden Path - Ben Potter, Coder

Monday September 16, 2024 14:15 - 14:55 CEST

Room 1.31-1.32 (Level 1)

In this presentation, we’ll share stories of how several organizations built an IDP around where developers spend the majority of their time; the development environment. The integrated development environment (IDE) is sacred to the developer, so we’ll discuss strategies for surveying developers, identifying pilot groups, and improving efficiency without disrupting core workflows.

Speakers

Ben Potter

Head of Product, Coder

Monday September 16, 2024 14:15 - 14:55 CEST
Room 1.31-1.32 (Level 1)

CloudOpen

15:25 CEST

How to Make Your Kubernetes Add-Ons Management Painless in Multi Cloud - Eleni Grosdouli & Gianluca Mardente, Cisco Systems

Monday September 16, 2024 15:25 - 16:05 CEST

Room 2.15 (Level 2)

One of the most powerful aspects of Kubernetes is its extensibility. But with flexibility comes complexity. Deploying Kubernetes add-ons extend its functionality, but with most platform engineers managing and maintaining multiple clusters across different environments comes the pain. Giving a breather to platform administrators will allow them to be more productive and creative, while enabling them to perform deployments easily, quickly and reliably. From a small home lab to large-scale production environments, keeping up with Kubernetes add-ons deployment and management in a consistent, reliable, and maintainable manner can be like trying to find Nemo on the CNCF landscape. In this engaging session, we will demonstrate: - How smoothly Flux synchronises Kubernetes resources - How to use different add-on formats, including Helm charts, raw YAML/JSON highlighting the Lua language template creation for advanced deployments and logical application - How to deploy Cilium as a CNI - How to deploy Kyverno policies to clusters based on their scope as templates Attendees will learn a new, easy and creative way of deploying applications whether on-prem or in the cloud.

Speakers

Gianluca Mardente

Principal Engineer, Cisco Systems

A passionate advocate for automation in Kubernetes environments, Gianluca brings a lot of experience to his role as a Principal Engineer at Cisco Systems. He contributes to the open-source community by actively maintaining Projectsveltos, a set of Kubernetes controllers that simplify... Read More →

Eleni Grosdouli

DevOps Consulting Engineer, Cisco Systems

The go-to person for DevOps and Kubernetes Automation, with a passion for networking, security, endpoint management, and endpoint security, Eleni brings diversity of experiences to her role as a DevOps Consulting Engineer at Cisco Systems. Always eager to learn, she enjoys trying... Read More →

Monday September 16, 2024 15:25 - 16:05 CEST
Room 2.15 (Level 2)

CloudOpen

Audience Level Intermediate

16:20 CEST

Fine-Grained Policies RBAC with OpenFGA - José Carlos Chávez, Okta

Monday September 16, 2024 16:20 - 17:00 CEST

Room 2.15 (Level 2)

The fine-grained nature of cloud native deployments requires fine-grained authorization at each component. However, this may require security policies to be centrally defined and the configurations reflecting them to be defined in each microservice to enable uniform, consistent enforcement across the entire system which is hard to model and maintain. OpenFGA is an open source solution to Fine-Grained Authorization that applies the concept of Relationship-based access control (ReBAC) where a subject's permission to access a resource is defined by the presence of relationships between those subjects and resources. It was designed for reliability and low latency at a high scale. This talk will offer an overview of OpenFGA, ReBAC and its advantages over more traditional RBAC and ABAC in the context of Zero Trust.

Speakers

José Carlos Chávez

Security Software Engineer, Okta

José Carlos Chávez is a Security Software Engineer at Okta, an OWASP Coraza co-leader and a Mathematics student at the University of Barcelona. He enjoys working in Security & Compliance, compiling to WASM, designing APIs and building distributed systems. While not working with... Read More →

Monday September 16, 2024 16:20 - 17:00 CEST
Room 2.15 (Level 2)

CloudOpen

Audience Level Intermediate

11:00 CEST

Green Tech, Lean Budgets: A Journey to Saving Money (and the Planet) with Kubernetes - Timo Derstappen, Giant Swarm

Tuesday September 17, 2024 11:00 - 11:40 CEST

Room 2.15 (Level 2)

Raise your hand if you didn't get cost pressure in 2023! Cost efficiency and sustainability topics have been hotter than ever last year. In this session, we will delve into the techniques we employed to reduce costs and carbon footprints for our end-users in a painless way, leveraging the capabilities of the Kubernetes ecosystem. From PDBs to Spot Instances, we have a comprehensive exploration in store and many ideas for the future.

Speakers

Timo Derstappen

CTO, Giant Swarm

Timo Derstappen is CTO and co-founder of Giant Swarm. He has many years of experience in building scalable and automated cloud architectures.

Tuesday September 17, 2024 11:00 - 11:40 CEST
Room 2.15 (Level 2)

CloudOpen

Audience Level Intermediate

11:55 CEST

Dude, Where’s My Error?: How OpenTelemetry Records Errors, and Why It Does It Like That - Adriana Villela, ServiceNow Cloud Observability & Reese Lee, New Relic

Tuesday September 17, 2024 11:55 - 12:35 CEST

Room 2.15 (Level 2)

When an app crashes or throws an exception, these errors are not just useful, but vital, to record. However: * How an error is visualized in a backend may not be where you think it’ll be, or how you expect it to look. * Only looking at errors could mean you’re missing out on understanding your system holistically, including other failures that may be causing user dissatisfaction. In this session, Adriana & Reese will examine errors using OpenTelemetry (OTel). They will discuss how OTel records errors, how to enhance spans with metadata to streamline troubleshooting, and explore the distinction between errors and exceptions. They'll also look at how the same error is visualized in different backends, and teach about the different span kinds and how they affect error reporting. Attendees will be empowered to navigate the complexities of error handling in their software applications by leveraging OTel’s capabilities to better understand how things are working (or not) in their apps.

Speakers

Reese Lee

Senior Developer Relations Engineer, New Relic

Reese Lee is a Senior Developer Relations Engineer at New Relic, where she is focused on enabling customers and colleagues on OSS via workshops, blog posts, and documentation. She enjoys figuring out solutions to technical problems, learning about interesting user stories and use... Read More →

Adriana Villela

Sr. Staff Developer Advocate, ServiceNow Cloud Observability

Adriana Villela is a Sr. Developer Advocate, helping companies achieve reliability greatness through Observability, SRE, & DevOps practices. Before her current role, she managed a Platform Engineering team & an Observability Practices team at Tucows. Adriana has worked at various... Read More →

Tuesday September 17, 2024 11:55 - 12:35 CEST
Room 2.15 (Level 2)

CloudOpen

Audience Level Beginner

14:00 CEST

Evolving GitOps: Harnessing Kubernetes Resource Model for 5G Core - Ashan Senevirathne & Joel Studler, Swisscom

Tuesday September 17, 2024 14:00 - 14:40 CEST

Room 2.15 (Level 2)

In the forefront of 5G deployment, Swisscom leads by evolving GitOps through the adoption of the Kubernetes Resource Model (KRM), setting a new standard for dynamic configuration management and abstraction in 5G core networks. This strategic enhancement leverages the strengths of GitOps while introducing the flexibility and scalability of Kubernetes, aiming for increased deployment agility and operational efficiency. Our initiative extends Kubernetes API by integrating with custom Kubernetes Operators, alongside CI/CD advancements through Flux, to refine and empower GitOps practices. This talk will delve into our journey of merging GitOps with KRM, showcasing the transformative impact on 5G network operations, from increased reliability to seamless automation. Join us to explore how Kubernetes is reshaping the future of network management and GitOps methodologies.

Speakers

Ashan Senevirathne

Product Owner, Swisscom

Experienced Product Owner and Senior DevOps Engineer with a proven track record in driving innovation and efficiency in telecommunications. Currently with Swisscom, leading the development of a cloud-native orchestration framework for 5G Core using Kubernetes. Adept at optimizing... Read More →

Joel Studler

DevOps Engineer & System Architect, Swisscom

Joel is a DevOps Engineer who currently works in a team that delivers databases as a service to internal and external customers. He is experienced in infrastructure automation, software defined networking and highly available databases. He is CKA and CKAD certified and has written... Read More →

Tuesday September 17, 2024 14:00 - 14:40 CEST
Room 2.15 (Level 2)

CloudOpen

Audience Level Advanced

14:55 CEST

Panel Discussion: Do One Thing, and Do It Well: Special Purpose OSes Apply the Unix App Philosophy to the Whole OS - Danielle Tal, Microsoft; Mauro Morales, Spectro Cloud; Felipe Huici, Unikraft GmbH; and Richard Brown, SUSE; Erik Nordmark, Zededa

Tuesday September 17, 2024 14:55 - 15:35 CEST

Room 2.15 (Level 2)

Our BoF panel features representatives of popular, highly specialized Linux distributions like Kairos, Flatcar, Eve, BottleRocket, Unikraft, SUSE MicroOS, and others. After a brief introduction we will open a discussion with the audience about the purpose, and limits, of special-purpose operating systems, on operational challenges, and on differences to general purpose operating systems. Discussions may include a wide variety of topics our audience is interested in discussing, e.g. opportunities to improve operations reliability and security, developing and operating cloud-native workloads, workload isolation, and trusted/measured boot.

Speakers

Erik Nordmark

CTO and co-founder, Zededa

Erik is co-founder and CTO at ZEDEDA, and is an expert on architecting and implementing large scale software systems. Prior to ZEDEDA he developed software at Arista Networks, was a Cisco Distinguished Engineer & was a Sun Microsystems Distinguished Engineer. He has been driving Internet... Read More →

Richard Brown

Distributions Architect, SUSE

Richard is an openSUSE contributor since the project began and the founder of the Aeon Desktop. A Former Systems Manager, QA Engineer, openSUSE Board Member & openSUSE Chairperson, Richard is currently a Distributions Architect at SUSE Aeon extends openSUSE's Immutable MicroOS to... Read More →

Felipe Huici

CEO & Co-Founder, Unikraft GmbH

Dr. Felipe Huici is CEO and Co-Founder of Unikraft, a start-up dedicated to lightweight and open source virtualization tech. Prior he worked as chief researcher at NEC Laboratories Europe, has published in several top tier conferences such as SOSP, ASPLOS, OSDI, Eurosys, SIGCOMM... Read More →

Danielle Tal

Program Manager, Microsoft

Danielle Tal is a Program Manager at Microsoft and an integral part of the team responsible for maintaining Flatcar Container Linux. The team is contributes to Linux OS distributions and Linux Security within Azure and other upstream projects. With a background in supporting diverse... Read More →

Mauro Morales

Open Source Developer Specialist, Spectro Cloud

Mauro is a Guatemalan software developer with more than 17 years of professional experience. His main focus is on backend and CLI applications using the Ruby and Go programming languages. He’s also had a chance to participate in the Open-Source community on projects like Cloud Foundry... Read More →

Tuesday September 17, 2024 14:55 - 15:35 CEST
Room 2.15 (Level 2)

CloudOpen

Audience Level Any

16:00 CEST

Cloud Native Threat Intelligence for Everyone - James Callaghan, ControlPlane & Constanze Roedig, Technische Universität Wien

Tuesday September 17, 2024 16:00 - 16:40 CEST

Room 2.15 (Level 2)

Accurate and current threat intelligence data plays a vital role in threat modelling, as we can learn about what attackers are doing in the wild, and how likely certain attack paths are to be exploited. Whilst open source threat intelligence does exist, it is often ‘event-based’, focusing on historical incidents of attackers using particular techniques to exploit specific vulnerabilities. However, what if we want to quantify our own threat models, which may involve chaining together many such attack vectors? The Kubernetes Storm Centre is a newly established open source initiative that aims to provide a framework for independent quantification of cloud native attack paths, with contributing organisations running diverse ‘honey-clusters’ and sharing their results with a central hub for the world to freely consume. In this session, we will discuss the progress made by the project so far, share our initial results and insights, and explain how interested parties can contribute.

Speakers

Dr. Constanze Roedig

Head of the Austrian Open Cloud Community, Technische Universität Wien

Constanze earned her doctorate at the Albert Einstein Institute in relativistic radiation hydrodynamics. After 8 years as a software architect focussed on reimplementing legacy systems with transparent, performant, scalable and defensible designs, she returned to academia for an Austrian-wide... Read More →

James Callaghan

Principal Consultant, ControlPlane

Dr. James Callaghan is a Cloud Native Security Architect at ControlPlane. He started off working as a Theoretical Physicist, but long nights of coding sparked an interest in how easy it can be for vulnerabilities to creep in. James then spent a number of years consulting as a Security... Read More →

Tuesday September 17, 2024 16:00 - 16:40 CEST
Room 2.15 (Level 2)

CloudOpen

Audience Level Intermediate

16:55 CEST

MicroCeph: Simplifying Storage from Laptop to Data Center - Peter Sabaini, Canonical

Tuesday September 17, 2024 16:55 - 17:35 CEST

Room 2.15 (Level 2)

Need to get started quickly with storage? Need a robust storage cluster that doesn't require a team of experts to maintain and grow? MicroCeph aims to make software defined storage effortless to install, and scales from your laptop to dozens of racks. MicroCeph is a self-contained packaging of the Ceph cluster software --it integrates well into existing environments, and is great choice wherever you need repeatable installs and ease of operation, such as edge clouds, labs or remote sites. This talk will give an overview of MicroCeph and shows use cases and demos. It will show how to scale from a single-node dev environment to a multi-node cluster, how object storage and distributed filesystem can be provided, and how to integrate MicroCeph into existing environments. Furthermore options for encryption at rest and disaster recovery as well as hardware acceleration will be presented.

Speakers

Peter Sabaini

Software Engineer, Canonical

Peter is a Software Engineer at Canonical, working on Ceph storage solutions. Before that, he was part of the managed services team there. He has worked in software development and (Linux) ops roles throughout his career.

Tuesday September 17, 2024 16:55 - 17:35 CEST
Room 2.15 (Level 2)

CloudOpen

Audience Level Intermediate

11:00 CEST

Learning from Firefighters to Improve Systems Reliability - Kerim Satirli, HashiCorp

Wednesday September 18, 2024 11:00 - 11:40 CEST

Room 2.15 (Level 2)

Almost seventy years ago, wilderness firefighters who reeled from major losses developed a set of rules with the goal of improving incident management. These rules came to be known as the "Ten Standard Firefighting Orders" and have been the authoritative way of preparing and training for critical operations. In this talk, Kerim explains how the systematic approach of these orders can be adapted to a software engineering context, with the ultimate goal of improving operational reliability and, in the case of an outage, limit damage to human operators and (IT) infrastructure.

Speakers

Kerim Satirli

Senior Developer Advocate, HashiCorp

Kerim is a senior developer advocate at HashiCorp and AWS Community Builder for Security & Identity. Before he joined HashiCorp, Kerim worked on Industrial IoT for the Amsterdam airport and helped museums bring more of their collections online. When Kerim isn't working, he's either... Read More →

Wednesday September 18, 2024 11:00 - 11:40 CEST
Room 2.15 (Level 2)

CloudOpen

Audience Level Advanced

11:55 CEST

Painless Multi-Tenant Kafka on Kubernetes with Istio at ASML - Thomas Reichel, ASML Holding & Dominique Chanet, Klarrio

Wednesday September 18, 2024 11:55 - 12:35 CEST

Room 2.15 (Level 2)

ASML is building a self-service, multi-tenant data platform that enables teams to work independently on data products and applications. In a secure multi-tenant Kubernetes setup, tenants get an isolated view of the cluster, allowing them to deploy workloads independently of each other. Data sharing among tenants is governed by a global policy-based access control layer. Our challenge was to introduce a shared Kafka cluster into this setup, with proper tenant isolation and seamless integration with the global access control layer. We used Istio to enable zero-configuration authentication for Kafka clients operating inside the Kubernetes cluster. This allows Kafka authentication to be done with the Kubernetes-native tenant/namespace/serviceaccount idiom. A custom operator reconciles the tenant's topic definitions and topic access requests with the platform administrator's resource allocations and the global data sharing policy, and dynamically configures the right Kafka ACLs and resource quota.

Speakers

Thomas Reichel

Lead Architect Common Digital Platform ASML, ASML Holding

Thomas Reichel is Lead Architect for the Next Generation Digital Platform at ASML, one of the world’s leading manufacturers of chip-making equipment. Previously, he was Lead Architect for Digital Platforms, Data & Analytics at a Dutch incumbent telecom operator.

Dominique Chanet

Lead Architect, Klarrio

Dominique Chanet is Lead Architect at Klarrio, a system integrator providing real-time data streaming and large scale data processing solutions. He holds a PhD from Ghent university on link-time optimization of operating system kernels... Read More →

Wednesday September 18, 2024 11:55 - 12:35 CEST
Room 2.15 (Level 2)

CloudOpen

Audience Level Advanced

14:00 CEST

Lightning Talk: Fort Kairos: A New Dawn for Secure Linux in Untrusted Environments - Mauro Morales, Spectro Cloud

Wednesday September 18, 2024 14:00 - 14:10 CEST

Room 2.15 (Level 2)

At the edge, there's one thing we know for sure: it's not to be trusted. But imagine if Kairos could change that, letting you sleep soundly knowing your intellectual property is secure. Kairos is a fully open source project to run kubernetes at the edge. As such, we have put Trusted Boot into action. Inspired by Lennard Pottering, the mind behind Systemd, we've leveraged Secure Boot, Trusted Boot, TPM, and disk encryption. The result? A Linux OS that's built tough against the challenges of untrusted environments.

Speakers

Mauro Morales

Open Source Developer Specialist, Spectro Cloud

Wednesday September 18, 2024 14:00 - 14:10 CEST
Room 2.15 (Level 2)

CloudOpen

Audience Level Intermediate

14:10 CEST

Lightning Talk: The Open Source Smart Garden - Ivan Šarić, TripAdvisor

Wednesday September 18, 2024 14:10 - 14:20 CEST

Room 2.15 (Level 2)

This presentation outlines the design of a smart garden system. The system consists of a cloud component where data is streamed to and commands are relayed from the local sites. The other component is the locally positioned SBC-powered system that orchestrates a group of sensors and controllers while maintaining a tunnel to the cloud. The choice of protocol for local communication between the SBC-based coordinator, sensors and controllers is open. The current set up is based around Zigbee due to the small size of the deployment site and the unobstructed nature of the terrain on which the system was developed. The system leverages the power of the open-source graph visualization and monitoring platform Grafana and the time-series database Prometheus. Grafana is a natural choice for a user dashboard that can display real-time site statistics like soil-moisture, ph score and EC. Grafana provides monitoring capabilities that will be used by the operators to ensure functioning. The cloud component provides long-term storage of all locally-streamed data. It also allows the owner to export all collected data for analysis by a third-party expert.

Speakers

Ivan Šarić

Software Engineer, TripAdvisor

Ivan Šarić is a Software Engineer at TripAdvisor.He previously worked as a freelance Technical Architect and Software Developer through his company Path Variable LLC.He holds an MA degree in Political Science and Government from Central European University, where he studied topics... Read More →

Wednesday September 18, 2024 14:10 - 14:20 CEST
Room 2.15 (Level 2)

CloudOpen

Audience Level Intermediate

14:20 CEST

Lightning Talk: Millisecond Scale-to-Zero and the Quest to Never Pay for Idle Again - Felipe Huici, Unikraft GmbH

Wednesday September 18, 2024 14:20 - 14:30 CEST

Room 2.15 (Level 2)

Cloud traffic is intermittent and bursty, but cloud bills are on 24/7. While many cloud providers have scale to zero mechanisms (i.e., putting an app to sleep if it's idle, and waking it up when requests for it arrive once again), these are slow, taking seconds or minutes to kick-in. In this lightning talk, we will show that leveraging tech from the Linux Foundation OSS Unikraft project (www.unikraft.org) we can fundamentally disrupt the semantics of scale to zero and autoscale in modern cloud deployments. Concretely, we will demo the ability to (1)*cold* start standard apps (web servers, databases, etc) in milliseconds; (2) scale them to 0 within milliseconds; and (3) wake them up within milliseconds of the next request coming in -- within an Internet RTT and thus not noticeable by end users. Finally, for a bit of fun, we will push the server to the limit, by loading it with thousands of these scaled to zero instances -- and take bets from the audience as to where the system might break.

Speakers

Felipe Huici

CEO & Co-Founder, Unikraft GmbH

Wednesday September 18, 2024 14:20 - 14:30 CEST
Room 2.15 (Level 2)

CloudOpen

Audience Level Beginner

14:30 CEST

Lightning Talk: With Great Traces Comes Great Costs: How to Reduce That Bill? - Prashansa Kulshrestha, Independent

Wednesday September 18, 2024 14:30 - 14:40 CEST

Room 2.15 (Level 2)

Is Distributed Tracing an observability essential or just a high-maintenance diva? Hardly, anyone wants to compromise on a trace. For an adventure, try tracing everything and watch your cloud bill explode. Yes! All those spans that you decide to keep are expensive. If you use an external APM provider, god help you before you break your bank. While tracing has solved a number of problems, the cost problem is genuine and it keeps increasing with scale. In this presentation, Prashansa narrates her experiences when she was trying to balance the costs while keeping the traces sane. It’s a humorous journey lined with some failed experiments, small peaks of joy, troughs of sorrow and finally tumbling upon a good enough solution. Join her to know how you can also maintain good and sane enough tracing with a manageable bill, with some span tweaking magic, custom sampling algorithm and fully utilising OpenTelemetry capabilities. Trace smarter to save better.

Speakers

Prashansa Kulshrestha

Software Engineer, Independent

Prashansa Kulshrestha has worked at Postman for 4 years in the Reliability Engineering team. Thus, her mindset is observability-first. Currently, she is enjoying a career break while she explores new opportunities that come her way. She is interested in Linux and cloud-native tech... Read More →

Wednesday September 18, 2024 14:30 - 14:40 CEST
Room 2.15 (Level 2)

CloudOpen

Audience Level Intermediate

15:10 CEST

Multi-Cloud Global Content Distribution at Cloud Native Speeds - Jiri Kremser, k8gb Project & Yury Tsarev, Upbound

Wednesday September 18, 2024 15:10 - 15:50 CEST

Room 2.15 (Level 2)

If you’ve been globally distributing digital content for a while, you’ll understand that merely having numerous datacenters with advanced caching patterns isn’t sufficient. When your users need to retrieve an object that’s available in different locations worldwide, they should ideally be directed automatically to the location that’s nearest and fastest for the best experience. Cloud service providers typically offer services to handle this for you within their own clouds, but what if you are running a multi-cloud or hybrid environment? K8GB is a cloud-native solution that handles GeoDNS across heterogeneous environments and enables you to reach the same level of multiregion service resilience offered by cloud providers.

Speakers

Jiri Kremser

Core Maintainer, k8gb project

Yury Tsarev

Principal Solutions Architect, Upbound

Yury is an experienced software engineer who strongly focuses on open-source, software quality and distributed systems. As the creator of k8gb (https://www.k8gb.io) and active contributor to the Crossplane ecosystem, he frequently speaks at conferences covering topics such as Control... Read More →

Wednesday September 18, 2024 15:10 - 15:50 CEST
Room 2.15 (Level 2)

CloudOpen

Audience Level Intermediate

16:05 CEST

Scalable Multi-Node AI Workloads in Multi-Tenant AI Clouds Using SDN K8s Networking - Girish Moodalbail, NVIDIA Inc & Leonid Grossman US, NVIDIA

Wednesday September 18, 2024 16:05 - 16:45 CEST

Room 2.15 (Level 2)

Within AI workloads, a few key traffic flows drive significant data movement between GPUs across nodes. Optimizing these flows for efficient bandwidth, low latency, and minimal jitter is critical to prevent GPU underutilization. Additionally, in the context of AI Cloud infrastructure, accommodating numerous users and concurrent AI workloads introduces competition for shared network resources, potentially impacting application performance. Hence, ensuring isolation between workloads within and across tenants is paramount. This session will explain ways to achieve network isolation (overlay virtual network topology) and efficient bandwidth (end-to-end QoS) between AI workloads using Open Source SDN solution, namely, Open vSwitch (OVS), Open Virtual Network (OVN), and OVN-Kubernetes CNI. With OVS-offloadable hardware the gains are much more significant.

Speakers

Girish Moodalbail

Distinguished Engineer, NVIDIA Inc

Girish Moodalbail is a Distinguished Engineer at Nvidia Inc. Girish is responsible for building Kubernetes based GPU compute using Smart NICs for Gaming, AI Training, and AI Inferencing with low-latency, high-throughput, reliable, scalable, and secure networking using OSS projects... Read More →

Leonid Grossman

Sr. Director, NVIDIA

Leonid is a Senior Director of Cloud Networking at Nvidia, responsible for SDN in a GPU-based Cloud. Before joining Nvidia, Leonid was responsible for Oracle Solaris Networking. Prior to Oracle, Leonid was a Founder and a VP at Neterion, a Silicon Valley venture-backed startup pioneering... Read More →

Wednesday September 18, 2024 16:05 - 16:45 CEST
Room 2.15 (Level 2)

CloudOpen

Audience Level Beginner