SREcon24 Europe/Middle East/Africa

Laura Nolan; Niall Murphy, Stanza


Effective load management is a core aspect of the SRE role. In this workshop, participants will be introduced to a number of Envoy proxy features that are used for loadshedding and isolation, such as circuit breaking, adaptive concurrency, and ratelimiting. Participants will also use custom Go plugins to perform loadshedding. As part of the practical element of the workshop, participants will interact with Envoy configurations and status/control pages and endpoints, as well as Envoy’s telemetry.


https://www.usenix.org/conference/srecon24emea/presentation/nolan

Leila Vayghan, Shopify


This talk is about enhancing the search infrastructure of Shopify, a large-scale ecommerce platform that supports over 3 million merchants and handles more than two petabytes of data.

This talk explains how we leverage Kubernetes on Google Cloud Platform to ensure high availability and performance, crucial for maintaining our platform's robust search functionality. It will also elaborate on our innovative approach using dedicated reindexing nodes within existing clusters, which significantly improves indexing and reindex performance while cutting infrastructure costs. We will explore the application of Kubernetes Event-Driven Autoscaling (KEDA) to dynamically manage resource allocation, enhancing operational efficiency and reducing on-call fatigue. This strategy not only supports seamless user experiences but also boosts Gross Merchandise Value (GMV) and revenue through improved system responsiveness.

This presentation is ideal for those involved in managing large-scale data systems or interested in advanced Elasticsearch optimizations.


https://www.usenix.org/conference/srecon24emea/presentation/vayghan

Moeid Heidari


This research tackles the limitations of traditional autoscaling systems, which typically operate within a single cloud provider. We propose a new Kubernetes autoscaling operator that dynamically adjusts resources across multiple cloud platforms and on-premise systems. By integrating with various provisioning systems and allowing user-defined scaling strategies, this operator addresses the inefficiencies and vendor lock-in issues of conventional solutions. Our approach not only enhances scalability and system resilience but also improves cost-efficiency, as demonstrated by a significant increase in system availability. Metrics are collected and analyzed to predict scaling needs, ensuring optimal performance and resource utilization.


https://www.usenix.org/conference/srecon24emea/presentation/heidari

Marc Tudurí, Grafana Labs


eBPF allows to attach programs in the Linux Kernel and inspect the runtime memory of the Kernel and user programs at runtime. Join us in this session to discover how Grafana Beyla works, our eBPF-based instrumentation tool, and how is a Kubernetes a first-class citizen. We will describe how we match the low-level abstractions from eBPF with the Kubernetes metadata, allowing Kubernetes users to have out-of-the box observability for their running applications.


https://www.usenix.org/conference/srecon24emea/presentation/tudur%C3%AD

Daniel Hodges, Meta


This talk will discuss how eBPF-based schedulers can be used to enhance application performance at scale. The presentation will begin by explaining the fundamental eBPF capabilities necessary for constructing schedulers, providing a foundation for understanding their design. Following this introduction a discussion of schedulers and their design will be presented. Finally, some practical lessons for deploying schedulers in production environments will be given.


https://www.usenix.org/conference/srecon24emea/presentation/hodges

Chris Engelbert, simplyblock GmbH


For more than two decades, iSCSI was the go-to protocol standard for remote block storage over commodity network hardware, utilizing normal Ethernet networks, hence mitigating specialist hardware, saving cost, and providing a much lower entry barrier than Fibre Channel or Infiniband.

However, the underlying storage technologies made leaps during that time, and today iSCSI is often a bottleneck for high-performance storage deployments, backed by SSDs or NVMe. Therefore, the NVMe Express group defined the NVMe over Fabrics protocol family, with NVMe over TCP being at the forefront to replace iSCSI, while offering lower latency, higher throughput, and less protocol overhead.

Let’s dive into NVMe, NVMe over TCP, and how it’s superior to iSCSI, as well as the support landscape.


https://www.usenix.org/conference/srecon24emea/presentation/engelbert

Darin E. Langone


In the ever-changing landscape of CVEs, bug fixes, enhancements, etc., vendors are taking a more rigid stance when it comes to applying patches and security fixes that they have provided. If you are not careful and do as they say without implementing any pre- and post-patch testing and analysis, you open your hardware and systems up to potentially significant performance impact.


https://www.usenix.org/conference/srecon24emea/presentation/langone

Lasse Hels, Maersk


How do you run a time series database exclusively on spot nodes? With great difficulty!

Grafana Mimir is the centrepiece of our observability platform at Maersk. For a long time, rollouts of Mimir's most crucial component would consistently trigger significant performance degradations in the platform. Getting to the root cause of the issue proved laborious and took us deep into the internals of Mimir.

Join us as we go through the issue postmortem and reflect on how to create consistency in a chaotic environment. The talk touches on topics such as CPU throttling, hash rings, compute utilisation analysis and metric series cardinality.


https://www.usenix.org/conference/srecon24emea/presentation/hels

Oxana Kharitonova, Cloudflare


It's difficult to imagine the modern world without cryptography. We use cryptography to encrypt data before transmitting it over the Internet or storing it on a disk. But we don't think much about how it works, we just pick the most popular cryptographic user space library for our next application and let it do the work for us. What if it's not as secure as we hope? There is another way to do it with the Linux Kernel itself. It can encrypt & decrypt data in the same way as user space libraries do it but in a much more secure way. Through the talk we will explore how to integrate this feature in user space applications written in Golang and Rust languages. You don’t need to be a Linux kernel ninja to start using it.


https://www.usenix.org/conference/srecon24emea/presentation/kharitonova

Carly Richmond, Elastic


Despite the emergency of DevOps to unite development, support and SRE factions together using common processes, we still face cultural and tooling challenges that create the Dev and SRE silos. Specifically, we often use different tools to achieve similar testing: case in point validating the user experience in production using Synthetic Monitoring and in development using E2E testing.

By joining forces around common tooling, we can use the same tool for both production monitoring and testing within CI. In this talk, I will discuss how Synthetic Monitoring and E2E Testing are two sides of the same coin. Furthermore, I shall show how production monitoring and development testing can be achieved using Playwright, GitHub Actions and Elastic Synthetics.


https://www.usenix.org/conference/srecon24emea/presentation/richmond

Alvaro Leiva Geisse and Anita Zhang, Meta
IMPORTANT: If you are attending this workshop, please work through the Getting Started section in order to download the image and set up your environment.
systemd (with lowercase S and D) remains up until this day, both one of the most critical pieces of a system, and the least understood one. This workshop is designed to touch upon the beginner features of systemd and explain how you can use systemd to solve common problems, including some that you didn't even know you had. What problems do you ask? You’ll have to come and see.
https://www.usenix.org/conference/srecon24emea/presentation/geisse