Loading…
In-person + Virtual
November 6-9
Learn More and Register to Attend

The Sched app allows you to build your schedule but is not a substitute for your event registration. You must be registered for KubeCon + CloudNativeCon North America 2023 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.

Please note: This schedule is automatically displayed in Central Standard Time (UTC -6). To see the schedule in your preferred timezone, please select from the drop-down menu to the right, above "Filter by Date." The schedule is subject to change.
Back To Schedule
Thursday, November 9 • 2:55pm - 3:30pm
Scaling Kubernetes Networking to 1k, 5k, ... 100k Nodes!? - Marcel Zięba, Isovalent & Dorde Lapcevic, Google

Sign up or log in to save this to your schedule, view media, leave feedback and see who's attending!

Tweet Share
Feedback form is now closed.


Setting up clusters with thousands of nodes can be challenging especially when running sophisticated networking like Cilium, which is required when serving internet-scale applications. In this session, you will learn best practices around scaling Cilium and Kubernetes from tech leads from Google Cloud (which allows 15,000 node clusters) and Isovalent (which scales Cilium Cluster Mesh-based clusters up to 256 clusters/100k nodes). It will compare two perspectives - a large single-cluster as well as an alternative - managing multiple smaller clusters and how these decisions impact performance/scalability/reliability. You’ll be able to hear from practitioners in the space how to configure your clusters, what metrics to monitor, and how to improve the reliability of your production environment. If you want to understand how networking features impact the Kubernetes control plane, how to minimize the blast radius of outages, and learn about large-scale incidents, this session is for you!
Speakers
avatar for Dorde Lapcevic

Dorde Lapcevic

Software Engineer, Google
Dorde is a software engineer at Google, working on networking performance and scalability of GKE (Google Kubernetes Engine). The main part of the work is designing scalable networking features, optimizing their performance and reliability, and testing the system to the limits, to... Read More →
avatar for Marcel Zięba

Marcel Zięba

Staff Software Engineer, Isovalent
Marcel Zięba is a Staff Software Engineer at Isovalent and is leading SIG Scalability in the Kubernetes open-source community. Previously, Marcel worked on Kubernetes and Google Kubernetes Engine since 2020 focusing mainly on performance and scalability. Now he is focusing on the... Read More →

Scaling Kubernetes Networking to 1k, 5k, ... 100k Nodes! .pptx pdf
Thursday November 9, 2023 2:55pm - 3:30pm CST
W179 (Ground Level)
  Operations + Performance