Are you a Amazon Web Services EKS customer or run Kubernetes on your own on EC2? Please see kubernetes.io/blog/2023/02/0… and kubernetes.io/blog/2023/03/1… for some self-help tips! Please read on (1/n)

Hmm.. wonder how this bot's computing contributions. Any idea? Davanum Srinivas Kubernetes

A good write-up of some of the contributions some of our AWS teams are making to Cloud Native Open Source projects, including Kubernetes, containerd, and nerdctl to name a few: aws.amazon.com/blogs/opensour…

We are deeply saddened to share the passing of a wonderful member of our community, Carolyn Van Slyck. Carolyn was passionate about serving the contributor community in many ways. Community members can share their memories of Carolyn on her memorial page, github.com/cncf/memorials…

Took us 5 years to make Kubernetes (mostly) boring for our customers. Another 5 and I'm hoping we make it invisible for the world :)

Oof.. Oppenheimer really put "blast radius" back into perspective

"The use of Paxos in this disaggregated architecture demonstrates that there are alternatives that might fit your needs better than the more monolithic Raft." jack-vanlightly.com/analyses/2023/…

For your weekend reading! (if you use #AmazonEKS) aws.amazon.com/blogs/containe…

An interesting microcosm of how herd mentality could send societies spiraling down.

Now, Shyam Jeedigunta and Wojciech Tyczyński speaking on #kubernetes SIG Scalability at #KubeConEU 2024

Ever wondered how Amazon EKS manages k8s control plane and #etcd failures when the underlying hardware fails or an entire Availability Zone disappears? Check out this excellent talk by Jyoti and Shyam, where they discuss how Amazon EKS handles zonal outages. Each failure

True time with ūs accuracy. What makes this most exciting to me is that many of today's distributed systems rely on transactional ordering - and time at this granularity allows them to switch from synthetic sequencers to the one true sequencer the universe gifted us with :)

Don't miss this deep dive post on scaling EKS to 100,000 node clusters! It's full of hard won, real world, distributed systems knowledge.

🚀 Big breakthrough: Amazon EKS now scales up to an incredible 100,000 worker nodes in a single cluster, enabling customers to scale up to 1.6 million AWS Trainium accelerators or 800K NVIDIA GPUs to train and run the largest AI/ML models. Here’s our breakdown of what happened