Martynas Pumputis

@michi-covalent Thanks! Could you TL;DR a new workflow when adding new feature / tests to cilium/cilium? In particular, how they will be run by CLI in the existing GH workflows?

@mmerickel What's your cluster configuration? AWS CNI chaining?

Just relaying relevant bits @learnitall said in a private thread: > As for why this happens, I believe the AWS VPC CNI isn't playing nice and is somehow forcing pods...

Could you please try the following images https://github.com/cilium/cilium/actions/runs/8737485006/job/23975228008?pr=32047#step:4:19 (based on v1.15), and report back whether it has resolved the performance issues?

@kvaps Thanks for the PR. Do you mind to update the documentation too (` Documentation/network/kubernetes/kubeproxy-free.rst`)?

> I see this has a milestone of v1.10. Is that going to happen? Best effort, but very unlikely.

BTW, with this PR merged, we can easily tackle: > Create and load from-wireguard instead of from-netdev (https://github.com/cilium/cilium/pull/19401#discussion_r1066070869). From https://github.com/cilium/cilium/issues/23032. It will give us a few CPU cycles back :sunglasses:

/test

/test

/ci-ipsec-e2e