Leader is reachable but not forwarding traffic

[Hamdiovish]

Hi,
I'm facing issue with Kilo inside k3s hosted in multiple EC2 instances with onprem worker nodes.

Full mode is working fine and all nodes can ping each other, but when I tried to make one node as leader for aws location, my onprem worker nodes became unable to ping all ec2 nodes except the leader.

Are there any particular configuration needs to be done to allow the leader to forward traffic to other nodes within its location?

Thanks

[squat]

The most common issue here is the encapsulation setting for the mesh. What value are you using?

Alternatively this might have something to do with the compatibility layer setting. Compatibility settings are really best effort and have sharp edges. Currently, only Cilium compatibility is at 100%. Flannel compatibility works in full-mesh but does not work 100% in other topologies. Are you using a compatibility setting?