diff --git a/terraform/files/cilium/l2-announcement.yaml b/terraform/files/cilium/l2-announcement.yaml index a3ba764..3e95db6 100644 --- a/terraform/files/cilium/l2-announcement.yaml +++ b/terraform/files/cilium/l2-announcement.yaml @@ -11,3 +11,10 @@ spec: loadBalancerIPs: true interfaces: - eno1 + # Only control-plane nodes may hold the L2 lease. They have the `eno1` LAN NIC; + # the GPU worker's NICs are enp28s0f*np* (Mellanox) with NO eno1 — if it won the + # lease it held the LB VIP but couldn't ARP it, turning .160 into a LAN black + # hole (cluster-wide outage that flapped as reboots reshuffled the lease). + nodeSelector: + matchLabels: + node-role.kubernetes.io/control-plane: ""