Resolved
This incident has been resolved.
Investigating
Hypervisor IAD03C25 was down due to NIC issue.
Unfortunately, one of our Kubernetes masters was on that node and failover wasn't executed successfully.So ingress of control plane services are ALL down during the outage.
All services are back and we'll now close this incident and check why failover didn't work.
Investigating
We'll now reboot one of our core routers to fix a module issue.It will cause ~ 10 minutes downtime to some circuits.