One instance of the load balancer has been unreachable, we have performed a patch and rebooted it.
We are watching the load balancer.
EDIT 14:00 UTC : We have updated the load balancer configuration, you may have seen some connections cut during the reload.
EDIT 14:30 UTC : We have seen the same instabilities on RBX HDS database load balancer configuration, we have applied the patch that thr RBX database load balancer.
EDIT 2024-03-19T10:00:00Z : After a few days of observation, the currently deployed patched does not handle the issue correctly, we are are working on improving it.
EDIT 2024-03-19T11:30:00Z : We have deployed a new version of the patch that should handle the issue, we are watching the metrics to validate it
EDIT 2024-03-19T18:30:00Z : We have rolled out the patch as it handles the issue correctly. We are still watching metrics. However, we will need a few days to validate the behavior.
EDIT 2024-03-19T16:00:00Z : The patch is validated as we do not see the issue occurring.