No components marked as affected
Resolved
A small number instances in our backend were getting into an unhealthy state. This caused a small percentage of requests to fail. These instances were identified and terminated.
All systems are now functioning normally.
Monitoring
We are continuing to monitor the situation. Service has returned to normal levels.
Monitoring
Elevated error rates have come down. We are continuing to monitor and investigate root cause
Investigating
We are continuing to investigate this issue.
Investigating
We are investigating slightly elevated error rates on our api