Updates
Resolved
We've confirmed that the elevated 5xx errors and high response times were isolated to the ap-southeast-1 region. Other regions remained healthy throughout the incident. Dashboards showed a sharp spike in 5xx errors and response times for ap-southeast-1, with metrics rapidly recovering after remediation steps. For more details, see the realtime-service combined dashboard. The incident was the result of a resource constraint. We have added the required resources and will take this into account in our future planning. We're continuing to monitor system health to confirm stability.
Monitoring
We are continuing to monitor for any further issues.
Monitoring
The performance of the impacted components has improved.
Investigating
We're currently investigating increased error rates across all regions