Overview
On June 3, 08:45 UTC an incident was declared for the us-3 region. The issue was traced back to the infrastructure provider.
What Happened
Our internal monitoring detected multiple site down alerts for projects on a single grid host in the us-3 region. The data storage service was unresponsive due to a loss in disk connectivity.
Resolution
We immediately reached out to the provider to begin an investigation and restore connectivity. Their internal monitoring also detected the issue and they were already working on restoring service. We shortly thereafter began to see an improvement of the health of our data storage service.
Impact
The incident lasted a total of 23 minutes.