All services operational as of 11:06 UTC.

We have just finished spinning up a new database instance from backup and pointing traffic to it. We are seeing recovery for users, and are actively keeping a close eye on metrics.

We have escalated this issue to AWS, and also are working on restoring a copy of the database in parallel.

We are currently in the process of figuring out the best mitigation plan that will minimize risk and downtime once it is complete.

We are investigating and believe we have diagnosed the problem: we are having an active incident with our database and are actively working on mitigating.

CPU functions, GPU functions, Snapshot restores (beta), and 2 other resources went down.