a.t.m.o is returning 503: Service Unavailable: Back-end server is at capacity.
The analysis service was not running on the ec2 instance that powers a.t.m.o - this is the default load balancer error when it doesn't have any healthy instances. I started the service back up and it came back to life. I don't know yet what the root cause of the failure was - the same thing happened on Friday around 10am PDT too, so we should determine the cause (and solution) before closing this bug out).
The machine had an OOM problem due to running some manual backfill jobs. This is not likely to recur.
Status: NEW → RESOLVED
Last Resolved: 3 years ago
Resolution: --- → FIXED
You need to log in before you can comment on or make changes to this bug.