We've identified a few likely sources of the outage and corrected them. We will continue to monitor for problems.
Posted May 16, 2018 - 12:55 PDT
Update
We are continuing to investigate this issue.
Posted May 16, 2018 - 12:13 PDT
Update
Execution worker services appear to have crashed at the VM-level at 11:40am or so. We've brought up new instances but are still investigating root cause.