For several hours in the evening of Nov 18, three of our servers experienced high load, degraded performance, and intermittent issues with web requests. We investigated the issues internally for several hours and escalated to several of our software vendors for assistance in locating the root cause. The problem was caused by a network health metric we were previously not monitoring. At this time, all servers are working normally and the outage is resolved.
Event start time: 7:28pm ET | Nov 18
Resolved time: 1:11am ET | Nov 19
Impacted servers: P1, S1, S4
Additional details may be available at a later time. The staff who have more technical details are currently getting some much needed sleep.
We apologize for any inconvenience the outage may have caused and appreciate the patience and reports so many of you shared with us. As always, please feel free to ask any general questions here. If your question is specific to your account, please direct it to our support department by email or ticket.