For a period of 12 minutes, between 18:19 PM GMT and 18:31 PM GMT, we experienced unusually high load to a gateway with poor performance characteristics. This saturated our available capacity before we could (manually) open the circuit breaker for that gateway.
This is similar to previous intermittent incidents, for which we have already added capacity. In addition, an automated and more permanent fix is currently under development and is expected to be deployed by next week.
Posted about 2 years ago. Jun 22, 2017 - 15:02 EDT