Incident Summary
On July 30, 2016 around 0522AM ET, QTS OSC started receiving isolated reports from customers concerning internet connectivity issues at our Sacramento, CA Data Center. QTS OSC Engineers started troubleshooting with our upstream provider. At around 946AM ET, additional customers started to call QTS OSC concerning internet connectivity issues. At approximately 1013AM ET, QTS OSC Engineers determined that there was an upstream provider issue. QTS OSC escalated this issue to QTS Network Engineering team and by 1130AM ET they performed a manual fail over to QTS redundant upstream provider to restore services to all the impacted customers.
Root Cause
QTS upstream provider was performing maintenance and made an unannounced change to their routing configuration.
Resolution
QTS Network Engineers rerouted all traffic to QTS redundant upstream provider. The Upstream provider rolled back their change, which restored services for their customers.
Future Measures
Upstream provider maintenance notifications were being sent to an incorrect distribution list. QTS is working with the upstream provider to ensure that they update QTS on all of their scheduled maintenances that could potentially impact QTS.
QTS is performing additional training from lessons learned to QTS engineers to decrease mean time to resolution