Pingdom says we're down and the team is taking a closer look.

Pingdom says we're back online....

Our team is investigating the issiue.

We've fixed the core issue, and are waiting for things to recover.

We've now resolved the incident. Thanks for your patience.

Root Cause The outage was caused by a loss of quorum within our primary cluster management layer. As new instances were being rotated into the cluster, the management nodes experienced a sharp increase in resource utilization. This spike in load prevented the nodes from communicating effectively, leading to the loss of a cluster leader and a subsequent breakdown in task scheduling and service discovery.