Increased latency for a limited set of tenants

Incident Report for Magicline

Resolved

One of our database clusters saw an increased CPU load between 5:15 pm and 6:25 pm. This lead to an increased latency for most services in a limited set of tenants.

We identified a root cause and plan to release an update tomorrow to make our systems more resilient. In the meantime we added more computing power to handle the increased load. All systems are running as expected since 6:25 pm.

Posted Jan 31, 2023 - 17:14 CET