Increased response times and errors for sign API V2
We currently see more errors and a higher response time than usual and are investigating the problem.
System configuration of our crypto servers was changed in order to handle higher load (1k tps+). The crypto servers had to be restarted. Our Dashboards already show the system going back to normal operational mode, we'll keep monitoring and resolve after full confirmation.
On some TSS we see further problems. The team is analyzing.
Some SMAERS processes will need to be restarted, we're now gathering the IDs and performing controlled and monitored restarts.
The status of the incident is updated to "partial outage", as the situation has not yet improved sustainably. The team is working on a solution.
We have waited for a period with peak load for stress testing of the applied stability improvements. According to our monitoring, the response times and error rates have stabilized. Consequently, we consider this incident resolved.