Subject: Service disruption on August 24 — cause, impact, and measures taken
Dear Customer,
On August 24, between approximately 6:00 pm and 10:00 pm CEST, our platform experienced a disruption that temporarily affected parts of our services. We would like to inform you about the cause, the impact, and the measures we have taken.
What happened: In our storage infrastructure, a faulty component failed to automatically clean up temporary data that was no longer needed over an extended period. As a result, the available capacity on two storage nodes reached its limit, which caused the limitations described above.
Your data was protected at all times: No customer data was lost. Our backups continued to run as scheduled throughout the entire period; the affected data is backed up on the regular daily cycle, and we have verified these backup runs.
Restoring service: Our team started working on a fix as soon as the first signs appeared and restored the services the same evening. The storage infrastructure now runs with significantly larger capacity reserves than before the incident.
What we are changing: We have fully identified the cause and are implementing several measures: expanded monitoring that reports this kind of gradual development at an early stage, an update to the affected component, and an additional safeguard so that capacity shortages cannot affect other areas.
We regret the disruption and thank you for your understanding.
