Between ~15:16 UTC and 20:55 UTC on March 24, 2025, customers may have experienced errors and timeouts when accessing Object Storage resources or an inability to create buckets in the London data center.. This issue stemmed from a memory usage spike on our infrastructure platform,  which led to continued degradation until we safely updated memory allocation across leader nodes. This resolved the problem. We have since identified the source of this memory spike and are formulating a long-term mitigation strategy.. In the meantime, we increased memory resources globally to reduce the risk of impact on other clusters.

‌

This summary provides an overview of our current understanding of the incident given the information available. Our investigation is ongoing and any information herein is subject to change.