US region: Widespread service disruption due to upstream cloud provider incident

Update timeline

1. investigating Oct 20, 2025, 07:13 AM UTC

   We are investigating reports of sign‑in failures in our US region. The first errors began at approximately 06:48 UTC. EU and CA regions remain healthy. We'll share more as we learn. Next update within 30 minutes.

2. identified Oct 20, 2025, 07:24 AM UTC

   We have identified that the sign‑in failures correlate with a regional incident at our cloud infrastructure provider in their US‑East region. Customers served from our US region may see "incorrect password" messages or slow/failed requests. Our EU and CA regions remain healthy.

3. identified Oct 20, 2025, 08:28 AM UTC

   The issue persists. Our cloud infrastructure provider continues to experience a region-wide incident in their US‑East region. We are actively working with the provider to reduce impact.

4. monitoring Oct 20, 2025, 09:29 AM UTC

   US region services have returned to normal operation as of 09:22 UTC. This incident stemmed from a region‑wide issue at our cloud infrastructure provider and caused intermittent errors and latency across multiple US services. Impact window: 06:48-09:22 UTC (2 hours 34 minutes). No data was lost. EU and CA regions were not affected. Thank you for your patience.

5. resolved Oct 20, 2025, 10:14 AM UTC

   This incident has been resolved.