The incident is now resolved and all services are returned to their normal state. We will share a full post-mortem within 24 hours.
Posted 14 days ago. May 08, 2019 - 12:13 UTC
Our fix has propagated out to our API cluster and latencies should be returning to normal over the next few minutes.
Posted 14 days ago. May 08, 2019 - 12:08 UTC
We've identified the root cause of the issue, which is causing some requests to be rejected from our API. Further, we've implemented a fix, and we expect resolution to happen within 10 minutes once the fix propagates out into our API cluster.
Posted 14 days ago. May 08, 2019 - 12:04 UTC
We've been alerted to an increase in latency being seen via our API, we're currently investigating the causes. We will update this as soon as we know more.