The API latencies have returned to their usual from 1313 UTC, after switching failing over to our secondary BigTable cluster.

We have put a fix in place and response times for all API requests have returned to normal. We are still monitoring the situation.

We are seeing a slight increase in response times from our API, affecting 2% of traffic. This increased response time is coming from increased latency of our BigTable cluster which we continue to investigate.

We are seeing a slight increase in response times from our API. This is affecting a very small number of requests. We are investigating the cause. More updates to follow

We've spotted that something has gone wrong. We're currently investigating the issue, and will provide an update soon.