aws-us-east region down

Still recovering data. The region remains fully operational.

All components are working normally. We're catching up with delayed ingestion. We're prioritising stability and expect to be up-to-date in the next ~3hours.

The fix is having the expected impact. Ingestion is back up, and so are most other components. We're still very much on top of this.

We've now applied the change that we hope will get us out of this incident. We'll monitor that it's having the intended effect and start recovering components.

We're still working on this. Ingestion is still down as we continue to stabilise the rest of the platform.

We're still working on this. Our first priority is to recover ingestion.

We're having downtime in ingestion as we try to stabilise the situation.

Ingestion is the component suffering the most. We're working on stabilising the situation. We've added more capacity to the component in charge of data replication so it doesn't become a bottleneck again.

Performance is degraded as we're bringing the region back online.

The component in charge of orchestrating data replication suffered as the region came back online. We've stabilised the situation again and continue to monitor the region closely.

We're seeing delays in some ingestion paths. We think it's caused by the increased load after the region going back online.

We continue to monitor the situation closely. As the region goes back online, we might return some transitive errors.

We've applied the fix and are monitoring the situation.

The component we use for rate limits and shared region metadata started getting an increased number of connections. That's what triggered the incident in the first place. We've been manually keeping the load down, and will soon deploy a fix to prevent this from happening again.

We're managing to stabilise the situation while we continue to fully diagnose the problem

We have a suspect of what's causing the issues, investigations continue.

We're investigating a problem in the region.