Incident affecting multiple servers in US-EAST-6

DigitalOcean have marked their upstream incident as resolved. We're not seeing any issues any more across Servd so are satisfied the issue fixed.

DigitalOcean are still pursuing the root cause of the issue, and we've seen the impact to the US-EAST-6 cluster resurge again this morning. We're able to temporarily recover from when it occurs by triggering the impacted servers to restart.

We're seeing connectivity to impacted nodes improving, but waiting on DigitalOcean to give the all clear.

DigitalOcean are zeroing in on the root cause, we'll keep you updated once we receive an update.

Sincerest apologies to effected customers, DigitalOcean are continuing to dig into the root cause. We're working closely with them to gather relevant logs and information so that they're able to reproduce the issue and zone in on what's going on.

DigitalOcean are continuing to investigate the issue. Our team is looking to mitigate the issue for projects where we can.

DigitalOcean has posted a related incident on their status page about an issue impacting their Kubernetes infrastructure https://status.digitalocean.com/incidents/fsfsv9fj43w7

We're investigating multiple nodes in our US-EAST-6 cluster going into an unresponsive state. The underlying host for the cluster, DigitalOcean, is digging in further into the root cause.