Resolved -
This incident has been resolved.
Jul 22, 16:58 UTC
Update -
We are continuing to monitor for any further issues.
Jul 22, 16:52 UTC
Monitoring -
After a period of slow object storage reads, our load balancers were overly aggressive in removing machines from rotation in us-central1. We've updated our health check configs to be more tolerant to object storage latency variability and are actively monitoring.
Jul 22, 16:40 UTC
Investigating -
We are currently investigating this issue.
Jul 22, 16:32 UTC