Further investigation determined that a recent change affecting instance provisioning behavior contributed to the issue. Technical teams completed a rollback of the change and validated recovery. Following the rollback, error levels returned to normal and new instance provisioning resumed successfully.
Throughout the incident, existing instances and workloads remained operational. The impact was limited to new instance launches and cluster scale-up operations.
The issue is now considered resolved. A detailed post-mortem report will be shared following completion of the root cause analysis and post-incident review, documenting the full sequence of events, contributing factors, lessons learned, and any follow-up actions identified.
Posted Sep 24, 2026 - 15:16 PDT
Identified
Incident Description: We are investigating an issue affecting Spot Ocean for AWS. Customers may be unable to launch new instances due to instance provisioning failures. As a result, affected clusters may be unable to scale as expected. Existing workloads remain operational. Our technical teams are actively investigating the scope and impact of the issue.
Priority: P2
Restoration Activity: Our technical teams have identified a potential issue related to a recent change affecting instance provisioning and are actively validating the impact. Mitigation activities are underway, including rollback of a recent change while teams monitor recovery and service behavior. Further updates will be provided as more information becomes available.