DigitalOcean incident: Power Degradation impacting GPU Performance in ATL1

Affected components

• ATL1

1. resolvedSep 9, 2026, 12:25 UTC

   This incident is now resolved. Power redundancy has been fully restored, and we have confirmed that customer impact has been mitigated. We are closing this incident.

2. monitoringSep 9, 2026, 11:32 UTC

   The power issue affecting part of our ATL1 datacenter has been fully resolved. Power redundancy has been restored, and any potential customer impact has been mitigated. We will continue monitoring the environment to ensure continued stability.

3. investigatingSep 9, 2026, 10:47 UTC

   We are investigating a power issue affecting part of our ATL1 datacenter. Redundant power systems are keeping servers online, and we have not observed any server outages. However, available power capacity is reduced, which may cause degraded performance for some GPU workloads, particularly during periods of high utilization. Our datacenter and infrastructure teams are working to restore full power redundancy. We will provide an update as more information becomes available. We apologize for the inconvenience and appreciate your patience.

What APIStatus.watch saw

• Sep 9, 2026, 10:50 UTCoperational → degraded
• Sep 9, 2026, 11:35 UTCdegraded → operational

Other services with incidents at the same time

Overlapping incidents aren't necessarily related.

• Elasticsearch: Replication bug causing slow recoveriesMajor · Sep 1, 2026, 08:16 UTC
• MongoDB Atlas: Impaired Cluster operations in AWS me-central-1 and AWS me-south-1Major · Sep 3, 2026, 16:44 UTC
• Miro: Sign-in with username and password is unavailableMajor · Sep 8, 2026, 19:21 UTC
• Confluent Cloud: Connectivity degradation - AWS us-east-1Major · Sep 8, 2026, 20:01 UTC
• OVHcloud: [EU-SOUTH-MIL][Containers & Orchestration] - Managed Private Registry incident notificationMinor · Aug 26, 2026, 15:00 UTC
• Snowflake: INC20000150Minor · Aug 28, 2026, 00:07 UTC
• Telnyx: Intermittent delays for some outbound messagesMinor · Sep 2, 2026, 21:33 UTC
• Confluent Cloud: Service Disruption affecting Authentication, Schema Registry, ksqlDB, and Flink in AWS us-east-1Minor · Sep 8, 2026, 09:17 UTC
• Grafana Cloud: Investigating elevated database load in AWS GermanyMinor · Sep 9, 2026, 11:27 UTC

How often does DigitalOcean have incidents?

DigitalOcean reported 20 incidents in the last 90 days, 3 of them major or critical. A typical incident lasted 5h 35m. See DigitalOcean's uptime and incident history