Who is down right now

Nebius · AIMar 10, 2026, 15:47 UTC 7 months ago

Power issues during planned maintenance

MajorNot disclosedUpdated 2h ago
Mar 10, 15:47 UTCMar 11, 00:49 UTC
Duration
9h 2m
Impact
Major
Root cause
Not disclosed
Nebius, 90 days
22 incidents
Affected
Compute CloudObject StorageVirtual Private Cloud (Networking)Managed Service for Kubernetes®MonitoringToken FactoryManaged Service for MLflowManaged Service for PostgreSQL®Standalone ApplicationsUS-CENTRAL1 - Compute CloudUS-CENTRAL1 - Object StorageUS-CENTRAL1 - Virtual Private Cloud (Networking)US-CENTRAL1 - Managed Service for Kubernetes®US-CENTRAL1 - Monitoring
Status page

Final update

This incident has been resolved and all services and clusters should be operational now.

Timeline

  1. Resolved · Mar 11, 00:49 UTC
    This incident has been resolved and all services and clusters should be operational now.
  2. Monitoring · Mar 10, 23:37 UTC
    Maintenance has been completed, and we do not expect any further power-related issues. We are now recovering services and closely monitoring system status.
  3. Investigating · Mar 10, 22:00 UTC
    We are continuing to investigate this issue.
  4. Investigating · Mar 10, 21:40 UTC
    We are continuing to investigate this issue.
  5. Investigating · Mar 10, 20:39 UTC
    We are currently experiencing another service disruption due to ongoing on-site maintenance. Our engineers are actively working to stabilize the affected clusters and maintain service throughout the maintenance period.
  6. Monitoring · Mar 10, 18:14 UTC
    We have identified failed switches and nodes. All major services were recovered, we are now collecting faulty instances and recovering them.
  7. Identified · Mar 10, 18:12 UTC
    We are continuing to work on a fix for this issue.
  8. Identified · Mar 10, 15:59 UTC
    We are continuing to work on a fix for this issue.
  9. Identified · Mar 10, 15:54 UTC
    We are continuing to work on a fix for this issue.
  10. Identified · Mar 10, 15:47 UTC
    During planned maintenance we experienced unexpected issues with power supply. We have identified the faulty circuits and already bringing nodes that are not part of planned maintenance back to work.

More from Nebius

Full history
MinorOct 8, 08:48 UTC
Metrics unavailable in Management Console for Monitoring in eu-west1lasted 11m
MajorOct 7, 16:37 UTC
Problems with power for several dozens of nodeslasted 14h 45m
MinorOct 4, 15:54 UTC
Issues with preempted Managed Kubernetes nodes in all regionslasted 24h
MinorOct 3, 02:30 UTC
InfiniBand connectivity issues for GPU clusters in eu-west2lasted 6h 28m
MajorOct 2, 01:58 UTC
Compute VM creation and Object storage are partial unavailablelasted 9m
MajorSep 23, 05:20 UTC
Network issues in eu-west2lasted 3h 12m