Deprecated: The each() function is deprecated. This message will be suppressed on further calls in /home/zhenxiangba/zhenxiangba.com/public_html/phproxy-improved-master/index.php on line 456
Nebius Status
[go: Go Back, main page]

Nebius Service Health Status
Major outage
Partial outage
No downtime recorded on this day.
No data exists for this day.
had a major outage.
had a partial outage.

Scheduled Maintenance

Scheduled firmware upgrade in uk-south1 affecting B300-based instances Jun 22, 2026 08:00 - Jun 25, 2026 08:00 UTC

Update - This is a follow-up to our earlier notice of planned maintenance in uk-south1 affecting GPU workloads. The maintenance has been rescheduled to a new date.

Start: Monday, June 22 at 08:00 UTC
Duration: up to 72 hours
Region: uk-south1
IB fabric: uk-south1-a

We apologize for any inconvenience this change may cause and appreciate your understanding and patience.

We will notify you as soon as the maintenance is complete and your GPU workloads are ready to resume. Thank you for your patience, and please reach out if you have any questions.

Jun 09, 2026 - 18:11 UTC
Scheduled - Nebius will be performing scheduled firmware upgrade during the above window.

Region: uk-south1
IB fabric: uk-south1-a

- B300-based workloads: will be automatically stopped by Nebius as part of this maintenance. No action is required from your side.
- All other workloads: no interruption is expected. If you encounter any issues during this period, please open a support request.

This maintenance is aiming to upgrade the GPU & InfiniBand firmware and roll out a new DOCA version across all nodes, improving GPU node stability and the quality of the InfiniBand interconnect.

There is no action required from your side, however we recommend checkpointing or pausing your GPU jobs before the start time to avoid any progress loss.

We understand the importance of predictability and apologize for any inconvenience this may cause. Our Support team is available 24/7 to assist with any questions or workload planning.

If you have any questions or need assistance, please open a support request. We will continue to provide updates on the maintenance status through this page.

Jun 05, 2026 - 09:55 UTC
Jun 12, 2026

No incidents reported today.

Jun 11, 2026

No incidents reported.

Jun 10, 2026
Resolved - This incident has been resolved.
Jun 10, 23:28 UTC
Investigating - We're currently investigating an issue affecting Compute instances startup. Some requests to create or start instances may fail. Already-running instances are not affected.
Our engineering team is actively investigating.

Jun 10, 20:56 UTC
Jun 9, 2026
Resolved - Some of public IPs became unreachable.
Jun 9, 10:30 UTC
Jun 8, 2026

No incidents reported.

Jun 7, 2026

No incidents reported.

Jun 6, 2026

No incidents reported.

Jun 5, 2026

No incidents reported.

Jun 4, 2026
Resolved - This incident has been resolved.
Jun 4, 11:14 UTC
Monitoring - The issue has been resolved, and affected services have recovered.
The situation continues to be monitored to ensure service stability.

Jun 4, 10:29 UTC
Investigating - An issue with Internet connectivity in the data center has been detected.

Impact:
- Logs and metrics from virtual machines are not being delivered.
- Object Storage is currently unavailable from internet.
- Container registry is currently unavailable from internet.
- Additional services relying on external connectivity may be affected.

The issue is under investigation.

Jun 4, 09:46 UTC
Jun 3, 2026
Resolved - This incident has been resolved.
Jun 3, 11:06 UTC
Monitoring - Public IPv4 address capacity has been restored in eu-north1, and new public IPv4 addresses can be allocated to workloads again. We are monitoring the service to confirm full recovery before resolving this incident.
Jun 2, 12:36 UTC
Identified - We have identified the cause: the pool of available public IPv4 addresses in eu-north1 is currently exhausted, which is why new public IPv4 addresses cannot be allocated to workloads.

We are reclaiming and reallocating addresses to restore allocation capacity. Workloads that already have a public IPv4 address assigned remain unaffected. We will provide a further update once new allocations are succeeding.

Jun 2, 11:52 UTC
Investigating - We are investigating an issue in eu-north1 affecting Virtual Private Cloud (Networking). New public IPv4 addresses cannot currently be allocated to workloads. Customers may be unable to assign a public IP when creating or modifying resources — for example, attaching a public IP to a virtual machine or load balancer in this region.

Resources that already have a public IPv4 address assigned are not affected and continue to operate normally. We will provide an update as we learn more.

Jun 2, 10:53 UTC
Jun 2, 2026
Jun 1, 2026

No incidents reported.

May 31, 2026

No incidents reported.

May 30, 2026

No incidents reported.

May 29, 2026
Resolved - Several servers were rebooted.
May 29, 21:22 UTC