Increase in the level of replication on our CEPH cluster

Updates

Resolved
December 11, 2023 at 9:41 PM
Resolved
December 11, 2023 at 9:41 PM
Good evening,

The operation at our CEPH cluster is complete. We confirm that all virtual machines are completely operational again. Storage performance is back to normal.

If you are still having problems accessing your VPS, we recommend restarting your VPS. In case you are still having problems, do not hesitate to open a ticket so that the situation can be resolved as quickly as possible.

We are truly sorry for the inconvenience caused by this operation.

We thank you for your confidence.

Best regards,
The Sapinet technical team
Identified
December 11, 2023 at 8:09 PM
Identified
December 11, 2023 at 8:09 PM
Good evening,

We have an update regarding the status of the cluster. From what we observe, VPS are still accessible but access is very complicated due to object reconstruction. The object reconstruction operation gives us an ETA of around 1 to 2 hours. We believe that the situation should stabilize once the operation is 70-75% complete. We will add a service status update within 30 minutes.

We thank you for your understanding.

Best regards,
The Sapinet technical team
Investigating
December 11, 2023 at 7:44 PM
Investigating
December 11, 2023 at 7:44 PM
Good evening,

In order to increase the resilience of our CEPH storage following the migration to the new cluster on Friday evening, we have launched the increase in the number of replicas on our cluster. This operation should normally be without impact.

We note that the VPS infrastructure is currently in a degraded state, you may experience difficulty accessing your VPS. We are currently investigating to stabilize the situation as much as possible.

We will keep you informed of developments in this status post.

We thank you for your confidence.

Best regards,
The Sapinet technical team

Sapinet - Increase in the level of replication on our CEPH cluster – Incident details

All systems operational