Past Incidents

We are currently seeing elevated error rates on the old Cellar cluster. A few nodes went down making operations longer than usual, leading to timeouts or 500 / 503 errors. Nodes are already getting back up.

EDIT 00:21 UTC: The cluster is getting back to normal, errors have already significantly decreased and most of the requests should now be successful. We keep monitoring failed requests.

EDIT 03:00 UTC: No more failed request over the last 30 minutes, the incident is closed. We are still in the process of migrating this cluster data to the new cluster. Until we automatically migrate your buckets, you can migrate them yourself. Feel free to contact our support for more information

The new Cellar cluster (cellar-c2.services.clever-cloud.com) had a brief interruption between 19:31:30 and 19:33:20 UTC on 23/08/2019 where most of the requests couldn't be handled or were dropped if already started. The problem has been identified and automatic actions have restored access to the cluster. The main issue will be investigated.

Deployments are delayed, we are looking into it.

12:11: An orchestrator was experiencing intermittent network issues. The issue is now fixed.

From 20:30 UTC to 21:30 UTC, 16% of the hypervisors of the Paris zone failed to resolve the monitoring service domain name.

Applications which had instances on these hypervisors have been redeployed automatically because the monitoring could not reach them (even though they were available).