As of 05:50 CEST, one of the Gandi email servers has stopped responding. We have a team looking at the issue. We will update this posting as soon as we have a new status to report.
Edit: 6:46 AM CET, the problem is resolved. There was a disk issue that made the machine freeze.
To give you a little more time to adapt, we have left the old version of Gandi's website accessible at the following address: http://v3.gandi.net
Of course, all the operations that you could do on the old version will work on the new :)
Also, if you are still a little bit lost, despite our efforts to not totally mess-up the interfaces, you can continue to perform all your operations on the old version of the website. We will keep it in place for 2 to 3 weeks, so that you will have enough time to become used to the new site ;)
Finally, if you find bugs, things that dont quite work well, anomalies, or you would simply like to give us some feedback, please feel free to write to feedback@gandi.net
Not many of you are still using it, and it is no longer really compatible with modern web browsers, so we have decided to stop using the http://mail.gandi.net interface, in favor of the RoundCube interface available at http://webmail.eu.com
If you are still using the old webmail (e.g. http://webmail.example.com), we are going to migrate the DNS configuration of your domain to RoundCube (new domains have been pointing there already since Monday).
There is currently an issue on Paris datacenter affecting some IaaS/Cloudserver & PaaS/SimpleHosting physical machines.
Our technical team is currently analyzing the issue, and is on-site in the datacenter.
More information to come on this article.
EDIT : All hosting operations are currently stopped.
EDIT : It seems that it was located on a network device. The physical nodes and the VMs are coming back up. We monitor the impacted VMs to be sure that they respond in the next minuts.
EDIT : The issue has been solved. The hosting operations are up.
Tuesday June 19th 2012 at 9:30 GMT: our mail platform is currently experiencing a slowdown. Our technical team is on location and performing diagnostics to determine the reason for this incident. Affected services are email reception, Gandi's webmail, as well as the customer support ticket processing platform.
Please accept our apologies for the inconvienence. We will keep you informed of developments below as we learn more about the incident.
update 9:50 GMT: Our teams have fixed the problem, and the service is back to normal again.
Update Wednesday June 20 at 14:15 GMT: another machine has experienced the same problem as yesterday. We rebooted it as preventative measure, however it is currently in a filesystem correction. The service on this machine should return to normal in about 45 minutes.
Wednesday June 20th 2012 15:29 GMT: The unit has returned to normal operating conditions.
We are currently experiencing issues with webmail authentication. Our teams are working to resolve the problem as soon as possible. This issue does not impact reception of your emails, but only accessing them.
We apologise for the inconvenience.
Update 29/02/2012: 13:30 GMT: The issue has been stabilised since the end of the afternoon yesterday. We are nevertheless working on the platform to avoid furture recurrence of this issue.
To correctproblems we have identified inourstorage systems,we need to performcorrective maintenance procedurestonightbetween 23:30 and3:30 CET. This will impact some of your server systems, making certain data volumes unavailable for a period of 15 to20 minutes. Werecommend that you donotrestart yourservers duringthis period. All services should return to normal immediately following the termination of the maintenance window. If you will be affected by thismaintenance,you should have receivedamail from us advising you of the issues and timining. Please see this page for the contents of that message. We will updatethis postto keep you informedof our progress.
Edit 23:30 CET: operation started
Edit 00:32 CET: first reboot done, equipment beeing behaving as expected, we proceed further
Edit 01:00 CET: most reboots are now ongoing, our first upgrades having been successful
Edit 01:30 CET: most of our storage units have been upgraded - if your server recovered from I/O stalls, this issue is fixed for you -- otherwise, this upgrade will be finished in the next hour
Edit 01:34 CEST: a compute node crashed during this operation, we are starting the affected virtual servers on another machine right now.
Edit 02h30: maintenance is finished, thank your for your patience during this operation.
A piece of storage equipment is failing,likely due to defective components.Our teamsarecurrently workingto restorethesituationas soon as possible.Werecommend that you donotrestartyour serverif you areimpacted.Wewill keep you informedof our progress ofthis incidentin this article.
[02:28 CET] Recovery sucessful. Components repaired and storage unit now nominal.