Power outage in one of our (York) racks

Expected resolution: 23 Mar 2017, 11:30 UTC
Return to issues
Issue status: Resolved Date:

23 Mar 2017
11:22 UTC

Posted by:

Jamie Nguyen

We think that one of the breakers was tripped by a faulty PSU in one of the servers. We've now replaced the PSU in that server.

As far as we can tell, all service for the servers in that rack are back online and fully functional from a hardware and networking point of view. However, if your server went offline this morning and still isn't behaving properly, please do get in touch at https://www.bytemark.co.uk/help and we'll be more than happy to help!

Issue status: Investigating Date:

23 Mar 2017
10:48 UTC

Posted by:

Jamie Nguyen

We think that one of the breakers was tripped by a faulty PSU in one of the servers. We've now replaced the PSU in that server.

There are two servers remaining that are having trouble with network connectivity, which is possibly due to faulty network hardware. We're troubleshooting that at the moment and the two affected customers have been informed.

As far as we can tell, only the above two servers are remaining problematic. There may be other issues that we're not aware of. If your server went offline this morning and still isn't behaving properly, please do get in touch at https://www.bytemark.co.uk/help and we'll be more than happy to help!

Issue status: Investigating Date:

23 Mar 2017
09:56 UTC

Posted by:

Jamie Nguyen

Thanks for your patience! Power is restored to the whole of the rack. Most servers should be coming back online now. We're still troubleshooting some remaining issues, possibly due to blown PSUs in the servers themselves.

Issue status: Investigating Date:

23 Mar 2017
09:17 UTC

Posted by:

Steve Kemp

We've got an engineer on site, and half of the rack is now back online.

We're aiming to restore power to the other half of that rack as a matter of some urgency.

Issue status: Investigating Date:

23 Mar 2017
08:31 UTC

Posted by:

Steve Kemp

It looks like we've suffered a power outage in one of our racks, which has taken down approximately 40 hosts.

We've got an engineer en route to the location to diagnose this further, and attempt to resolve as quickly as possible.

Return to issues

Issue still not addressed? Please contact support.