Luna Node Status

Information about upcoming maintenance, current downtime, and RFO for past downtime will be posted here. Updates more than six months old may be purged.

Please contact for technical support inquiries.

Planned maintenance / current issues

There are no planned maintenance or ongoing issues at this time.

Resolved issues

Montreal hypervisor downtime (05 July 2019 04:01 EDT)

Update 7 (06 July 2019 10:46 EDT): Remaining failed disk has now been replaced and RAID10 is rebuilt. VMs were offline on 05 July 2019 from 04:01 EDT to 13:20 EDT. Customers have been compensated 55% of the monthly cost for affected virtual machines, check "Account Credit for Montreal Hypervisor Downtime" e-mail for details. Volume-backed VMs (where volume is root partition) were not affected as they were evacuated to other hypervisors shortly after the hardware failure.

Update 6 (05 July 2019 13:30 EDT): Power Supply failure led to multiple component (motherboard, cpu, ram) failure. Faulty components replaced and server is currently back online. A hdd for OS partition (not relevant to customer disk images) remains faulty and requires replacement. We will schedule for this later.

Update 5 (05 July 2019 12:50 EDT): The issue is still being investigated. Next expected updated from datacenter staff is 13:30 EDT

Update 4 (05 July 2019 10:30 EDT): Datacenter still investigating the issue, we continue to wait for updates. Technician advises that they are missing some replacement hardware components and they are looking for it.

Update 3 (05 July 2019 07:00 EDT): still waiting for resolution to hardware issue, latest update from datacenter technician is that they fixed a component and are verifying that other components were not damaged.

Update 2 (05 July 2019 04:40 EDT): ETA 40 minutes until they are able to investigate. Appears to be hardware issue.

Update 1 (05 July 2019 04:27 EDT): we contacted the upstream provider (OVH) and they are investigating now.

We are investigating fault in one Montreal SSD hypervisor. VMs on this hypervisor are offline.

Toronto network downtime (23 April 2019 03:00 EDT)

Update 11 (23 April 2019 06:15 EDT): Circuits are now back online. A combination of hardware failure and software misconfiguration on upstream provider resulted in extended down time for Toronto region. We will continue to monitor the situation and follow up as needed.

Update 10 (23 April 2019 06:00 EDT): Upstream technician still working on the issue.

Update 9 (23 April 2019 05:45 EDT): Upstream technician still working on the issue.

Update 8 (23 April 2019 05:30 EDT): Upstream technician still working on the issue.

Update 7 (23 April 2019 05:15 EDT): Upstream technician still working on the issue.

Update 6 (23 April 2019 05:00 EDT): Upstream technician still working on the issue.

Update 5 (23 April 2019 04:45 EDT): Upstream technician still working on the issue

Update 4 (23 April 2019 04:30 EDT): Upstream technician still onsite investigating

Update 3 (23 April 2019 04:15 EDT): Upstream situation unchanged, we are heading to datacenter to monitor the situation and to be physically present if anything is needed from our end

Update 2 (23 April 2019 04:00 EDT): Upstream provider still investigating the issue

Update 1 (23 April 2019 03:45 EDT): Contacted upstream provider and it appears they ran into complication and tech has been dispatched to investigate the issue

Our upstream provider is performing a scheduled upgrade to the core router and network is affected. We will update once we have more information

Toronto network downtime (20 April 2019 20:30 EDT)

Update 1 (20 April 2019 23:00 EDT): the affected VMs should be online at this time. VMs on virtual networks that were utilizing the failed router node were down for an extended period. In addition to the router node failure, the OpenStack controller node went offline, which prevented quick fallback to another router node. While the failed router node came back online quickly, we were not able to bring the controller server up for some time, which led to this extended downtime.

We are working to resolve network outage after a router node failed in Toronto.

Roubaix network downtime (18 March 2019 17:20 EDT)

We are investigating packet loss affecting SSD virtual machines in Roubaix.

Toronto network downtime (16 February 2019 13:30 EST)

Several VMs had loss of network connectivity due to loose cable while installing new equipment. Connectivity was restored at 13:55 ET.

Toronto network downtime (23 January 2019 15:18 EST)

Some VMs had loss of network connectivity due to hardware failure on one of three network nodes. After migrating the affected virtual networks to the two other nodes, services were back online at 15:23 EST.

Roubaix network downtime (16 January 2019 22:14 EST)

Update 1 (23:55 EST): Roubaix network was down from 22:10 EST to 22:37 EST due to a datacenter-wide outage incident (see details here).

We are currently investigating network downtime in Roubaix.