Service Announcement

All VMs that were paused as part of the outage have been resumed. We are conducting final checks and plan to mark the outage as completed within the hour.
Update posted 2 weeks, 2 days ago.

We have begun resuming existing virtual machines. This process will take at least an hour.
Update posted 2 weeks, 2 days ago.

Overnight we fixed a remaining issue with the network and our OpenStack control plane is now stable and able to host virtual machines. We are working with Nectar core services to remediate some database issues encountered in the core after which we should be able to resume existing virtual machines.
Update posted 2 weeks, 2 days ago.

There are still issues associated with services that provide resources to the backplane fabric of the Swinburne Nectar Node. Further update will be provided very early tomorrow morning.
Update posted 2 weeks, 3 days ago.

We will have re-connected Swinburne-01 to Nectar core services. Initial benchmarks show performance is acceptable. We are now running health checks to ensure the service is stable. It is likely we can begin resuming VMs today. Further update expected at 1800 AEDT.
Update posted 2 weeks, 3 days ago.

Our underlying storage is back online, and we have performed basic health checks of the OpenStack infrastructure. We will now attempt to re-connect Swinburne-01 to Nectar. If, after running further checks and benchmarks, the cloud appears stable and performant we will begin resuming VMs. Next update expected approx 16:30 AEDT.
Update posted 2 weeks, 3 days ago.

The Network Configuration has been restored to its previous state. We have begun the work to resume the underlying storage services and will test those prior to enabling the OpenStack components. This will take approximately 2 hours. Expect next update at 15:30 AEDT
Update posted 2 weeks, 3 days ago.

A distribution switch in our primary datacentre had a hardware failure during the network change, causing widespread problems. We have redundant switching and a backup datacentre that would allow us to continue with the network change. However, the risks due to the increased chance of failure and performance impacts were deemed too high. Therefore, the network team will be restoring the original network configuration. This work is expected to take at least 4 hours, after which we will begin to restore services. Next update expected approximately 1500 AEDT.
Update posted 2 weeks, 3 days ago.

Our network team has encountered technical issues that may delay our access to Nectar Cloud infrastructure. These unexpected issues had an impact to university services beyond the anticipated scope of the planned change. We will know more by approximately 0900 AEDT tomorrow and will update at that time.
Update posted 2 weeks, 4 days ago.

Our network team continues to work into the night to remediate the network. We expect to regain access to our infrastructure around 0900 AEDT tomorrow and will work to restore services if the environment is stable. We expect to be able to provide a further update around 1200 AEDT tomorrow.
Update posted 2 weeks, 4 days ago.

the Swinburne Nectar Node is no longer available - the network change is about to begin
Update posted 2 weeks, 4 days ago.

Scheduled outage started.
Update posted 2 weeks, 4 days ago.