Cluster Status

From ACENET
Jump to: navigation, search
Ambox notice.png This page is maintained manually. It gets updated as soon as we learn new information.

Clusters

Please click on the name of the cluster below in the table to quickly get to the corresponding section of this page. The outage schedule section is a single place where data about all scheduled outages are represented.

Cluster Status Planned Outage Notes
Placentia Online Partial Dec 17-21
Glooscap Online Partial Nov 26-Jan 3
Arbutus See status.computecanada.ca (west.cloud.computecanada.ca)
Cedar See status.computecanada.ca
Graham See status.computecanada.ca
Niagara See status.computecanada.ca

Services

Service Status Planned Outage Notes
WebMO Online No outages
Account creation Manual No outages Write support
PGI and Intel licenses Online No outages
Legend:
Online cluster is up and running
Offline all users cannot login or submit jobs, or service is not working
Online some users can login and/or there are problems affecting your work

Outage schedule

Grid Engine will not schedule any job with a run time (h_rt) that extends into the beginning of a planned outage period. This is so the job will not be terminated prematurely when the system goes down.

  • Glooscap capacity will be temporarily reduced by 1120 cores beginning the morning of Monday November 26, in order to facilitate maintenance on the cooling systems in the Killam Data Centre. The head node and storage will remain accessible, as will about 30% of the compute capacity. Originally scheduled to be complete by Dec 15, the work has been extended to Dec 21 which does not leave us time to restore service before the Christmas break. Return to service is now expected on 2019 January 3.
  • Placentia capacity will be temporarily reduced by 300 cores beginning the morning of Monday December 17 to facilitate maintenance on the cooling systems in the data centre. The work is expected to be complete by the end of the week. The head node and storage will remain accessible. The reduction in compute capacity will be small but will include the large-memory "gaussian.q" nodes.


Placentia

  • Over the past days we have been large numbers of jobs failing immediately with Eqw errors. This was caused by one of the switches in our data-network. The problem has now been resolved.
11:30, November 22, 2018 (AST)
  • The WebMO web-service has been migrated to a different physical machine on the afternoon of Thursday November 15 2018. Further reboots were necessary on the morning of Friday Nov. 16. Running jobs have not been effected.
08:59, November 16, 2018 (AST)
  • A power fluctuation on the morning of Wednesday November 14 2018 around 6:30am in the Placentia data centre, has caused about 20 compute nodes to crash, which had to be rebooted. This would have effected a small number of jobs.
9:25, November 15, 2018 (ADT)

Glooscap

  • Glooscap is back in service after a planned interruption this weekend (Sep 7-10). The metadata server component of the file system has been relocated and a full fschk has been run. We hope this will alleviate file system load problems.
10:54, September 10, 2018 (ADT)
  • Glooscap is back in service again. We believe we may have identified a source of unusual load that was causing the trouble. Please check on the status of any jobs you have in the system to ensure they are running properly.
16:25, August 23, 2018 (ADT)
  • Glooscap is not accepting logins again. The sysadmin is investigating the cause.
10:48, August 23, 2018 (ADT)

Fundy

  • Fundy has been retired from service.
10:01, April 5, 2018 (ADT)

Mahone

  • Mahone has been retired from service.
10:00, April 5, 2018 (ADT)
User Support
Resources