You are here

WestGrid System Status

  • System fully operational
  • Downtime has been scheduled
  • Available with some conditions
  • Online but maybe unstable
  • System presently unavailable
  • Obsolescent
  • System to be defunded

Visit this page to get up-to-date information on the WestGrid systems you are using. Both planned maintenance and unexpected outages will be reported. View the update notes and legend below for more information. If you have any questions about any of these systems or their status, please contact WestGrid Support.

Follow @WGSystems on Twitter to automatically receive system notifications and status updates for WestGrid's computing and data storage facilities.

Post date System Update Notes
2017-02-22 - 14:46 PST Bugaboo

Bugaboo downtime Feb. 27

On Feb. 27 at high-voltage relay will be installed in the data centre that houses the Bugaboo facility. The Bugaboo system will be shutdown at 5am (Pacific) and the power outage will last all day. This work had been scheduled for January but had to be postponed because an incorrect part was delivered. This is the last part of upgrades to the data centre in preparation of the new Cedar facility.

2017-02-18 - 22:27 PST Lattice

Service Restored

Lattice and Parallel are functioning normally once again.

2017-02-18 - 22:27 PST Parallel

Service Restored

Lattice and Parallel are functioning normally once again.

2017-02-07 - 16:36 PST Orcinus

Lustre Filesystem Issue

The problem has been resolved.

2017-02-07 - 10:59 PST Grex

Lustre file system is working again.

Lustre file system on Grex is working again. Some of the running jobs might have expired while FS was not available.

2017-02-02 - 15:56 PST Hermes/Nestor

Scheduled Logical Network Changes Hermes/Nestor/West Cloud

Scheduled work has been completed.

-----------

On Thursday Feb 2 between 13:00-16:00 PT there will be some logical network changes which may cause brief periods of packet loss during this maintenance window. We have tested the changes and users likely will not notice any issues during this window. 

2017-02-02 - 15:56 PST CC-Cloud

Scheduled Logical Network Changes Hermes/Nestor/West Cloud

Scheduled work has been completed.

-----------

On Thursday Feb 2 between 13:00-16:00 PT there will be some logical network changes which may cause brief periods of packet loss during this maintenance window. We have tested the changes and users likely will not notice any issues during this window. 

2017-01-31 - 16:30 PST Network

UVic network issues.

Update:

The issue is resolved.

Original Notice:

Getting to other clusters such as jasper, orcinus and grex from within UVic is not working. Please  log into hermes/nestor and then from there to other clusters until the issue is resolved.

2017-01-24 - 09:38 PST Silo

System fully operational

Greetings,

Silo controller has been restored to full service. Appears to have been a firmware bug that should not recur with any frequency, but I've asked DDN for further analysis.  The expectation seems to be that it is unlikely that the problem will recur before Silo is retired.

Cheers,

Rob Wagner

2016-12-08 - 09:02 PST Hungabee

Hungabee back in production with upgraded OS: SLES 11 SP4.

Hungabee back in production with upgraded OS: SLES 11 SP4

Hungabee OS was upgraded to SlESS 11 SP4 for security and other reasons. This may have updated the libraries, your code relies on such as MPT. If this is the case your code may require a recompile to use new versions of libraries installed. Please also note the some software was updated an some module names and versions have changed.

2016-11-24 - 15:40 PST Jasper

MIGRATION UPDATE FOR JASPER:


Due to generous support from the University of Alberta, the defunding date for Jasper has been rescheduled to March 31, 2017 (instead of January 01, 2017 as announced earlier). Researchers affiliated with the University of Alberta should contact support@westgrid.ca for more information about accessing this system after March 31, 2017. Please visit the Compute Canada Documentation Wiki's Jasper Hungabee Migration 2016 page for more information.

2016-11-08 - 08:30 PST WestGrid portal

HA server has crashed but has been restarte

The HA server which runs the portal had crashed. It has been restarted.

2016-10-27 - 22:29 PDT Breezy

Breezy back to normal operations after system upgrade.

Breezy has been upgraded to the latest CentOS 6.8 operating system.
Should you discover any issues, please report them to support@hpc.ucalgary.ca. Thank you.

2016-05-01 - 21:01 PDT ownCloud

System fully operational

Finished on May 2, 2016 - 4:00 GMT