Main Page

From SciNet Users Documentation
Revision as of 14:34, 3 June 2024 by Rzon (talk | contribs)
Jump to navigation Jump to search

System Status

Niagara Mist Teach Rouge
Jupyter Hub Scheduler File system Burst Buffer
HPSS Login Nodes External Network Globus
Balam CCEnv

Monday, Jun 3, 10:50 AM EDT The file system issues affect all nodes, so all systems are inaccessible to users at the moment. No time estimate yet for when the systems may be back.

Monday, Jun 3, 7:58 AM EDT Login issues for Niagara and Mist. There are file system issues as well. Investigating.

Sunday, Jun 2, 12:00 PM EDT CCEnv modules missing, investigating.

Wednesday May 29, 5:50 PM EDT Niagara compute nodes are up.

Wednesday May 29, 4:40 PM EDT Niagara compute nodes are coming up.

Wednesday May 29, 4 PM EDT Niagara login nodes and jupyterhub are up; file system is now accessible.

Wednesday May 29, 2 PM EDT Electricians are checking and testing all junction boxes and connectors under the raised floor for safety. Some systems are expected to be back up later today (storage, login nodes), and compute systems will be powered up as soon as it is deemed safe.

Tuesday May 28, 3 PM EDT Cleaning crews are at the datacentre, to pump the water and install dryers. Once the floors are dry, we need to inspect all electrical boxes to ensure safety. We do not expect to have a fully functional datacentre before Thursday, although we hope to be able to turn on the storage and login nodes sometime tomorrow, if circumstances permit. Apologies, and thank you for your patience.


Tuesday May 28, 7 AM EDT A water mains break outside our datacentre has caused extensive flooding, and all systems have been shut down preventatively.


Friday May 17, 10 PM EDT - Saturday May 18, 2 AM EDT: The external network will be unavailable for maintenance. Running and queued jobs on the systems will not be affected.

Tuesday May 14, 6:45 PM EDT: All systems are recovered now.

Tuesday May 14, 5 PM EDT: Power loss at the datacentre resulted in loss of cooling. Systems are being restored.

Friday May 3, 10 PM EDT - Saturday May 4, 2 AM EDT: The external network will be unavailable for maintenance. Running and queued jobs on the systems will not be affected.

Previous messages

QuickStart Guides

Tutorials, Manuals, etc.