Main Page

From SciNet Users Documentation
Jump to navigation Jump to search

System Status

✓ Trillium ✓ OnDemand ✓ Globus
✓ HPSS ✗ Balam ✗ S4H
✓ Teach ✓ File system ✓ External Network

System status information is updated during regular business hours (Eastern Time). Outside these hours, updates are provided on a best-effort basis. For questions or assistance, please contact support@scinet.utoronto.ca. The support mailbox is monitored during regular business hours, with inquiries received outside these hours addressed as soon as possible.

Mon Nov 09, 2026, 7:00 AM EST: HPSS scheduled maintenance: HPSS will be offline for an OS upgrade to RHEL 9.8 (including security patches), an HPSS update to v11.3_u11 (bug fixes), and the deployment of several new hardware components and servers. Globus alliancecan#hpss collection will be offline as well. The maintenance may extend over several consecutive days. We will make every effort to complete the work and restore service as quickly as possible.

Thu Nov 5, 2026: Balam and Neptune (inc. S4H) nodes are down because of a CDU issue. We are investigating.

Mon Oct 30, 2026: approx. 12:00 to 14:30 EDT Many nodes had issues with the cvmfs software stack, and trouble loading modules.

Mon Oct 5, 2026: 8:20 AM EDT Systems back to normal.

Mon Oct 5, 2026: 6:00 AM EDT Logins to Trillium-CPU, Teach, and OnDemand are experiencing issues; we are investigating. For now, to log into Trillium-CPU, go via trillium-gpu.scinet.utoronto.ca and ssh to tri-login01.

Mon Sept 28, 2026: 10:50 AM EDT Switch Fixed.

Mon Sept 28, 2026: 8:47 AM EDT More issues with the switch. Various services are affected. We are working on replacing the defective switch.

Sun Sept 27, 2026: 8:55 AM EDT More issues with the switch. Various services are affected. We are investigating.

Sat Sept 26, 2026: 11:10 AM EDT Switch fixed; all systems are back online. Some compute jobs may have died; users should resubmit those jobs.

Sat Sept 26, 2026: 12:30 AM EDT A switch-related problem has caused problems for the systems in the SciNet Data Centre. We are investigating.

Trillium AI Expansion Installation Maintenance Shutdown Schedule

  1. May 26/27, 2026: Shutdown of the Trillium compute nodes and HPSS, starting at 4 AM EDT on May 26th. The Trillium login nodes as well as OnDemand, the Teach cluster, and Balam, will remain available during this maintenance. HPSS will be back in service later on the same day (May 26th), while the Trillium compute nodes are expected to be back in service at some time on May 27th.
  2. June 9/10, 2026: A multi-day chiller maintenance; this will involve a shutdown of all systems.
  3. June 22-26, 2026: A 4-day full datacentre shutdown. The SciNet datacentre will undergo maintenance of several critical parts of the centre. This will require a full shutdown of all SciNet systems (Trillium, Balam, S4H, HPSS, Teach, as well as hosted equipment).
  4. July 13-24, 2026: A 12-day-long shutdown of Trillium compute nodes will be required. During most of this time the Trillium login nodes, HPSS, Globus, storage and Open Ondemand will remain up, as well as the S4H, Balam, Neptune, and Teach Cluster. The latter services and systems will also briefly go down on July 21st when transformer maintenance will take place.
  5. September 8-10, 2026: A 3-day-long shutdown of Trillium compute nodes will be required for the integration of the expansion into the cooling system. We also plan to run HPL benchmarks as a stress test and to obtain the required benchmark results. During this time, the Trillium login nodes, HPSS, Globus, storage and Open Ondemand will remain up, as well as the S4H, Balam, Neptune, and Teach Cluster.

Previous messages

QuickStart Guides

Tutorials, Manuals, etc.
Retrieved from "https://docs.scinet.utoronto.ca/index.php?title=Main_Page&oldid=7932"