Regular maintenance of clusters requires downtime. A maintenance schedule can reduce surprises and not unnecessarily delay required maintenance.
See also
- For a snapshot inventory, and the costs to CCB if they were hosted elsewhere, see ChemIT's spreadsheet in <R:\Chem IT\Projects & Tracking>. The data and analysis is in spreadsheet, "Chem IT Support & Services", tab "Alternative server costs".
- 1) CCB High Performance Computers (HPC)
Documentation for staff, in support of cluster maintenance
Cluster Maintenance SOP
This page includes a checklist for preparing any maintenance work, and a listing of the sequence of steps to take.
Templates of notification emails
- Communication timeline — Sequence of communications for cluster maintenance.
- Downtime warning email template — Page contains process and template text. Text is used two weeks before downtime, and again 24 hours before.
- Maintenance complete/delayed email template — One email will be sent to all group users about the completion of the work or delay of the downtime will be posted.
Specifics, per research group's cluster
(Table started November 2015)
| Group | Maintenance Cycle | Next Scheduled Downtime | Following Scheduled Downtime | Default day and time of day | First warning email sent when | Second warning email sent when | Notes |
|---|---|---|---|---|---|---|---|
| Scheraga | 1 | Jun. 9, 2021 | March 11, 2020 | 2rd Wednesday of the month 9:30am | 2 weeks before | 24 hours before | |
| Hoffmann | 2 | Jul. 20, 2021 | Apr. 21, 2020 | 3nd Tuesday of the month 9:30am | 2 weeks before | 24 hours before | |
| Cluster2020 | 3 | May. 4, 2021 | May 5, 2020 | 1st Tuesday of the month 9:30am | 2 weeks before | 24 hours before | |
| Eldor ( Freed ) | 3 | May. 13, 2021 | Feb. 13, 2020 | 2nd Thursday of the month 9:30am | 2 weeks before | 24 hours before | |
Crane Linux Workstations | 3 | May. 19, 2021 | Feb. 19, 2020 | 3rd Wednesday of the month 9:30am | 2 weeks before | 24 hours before | |
| Petersen Independent Nodes | Will be moved to Germany |