Maintenance at December third

[xuanweishan]

To do:

• [ ] Check unstable nodes: 13
• [ ] Replace RTX 3080ti with RTX 2080 on eureka32
• [ ] Change unstable nodes to different q name.
• [ ] [optional] Update the drive of IB switch.
• [x] Replace thermal paste.

[xuanweishan]

The process of changing the q name

1. Activate super user : su
2. Edit /var/spool/TORQUE/server_priv/nodes to assign names to the target subset of nodes --> For example: eureka32 np=16 queue_name1 queue_name2
3. systemctl restart pbs

Update the SSD firmware of IB switch

1. enable to get the authority of root
2. CLI Configuration Backup
   1. configuration write
   2. configuration upload active <upload URL>
3. Reset Factory :

   reset factory
   # Warning - confirming will cause system reboot.
   # Type 'YES' to confirm reset: YES
   # Resetting and rebooting the system -- please wait...

4. Restore Configuration:

   configuration fetch <download url>
   configuration switch-to <filename>

5. Updating SSD Firmware