Update on the HPC issue:
Temperature in main HPC room stabilised, I brought login nodes and main server and file servers up. Until further update from Estates about the cooling system stability in the room, most of the compute nodes in that room will be offline (that includes new Broadwell nodes)
I brought some Nehalem (half of 8-CPU nodes) and Sandybridge (12-CPU “GPU” queue) compute nodes up in unaffected by cooling failure room (zeus[100-171], zeus[200-217]), they can be used as file servers now are operational.
Regards,
Alex
0 Comments.