We are actively investigating intermittent slowness on the shared /fs/scratch filesystem.

OSC systems staff will execute a rolling reboot across all active compute clusters (Pitzer, Ascend, and Cardinal) beginning Thursday, November 05.

starccm 20.04.007 experiences errors like:

starccm/20.04.007 openmpi receives UCX errors

Category: 
Resolution: 
Unresolved
Affected Software: 

starccm 20.04.007 experiences errors like:

[1794246279.911182] [c0320:1166331:0]       ib_iface.c:1139 UCX  ERROR Invalid active_speed on mlx5_0:1: 128
[1794246279.911463] [c0320:1166343:0]       ib_iface.c:1139 UCX  ERROR Invalid active_speed on mlx5_0:1: 128

This may not affect performance. If it does, please use intelmpi