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.

Known issues

Unresolved known issues

Known issue with an Unresolved Resolution state is an active problem under investigation; a temporary workaround may be available.

Resolved known issues

A known issue with a Resolved (workaround) Resolution state is an ongoing problem; a permanent workaround is available which may include using different software or hardware.

A known issue with Resolved Resolution state has been corrected.

Known Issues

Title Category Resolutionsort descending Description Posted Updated
NCCL hang on Ascend dual-GPU nodes Ascend, GPU, Software Resolved
(workaround)

Users may encounter the following message and experience NCCL hangs if the first operation is a barrier when running multi-GPU training. We have identified...

Read more
1 year 5 months ago 1 year 5 months ago
"Forgot your password?" Unavailable Account Management, client portal Resolved

Password changes cannot be completed via the "Forgot your password?" tool at the login page of the Client Portal (my.osc.edu).

Passwords can be changed once you log into the Client Portal...

Read more
7 years 4 months ago 7 years 4 months ago
openmpi/4.1.1 is deprecated Resolved

openmpi/4.1.1-hpcx will be removed on November 29th, 2022 due to InfiniBand drivers (MOFED) update. Please use compatible and bug-fixed version 'openmpi/4.1.2-hpcx' to run ORCA or your MPI...

Read more
3 years 11 months ago 3 years 11 months ago
Scratch and Project are hung; schedulings have been paused Batch, filesystem Resolved

1:00PM 4/6/2017 Update:  The Scratch and Project file systems are back to normal service. Scheduling on systems are resumed. We are still investigating the causes to this problem...

Read more
9 years 7 months ago 9 years 7 months ago
OSC OnDemand is not responsive OnDemand Resolved

OSC OnDemand is not responsive now. We are investigating the problem now. Please use other ways like ssh to connect to OSC HPC systems. 

We apologize for any inconvenience this may cause...

Read more
6 years 8 months ago 6 years 8 months ago
Login Shell Issues on Oakley Account/Shell Resolved

UPDATE: The shells have all been switched back for affected users, and you can submit jobs normally again.  Additionally, if you are still logged in and have the incorrect shell, logging back out...

Read more
12 years 4 months ago 12 years 4 months ago
Temporary Login Node Instability on Ascend and Cardinal Ascend, Cardinal Resolved

We are currently experiencing temporary instability on the Ascend and Cardinal login nodes, which may result in slow response times or unexpected session disconnects. Our team is actively...

Read more
5 months 2 weeks ago 1 month 3 days ago
STAR-CCM+ MPI job failure Cardinal, Software Resolved
(workaround)

STAR-CCM+ encounters errors when running MPI jobs using Intel MPI or Open MPI, displaying the following message:

ib_iface.c:1139 UCX ERROR Invalid active_speed on...
Read more
2 years 3 weeks ago 4 months 2 weeks ago
Oakley login node instability Operations Resolved

Oakley login nodes are seeing some instability related to Lustre. We will reboot the nodes on Thursday, October 2nd 2014 to resolve the issue. If a login node crashes before then and we have the...

Read more
12 years 1 month ago 12 years 1 week ago
Core and Node labels on Classroom app are incorrect Resolved

The core and node labels on the Classroom app (class.osc.edu) incorrectly displays as '0', regardless of the requested number of cores for a job. While this label is incorrect, the job is still...

Read more
1 year 10 months ago 1 year 9 months ago

Pages