Administration

Showing 25

Would like a way to stop/suspend/resume a task inside a Session Scheduler job

This would be pretty useful for debugging a broken task or one that needs to be suspended for a time.

about 1 year ago in Spectrum LSF / Administration 1 Delivered

Provide a bjobs equivalent for all active sessions in a Session Scheduler job

We need to have a way to see which tasks are running and how long they have been running to find potentially 'stuck' processes.

about 1 year ago in Spectrum LSF / Administration 1 Delivered

5 VOTE

expand -o options for bqueues

The current bqueues -o options are useful, and it would be helpful to add the resource limits (e.g., memlimit, cpulimit, etc.) as they currently require 'bqueues -l |grep -A1 LIMIT' to collect the information.

over 5 years ago in Spectrum LSF / Administration 2 Delivered

2 VOTE

LSF blimits command new option

blimits -o option to list only relevant resource and consumer columns, because many are irrelevant with the value of "-"

almost 3 years ago in Spectrum LSF / Administration 2 Delivered

1 VOTE

hostcache auto-delete function in the mbatchd restart

Dynamic hosts remain in the cluster unless you intentionally remove them.And the manual related to it is as follows.https://www.ibm.com/docs/en/spectrum-lsf/10.1.0?topic=cluster-remove-dynamic-hostsSuppose we delete the hostcache file, not modify ...

over 1 year ago in Spectrum LSF / Administration 2 Delivered

1 VOTE

Have LSF Handle ZOMBI job searching using either BTREE or HASH ALGO's

Large number of ZOMBI jobs can impact very large clusters operations resulting in high backlogs and additional lost job status. Improving the ZOMBI search algorithm from Linear Search to BTREE or HASH would reduce this impact.

over 1 year ago in Spectrum LSF / Administration 1 Delivered

1 VOTE

Make the TCP Backlog for the MBATCH and MBATCHD Query Port Configurable for Large Clusters

We have been monitoring the TCP backlogs for LIM, MBD, and the Query port for some time, and there are periods where the MBD query port becomes overloaded resulting in a higher than expected count of UNKNOWN and sometimes eventually ZOMBI jobs, an...

over 1 year ago in Spectrum LSF / Administration 1 Delivered

1 VOTE

fix systemctl script to restart sbatchd

The root sbatchd crashes frequently in our cluster (and without anything useful in the log), but systemctl is not configured to restart the daemon. Please see the details in the related support case, but essentially we need to make it so this daem...

over 1 year ago in Spectrum LSF / Administration 1 Delivered

2 VOTE

GPU report to show GPU usage and GPU memory usaage

We use the resource usage reporting of LSF and would like to have a GPU report that is similar to the CPU accounting. Right now, GPU accounting is quite simple. For example, we would like to have something like GPU memory usage, charge back, faile...

almost 4 years ago in Spectrum LSF / Administration 0 Delivered

1 VOTE

Set the "+pref_level" for hosts or host_groups in lsb.hosts

Currently it's possible in lsb.queues to set the "+pref_level" for hosts or host_groups in the "HOSTS" section to prioritize some hosts for job submission. We have various host groups defined in lsb.hosts and would like to set the +pref_level for ...

over 2 years ago in Spectrum LSF / Administration 2 Delivered

Please enter your email address

FILTER BY CATEGORY