Administration

Showing 76

Spectrum LSF's k8s support

Spectrum LSF used to provide an adapter for k8s as a container orchestration to use with LSF's job scheduling as its add-on function, which is withdrawn now. The customer would like to restore it so they could improve portability/availability and ...

about 1 month ago in Spectrum LSF / Administration 1 Needs more information

1 VOTE

Support RUN_TIME_DECAY on GPU Runtime

Currently RUN_TIME_DECAY only modifies Fairshare for CPU jobs and not GPU jobs.

20 days ago in Spectrum LSF / Administration 0 Under review

2 VOTE

Allow to set/modify the same option in multiple esubs

Currently a specific option can only be set or modified once through an esub, even if multiple esub's are run. If an option is set a second time, the error message ... Conflict parameter <PARAMETER_NAME> - Ignored. appears. There are at leas...

2 months ago in Spectrum LSF / Administration 1 Future consideration

3 VOTE

Allow Flagging Jobs for Reservation Through Rules and/or Through a "bsub --plan" Option

Today, reservations in LSF are handled by the Top X jobs by ordered by Dynamic Priority using the variable MAX_JOB_RESERVE. We believe that this is a shotgun approach. We have millions of jobs a day that require 1 cores and less than 1GB of memory...

4 months ago in Spectrum LSF / Administration 0 Future consideration

2 VOTE

Update lsf.shared with up-to-date CPU models

The file `lsf.shared` provided with Spectrum LSF is outdated. The CPU models listed seem to be 10 years old and older and there don't seem to be any updates from IBM. I suggest that IBM regularly updates this file with up-to-date CPU models and me...

3 months ago in Spectrum LSF / Administration 1 Not under consideration

24 VOTE

btop/bbot at usergroup level

This is the current bbot/btop functionality:- Group administrators can change the position of all jobs submitted by users who are members of the user group within a queue (move the selected job before/after the first/last job with the same priorit...

over 3 years ago in Spectrum LSF / Administration 0 Not under consideration

6 VOTE

Get available VM count value from cyclecloud provider for resource connector templates using badmin rc view -c templates command

It would be useful if quota from the Azure backend is completely used, LSF admins can easily check if VMs are available in the quota from Azure.

11 months ago in Spectrum LSF / Administration 0 Future consideration

2 VOTE

In the world of Multi-core processors, the context switches per second has become a KPI. It should be a standard performance metric like mem, r1m, etc.

When we try to oversubscribe hosts, it would be very beneficial to have ctx/second available as a base metric. It's available in all OS' these days. We could set a busy threshold for that say above 40k/second. For the longest time (maybe 31 years)...

5 months ago in Spectrum LSF / Administration 0 Future consideration

1 VOTE

Enhance bmod to not allow modifying a jobs memory reservation to not exceed the total additional reservable memory on the host if the job is running

This is important if a users wants to either decrease of increase a memory reservation for a running job. We have some applications that reserved multiple CPU's and large amounts of memory. These jobs are long tailed, and once they reach the long ...

3 months ago in Spectrum LSF / Administration 0 Future consideration

1 VOTE

Add additional bhist information about personnel who modified the LSF job

Enhance bhist to show who modifies the job. The information is not presented in JOB_MODIFY2 event record. Current user info in JOB_MODIFY2 is job owner and user auth for remote job in MC

3 months ago in Spectrum LSF / Administration 0 Future consideration

Please enter your email address

FILTER BY CATEGORY