Spectrum LSF

Showing 508 of 15598

Smart Memory Limit at the host/hostgroup level

Enabling the Smart Memory Limit to allow more than one value for the entire cluster. Current implementation only allows a single value of mem:swap combination for the entire cluster. Allowing smart memlimt to be configured at a host/hostgroup leve...

almost 6 years ago in Spectrum LSF 0 Not under consideration

1 VOTE

Add Additional "stats" Table Metrics

For operations and KPI management, having some additional metrics in the various stats tables is important. For our use here, it would be helpful to have the following metrics: Pend Time Metrics: (eligible based upon job class not LSF setting)* av...

almost 2 years ago in Spectrum LSF / Operations/RTM 1 Not under consideration

1 VOTE

Improving job status problem due to defunct process

Sometimes, defunct can occur in job processes for a variety of reasons. For example, 29460 below is one of the processes of some job. ps -ef | grep bg92 bg92.pa+ 29460 1 1 2022 ? 08:03:02 [Novas] <defunct> And if a defunct process occurs, L...

almost 2 years ago in Spectrum LSF / Administration 2 Not under consideration

1 VOTE

When Exporting Jobs Records Do Not Sort Them

Sorting the job records adds quite a bit of overhead to the export process.

almost 2 years ago in Spectrum LSF / Operations/RTM 1 Not under consideration

3 VOTE

When a job is running and stopped by "bstop" command, the slots of the suspended job can not be used by other pending jobs. T

When a job is running and stopped by "bstop" command, the slots of the suspended job can not be used by other pending jobs. The behavior is not reasonable because it causes the computing resources are wasted. We request the slots of the suspended ...

almost 6 years ago in Spectrum LSF 1 Not under consideration

2 VOTE

RC_Account visibility in RTM Job Info fields

IBM LSF Resource Connector has gone through many enhancements, like job level RC_Account. However, this field is not visible in RTM. This new filed should be added in RTM job information.

almost 4 years ago in Spectrum LSF / Cloud Bursting / Operations/RTM 5 Not under consideration

2 VOTE

Add support to Kerberos ticket with new "renew-until" date for already submitted jobs

While using Kerberos ticket forwarding on a LSF cluster: Currently TGT found on the submission host is copied to LSF cache and forwarded to the execution host at job submission; These tickets can be renewed automatically by LSF until the TGT "rene...

almost 4 years ago in Spectrum LSF / Scheduling 4 Not under consideration

3 VOTE

prevent LSF docker jobs from failing with unuseful error message

When submitting docker jobs, using LSF (with the -app bsub option), the entire user's env is sent directly to the docker-current command (with the --env-file docker option), even though the docker-current command does not accept certain env variab...

almost 6 years ago in Spectrum LSF 1 Not under consideration

3 VOTE

To be able to kill a specific process from a job

Hello, Sometimes, a job is completely stucked due to a specific process. Customer doesn't want to kill the whole job because he is waiting for the result of job. Would it possible to add the ability to kill a specific process from a job without ki...

about 6 years ago in Spectrum LSF 4 Not under consideration

1 VOTE

LSF should support output/error file path that exists only in a container

As of now LSF cannot handle a scenario where the output/error file path exists only in the container and does not exist on the underlying host where the container is running .For example:bsub -o <path_in_container_only> --app <my_bapp>...

about 2 years ago in Spectrum LSF / Other 1 Not under consideration

Please enter your email address

FILTER BY CATEGORY